Novel reverse transcriptases and uses thereof

Abstract

Compositions and methods for binding to a target sequence of interest are provided. The compositions find use in editing a target sequence of interest via polymerase editing. Compositions comprise: reverse transcriptases (RTs) (and polynucleotides encoding the same); DNA-binding polypeptides (and polynucleotides encoding the same); polymerase editor (PE)-enhancing polypeptides (and polynucleotides encoding the same); fusion proteins comprising an RT and a heterologous polypeptide, where the heterologous polypeptide can include a DNA-binding polypeptide and a PE-enhancing polypeptide; polymerase editors (PEs) comprising an RT and a DNA-binding polypeptide, optionally further including a PE-enhancing polypeptide (or one or more polynucleotides encoding any or all components of the PE); and PE systems comprising the PEs and one or more polymerase editing guide RNAs (PEgRNAs) (or polynucleotide(s) encoding the same). Vectors and host cells comprising the polynucleotides are also provided.

Description

[0001] NOVEL REVERSE TRANSCRIPTASES AND USES THEREOF CROSS-REFERENCE TO RELATED APPLICATIONS This application claims priority to U.S. Provisional Application No.63 / 663,741, filed June 5 25, 2024, which is incorporated by referenced herein in its entirety. REFERENCE TO A SEQUENCE LISTING SUBMITTED ELECTRONICALLY AS AN XML FILE The instant application contains a Sequence Listing which has been submitted in xml format 10 and is hereby incorporated by reference in its entirety. Said xml copy, created on June 19, 2025, is named L103438_1430WO_00376_SL, and is 1,292,510 bytes in size. FIELD OF THE INVENTION The present invention relates to the field of molecular biology and gene editing. 15 BACKGROUND OF THE INVENTION Targeted genome editing is rapidly becoming an important tool for basic and applied research. Initial methods involved engineering nucleases such as meganucleases, zinc finger fusion proteins or TALENs, requiring the generation of chimeric nucleases with engineered, programmable, sequence- 20 specific DNA-binding domains specific for each particular target sequence. RNA-guided nucleases (RGNs), such as the Clustered Regularly Interspaced Short Palindromic Repeats (CRISPR)-associated (Cas) proteins of the CRISPR-Cas bacterial system, allow for the targeting of specific sequences by complexing the nucleases with guide RNA that specifically hybridizes with a particular target sequence. Producing target-specific guide RNAs is less costly and more efficient than generating 25 chimeric nucleases for each target sequence. Such RGNs can be used to edit genomes optionally through the introduction of a sequence-specific, double-stranded break that is repaired via error-prone non-homologous end-joining (NHEJ) to introduce a mutation at a specific genomic location. Alternatively, heterologous DNA may be introduced into the genomic site via homology-directed repair. RGNs can also be used for base editing when fused with a deaminase or prime editing when 30 fused with reverse transcriptase. Prime editing is a versatile and precise genome editing method that directly writes new genetic information into a specified DNA site using an RNA-guided DNA binding protein (e.g., RGN) working in association with a reverse transcriptase (RT; described in, e.g., US 11,447,770B1; WO2021072328; WO2021226558; WO2020156575; WO2021042047; US11193123; each 35 incorporated by reference in its entirety herein). The prime editing system uses an RGN that is a nickase and a reverse transcriptase, and the system is programmed with a prime editing guide RNA 1 Atty Dkt No: L1034381430WO (00376)

[0002] that comprises a primer binding site (PBS) and a DNA synthesis template (e.g., RT template) that serves as the template for the replacement strand comprising the edit. The prime editor nicks the non- target strand upstream of the sequence to be edited and upstream of the protospacer adjacent motif (PAM), creating a 3' flap on the non-target strand. The PBS is complementary to the 3' flap of the 5 non-target strand and hybridrization of the PBS and 3' flap of the non-target strand allows for the polymerization of the replacement strand containing the edit using the DNA synthesis template. However, prime editing has very low editing efficiency due to unoptimized RT template and / or PBS sequences, distance to edit of interest, guide structure and stability, low reverse transcriptase activity, endogenous repair pathways and other factors (Petrova and Smirnikhina, The 10 Development, Optimization and Future of Prime Editing. Int. J. Mol. Sci.2023, 24, 17045). Thus, it is desirable to enhance the editing efficiency of the prime editing system. BRIEF SUMMARY OF THE INVENTION Compositions and methods for binding and editing a target sequence of interest in a target 15 polynucleotide are provided. The compositions find use in editing a target polynucleotide of interest via polymerase editing. Compositions comprise reverse transcriptases (RTs) or polynucleotides encoding the same, as well as fusion proteins comprising an RT and a heterologous polypeptide (or polynucleotides encoding the same). Heterologous polypeptides that can be operably fused to the RTs of the disclosure include DNA-binding polypeptides, such as an RGN polypeptide, and a polymerase 20 editor (PE)-enhancing polypeptide. Polymerase editors (PE) comprising an RT and a DNA-binding polypeptide, or one or more polynucleotides encoding any or all components of the PE, are provided. The PE can further comprise a PE-enhancing polypeptide, or a polynucleotide encoding the same. Polymerase editor (PE) systems comprising one or more polymerase editing guide RNAs (PEgRNAs), an RT, and a DNA-binding polypeptide (e.g., an RGN polypeptide) of the disclosure, or one or more 25 polynucleotides encoding any or all components of the PE system, are also provided. The present disclosure is also directed to vectors and host cells comprising polynucleotides encoding the RTs or fusion proteins thereof, and one or more polynucleotides encoding any or all components of PEs, or any or all components of PE systems. Provided are pharmaceutical compositions comprising a pharmaceutically acceptable carrier and the presently disclosed RTs or fusion proteins thereof (or 30 polynucleotides encoding the same), PEs (or one or more polynucleotides encoding any or all components of the PEs), PE systems (or one or more polynucleotides encoding any or all components of the PE systems), or cells edited by the presently disclosed PE systems. Methods disclosed herein are drawn to editing a target sequence of interest in a target polynucleotide via polymerase editing or treating a subject having or at risk of developing a disease, disorder, or condition with the presently 35 disclosed RTs or fusion proteins thereof (or polynucleotides encoding the same), PEs (or one or more polynucleotides encoding any or all components of the PEs), PE systems (or one or more 2 Atty Dkt No: L1034381430WO (00376)

[0003] polynucleotides encoding any or all components of the PE systems), or cells edited by the presently disclosed PE systems. BRIEF DESCRIPTION OF THE FIGURES 5 FIG.1 shows that WT MMLV-RT performed poorer than two exemplary engineered retroviral RTs from Table 4. FIG.2 shows schematics of domains (palm, fingers, thumb, connection, RNaseH) of reverse transcriptase (RT) proteins representing different RT groups or RT types: MMLV-RT, retroviral RTs, retrotransposon RTs, Group II Intron RTs, and Retron RTs. The numbers indicate approximate amino 10 acid positions defining the domains for each RT group or type. DETAILED DESCRIPTION Many modifications and other embodiments of the inventions set forth herein will come to mind to one skilled in the art to which these inventions pertain having the benefit of the teachings 15 presented in the foregoing descriptions and the associated drawings. Therefore, it is to be understood that the inventions are not to be limited to the specific embodiments disclosed and that modifications and other embodiments are intended to be included within the scope of the appended embodiments. Although specific terms are employed herein, they are used in a generic and descriptive sense only and not for purposes of limitation. 20 I. Overview Provided herein are novel reverse transcriptases (RTs). An RT, having a polymerase domain, can function as a polymerase component in a polymerase editing system to edit target nucleic acid molecules by DNA synthesis. Also provided herein are fusion proteins comprising a presently 25 disclosed RT and a heterologous polypeptide. The heterologous polypeptide can include an RGN polypeptide and / or a polymerase editor (PE)-enhancing polypeptide. As used herein, a “polymerase editor” or “PE” refers to a protein or a plurality of proteins comprising an RT and a DNA-binding polypeptide (e.g., RGN polypeptide) that, along with a polymerase editing guide RNA (PEgRNA) comprising an extension arm comprising a PBS and a 30 DNA synthesis template comprising a desired edit, is capable of editing a double-stranded polynucleotide through the replacement of a target sequence using the DNA synthesis template as a template for the RT. The PE can further comprise a PE-enhancing polypeptide. In certain embodiments, the RT and the DNA-binding polypeptide (e.g., RGN polypeptide) are operably linked (by fusion or insertion). In other embodiments, the RT and the DNA-binding polypeptide (e.g., RGN 35 polypeptide) are not operably linked and are translated as two separate polypeptides. In certain embodiments, a PE comprising an RT, a DNA-binding polypeptide (e.g., RGN polypeptide), and a 3 Atty Dkt No: L1034381430WO (00376)

[0004] PE-enhancing polypeptide can have two of the three polypeptides operably linked (by fusion or insertion). In other embodiments, the RT, the DNA-binding polypeptide (e.g., RGN polypeptide), and the PE-enhancing polypeptide are operably fused as a single protein. In some embodiments, the RT, the DNA-binding polypeptide (e.g., RGN polypeptide), and the PE-enhancing polypeptide are not 5 operably linked and are translated as three separate polypeptides. In some embodiments, the PE does not require the introduction of a double-stranded break, but rather utilizes an RGN nickase that nicks the non-target strand upstream of the sequence to be edited and upstream of the PAM, creating a 3' flap on the non-target strand. The PBS of the PEgRNA is complementary to the 3' flap of the non-target strand and hybridrization of the PBS and 3' flap of 10 the non-target strand allows for the polymerization of the replacement strand containing the edit using the DNA synthesis template and RT. Polymerase editors that utilize a reverse transcriptase as the polymerase can be referred to herein as “RT editors” or “RTEs”. The presently disclosed RTs can edit target nucleic acid molecules when provided in trans with a DNA-binding polypeptide (e.g., RGN polypeptide) or when provided as a fusion with the 15 DNA-binding polypeptide (e.g., RGN polypeptide). Further, the presently disclosed RTs can edit target nucleic acid molecules when provided with a DNA-binding polypeptide (e.g., RGN polypeptide) and a PE-enhancing polypeptide, both provided in trans to the RT, or when provided as a fusion with the DNA-binding polypeptide (e.g., RGN polypeptide) or the PE-enhancing polypeptide, or as a single protein fusion with both the DNA-binding polypeptide (e.g., RGN 20 polypeptide) and the PE-enhancing polypeptide. Thus, also provided herein are fusion proteins comprising a presently disclosed RT, a DNA-binding polypeptide (e.g., RGN polypeptide), and / or a PE-enhancing polypeptide. Also provided herein are PEs, PE systems, and methods of using the same for editing a target DNA molecule, wherein a PE comprises an RT and a DNA-binding polypeptide (e.g., RGN polypeptide), or wherein a PE comprises an RT, a DNA-binding polypeptide (e.g., RGN 25 polypeptide), and a PE-enhancing polypeptide. II. Reverse transcriptases (RTs) Compositions of the disclosure, including fusion proteins, PEs and PE systems, can comprise polymerases (e.g., DNA polymerases, reverse transcriptases, etc.). As used herein, a “polymerase” is 30 an enzyme that catalyzes the formation of a nucleic acid polymer. A polymerase can be an RNA polymerase (catalyzing the formation of an RNA polymer) or a DNA polymerase (catalyzing the formation of a DNA polymer). In some embodiments, the polymerase of the PE or PE system is a DNA polymerase. The PE or PE system can comprise a DNA-dependent DNA polymerase (uses DNA as a template) or an RNA-dependent DNA polymerase (uses RNA as a template). In some35 embodiments, the DNA polymerase of the presently disclosed PEs and PE systems is an RNA- dependent DNA polymerase (i.e., reverse transcriptase). 4 Atty Dkt No: L1034381430WO (00376)

[0005] The present disclosure provides compositions, including fusion proteins, PEs and PE systems, that comprise novel RTs. The RTs were identified through a number of approaches, including bioinformatics, engineering of identified RTs, and screening of identified RTs and engineered RTs for editing activity of target genes, for example, in mammalian cells. RTs are a class of enzymes that 5 catalyze the transcription of RNA into DNA, a process known as reverse transcription. This enzymatic activity is critical in the life cycles of retroviruses, such as Human Immunodeficiency Virus (HIV), and in the replication of various mobile genetic elements, including retrotransposons. First, the RT uses its RNA-dependent DNA polymerase activity to convert single-stranded RNA (ssRNA) templates into complementary DNA (cDNA). RTs can also possess RNase H activity, which 10 degrades the RNA strand of an RNA-DNA hybrid, providing a template for the synthesis of the second DNA strand. The RT then synthesizes the second DNA strand through its DNA-dependent DNA polymerase activity, resulting in a double-stranded DNA (dsDNA) molecule that can integrate into the host genome. As used herein, a “reverse transcriptase” or “RT” is an enzyme that has polymerase activity to catalyze the formation of a nucleic acid polymer. In some embodiments, the 15 RT synthesizes a nucleic acid polymer using a template nucleic acid molecule. In some embodiments, the polymerase activity is a DNA polymerase activity. In some embodiments, an RT catalyzes the addition of nucleotides to a nicked polynucleotide strand, using a template. RTs include retroviral RTs such as HIV-1 RT, hepatitis B RT, and Murine Leukemia Virus (MLV)-RT (also known as Moloney Murine Leukemia Virus (MMLV)-RT). MLV-RT serves as a 20 model for understanding the basic mechanisms of reverse transcription. Telomerase is a specialized RT that extends telomeres, the repetitive nucleotide sequences at the ends of eukaryotic chromosomes. RTs can include non-retroviral RTs. Non-retroviral RTs can include Group II intron RTs, retrotransposon RTs, and retron RTs. Group II intron RTs are the most abundant class of RTs. The Group II introns are mobile bacterial ribozymes that invade genomes by reverse splicing and 25 reverse transcription. Retrotransposon RTs are involved in the replication of retrotransposons, which are genetic elements that can move around within the genome. Examples include Long Interspersed Nuclear Elements (LINEs) such as LINE-1 in humans. These elements encode their own RT, which facilitates their transcription into cDNA and subsequent insertion into new genomic locations. Retron RTs are smaller RTs that are encoded by retrons, bacterial genetic elements involved in anti-phage 30 defense. Reverse transcriptases typically exhibit a "right hand" structure with three main domains: a ‘finger’ or ‘fingers’ domain involved in binding the template-primer and dNTPs; the ‘palm’ domain containing the active site with highly conserved motifs responsible for catalysis; and the ‘thumb’, which maintains the enzyme's interaction with the nucleic acid substrate. RTs have distinct 35 polymerase (comprising fingers, palm, and thumb) and RNase H domains, where the polymerase domain is responsible for nucleic acid molecule (e.g., DNA) synthesis, and the RNase H domain degrades the RNA strand in RNA-DNA hybrids to allow second-strand DNA synthesis. An optional 5 Atty Dkt No: L1034381430WO (00376)

[0006] connection domain can connect the thumb domain to the RNaseH domain. In some embodiments, the polymerase portion of an RT comprises at least one palm domain, at least one fingers domain, and at least one thumb domain. The polymerase active site can comprise two conserved Asp (D) residues located on a structurally conserved epitope in a palm domain. RTs are important tools in molecular 5 biology and biotechnology, with uses in RT-PCR, cDNA synthesis from RNA, amplification and quantification of RNA, RNA Sequencing (RNA-Seq), preparing cDNA libraries from RNA samples, and gene cloning and expression studies. An RT of the presently disclosed compositions and methods can comprise an amino acid sequence having at least 40%, at least 41%, at least 42%, at least 43%, at least 44%, at least 45%, at 10 least 46%, at least 47%, at least 48%, at least 49%, at least 50%, at least 51%, at least 52%, at least 53%, at least 54%, at least 55%, at least 56%, at least 57%, at least 58%, at least 59%, at least 60%, at least 61%, at least 62%, at least 63%, at least 64%, at least 65%, at least 66%, at least 67%, at least 68%, at least 69%, at least 70%, at least 71%, at least 72%, at least 73%, at least 74%, at least 75%, at least 76%, at least 77%, at least 78%, at least 79%, at least 80%, at least 81%, at least 82%, at least 15 83%, at least 84%, at least 85%, at least 86%, at least 87%, at least 88%, at least 89%, at least 90%, at least 91%, at least 92%, at least 93%, at least 94%, at least 95%, at least 96%, at least 97%, at least 98%, at least 99%, at least 99.1%, at least 99.2%, at least 99.3%, at least 99.4%, at least 99.5%, at least 99.6%, at least 99.7%, at least 99.8%, or at least 99.9% sequence identity to any one of SEQ ID NOs: 1-41, 45-228, 233-334, 492-511, 807, 823-871, 881-898, and 917-934. In some embodiments, 20 the phrase “having at least [specific number]% sequence identity to” a sequence refers to “having at least [specific number]% sequence identity over the full-length of” that sequence. An RT of the presently disclosed compositions and methods can comprise an amino acid sequence having at least one, at least two, at least three, at least four, at least five, at least six, at least seven, at least eight, at least nine, at least ten, at least eleven, at least twelve, at least thirteen, at least fourteen, or at least 25 fifteen amino acid substitution(s) as compared to the amino acid sequence of any one of SEQ ID NOs: 1-41, 45-228, 233-334, 492-511, 807, 823-871, 881-898, and 917-934. An RT of the presently disclosed compositions and methods can comprise an amino acid sequence having at least 40%, at least 41%, at least 42%, at least 43%, at least 44%, at least 45%, at least 46%, at least 47%, at least 48%, at least 49%, at least 50%, at least 51%, at least 52%, at least 30 53%, at least 54%, at least 55%, at least 56%, at least 57%, at least 58%, at least 59%, at least 60%, at least 61%, at least 62%, at least 63%, at least 64%, at least 65%, at least 66%, at least 67%, at least 68%, at least 69%, at least 70%, at least 71%, at least 72%, at least 73%, at least 74%, at least 75%, at least 76%, at least 77%, at least 78%, at least 79%, at least 80%, at least 81%, at least 82%, at least 83%, at least 84%, at least 85%, at least 86%, at least 87%, at least 88%, at least 89%, at least 90%, at 35 least 91%, at least 92%, at least 93%, at least 94%, at least 95%, at least 96%, at least 97%, at least 98%, at least 99%, at least 99.1%, at least 99.2%, at least 99.3%, at least 99.4%, at least 99.5%, at least 99.6%, at least 99.7%, at least 99.8%, or at least 99.9% sequence identity to any one of SEQ ID 6 Atty Dkt No: L1034381430WO (00376)

[0007] NOs: 1-41, 45-133, 242-271, 311-314, 807, 823-871, and 881-898. An RT of the presently disclosed compositions and methods can comprise an amino acid sequence having at least one, at least two, at least three, at least four, at least five, at least six, at least seven, at least eight, at least nine, at least ten, at least eleven, at least twelve, at least thirteen, at least fourteen, or at least fifteen amino acid 5 substitution(s) as compared to the amino acid sequence of any one of SEQ ID NOs: 1-41, 45-133, 242-271, 311-314, 807, 823-871, and 881-898. An RT of the presently disclosed compositions and methods can comprise an amino acid sequence having at least 40%, at least 41%, at least 42%, at least 43%, at least 44%, at least 45%, at least 46%, at least 47%, at least 48%, at least 49%, at least 50%, at least 51%, at least 52%, at least 10 53%, at least 54%, at least 55%, at least 56%, at least 57%, at least 58%, at least 59%, at least 60%, at least 61%, at least 62%, at least 63%, at least 64%, at least 65%, at least 66%, at least 67%, at least 68%, at least 69%, at least 70%, at least 71%, at least 72%, at least 73%, at least 74%, at least 75%, at least 76%, at least 77%, at least 78%, at least 79%, at least 80%, at least 81%, at least 82%, at least 83%, at least 84%, at least 85%, at least 86%, at least 87%, at least 88%, at least 89%, at least 90%, at 15 least 91%, at least 92%, at least 93%, at least 94%, at least 95%, at least 96%, at least 97%, at least 98%, at least 99%, at least 99.1%, at least 99.2%, at least 99.3%, at least 99.4%, at least 99.5%, at least 99.6%, at least 99.7%, at least 99.8%, or at least 99.9% sequence identity to SEQ ID NO: 35, 39, or 41. In some embodiments, an RT of the disclosure comprises the amino acid sequence of SEQ ID NO: 35, 39, or 41. 20 An RT of the presently disclosed compositions and methods can comprise an amino acid sequence having at least 60%, at least 61%, at least 62%, at least 63%, at least 64%, at least 65%, at least 66%, at least 67%, at least 68%, at least 69%, at least 70%, at least 71%, at least 72%, at least 73%, at least 74%, at least 75%, at least 76%, at least 77%, at least 78%, at least 79%, at least 80%, at least 81%, at least 82%, at least 83%, at least 84%, at least 85%, at least 86%, at least 87%, at least 25 88%, at least 89%, at least 90%, at least 91%, at least 92%, at least 93%, at least 94%, at least 95%, at least 96%, at least 97%, at least 98%, at least 99%, at least 99.1%, at least 99.2%, at least 99.3%, at least 99.4%, at least 99.5%, at least 99.6%, at least 99.7%, at least 99.8%, or at least 99.9% sequence identity to SEQ ID NO: 1, 34, or 40. In some embodiments, an RT of the disclosure comprises the amino acid sequence of SEQ ID NO: 1, 34, or 40. 30 An RT of the presently disclosed compositions and methods can comprise an amino acid sequence having at least 65%, at least 66%, at least 67%, at least 68%, at least 69%, at least 70%, at least 71%, at least 72%, at least 73%, at least 74%, at least 75%, at least 76%, at least 77%, at least 78%, at least 79%, at least 80%, at least 81%, at least 82%, at least 83%, at least 84%, at least 85%, at least 86%, at least 87%, at least 88%, at least 89%, at least 90%, at least 91%, at least 92%, at least 35 93%, at least 94%, at least 95%, at least 96%, at least 97%, at least 98%, at least 99%, at least 99.1%, at least 99.2%, at least 99.3%, at least 99.4%, at least 99.5%, at least 99.6%, at least 99.7%, at least 99.8%, or at least 99.9% sequence identity to SEQ ID NO: 6, 8, 9, 36, 37, 837, or 846. In some 7 Atty Dkt No: L1034381430WO (00376)

[0008] embodiments, an RT of the disclosure comprises the amino acid sequence of SEQ ID NO: 6, 8, 9, 36, 37, 837, or 846. An RT of the presently disclosed compositions and methods can comprise an amino acid sequence having at least 73%, at least 74%, at least 75%, at least 76%, at least 77%, at least 78%, at 5 least 79%, at least 80%, at least 81%, at least 82%, at least 83%, at least 84%, at least 85%, at least 86%, at least 87%, at least 88%, at least 89%, at least 90%, at least 91%, at least 92%, at least 93%, at least 94%, at least 95%, at least 96%, at least 97%, at least 98%, at least 99%, at least 99.1%, at least 99.2%, at least 99.3%, at least 99.4%, at least 99.5%, at least 99.6%, at least 99.7%, at least 99.8%, or at least 99.9% sequence identity to SEQ ID NO: 4. In some embodiments, an RT of the disclosure 10 comprises the amino acid sequence of SEQ ID NO: 4. An RT of the presently disclosed compositions and methods can comprise an amino acid sequence having at least 78%, at least 79%, at least 80%, at least 81%, at least 82%, at least 83%, at least 84%, at least 85%, at least 86%, at least 87%, at least 88%, at least 89%, at least 90%, at least 91%, at least 92%, at least 93%, at least 94%, at least 95%, at least 96%, at least 97%, at least 98%, at 15 least 99%, at least 99.1%, at least 99.2%, at least 99.3%, at least 99.4%, at least 99.5%, at least 99.6%, at least 99.7%, at least 99.8%, or at least 99.9% sequence identity to SEQ ID NO: 895 or 897. In some embodiments, an RT of the disclosure comprises the amino acid sequence of SEQ ID NO: 895 or 897. An RT of the presently disclosed compositions and methods can comprise an amino acid sequence having at least 80%, at least 81%, at least 82%, at least 83%, at least 84%, at least 85%, at 20 least 86%, at least 87%, at least 88%, at least 89%, at least 90%, at least 91%, at least 92%, at least 93%, at least 94%, at least 95%, at least 96%, at least 97%, at least 98%, at least 99%, at least 99.1%, at least 99.2%, at least 99.3%, at least 99.4%, at least 99.5%, at least 99.6%, at least 99.7%, at least 99.8%, or at least 99.9% sequence identity to SEQ ID NO: 18, 19, 20, 21, 22, 23, 892, or 896. In some embodiments, an RT of the disclosure comprises the amino acid sequence of SEQ ID NO: 18, 19, 20, 25 21, 22, 23, 892, or 896. An RT of the presently disclosed compositions and methods can comprise an amino acid sequence having at least 82%, at least 83%, at least 84%, at least 85%, at least 86%, at least 87%, at least 88%, at least 89%, at least 90%, at least 91%, at least 92%, at least 93%, at least 94%, at least 95%, at least 96%, at least 97%, at least 98%, at least 99%, at least 99.1%, at least 99.2%, at least 30 99.3%, at least 99.4%, at least 99.5%, at least 99.6%, at least 99.7%, at least 99.8%, or at least 99.9% sequence identity to SEQ ID NO: 891. In some embodiments, an RT of the disclosure comprises the amino acid sequence of SEQ ID NO: 891. An RT of the presently disclosed compositions and methods can comprise an amino acid sequence having at least 85%, at least 86%, at least 87%, at least 88%, at least 89%, at least 90%, at 35 least 91%, at least 92%, at least 93%, at least 94%, at least 95%, at least 96%, at least 97%, at least 98%, at least 99%, at least 99.1%, at least 99.2%, at least 99.3%, at least 99.4%, at least 99.5%, at least 99.6%, at least 99.7%, at least 99.8%, or at least 99.9% sequence identity to SEQ ID NO: 889 or 8 Atty Dkt No: L1034381430WO (00376)

[0009] 898. In some embodiments, an RT of the disclosure comprises the amino acid sequence of SEQ ID NO: 889 or 898. An RT of the presently disclosed compositions and methods can comprise an amino acid sequence having at least 80%, at least 81%, at least 82%, at least 83%, at least 84%, at least 85%, at 5 least 86%, at least 87%, at least 88%, at least 89%, at least 90%, at least 91%, at least 92%, at least 93%, at least 94%, at least 95%, at least 96%, at least 97%, at least 98%, at least 99%, at least 99.1%, at least 99.2%, at least 99.3%, at least 99.4%, at least 99.5%, at least 99.6%, at least 99.7%, at least 99.8%, or at least 99.9% sequence identity to SEQ ID NO: 7, 38, 262, 881, 883, or 893. In some embodiments, an RT of the disclosure comprises an amino acid sequence having at least 90%, at least 10 91%, at least 92%, at least 93%, at least 94%, at least 95%, at least 96%, at least 97%, at least 98%, at least 99%, at least 99.1%, at least 99.2%, at least 99.3%, at least 99.4%, at least 99.5%, at least 99.6%, at least 99.7%, at least 99.8%, or at least 99.9% sequence identity to SEQ ID NO: 7, 38, 262, 881, 883, or 893. In some embodiments, an RT of the disclosure comprises the amino acid sequence of SEQ ID NO: 7, 38, 262, 881, 883, or 893. 15 An RT of the presently disclosed compositions and methods can comprise an amino acid sequence having at least 80%, at least 81%, at least 82%, at least 83%, at least 84%, at least 85%, at least 86%, at least 87%, at least 88%, at least 89%, at least 90%, at least 91%, at least 92%, at least 93%, at least 94%, at least 95%, at least 96%, at least 97%, at least 98%, at least 99%, at least 99.1%, at least 99.2%, at least 99.3%, at least 99.4%, at least 99.5%, at least 99.6%, at least 99.7%, at least 20 99.8%, or at least 99.9% sequence identity to SEQ ID NO: 887 or 888. In some embodiments, an RT of the disclosure comprises an amino acid sequence having at least 92%, at least 93%, at least 94%, at least 95%, at least 96%, at least 97%, at least 98%, at least 99%, at least 99.1%, at least 99.2%, at least 99.3%, at least 99.4%, at least 99.5%, at least 99.6%, at least 99.7%, at least 99.8%, or at least 99.9% sequence identity to SEQ ID NO: 887 or 888. In some embodiments, an RT of the disclosure 25 comprises the amino acid sequence of SEQ ID NO: 887 or 888. An RT of the presently disclosed compositions and methods can comprise an amino acid sequence having at least 80%, at least 81%, at least 82%, at least 83%, at least 84%, at least 85%, at least 86%, at least 87%, at least 88%, at least 89%, at least 90%, at least 91%, at least 92%, at least 93%, at least 94%, at least 95%, at least 96%, at least 97%, at least 98%, at least 99%, at least 99.1%, 30 at least 99.2%, at least 99.3%, at least 99.4%, at least 99.5%, at least 99.6%, at least 99.7%, at least 99.8%, or at least 99.9% sequence identity to SEQ ID NO: 24, 25, 26, 27, 28, 29, 30, 31, 32, 33, 885, or 894. In some embodiments, an RT of the disclosure comprises an amino acid sequence having at least 95%, at least 96%, at least 97%, at least 98%, at least 99%, at least 99.1%, at least 99.2%, at least 99.3%, at least 99.4%, at least 99.5%, at least 99.6%, at least 99.7%, at least 99.8%, or at least 35 99.9% sequence identity to SEQ ID NO: 24, 25, 26, 27, 28, 29, 30, 31, 32, 33, 885, or 894. In some embodiments, an RT of the disclosure comprises the amino acid sequence of SEQ ID NO: 24, 25, 26, 27, 28, 29, 30, 31, 32, 33, 885, or 894. 9 Atty Dkt No: L1034381430WO (00376)

[0010] An RT of the presently disclosed compositions and methods can comprise an amino acid sequence having at least 80%, at least 81%, at least 82%, at least 83%, at least 84%, at least 85%, at least 86%, at least 87%, at least 88%, at least 89%, at least 90%, at least 91%, at least 92%, at least 93%, at least 94%, at least 95%, at least 96%, at least 97%, at least 98%, at least 99%, at least 99.1%, 5 at least 99.2%, at least 99.3%, at least 99.4%, at least 99.5%, at least 99.6%, at least 99.7%, at least 99.8%, or at least 99.9% sequence identity to SEQ ID NO: 2, 3, or 5. In some embodiments, an RT of the disclosure comprises an amino acid sequence having at least 98%, at least 99%, at least 99.1%, at least 99.2%, at least 99.3%, at least 99.4%, at least 99.5%, at least 99.6%, at least 99.7%, at least 99.8%, or at least 99.9% sequence identity to SEQ ID NO: 2, 3, or 5. In some embodiments, an RT of 10 the disclosure comprises the amino acid sequence of SEQ ID NO: 2, 3, or 5. A retroviral type RT, or an active variant or fragment thereof, of the disclosure can have: a) a palm domain that is within or includes: amino acid residues about 1 to about 38; amino acid residues about 122 to about 157; and / or amino acid residues about 189 to about 273; b) a fingers domain that is within or includes: amino acid residues about 38 to about 122; and / or amino acid residues about 157 15 to about 189; c) a thumb domain that is within or includes amino acid residues about 273 to about 360; d) a connection domain that is within or includes amino acid residues about 360 to about 495; or a combination of domains thereof. In some embodiments, a retroviral type RT has the amino acid sequence set forth as any one of SEQ ID NOs: 1-33, 247-271, 807, 823-871, and 881-898. In some embodiments, an RT, or an active variant or fragment thereof, of the disclosure has at 20 least 90%, at least 91%, at least 92%, at least 93%, at least 94%, at least 95%, at least 96%, at least 97%, at least 98%, at least 99%, at least 99.1%, at least 99.2%, at least 99.3%, at least 99.4%, at least 99.5%, at least 99.6%, at least 99.7%, at least 99.8%, or at least 99.9% sequence identity across at least one domain comprising all or a portion of: amino acid residues 1 to 38; amino acid residues 122 to 157; amino acid residues 189 to 273; amino acid residues 38 to 122; amino acid residues 157 to 25 189; amino acid residues 273 to 360; amino acid residues 360 to 495; or a combination of domains thereof, of the amino acid sequence set forth as any one of SEQ ID NOs: 1-33, 262, 837, 846, 881, 883, 885, 887-889, and 891-898 and has at least 60%, at least 65%, at least 70%, at least 75%, at least 80%, at least 85%, at least 90%, at least 95%, at least 96%, at least 97%, at least 98%, at least 99%, at least 99.1%, at least 99.2%, at least 99.3%, at least 99.4%, at least 99.5%, at least 99.6%, at least 30 99.7%, at least 99.8%, or at least 99.9% sequence identity across the remaining portion of the amino acid sequence set forth as any one of SEQ ID NOs: 1-33, 837, 846, 881, 883, 885, 887-889, and 891- 898. A retrotransposon type RT, or an active variant or fragment thereof, of the disclosure can have: a) a palm domain that is within or includes: amino acid residues about 1 to about 16; amino acid 35 residues about 99 to about 133; and / or amino acid residues about 161 to about 239; b) a fingers domain that is within or includes: amino acid residues about 16 to about 99; and / or amino acid residues about 133 to about 161; c) a thumb domain that is within or includes amino acid residues 10 Atty Dkt No: L1034381430WO (00376)

[0011] about 239 to about 327; or a combination of domains thereof. In some embodiments, a retrotransposon type RT has the amino acid sequence set forth as any one of SEQ ID NOs: 34, 35, 40, 41, 45-71, 242-245, 247, 271, 807, and 823-826. In some embodiments, an RT, or an active variant or fragment thereof, of the disclosure has at 5 least 90%, at least 91%, at least 92%, at least 93%, at least 94%, at least 95%, at least 96%, at least 97%, at least 98%, at least 99%, at least 99.1%, at least 99.2%, at least 99.3%, at least 99.4%, at least 99.5%, at least 99.6%, at least 99.7%, at least 99.8%, or at least 99.9% sequence identity across at least one domain comprising all or a portion of: amino acid residues 1 to 16; amino acid residues 99 to 133; amino acid residues 161 to 239; amino acid residues 16 to 99; amino acid residues 133 to 161; 10 amino acid residues 239 to 327; or a combination of domains thereof, of the amino acid sequence set forth as SEQ ID NO: 34 or 40, and has at least 60%, at least 65%, at least 70%, at least 75%, at least 80%, or at least 85% sequence identity across the remaining portion of the amino acid sequence set forth as SEQ ID NO: 34 or 40. In some embodiments, an RT, or an active variant or fragment thereof, of the disclosure has at 15 least 90%, at least 91%, at least 92%, at least 93%, at least 94%, at least 95%, at least 96%, at least 97%, at least 98%, at least 99%, at least 99.1%, at least 99.2%, at least 99.3%, at least 99.4%, at least 99.5%, at least 99.6%, at least 99.7%, at least 99.8%, or at least 99.9% sequence identity across at least one domain comprising all or a portion of: amino acid residues 1 to 16; amino acid residues 99 to 133; amino acid residues 161 to 239; amino acid residues 16 to 99; amino acid residues 133 to 161; 20 amino acid residues 239 to 327; or a combination of domains thereof, of the amino acid sequence set forth as SEQ ID NO: 35 or 41, and has at least 40%, at least 45%, at least 50%, at least 55%, at least 60%, at least 65%, at least 70%, at least 75%, at least 80%, or at least 85% sequence identity across the remaining portion of the amino acid sequence set forth as SEQ ID NO: 35 or 41. A Group II intron type RT, or an active variant or fragment thereof, of the disclosure can 25 have: a) a palm domain that is within or includes amino acid residues about 94 to about 280; b) a fingers domain that is within or includes amino acid residues about 1 to about 94; c) a thumb domain that is within or includes amino acid residues about 280 to about 417; or a combination of domains thereof. In some embodiments, a Group II intron type RT has the amino acid sequence set forth as any one of SEQ ID NOs: 36, 37, 38, and 104-130. 30 In some embodiments, an RT, or an active variant or fragment thereof, of the disclosure has at least 90%, at least 91%, at least 92%, at least 93%, at least 94%, at least 95%, at least 96%, at least 97%, at least 98%, at least 99%, at least 99.1%, at least 99.2%, at least 99.3%, at least 99.4%, at least 99.5%, at least 99.6%, at least 99.7%, at least 99.8%, or at least 99.9% sequence identity across at least one domain comprising all or a portion of: amino acid residues 94 to 280; amino acid residues 1 35 to 94; amino acid residues 280 to 417; or a combination of domains thereof, of the amino acid sequence set forth as SEQ ID NO: 36 or 37, and has at least 70%, at least 75%, at least 80%, or at 11 Atty Dkt No: L1034381430WO (00376)

[0012] least 85% sequence identity across the remaining portion of the amino acid sequence set forth as SEQ ID NO: 36 or 37. In some embodiments, an RT, or an active variant or fragment thereof, of the disclosure has at least 95%, at least 96%, at least 97%, at least 98%, at least 99%, at least 99.1%, at least 99.2%, at 5 least 99.3%, at least 99.4%, at least 99.5%, at least 99.6%, at least 99.7%, at least 99.8%, or at least 99.9% sequence identity across at least one domain comprising all or a portion of: amino acid residues 94 to 280; amino acid residues 1 to 94; amino acid residues 280 to 417; or a combination of domains thereof, of the amino acid sequence set forth as SEQ ID NO: 38, and has at least 90%, at least 91%, at least 92%, at least 93%, at least 94%, at least 95%, at least 96%, at least 97%, at least 98%, at least 10 99%, at least 99.1%, at least 99.2%, at least 99.3%, at least 99.4%, at least 99.5%, at least 99.6%, at least 99.7%, at least 99.8%, or at least 99.9% sequence identity across the remaining portion of the amino acid sequence set forth as SEQ ID NO: 38. A retron type RT, or an active variant or fragment thereof, of the disclosure can have: a) a palm domain that is within or includes amino acid residues about 79 to about 253; b) a fingers domain 15 that is within or includes amino acid residues about 1 to about 79; c) a thumb domain that is within or includes amino acid residues about 253 to about 380; or a combination of domains thereof. In some embodiments, a retron type RT has the amino acid sequence set forth as any one of SEQ ID NOs: 39, 72-103, 131-133, and 246. In some embodiments, an RT, or an active variant or fragment thereof, of the disclosure has at 20 least 90%, at least 91%, at least 92%, at least 93%, at least 94%, at least 95%, at least 96%, at least 97%, at least 98%, at least 99%, at least 99.1%, at least 99.2%, at least 99.3%, at least 99.4%, at least 99.5%, at least 99.6%, at least 99.7%, at least 99.8%, or at least 99.9% sequence identity across at least one domain comprising all or a portion of: amino acid residues 79 to 253; amino acid residues 1 to 79; amino acid residues 253 to 380; or a combination of domains thereof, of the amino acid 25 sequence set forth as SEQ ID NO: 39, and has at least 98%, at least 99%, at least 99.1%, at least 99.2%, at least 99.3%, at least 99.4%, at least 99.5%, at least 99.6%, at least 99.7%, at least 99.8%, or at least 99.9% sequence identity across the remaining portion of the amino acid sequence set forth as SEQ ID NO: 39. An RT of the presently disclosed compositions and methods can lack an RNase H domain. 30 An RT of the presently disclosed compositions and methods can comprise at least one of: a) an N at a position corresponding to 200 of SEQ ID NO: 42; b) a P at a position corresponding to 330 of SEQ ID NO: 42; c) a K at a position corresponding to 306 of SEQ ID NO: 42; and d) an F at a position corresponding to 313 of SEQ ID NO: 42, when the amino acid sequence of said disclosed RT is aligned to the amino acid sequence set forth as SEQ ID NO: 42 for maximum sequence identity. 35 Alignment of two amino acid sequences for maximum sequence identity is described herein, for example, in Section VIII. 12 Atty Dkt No: L1034381430WO (00376)

[0013] An RT of the presently disclosed compositions and methods can comprise an amino acid sequence having at least 60%, at least 61%, at least 62%, at least 63%, at least 64%, at least 65%, at least 66%, at least 67%, at least 68%, at least 69%, at least 70%, at least 71%, at least 72%, at least 73%, at least 74%, at least 75%, at least 76%, at least 77%, at least 78%, at least 79%, at least 80%, at 5 least 81%, at least 82%, at least 83%, at least 84%, at least 85%, at least 86%, at least 87%, at least 88%, at least 89%, at least 90%, at least 91%, at least 92%, at least 93%, at least 94%, at least 95%, at least 96%, at least 97%, at least 98%, at least 99%, at least 99.1%, at least 99.2%, at least 99.3%, at least 99.4%, at least 99.5%, at least 99.6%, at least 99.7%, at least 99.8%, or at least 99.9% sequence identity to SEQ ID NO: 10, wherein said RT comprises at least one of: i) an N at a position 10 corresponding to 198 of SEQ ID NO: 10; ii) a K at a position corresponding to 304 of SEQ ID NO: 10; iii) an F at a position corresponding to 311 of SEQ ID NO: 10; and iv) a P at a position corresponding to 328 of SEQ ID NO: 10. In some embodiments, an RT of the disclosure comprises the amino acid sequence of SEQ ID NO: 10. An RT of the presently disclosed compositions and methods can comprise an amino acid 15 sequence having at least 80%, at least 81%, at least 82%, at least 83%, at least 84%, at least 85%, at least 86%, at least 87%, at least 88%, at least 89%, at least 90%, at least 91%, at least 92%, at least 93%, at least 94%, at least 95%, at least 96%, at least 97%, at least 98%, at least 99%, at least 99.1%, at least 99.2%, at least 99.3%, at least 99.4%, at least 99.5%, at least 99.6%, at least 99.7%, at least 99.8%, or at least 99.9% sequence identity to SEQ ID NO: 11 or 12, more preferably at least 98%, at 20 least 99%, at least 99.1%, at least 99.2%, at least 99.3%, at least 99.4%, at least 99.5%, at least 99.6%, at least 99.7%, at least 99.8%, or at least 99.9% sequence identity to SEQ ID NO: 11 or 12, wherein said RT comprises at least one of: i) an N at a position corresponding to 199 of SEQ ID NO: 11 or 12; ii) a K at a position corresponding to 305 of SEQ ID NO: 11 or 12; iii) an F at a position corresponding to 312 of SEQ ID NO: 11 or 12; and iv) a P at a position corresponding to 329 of SEQ 25 ID NO: 11 or 12. In some embodiments, an RT of the disclosure comprises the amino acid sequence of SEQ ID NO: 11 or 12. An RT of the presently disclosed compositions and methods can comprise an amino acid sequence having at least 70%, at least 71%, at least 72%, at least 73%, at least 74%, at least 75%, at least 76%, at least 77%, at least 78%, at least 79%, at least 80%, at least 81%, at least 82%, at least 30 83%, at least 84%, at least 85%, at least 86%, at least 87%, at least 88%, at least 89%, at least 90%, at least 91%, at least 92%, at least 93%, at least 94%, at least 95%, at least 96%, at least 97%, at least 98%, at least 99%, at least 99.1%, at least 99.2%, at least 99.3%, at least 99.4%, at least 99.5%, at least 99.6%, at least 99.7%, at least 99.8%, or at least 99.9% sequence identity to SEQ ID NO: 13, wherein said RT comprises at least one of: i) a K at a position corresponding to 306 of SEQ ID NO: 35 13; ii) an F at a position corresponding to 313 of SEQ ID NO: 13; and iii) a P at a position corresponding to 330 of SEQ ID NO: 13. In some embodiments, an RT of the disclosure comprises the amino acid sequence of SEQ ID NO: 13. 13 Atty Dkt No: L1034381430WO (00376)

[0014] An RT of the presently disclosed compositions and methods can comprise an amino acid sequence having at least 80%, at least 81%, at least 82%, at least 83%, at least 84%, at least 85%, at least 86%, at least 87%, at least 88%, at least 89%, at least 90%, at least 91%, at least 92%, at least 93%, at least 94%, at least 95%, at least 96%, at least 97%, at least 98%, at least 99%, at least 99.1%, 5 at least 99.2%, at least 99.3%, at least 99.4%, at least 99.5%, at least 99.6%, at least 99.7%, at least 99.8%, or at least 99.9% sequence identity to SEQ ID NO: 14, more preferably having at least 98%, at least 99%, at least 99.1%, at least 99.2%, at least 99.3%, at least 99.4%, at least 99.5%, at least 99.6%, at least 99.7%, at least 99.8%, or at least 99.9% sequence identity to SEQ ID NO: 14, wherein said RT comprises at least one of: i) an N at a position corresponding to 198 of SEQ ID NO: 14; ii) a K at a 10 position corresponding to 304 of SEQ ID NO: 14; iii) an F at a position corresponding to 311 of SEQ ID NO: 14; and iv) a P at a position corresponding to 328 of SEQ ID NO: 14. In some embodiments, an RT of the disclosure comprises the amino acid sequence of SEQ ID NO: 14. An RT of the presently disclosed compositions and methods can comprise an amino acid sequence having at least 80%, at least 81%, at least 82%, at least 83%, at least 84%, at least 85%, at 15 least 86%, at least 87%, at least 88%, at least 89%, at least 90%, at least 91%, at least 92%, at least 93%, at least 94%, at least 95%, at least 96%, at least 97%, at least 98%, at least 99%, at least 99.1%, at least 99.2%, at least 99.3%, at least 99.4%, at least 99.5%, at least 99.6%, at least 99.7%, at least 99.8%, or at least 99.9% sequence identity to SEQ ID NO: 15, 16 or 17, more preferably having at least 90%, at least 91%, at least 92%, at least 93%, at least 94%, at least 95%, at least 96%, at least 20 97%, at least 98%, at least 99%, at least 99.1%, at least 99.2%, at least 99.3%, at least 99.4%, at least 99.5%, at least 99.6%, at least 99.7%, at least 99.8%, or at least 99.9% sequence identity to SEQ ID NO: 15, 16 or 17, wherein said RT comprises at least one of: i) an N at a position corresponding to 198 of SEQ ID NO: 15, 16 or 17; ii) a K at a position corresponding to 304 of SEQ ID NO: 15, 16 or 17; iii) an F at a position corresponding to 311 of SEQ ID NO: 15, 16 or 17; and iv) a P at a position 25 corresponding to 328 of SEQ ID NO: 15, 16 or 17. In some embodiments, an RT of the disclosure comprises the amino acid sequence of SEQ ID NO: 15, 16 or 17. III. DNA-binding polypeptides The disclosure provides compositions including fusion proteins, PEs, and PE systems, that 30 comprise a DNA-binding polypeptide. Such fusion proteins, PEs, and PE systems, are useful for targeted editing of DNA in vitro, ex vivo, or in vivo. These novel fusion proteins, PEs, and PE systems, are active in mammalian cells and are useful for targeted editing of DNA molecules. As used herein, the term “DNA-binding polypeptide” refers to any polypeptide which is capable of binding to DNA. In certain embodiments, the DNA-binding polypeptide component of the35 presently disclosed compositions (e.g., fusion proteins, PEs, and / or PE systems) binds to double- stranded DNA. In particular embodiments, the DNA-binding polypeptide binds to DNA in a 14 Atty Dkt No: L1034381430WO (00376)

[0015] sequence-specific manner. As used herein, the terms “sequence-specific” or “sequence-specific manner” refer to the selective interaction with a specific nucleotide sequence. Two polynucleotide sequences can be considered to be substantially complementary when the two sequences hybridize to each other under stringent conditions. Likewise, a DNA-binding 5 polypeptide is considered to bind to a particular target sequence in a sequence-specific manner if the DNA-binding polypeptide binds to its sequence under stringent conditions. By “stringent conditions” or “stringent hybridization conditions” is intended conditions under which the two polynucleotide sequences (or the polypeptide binds to its specific target sequence) will bind to each other to a detectably greater degree than to other sequences (e.g., at least 2-fold over background). Stringent 10 conditions are sequence-dependent and will be different in different circumstances. Typically, stringent conditions will be those in which the salt concentration is less than 1.5 M Na ion, typically about 0.01 to 1.0 M Na ion concentration (or other salts) at pH 7.0 to 8.3, and the temperature is at least 30°C for short sequences (e.g., 10 to 50 nucleotides) and at least 60°C for long sequences (e.g., greater than 50 nucleotides). Stringent conditions may also be achieved with the addition of 15 destabilizing agents such as formamide. Exemplary low stringency conditions include hybridization with a buffer solution of 30 to 35% formamide, 1 M NaCl, 1% SDS (sodium dodecyl sulfate) at 37°C, and a wash in 1X to 2X SSC (20X SSC = 3.0 M NaCl / 0.3 M trisodium citrate) at 50 to 55°C. Exemplary moderate stringency conditions include hybridization in 40 to 45% formamide, 1.0 M NaCl, 1% SDS at 37°C, and a wash in 0.5X to 1X SSC at 55 to 60°C. Exemplary high stringency 20 conditions include hybridization in 50% formamide, 1 M NaCl, 1% SDS at 37°C, and a wash in 0.1X SSC at 60 to 65°C. Optionally, wash buffers may comprise about 0.1% to about 1% SDS. Duration of hybridization is generally less than about 24 hours, usually about 4 to about 12 hours. The duration of the wash time will be at least a length of time sufficient to reach equilibrium. The Tm is the temperature (under defined ionic strength and pH) at which 50% of a 25 complementary target sequence hybridizes to a perfectly matched sequence. For DNA-DNA hybrids, the Tm can be approximated from the equation of Meinkoth and Wahl (1984) Anal. Biochem. 138:267-284: Tm = 81.5°C + 16.6 (log M) + 0.41 (%GC) - 0.61 (% form) - 500 / L; where M is the molarity of monovalent cations, %GC is the percentage of guanosine and cytosine nucleotides in the DNA, % form is the percentage of formamide in the hybridization solution, and L is the length of the 30 hybrid in base pairs. Generally, stringent conditions are selected to be about 5°C lower than the thermal melting point (Tm) for the specific sequence and its complement at a defined ionic strength and pH. However, severely stringent conditions can utilize a hybridization and / or wash at 1, 2, 3, or 4°C lower than the thermal melting point (Tm); moderately stringent conditions can utilize a hybridization and / or wash at 6, 7, 8, 9, or 10°C lower than the thermal melting point (Tm); low 35 stringency conditions can utilize a hybridization and / or wash at 11, 12, 13, 14, 15, or 20°C lower than the thermal melting point (Tm). Using the equation, hybridization and wash compositions, and desired Tm, those of ordinary skill will understand that variations in the stringency of hybridization 15 Atty Dkt No: L1034381430WO (00376)

[0016] and / or wash solutions are inherently described. An extensive guide to the hybridization of nucleic acids is found in Tijssen (1993) Laboratory Techniques in Biochemistry and Molecular Biology— Hybridization with Nucleic Acid Probes, Part I, Chapter 2 (Elsevier, New York); and Ausubel et al., eds. (1995) Current Protocols in Molecular Biology, Chapter 2 (Greene Publishing and Wiley- 5 Interscience, New York). See Sambrook et al. (1989) Molecular Cloning: A Laboratory Manual (2d ed., Cold Spring Harbor Laboratory Press, Plainview, New York). In certain embodiments, the sequence-specific DNA-binding polypeptide is an RNA-guided, DNA-binding polypeptide (RGDBP). As used herein, the terms “RNA-guided, DNA-binding polypeptide” and “RGDBP” refer to polypeptides capable of binding to DNA through the 10 hybridization of an associated RNA molecule with the target DNA sequence. In some embodiments, the DNA-binding polypeptide of the fusion protein, PE, or PE system is a nuclease, such as a sequence-specific nuclease. As used herein, the term “nuclease” refers to an enzyme that catalyzes the cleavage of phosphodiester bonds between nucleotides in a nucleic acid molecule. In some embodiments, the DNA-binding polypeptide is an endonuclease, which is capable 15 of cleaving phosphodiester bonds between nucleotides within a nucleic acid molecule, whereas in certain embodiments, the DNA-binding polypeptide is an exonuclease that is capable of cleaving the nucleotides at either end (5' or 3') of a nucleic acid molecule. In some embodiments, the sequence- specific nuclease is selected from the group consisting of a meganuclease, a zinc finger nuclease, a TAL-effector DNA binding domain-nuclease fusion protein (TALEN), and an RNA-guided nuclease 20 (RGN) or variants thereof wherein the nuclease activity has been reduced or inhibited. As used herein, the term “meganuclease” or “homing endonuclease” refers to endonucleases that bind a recognition site within double-stranded DNA that is 12 to 40 bp in length. Non-limiting examples of meganucleases are those that belong to the LAGLIDADG family that comprise the conserved amino acid motif LAGLIDADG (SEQ ID NO: 490). The term “meganuclease” can refer to 25 a dimeric or single-chain meganuclease. As used herein, the term “zinc finger nuclease” or “ZFN” refers to a chimeric protein comprising a zinc finger DNA-binding domain and a nuclease domain. As used herein, the term “TAL-effector DNA binding domain-nuclease fusion protein” or “TALEN” refers to a chimeric protein comprising a TAL effector DNA-binding domain and a 30 nuclease domain. In certain embodiments, the DNA-binding polypeptide is one which is capable of generating a single-stranded region within a double-stranded DNA molecule. An example of a single-stranded region is the single-stranded loop comprised within an R-loop, which is a three-stranded nucleic acid structure comprising a region of single-stranded DNA that is formed within a double-stranded DNA 35 molecule that results from the hybridization of the complementary strand to a single-stranded RNA or DNA molecule. 16 Atty Dkt No: L1034381430WO (00376)

[0017] In some embodiments, the DNA-binding polypeptide that is capable of generating an R-loop within a double-stranded DNA molecule is an RNA-guided DNA-binding polypeptide or an RGN. As used herein, the term “RNA-guided nuclease” or “RGN” refers to an RNA-guided, DNA-binding polypeptide that has nuclease activity. RGNs are considered “RNA-guided” because guide RNAs 5 form a complex with the RNA-guided nucleases to direct the RNA-guided nucleases to bind to a target sequence and in some embodiments, introduce a single-stranded or double-stranded break at the target sequence. A composition (e.g., a fusion protein, a PE, and / or a PE system) provided herein can comprise an RGN comprising at least one nuclease domain (e.g., DNase, RNase domain) and at least 10 one RNA recognition and / or RNA binding domain to interact with guide RNAs. In some embodiments, the RGN of the composition (e.g., a fusion protein, a PE, and / or a PE system) comprises only one active nuclease domain and thus functions as a nickase. In some embodiments, the RGN nuclease domain that is active in an RGN nickase is a RuvC domain. In some embodiments, the RGN comprises an inactivated HNH nuclease domain. Further domains that can be found in RGNs 15 include, but are not limited to: DNA binding domains, helicase domains, protein-protein interaction domains, and dimerization domains. In some embodiments, the amino acid sequence of an RGN of the disclosure can have at least 70%, at least 75%, at least 80%, at least 85%, at least 90%, at least 91%, at least 92%, at least 93%, at least 94%, at least 95%, at least 96%, at least 97%, at least 98%, at least 99%, or more sequence identity to one or more of a DNA binding domain, helicase domain, 20 protein-protein interaction domain, and dimerization domain of an RGN disclosed in Table 1 or set forth as any one of SEQ ID NOs: 387-420, and 484-489. In various embodiments, a target sequence is bound by an RGN of a composition (e.g., a fusion protein, a PE, and / or a PE system) provided herein. In those instances wherein the target sequence is double-stranded (e.g., double-stranded DNA), the target strand of the target sequence 25 hybridizes with the guide RNA associated with the RGN. The target strand and / or the non-target strand of the target sequence (e.g., target DNA sequence) can then be subsequently cleaved by the RGN if the polypeptide possesses nuclease activity. The terms “cleave” or “cleavage” refer to the hydrolysis of at least one phosphodiester bond within the backbone of one or both strands of a double- stranded target sequence (e.g., target DNA sequence) that can result in either single-stranded or 30 double-stranded breaks within the target sequence. RGNs can cleave nucleotides within a polynucleotide, functioning as an endonuclease, or can be an exonuclease, removing successive nucleotides from the end (the 5' and / or the 3' end) of a polynucleotide. In some embodiments, RGNs can cleave nucleotides of a target polynucleotide within any position of a polynucleotide and thus function as both an endonuclease and exonuclease. The cleavage of a target polynucleotide by RGNs 35 can result in staggered breaks or blunt ends. A staggered cut in a polynucleotide leads to two sticky ends or overhanging ends, and is formed when the nuclease cuts each strand of a polynucleotide such that the cuts are not directly opposite each other. For each sticky end of the cut polynucleotide, one 17 Atty Dkt No: L1034381430WO (00376)

[0018] strand (i.e. the overhanging strand) is longer than the other (typically by at least a few nucleotides), such that the longer strand has bases which are left unpaired. The longer strand of an overhanging end of a cleaved polynucleotide can have one unpaired nucleotide, two unpaired nucleotides, 3 unpaired nucleotides, 4 unpaired nucleotides, 5 unpaired nucleotides, or more unpaired nucleotides. In some 5 embodiments, the longer strand of an overhanging end of a cleaved polynucleotide can have one unpaired nucleotide. The overhanging end of a cleaved polynucleotide can be a 3′ overhang or a 5′ overhang. In some embodiments, the overhanging end of a cleaved polynucleotide is a 3′ overhang. In some embodiments, the overhanging end of a cleaved polynucleotide is a 5′ overhang. In some embodiments, an RGN, or an active variant or fragment thereof, of the disclosure cleaves a target 10 polynucleotide to form a staggered cut, wherein the staggered cut creates a 3′ overhang with one unpaired nucleotide. By contrast, a blunt cut generates two blunt ends, such that each blunt end of the cut polynucleotide has both strands that are of equal length – i.e. there are no unpaired bases on either strand of a blunt end. RNA-guided nucleases (RGNs) allow for the targeted manipulation of a single site within a 15 genome and are useful in the context of gene targeting for therapeutic and research applications. In a variety of organisms, including mammals, RNA-guided nucleases have been used for genome engineering by stimulating either non-homologous end joining or homologous recombination. RGNs include CRISPR-Cas proteins, which are RNA-guided nucleases directed to the target sequence by a guide RNA (gRNA) as part of a Clustered Regularly Interspaced Short Palindromic Repeats 20 (CRISPR) RNA-guided nuclease system, or active variants or fragments thereof. Some aspects of this disclosure provide compositions (e.g., fusion proteins, PEs, and / or PE systems) that comprise an RNA-guided DNA-binding polypeptide. In some embodiments, the RNA- guided DNA-binding polypeptide is an RNA-guided nuclease (RGN). RGNs of the presently disclosed compositions (e.g., fusion proteins, PEs, and / or PE systems) can be wild-type sequences 25 derived from bacterial or archaeal species. Alternatively, the RGNs can be variants or fragments of wild-type polypeptides. The wild-type RGN can be modified to alter nuclease activity or alter PAM specificity, for example. In some embodiments, the RGN is not naturally-occurring. In further embodiments, the RNA-guided nuclease is a naturally occurring CRISPR-Cas protein or an active variant or fragment thereof. CRISPR-Cas systems are classified into Class 1 or 30 Class 2 systems. Class 2 systems comprise a single effector nuclease and include Types II, V, and VI. The Class 1 and 2 systems are subdivided into types (Types I, II, III, IV, V, VI), with some types further divided into subtypes (e.g., Type II-A, Type II-B, Type II-C, Type V-A, Type V-B). In certain embodiments, the RGN is a naturally occurring Type II CRISPR-Cas protein or an active variant or fragment thereof. As used herein, the term “Type II CRISPR-Cas protein,” “Type II 35 CRISPR-Cas effector protein,” or “Type II RNA-guided nuclease” refers to an RGN that requires a trans-activating RNA (tracrRNA) and comprises two nuclease domains (i.e., RuvC and HNH), each of which is responsible for cleaving a single strand of a double-stranded DNA molecule. In certain 18 Atty Dkt No: L1034381430WO (00376)

[0019] embodiments, the RGN of the fusion protein, PE, or PE system is a nickase variant of a naturally occurring Type II CRISPR-Cas protein or an active variant or fragment thereof or a Type V CRISPR- Cas protein or an active variant or fragment thereof. In some embodiments, the present disclosure provides a composition (e.g., a fusion protein, a PE, and / or a PE system) comprising a Cas9 protein, 5 such as Streptococcus pyogenes Cas9 (SpCas9) (SEQ ID NO: 484) or a SpCas9 H840A nickase (SEQ ID NO: 485), which are described in U.S. Pat. Nos.10,000,772 and 8,697,359, each of which is herein incorporated by reference in its entirety. In some embodiments, the present disclosure provides a composition (e.g., a fusion protein, a PE, and / or a PE system) comprising a Streptococcus thermophilus Cas9 (StCas9) (SEQ ID NO: 486), or a StCas9 H599A nickase (SEQ ID NO: 487), and 10 are disclosed in U.S. Pat. No.10,113,167, which is herein incorporated by reference in its entirety. In some embodiments, the present disclosure provides a composition (e.g., a fusion protein, a PE, and / or a PE system) comprising a Staphylococcus aureus Cas9 (SaCas9) (SEQ ID NO: 488), or a SaCas9 H488A nickase (SEQ ID NO: 489), which are disclosed in U.S. Pat. No.9,752,132, which is herein incorporated by reference in its entirety. 15 In some embodiments, the CRISPR-Cas protein is a naturally-occurring Type V CRISPR-Cas protein or an active variant or fragment thereof. As used herein, the term “Type V CRISPR-Cas protein,” “Type V CRISPR-Cas effector protein,” or “Type V RNA-guided nuclease” refers to an RGN that cleaves dsDNA and comprises a single RuvC nuclease domain or a split-RuvC nuclease domain and lacks an HNH domain (Zetsche et al 2015, Cell doi:10.1016 / j.cell.2015.09.038; Shmakov 20 et al 2017, Nat Rev Microbiol doi:10.1038 / nrmicro.2016.184; Yan et al 2018, Science doi:10.1126 / science.aav7271; Harrington et al 2018, Science doi:10.1126 / science.aav4294). In some embodiments, a presently disclosed composition (e.g., a fusion protein, a PE, and / or a PE system) comprises a Cas12 (e.g., Cas12a). It is to be noted that Cas12a is also referred to as Cpf1, and does not require a tracrRNA, although other Type V CRISPR-Cas proteins, such as Cas12b, do require a 25 tracrRNA. Most Type V effectors can also target ssDNA (single-stranded DNA), often without a PAM requirement (Zetsche et al 2015; Yan et al 2018; Harrington et al 2018). The terms “Type V CRISPR-Cas protein” and “Type V RGN” encompasses the unique RGNs comprising split RuvC nuclease domains, such as those disclosed in WO 2021 / 138247, the contents of each of which are incorporated herein by reference in its entirety. In some embodiments, the present disclosure provides 30 a composition (e.g., a fusion protein, a PE, and / or a PE system) comprising a Francisella novicida Cas12a (FnCas12a), the sequence of which is set forth as SEQ ID NO: 491 and is disclosed in U.S. Pat. No.9,790,490, which is herein incorporated by reference in its entirety, or any of the nuclease- inactivating mutants of FnCas12a disclosed within U.S. Pat. No.9,790,490. In some embodiments, the presently disclosed compositions (e.g., fusion proteins, PEs, and / or 35 PE systems) comprise an RGN, or a nickase or nuclease-dead variant thereof, that is disclosed in International Appl. Publ. Nos. WO 2019 / 236566, WO 2021 / 030344, WO 2021 / 217002, WO 19 Atty Dkt No: L1034381430WO (00376)

[0020] 2022 / 056254, WO 2023 / 139557, WO 2024 / 033901, and U.S. Provisional Application No.63 / 591,255 filed October 18, 2023, each of which is incorporated by reference herein in its entirety. In some embodiments, the presently disclosed compositions (e.g., fusion proteins, PEs, and / or PE systems) comprise an RGN, or a nickase or nuclease-dead variant thereof, listed in Table 1, and / or 5 set forth as SEQ ID NOs: 387-420. The guide RNA sequences (crRNA repeat and tracrRNA sequences) that can be used with each RGN of Table 1 are also provided, as well as the consensus PAM sequence. In certain embodiments, the composition (e.g., a fusion protein, a PE, and / or a PE system) comprises an active variant of an RGN (one able to bind to a nucleic acid molecule in an RNA-guided manner) listed in Table 1 and / or set forth as SEQ ID NOs: 387-420 having between 80% 10 and 99% or more sequence identity to any one of the amino acid sequences listed in Table 1 and / or set forth as SEQ ID NOs: 387-420, including but not limited to about or more than about 80%, about 81%, about 82%, about 83%, about 84%, about 85%, about 86%, about 87%, about 88%, about 89%, about 90%, about 91%, about 92%, about 93%, about 94%, about 95%, about 96%, about 97%, about 98%, about 99%, or more. In some embodiments, the composition (e.g., a fusion protein, a PE, and / or 15 a PE system) comprises an RGN having at least 80%, at least 81%, at least 82%, at least 83%, at least 84%, at least 85%, at least 86%, at least 87%, at least 88%, at least 89%, at least 90%, at least 91%, at least 92%, at least 93%, at least 94%, at least 95%, at least 96%, at least 97%, at least 98%, at least 99%, or more sequence identity to an RGN amino acid sequence disclosed in Table 1 and / or set forth as SEQ ID NOs: 387-420. In other embodiments, the composition (e.g., a fusion protein, a PE, and / or 20 a PE system) comprises a fragment of an RGN listed in Table 1 such as one that differs by as few as 1-15 amino acid residues, as few as 1-10, such as 6-10, as few as 5, as few as 4, as few as 3, as few as 2, or as few as 1 amino acid residue. In specific embodiments, the RGN comprises an N-terminal or a C-terminal truncation, which can comprise at least a deletion of 1, 2, 3, 4, 5, 10, 15, 20, 25, 30, 35, 40, 45, 50, 55, 60 amino acids or more from either the N or C terminus of the polypeptide. In some 25 embodiments, the RGN comprises an internal deletion which can comprise at least a deletion of 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 25, 30, 35, 40, 45, 50, 55, 60 amino acids or more. Table 1. Non-limiting examples of RGNs that can be used in the presently disclosed fusion 30 proteins, PEs, and PE systems. RGN Name RGN SEQ crRNA repeat tracrRNA PAM ID NO SEQ ID NO SEQ ID NO n 20 Atty Dkt No: L1034381430WO (00376)

[0021] RGN Name RGN SEQ crRNA repeat tracrRNA PAM ID NO: SEQ ID NO: SEQ ID NO: sequence APG05083.1 532 533 534 NNNNCC A 21 Atty Dkt No: L1034381430WO (00376)

[0022] RGN Name RGN SEQ crRNA repeat tracrRNA PAM ID NO: SEQ ID NO: SEQ ID NO: sequence APG01560 679 455 458 NNRYA A A A 22 Atty Dkt No: L1034381430WO (00376)

[0023] RGN Name RGN SEQ crRNA repeat tracrRNA PAM ID NO: SEQ ID NO: SEQ ID NO: sequence LPG10204 792 793 794 NNNNGTG, A A A or T / U; H = or C or T / U; M = or C 5 In some embodiments, RGNs that can be used in the presently disclosed compositions (e.g., fusion proteins, PEs, and / or PE systems) include LPG10221 (set forth as SEQ ID NO: 387 and previously described in International Appl. No. PCT / US2025 / 015624, filed February 12, 2025; which is herein incorporated by reference in its entirety), APG07433.1 (set forth as SEQ ID NO: 389 and previously described in International Appl. Publ. No. WO 2019 / 236566, which is herein incorporated 10 by reference in its entirety), APG05586 (set forth as SEQ ID NO: 388 and previously described in International Appl. Publ. No. WO 2021 / 217002, which is herein incorporated by reference in its entirety), LPG10145 (set forth as SEQ ID NO: 390 and previously described in International Appl. Publ. No. WO 2023 / 139557, which is herein incorporated by reference in its entirety), and APG01604 (set forth as SEQ ID NO: 391 and previously described in International Appl. Publ. No. WO 15 2021 / 217002, which is herein incorporated by reference in its entirety) RGNs, or active variants or fragments thereof, that retain the ability to bind to a target sequence in an RNA-guided sequence- specific manner. In some of these embodiments, the active fragment or variant of the LPG10221, APG07433.1, APG05586, LPG10145, and APG01604 RGN is capable of cleaving a single strand of a double-stranded target sequence. In some embodiments, an active variant of the LPG10221, 20 APG07433.1, APG05586, LPG10145, and APG01604 RGN comprises an amino acid sequence having at least 40%, 45%, 50%, 55%, 60%, 65%, 70%, 75%, 80%, 81%, 82%, 83%, 84%, 85%, 86%, 87%, 88%, 89%, 90%, 91%, 92%, 93%, 94%, 95%, 96%, 97%, 98%, 99% or more sequence identity to the amino acid sequence set forth as any one of SEQ ID NOs: 387-420. The composition (e.g., a fusion protein, a PE, and / or a PE system) can comprise an active 25 fragment of any one of the RGNs provided in Table 1, including LPG10221, APG07433.1, APG05586, APG01604, or LPG10145 RGN, that comprises at least 50, 100, 150, 200, 250, 300, 350, 23 Atty Dkt No: L1034381430WO (00376)

[0024] 400, 450, 500, 550, 600, 650, 700, 750, 800, 850, 900, 950, 1000, or more contiguous amino acid residues of the amino acid sequence set forth as any one of the SEQ ID NOs set forth in Table 1, including SEQ ID NOs: 387-420. In some embodiments, an RGN of the presently disclosed compositions (e.g., fusion proteins, 5 PEs, and / or PE systems) functions as a nickase, only cleaving a single strand of a double-stranded target sequence (e.g., target DNA sequence). Such RGNs have a single functioning nuclease domain. In particular embodiments, the nickase is capable of cleaving the target strand (has an active HNH domain) or the non-target strand (has an active RuvC domain) of the double-stranded target sequence (e.g., target DNA sequence). In order to effect the nicking of a single strand of a double-stranded 10 target polynucleotide (e.g., target DNA), at least one inactivating mutation (also referred to herein as a mutation that reduces nuclease activity) can be introduced into a nuclease domain of an RGN. For example, in order to reduce the activity of or inactivate the HNH domain of LPG10221 or APG07433.1, one or more of the following catalytic amino acid residues can be mutated to an alanine, for example, or another non-conserved amino acid residue: D603, H604, N618, N627. In order to 15 reduce the activity of or inactivate the HNH domain of APG05586, one or more of the following catalytic amino acid residues can be mutated to an alanine, for example, or another non-conserved amino acid residue: D600, H601, N615, N624. In order to reduce the activity of or inactivate the HNH domain of LPG10145, one or more of the following catalytic amino acid residues can be mutated to an alanine, for example, or another non-conserved amino acid residue: H611 and N634. In 20 order to reduce the activity of or inactivate the HNH domain of APG01604, one or more of the following catalytic amino acid residues can be mutated to an alanine, for example, or another non- conserved amino acid residue: H559 and N582. More than one mutation that reduces nuclease activity can be introduced into a nuclease domain of an RGN in order to further reduce or eliminate its activity. Thus, in some embodiments, the HNH nuclease domain of an RGN of a composition (e.g., a 25 fusion protein, a PE, and / or a PE system) comprises an alanine (or another non-conserved amino acid residue) at a position corresponding to 604 and an alanine (or another non-conserved amino acid residue) at a position corresponding to 627 of SEQ ID NO: 387 or 389; an alanine (or another non- conserved amino acid residue) at a position corresponding to 601 and an alanine (or another non- conserved amino acid residue) at a position corresponding to 624 of SEQ ID NO: 388; an alanine (or 30 another non-conserved amino acid residue) at a position corresponding to 559 and an alanine (or another non-conserved amino acid residue) at a position corresponding to 582 of SEQ ID NO: 391; or an alanine (or another non-conserved amino acid residue) at a position corresponding to 611 and an alanine (or another non-conserved amino acid residue) at a position corresponding to 634 of SEQ ID NO: 390. Non-limiting examples of DNA constructs encoding a PE comprising an RGN nickase with 35 double mutations within the HNH domain are set forth as SEQ ID NO: 412 (comprising LPG10221 HNH double mutant), SEQ ID NO: 416 (comprising APG07433.1 HNH double mutant), SEQ ID NO: 414 (comprising APG05586 HNH double mutant), SEQ ID NO: 420 (comprising APG01604 HNH 24 Atty Dkt No: L1034381430WO (00376)

[0025] double mutant), and SEQ ID NO: 418 (comprising LPG10145 HNH double mutant). In some embodiments, the RGN nickase comprises the sequence set forth as any one of SEQ ID NO: 411, 412, 413, 414, 415, 416, 417, 418, 419, and 420, or an active fragment or variant thereof, such as one having at least at least 70%, 75%, 80%, 85%, 90%, 91%, 92%, 93%, 94%, 95%, 96%, 97%, 98%, 5 99% or more sequence identity to any one of SEQ ID NOs: 411, 412, 413, 414, 415, 416, 417, 418, 419, and 420. RGN nickases with inactivated HNH domains can be used for polymerase editing and can be fused to an RT as described herein. In some embodiments, all or part of an HNH domain of an RGN polypeptide is replaced with an RT to generate a PE. In other embodiments, an RGN of the presently disclosed compositions (e.g., fusion proteins, 10 PEs, and / or PE systems) lacks nuclease activity altogether and is referred to herein as nuclease-dead or nuclease inactive. In some embodiments, nuclease-dead or nuclease inactive versions of the enzymes are used for editing a nucleic acid. Any method known in the art for introducing mutations into an amino acid sequence, such as PCR-mediated mutagenesis and site-directed mutagenesis, can be used for generating nickases or nuclease-dead RGNs. See, e.g., U.S. Publ. No.2014 / 0068797 and 15 U.S. Pat. No.9,790,490; each of which is incorporated by reference in its entirety. A composition (e.g., a fusion protein, a PE, and / or a PE system) of the disclosure can comprise an RGN, or an active variant or fragment thereof, that has a PAM-interacting (PI) domain that contributes to recognition of a PAM site in a target polynucleotide. The PI domain can comprise 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 20, 25, 30, 35, 40, 45, 50, 55, 60, 70, 80, 90, 100, 110, 120, 20 130, 140, 150 or more amino acid residues. In some embodiments, the PI domain of an RGN, or an active variant or fragment thereof, of the disclosure is located within the carboxy (C)-terminal region of the RGN. The C-terminal region comprising the PI domain of an RGN, or an active variant or fragment thereof, of the disclosure can include the C-terminal 151 amino acid residues, the C-terminal 150 amino acid residues, the C-terminal 140 amino acid residues, the C-terminal 135 amino acid25 residues, the C-terminal 132 amino acid residues, the C-terminal 130 amino acid residues, the C- terminal 125 amino acid residues, the C-terminal 120 amino acid residues, the C-terminal 110 amino acid residues, the C-terminal 100 amino acid residues, the C-terminal 90 amino acid residues, the C- terminal 80 amino acid residues, the C-terminal 70 amino acid residues, the C-terminal 60 amino acid residues, the C-terminal 50 amino acid residues, the C-terminal 40 amino acid residues, the C- 30 terminal 30 amino acid residues, the C-terminal 20 amino acid residues, or the C-terminal 10 amino acid residues of the RGN. In some embodiments, the PI domain of an RGN, or an active variant or fragment thereof, of the disclosure is within or includes amino acid residues 939-1071 or 999-1150 of the RGN. In some embodiments, the PI domain of an RGN having at least 90% sequence identity to SEQ ID NO: 387 or 389 has the amino acid sequence set forth as SEQ ID NO: 422. In some 35 embodiments, the PI domain of an RGN having the amino acid sequence set forth as SEQ ID NO: 388, or an active variant or fragment thereof, has the amino acid sequence set forth as SEQ ID NO: 421. In some embodiments, the PI domain of an RGN having the amino acid sequence set forth as 25 Atty Dkt No: L1034381430WO (00376)

[0026] SEQ ID NO: 390, or an active variant or fragment thereof, has the amino acid sequence set forth as SEQ ID NO: 423. In some embodiments, the PI domain of an RGN having the amino acid sequence set forth as SEQ ID NO: 391, or an active variant or fragment thereof, has the amino acid sequence set forth as SEQ ID NO: 424. 5 IV. Polymerase editor (PE)-enhancing polypeptides The disclosure provides compositions including fusion proteins, PEs, and PE systems, that comprise a polymerase editor (PE)-enhancing polypeptide. The presently disclosed PE-enhancing polypeptides can include U1 small nuclear ribonucleoprotein A (SNRPA; set forth as SEQ ID NO: 10 336), Tsu (SEQ ID NO: 338), SOSS complex subunit B1 (SSB1; set forth as SEQ ID NO: 339), Sso7d (SEQ ID NO: 340), RBM24 (SEQ ID NO: 483), FXR1 (SEQ ID NO: 482), small nuclear ribonucleoprotein G (SNRPG; set forth as SEQ ID NO: 343), and SsoSSB (SEQ ID NO: 344), as well as active variants and fragments thereof. While not being bound by any particular theory or mechanism of action, it is believed that the ability of PE-enhancing polypeptides (such as SNRPA, 15 SSB1, Sso7d, RBM24, FXR1, SNRPG, and SsoSSB) to bind to single-stranded RNA is important for its PE-enhancing activity. Thus, in some embodiments, active fragments of the presently disclosed PE-enhancing polypeptides comprise the RNA-binding domain of the full-length protein. In some embodiments, the ability of PE-enhancing polypeptides (such as SNRPA, SSB1, Sso7d, RBM24, FXR1, SNRPG, and SsoSSB, or variants or fragments thereof) to enhance polymerase editing activity 20 does not require binding a nucleic acid directly. The RNA recognition motif (RRM) of SNRPA is found at amino acid residues 7-95 of SEQ ID NO: 336. Truncated SNRPA, which comprises amino acid residues 91-282 of SEQ ID NO: 336 is set forth as SEQ ID NO: 335. The RRM of Tsu is found at amino acid residues 67-154 of SEQ ID NO: 338. Truncated Tsu 25 which comprises amino acid residues 72-151 of SEQ ID NO: 338 is set forth as SEQ ID NO: 337. The RRM of RBM24 is found at amino acid residues 11-95 of SEQ ID NO: 483, and is set forth as SEQ ID NO: 341 and referred to as RBM24 RRM core. The non-canonical RNA-binding domain of FXR1 is found at amino acid residues 410-468 of SEQ ID NO: 482, and is set forth as SEQ ID NO: 342 and referred to as FXR1 RNA-binding domain 30 (RBD). The PE-enhancing polypeptides described herein and variants or fragments thereof, include but are not limited to a PE-enhancing polypeptide having at least 50%, at least 60%, at least 70%, at least 80%, at least 85%, at least 86%, at least 87%, at least 88%, at least 89%, at least 90%, at least 91%, at least 92%, at least 93%, at least 94%, at least 95%, at least 96%, at least 97%, at least 98%, at 35 least 99%, or more sequence identity to SEQ ID NO: 335, 336, 337, 338, 339, 340, 341, 342, 343, 344, 482, or 483. 26 Atty Dkt No: L1034381430WO (00376)

[0027] The presently disclosed PE-enhancing polypeptides can include replication factor C subunit 4 (RFC4; set forth as SEQ ID NO: 359) and a truncated version thereof set forth as SEQ ID NO: 360, DNA-directed RNA polymerase subunit alpha (rpoA; set forth as SEQ ID NO: 813) and a truncated version thereof set forth as SEQ ID NO: 361; DNA integrity scanning protein DisAv (disAv; set forth 5 as SEQ ID NO: 814) and two truncated versions thereof referred to as disAv2 and disAv1 and set forth as SEQ ID NO: 362 and 363, respectively; tumor protein 63 (TP63; set forth as SEQ ID NO: 815) and a truncated version thereof set forth as SEQ ID NO: 364; RadA (set forth as SEQ ID NO: 816) and a truncated version thereof set forth as SEQ ID NO: 365; VTS1 (set forth as SEQ ID NO: 819) and a truncated version thereof set forth as SEQ ID NO: 366; NTHL1 (set forth as SEQ ID NO:10 821) and a truncated version thereof set forth as SEQ ID NO: 367; ankyrin repeat and SAM domain- containing protein 3 (ANKS3; set forth as SEQ ID NO: 822) and a truncated version thereof set forth as SEQ ID NO: 370; ERCC-1 (set forth as SEQ ID NO: 820) and a truncated version thereof set forth as SEQ ID NO: 368; Rad51 (set forth as SEQ ID NO: 817) and a truncated version thereof set forth as SEQ ID NO: 372; and Rad51C (set forth as SEQ ID NO: 818) and a truncated version thereof set 15 forth as SEQ ID NO: 371; and active variants and fragments thereof. While not being bound by any particular theory or mechanism of action, it is believed that the ability of PE-enhancing polypeptides to bind to single-stranded DNA is important for its PE-enhancing activity. Thus, in some embodiments, active fragments of the presently disclosed PE-enhancing polypeptides comprise the DNA-binding domain of the full-length protein or those truncated versions provided herein. In some 20 embodiments, the ability of PE-enhancing polypeptides (such as RFC4, rpoA, disAv2, disAv1, TP63, RadA, VTS1, NTHL1, ANKS3, ERCC-1, Rad51, and Rad51C, or variants or fragments thereof) to enhance polymerase editing activity does not require binding a nucleic acid directly. The DNA-binding domain of RFC4 (SEQ ID NO: 359 and referred to herein as RFC4 truncated) is found at amino acid residues 200-270 of the full-length RFC4 protein set forth as SEQ 25 ID NO: 359. The DNA-binding domain of rpoA (SEQ ID NO: 361 and referred to herein as rpoA truncated) is found at amino acid residues 230-344 of the full-length rpoA protein set forth as SEQ ID NO: 813. The DNA-binding domains of DisAv is found at amino acid residues 145-357 of the full- 30 length DisAv protein set forth as SEQ ID NO: 814. DisAv1 (SEQ ID NO: 363 and referred to herein as DisAv1 truncated) is found at amino acid residues 285-357 of the full-length DisAv protein set forth as SEQ ID NO: 814. DisAv2 (SEQ ID NO: 362 and referred to herein as DisAv2 truncated) comprises amino acid residues 145-357 of the full-length DisAv protein set forth as SEQ ID NO: 144. The DNA-binding domain of TP63 (SEQ ID NO: 364 and referred to herein as TP63 35 truncated) is found at amino acid residues 543-623 of the full-length TP63 protein set forth as SEQ ID NO: 815. 27 Atty Dkt No: L1034381430WO (00376)

[0028] The DNA-binding domain of RadA (SEQ ID NO: 365 and referred to herein as RadA truncated) is found at amino acid residues 1-100 of the full-length RadA protein set forth as SEQ ID NO: 816. The DNA-binding domain of Rad51 (SEQ ID NO: 372 and referred to herein as Rad51 5 truncated) is found at amino acid residues 1-100 of the full-length Rad51 protein set forth as SEQ ID NO: 817. The DNA-binding domain of Rad51C (SEQ ID NO: 371 and referred to herein as Rad51C truncated) is found at amino acid residues 1-76 of the full-length Rad51C protein set forth as SEQ ID NO: 818. 10 The DNA-binding domain of VTS1 (SEQ ID NO: 366 and referred to herein as VTS1 truncated) is found at amino acid residues 439-523 of the full-length VTS1 protein set forth as SEQ ID NO: 819. The DNA-binding domain of ERCC-1 (SEQ ID NO: 368 and referred to herein as ERCC-1 truncated) is found at amino acid residues 96-219 of the full-length ERCC-1 protein set forth as SEQ 15 ID NO: 820. The DNA-binding domain of NTHL1 (SEQ ID NO: 367 and referred to herein as NTHL1 truncated) is found at amino acid residues 64-240 of the full-length NTHL1 protein set forth as SEQ ID NO: 821. The DNA-binding domain of ANKS3 (SEQ ID NO: 370 and referred to herein as ANKS3 20 truncated) is found at amino acid residues 421-487 of the full-length ANKS3 protein set forth as SEQ ID NO: 822. The PE-enhancing polypeptides described herein and variants or fragments thereof, include but are not limited to a PE-enhancing polypeptide having at least 50%, at least 60%, at least 70%, at least 80%, at least 85%, at least 86%, at least 87%, at least 88%, at least 89%, at least 90%, at least 25 91%, at least 92%, at least 93%, at least 94%, at least 95%, at least 96%, at least 97%, at least 98%, at least 99%, or more identity to SEQ ID NO: 359, 360, 361, 362, 363, 364, 365, 366, 367, 368, 370, 371, or 372. The presently disclosed PE-enhancing polypeptides enhance polymerase editors or polymerase editing enacted thereby. As used herein, the term “enhance” or “enhancing” as it relates to 30 polymerase editors or polymerase editing refers to an increase in editing rates when a PE-enhancing polypeptide is present (as a fusion protein with an RT or DNA-binding polypeptide (e.g., RGN) or both an RT and DNA-binding polypeptide (e.g., RGN) or provided in trans) as compared to polymerase editing rates in the absence of the PE-enhancing polypeptide. An increase in editing rates with a PE-enhancing polypeptide versus the absence of the PE-enhancing polypeptide can be an 35 increase of about 1.1 fold, about 1.2 fold, about 1.3 fold, about 1.4 fold, about 1.5 fold, about 1.6 fold, about 1.7 fold, about 1.8 fold, about 1.9 fold, about 2 fold, about 2.1 fold, about 2.2 fold, about 2.3 fold, about 2.4 fold about 2.5 fold, about 2.6 fold, about 2.7 fold, about 2.8 fold, about 2.9 fold, about 28 Atty Dkt No: L1034381430WO (00376)

[0029] 3 fold, about 3.2 fold, about 3.5 fold, about 3.8 fold, about 4 fold, about 5 fold, about 6 fold, about 7 fold, about 8 fold, about 9 fold, about 10 fold, or more. In some embodiments, the PE-enhancing polypeptide increases polymerase editing rates by about 1.75 fold. 5 V. Fusion Proteins Comprising RTs The present disclosure provides fusion proteins comprising the presently disclosed RTs operably fused to at least one heterologous polypeptide, as well as polynucleotides encoding the fusion proteins. When used to refer to the joining of two protein coding regions, by “operably linked” or “operably fused” is intended that the coding regions are in the same reading frame, even if one is 10 inserted into another. In some embodiments, polypeptides that are “operably fused” or “operably linked” means that the structure and / or biological activity of each individual peptide is also present in the fusion. “Fusion protein,” “fusion,” “fuse,” or “fused” as used herein means two or more polypeptides are operably linked together, for example, by end-to-end joining or inserting one into another. 15 As used herein, “heterologous”, in reference to a polypeptide that is heterologous to another polypeptide (e.g., RT), is a polypeptide that is not operably fused to the presently described RTs in nature. The heterologous polypeptide can originate from a foreign species or from the same species. The heterologous polypeptide can be in its native form or is substantially modified from its native form in composition and / or genomic locus by deliberate human intervention. The heterologous 20 polypeptide can be any polypeptide, including but not limited to a localization signal, cell-penetrating domain, detectable label (e.g., fluorescent protein) or purification tag to aid in the purification of the RT. The disclosed RTs can be operably fused to a detectable label. A detectable label is a molecule that can be visualized or otherwise observed. Detectable labels that can be fused to the 25 presently disclosed RTs as a fusion protein include any detectable protein domain, including but not limited to, a fluorescent protein or a protein domain that can be detected with a specific antibody. Non-limiting examples of fluorescent proteins include green fluorescent proteins (e.g., GFP, EGFP, ZsGreen1) and yellow fluorescent proteins (e.g., YFP, EYFP, ZsYellow1). RTs can also comprise a purification tag, which is any molecule that can be utilized to isolate 30 a protein or fused protein from a mixture (e.g., biological sample, culture medium). Non-limiting examples of purification tags include biotin, myc, maltose binding protein (MBP), glutathione-S- transferase (GST), and 3X FLAG tag. The presently disclosed RTs can comprise at least one nuclear localization signal (NLS) to enhance transport of the protein to the nucleus of a cell, as described elsewhere herein. Other 35 localization signal sequences known in the art that localize polypeptides to particular subcellular location(s) can also be used to target the RTs, including, but not limited to, plastid localization 29 Atty Dkt No: L1034381430WO (00376)

[0030] sequences, mitochondrial localization sequences, and dual-targeting signal sequences that target to both the plastid and mitochondria. The NLS or other localization peptides or signals can be operably fused at the N-terminus, the C-terminus, or both the N-terminus and C-terminus of the RT or the heterologous polypeptide (e.g., a DNA-binding polypeptide and / or a PE-enhancing polypeptide). In 5 some embodiments, the NLS has an amino acid sequence having at least 80%, at least 81%, at least 82%, at least 83%, at least 84%, at least 85%, at least 86%, at least 87%, at least 88%, at least 89%, at least 90%, at least 91%, at least 92%, at least 93%, at least 94%, at least 95%, at least 96%, at least 97%, at least 98%, at least 99%, or more sequence identity to any one of SEQ ID NOs: 425-430. In some embodiments, the NLS has the amino acid sequence of any one of SEQ ID NOs: 425-430. 10 The presently disclosed RTs can comprise at least one cell-penetrating domain that facilitates cellular uptake of the RT, as described elsewhere herein. The heterologous polypeptide operably fused to the presently disclosed RTs can be a DNA- binding polypeptide (e.g., RGN polypeptide) as described elsewhere herein. The heterologous polypeptide operably fused to the presently disclosed RTs can be a PE-enhancing polypeptide as 15 described elsewhere herein. The heterologous polypeptide operably fused to the presently disclosed RTs can comprise both a DNA-binding polypeptide (e.g., RGN polypeptide) and a PE-enhancing polypeptide. The heterologous polypeptide can be located at the N-terminus, the C-terminus, or an internal location of the RT, either directly or indirectly via a peptide linker. Alternatively, the RT can be 20 located in an internal location of the heterologous polypeptide (e.g., a DNA-binding polypeptide such as an RGN polypeptide), either directly or indirectly via a peptide linker. A peptide linker of the disclosure can connect one polypeptide to another in a fusion protein. For example, a peptide linker can connect: an RT and a heterologous polypeptide; an RT and a DNA- binding polypeptide; an RT and a PE-enhancing polypeptide; or a DNA-binding polypeptide and a 25 PE-enhancing polypeptide. A fusion protein comprising 3 polypeptides (e.g., an RT, a DNA-binding polypeptide, and a PE-enhancing polypeptide) can comprise at least one peptide linker. In some embodiments, a peptide linker comprises at least one NLS. In some embodiments, a peptide linker comprises 2 NLSs. The peptide linker can be operably fused at the N-terminus, the C-terminus, or both the N-terminus and C-terminus of the RT or the heterologous polypeptide (e.g., a DNA-binding 30 polypeptide and / or a PE-enhancing polypeptide). In some embodiments, a peptide linker has a formula of –[(SGGS)x-NLS]m-(SGGS)y-, wherein x or y is 0, 1, 2, 3, or 4, and m is 1, 2, 3, or 4. In some embodiments, a peptide linker has a formula of –[(SGGS)x-NLS]m-(SGGS)y-, wherein x or y is 1, and m is 1, 2, 3, or 4. In some embodiments, a peptide linker has a formula of –[(SGGS)x-NLS]m- (SGGS)y-, wherein x is 1, y is 1, and m is 1, 2, 3, or 4. In some embodiments, a peptide linker has a 35 formula of –[(SGGS)x-NLS]m-(SGGS)y-, wherein x is 1, y is 1, and m is 1. In some embodiments, a peptide linker has a formula of –[(SGGS)x-NLS]m-(SGGS)y-, wherein x is 1, y is 1, and m is 2. In some embodiments, a peptide linker has a formula of –[(SGGS)x-NLS]m-(SGGS)y-, wherein x is 1, y 30 Atty Dkt No: L1034381430WO (00376)

[0031] is 1, and m is 3. In some embodiments, a peptide linker has a formula of –[(SGGS)x-NLS]m-(SGGS)y-, wherein x is 1, y is 1, and m is 4. In some embodiments, a peptide linker has a formula of -(SGGS)x- NLSm-(SGGS)y-NLSn-(SGGS)z-, wherein each of x, y, or z is 0, 1, 2, 3, or 4; and wherein each of m or n is 0 or 1. In certain embodiments, a peptide linker has a formula of -(SGGS)x-NLSm-(SGGS)y- 5 NLSn-(SGGS)z-, wherein each of x or z is 0, 1, 2, 3, or 4, and y is 0; and wherein one of m or n is 0, and the other is 1. In other embodiments, the peptide linker has a formula of -(SGGS)x-NLSm- (SGGS)y-NLSn-(SGGS)z-, wherein each of x, y, or z is 0, 1, 2, 3, or 4; and wherein each of m or n is 1, and y is not 0. In some embodiments, x, y, or z are not all 0. In some embodiments, a peptide linker comprises one or more copies of amino acid sequence SGGS (SEQ ID NO: 937). In some 10 embodiments, a peptide linker has a length of 2 amino acids, 3 amino acids, 4 amino acids, 5 amino acids, 6 amino acids, 7 amino acids, 8 amino acids, 9 amino acids, 10 amino acids, 11 amino acids, 12 amino acids, 13 amino acids, 14 amino acids, 15 amino acids, 16 amino acids, 20 amino acids, 21 amino acids, 22 amino acids, 23 amino acids, 24 amino acids, 25 amino acids, 30 amino acids, 35 amino acids, 40 amino acids, 41 amino acids, 42 amino acids, 43 amino acids, 44 amino acids, 45 15 amino acids, or more. In some embodiments, a peptide linker has a length of at least 13 amino acids, including but not limited to about 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30, 31, 32, 33, 34, 35, 36, 37, 38, 39, 40, 41, 42, 43, 44, 45, or more amino acids. In some embodiments, the peptide linker has an amino acid sequence having at least 80%, at least 81%, at least 82%, at least 83%, at least 84%, at least 85%, at least 86%, at least 87%, at least 88%, at least 89%, at least 90%, at 20 least 91%, at least 92%, at least 93%, at least 94%, at least 95%, at least 96%, at least 97%, at least 98%, at least 99%, or more sequence identity to any one of SEQ ID NOs: 431-436, and 935-937. In some embodiments, the peptide linker has the amino acid sequence of any one of SEQ ID NOs: 431- 436, and 935-937. In some embodiments, the heterologous polypeptide comprises a PE-enhancing polypeptide, 25 and the peptide linker between the PE-enhancing polypeptide and an RT or between the PE-enhancing polypeptide and a DNA-binding polypeptide (e.g., RGN polypeptide), comprises at least 2 amino acids, at least 3 amino acids, at least 4 amino acids, at least 5 amino acids, at least 6 amino acids, at least 7 amino acids, at least 8 amino acids, at least 9 amino acids, at least 10 amino acids, at least 11 amino acids, at least 12 amino acids, or at least 13 amino acids. In some embodiments, the peptide 30 linker between the PE-enhancing polypeptide and an RT or between the PE-enhancing polypeptide and a DNA-binding polypeptide (e.g., RGN polypeptide) comprises at least 13 amino acids, including but not limited to about 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30, 31, 32, 33, 34, 35, 36, 37, 38, 39, 40, 41, 42, 43, 44, 45, or more amino acids. In some embodiments, the fusion protein comprises a PE-enhancing polypeptide connected to an RT or a PE-enhancing polypeptide 35 connected to a DNA-binding polypeptide by a peptide linker having an amino acid sequence having at least 80%, at least 81%, at least 82%, at least 83%, at least 84%, at least 85%, at least 86%, at least 87%, at least 88%, at least 89%, at least 90%, at least 91%, at least 92%, at least 93%, at least 94%, at 31 Atty Dkt No: L1034381430WO (00376)

[0032] least 95%, at least 96%, at least 97%, at least 98%, at least 99%, or more sequence identity to SEQ ID NO: 431, 432, or 433. In some embodiments, the fusion protein comprises a PE-enhancing polypeptide connected to an RT or a PE-enhancing polypeptide connected to a DNA-binding polypeptide by a peptide linker having the amino acid sequence set forth as SEQ ID NO: 431, 432, or 5 433. A fusion protein of the disclosure can comprise a presently disclosed RT, a presently disclosed DNA-binding polypeptide, and a presently disclosed PE-enhancing polypeptide. In some embodiments, a fusion protein of the disclosure comprises from amino terminus to carboxy terminus: an RT, a PE-enhancing polypeptide, and a DNA-binding polypeptide. In some embodiments, a fusion 10 protein of the disclosure comprises from amino terminus to carboxy terminus: an RT, a DNA-binding polypeptide, and a PE-enhancing polypeptide. In some embodiments, a fusion protein of the disclosure comprises from amino terminus to carboxy terminus: a DNA-binding polypeptide, an RT, and a PE-enhancing polypeptide. In some embodiments, a fusion protein of the disclosure comprises from amino terminus to carboxy terminus: a DNA-binding polypeptide, a PE-enhancing polypeptide, 15 and an RT. In some embodiments, a fusion protein of the disclosure comprises from amino terminus to carboxy terminus: a PE-enhancing polypeptide, an RT, and a DNA-binding polypeptide. In some embodiments, a fusion protein of the disclosure comprises from amino terminus to carboxy terminus: a PE-enhancing polypeptide, a DNA-binding polypeptide, and an RT. In some embodiments, the fusion protein comprises an RT inserted within the heterologous 20 polypeptide, such as a DNA-binding polypeptide (e.g., RGN polypeptide). In some of those embodiments wherein the heterologous polypeptide is an RGN, the RT is inserted between surface amino acid residues. The RT can be inserted within or between a linker domain 2, a wedge (WED) domain, a RuvC domain, an HNH domain, a Rec-2 domain, or a PAM-interacting (PI) domain of the RGN as described in more detail elsewhere herein. 25 In those embodiments wherein the heterologous polypeptide of the fusion protein is an RGN having at least 90% sequence identity to SEQ ID NO: 387, 389, 392, 393, 394, or 395, the RT can be inserted within the RGN immediately after the amino acid position selected from the group consisting of: i) amino acid position corresponding to position 30 of SEQ ID NO: 387, 389, 392, 393, 394, or 395; ii) amino acid position corresponding to position 642 of SEQ ID NO: 387, 389, 392, 393, 394, or 30 395; iii) amino acid position corresponding to position 670 of SEQ ID NO: 387, 389, 392, 393, 394, or 395; iv) amino acid position corresponding to position 737 of SEQ ID NO: 387, 389, 392, 393, 394, or 395; v) amino acid position corresponding to position 772 of SEQ ID NO: 387, 389, 392, 393, 394, or 395; vi) amino acid position corresponding to position 775 of SEQ ID NO: 387, 389, 392, 393, 394, or 395; vii) amino acid position corresponding to position 778 of SEQ ID NO: 387, 389, 35 392, 393, 394, or 395; viii) amino acid position corresponding to position 802 of SEQ ID NO: 387, 389, 392, 393, 394, or 395; ix) amino acid position corresponding to position 900 of SEQ ID NO: 32 Atty Dkt No: L1034381430WO (00376)

[0033] 387, 389, 392, 393, 394, or 395; and x) amino acid position corresponding to position 910 of SEQ ID NO: 387, 389, 392, 393, 394, or 395. In those embodiments wherein the heterologous polypeptide of the fusion protein is an RGN having at least 90% sequence identity to SEQ ID NO: 388, the RT can be inserted within the RGN 5 immediately after the amino acid position selected from the group consisting of: i) amino acid position corresponding to position 342 of SEQ ID NO: 388; ii) amino acid position corresponding to position 518 of SEQ ID NO: 388; iii) amino acid position corresponding to position 630 of SEQ ID NO: 388; iv) amino acid position corresponding to position 661 of SEQ ID NO: 388; v) amino acid position corresponding to position 678 of SEQ ID NO: 388; vi) amino acid position corresponding to 10 position 736 of SEQ ID NO: 388; vii) amino acid position corresponding to position 778 of SEQ ID NO: 388; viii) amino acid position corresponding to position 788 of SEQ ID NO: 388; ix) amino acid position corresponding to position 922 of SEQ ID NO: 388; and x) amino acid position corresponding to position 1109 of SEQ ID NO: 388. In those embodiments wherein the heterologous polypeptide of the fusion protein is an RGN 15 having at least 90% sequence identity to SEQ ID NO: 391, the RT can be inserted within the RGN immediately after the amino acid position selected from the group consisting of: i) amino acid position corresponding to position 597 of SEQ ID NO: 391; ii) amino acid position corresponding to position 631 of SEQ ID NO: 391; iii) amino acid position corresponding to position 725 of SEQ ID NO: 391; iv) amino acid position corresponding to position 739 of SEQ ID NO: 391; and v) amino 20 acid position corresponding to position 744 of SEQ ID NO: 391. In those embodiments wherein the heterologous polypeptide of the fusion protein is an RGN having at least 90% sequence identity to SEQ ID NO: 390, 396, 397, 398, 399, 400, 401, 402, 403, 404, 405, 406, 407, 408, 409, or 410, the RT can be inserted within the RGN immediately after the amino acid position selected from the group consisting of: i) amino acid position corresponding to 25 position 347 of SEQ ID NO: 390, 396, 397, 398, 399, 400, 401, 402, 403, 404, 405, 406, 407, 408, 409, or 410; ii) amino acid position corresponding to position 524 of SEQ ID NO: 390, 396, 397, 398, 399, 400, 401, 402, 403, 404, 405, 406, 407, 408, 409, or 410; iii) amino acid position corresponding to position 640 of SEQ ID NO: 390, 396, 397, 398, 399, 400, 401, 402, 403, 404, 405, 406, 407, 408, 409, or 410; iv) amino acid position corresponding to position 666 of SEQ ID NO: 390, 396, 397, 30 398, 399, 400, 401, 402, 403, 404, 405, 406, 407, 408, 409, or 410; v) amino acid position corresponding to position 680 of SEQ ID NO: 390, 396, 397, 398, 399, 400, 401, 402, 403, 404, 405, 406, 407, 408, 409, or 410; vi) amino acid position corresponding to position 740 of SEQ ID NO: 390, 396, 397, 398, 399, 400, 401, 402, 403, 404, 405, 406, 407, 408, 409, or 410; vii) amino acid position corresponding to position 785 of SEQ ID NO: 390, 396, 397, 398, 399, 400, 401, 402, 403, 35 404, 405, 406, 407, 408, 409, or 410; viii) amino acid position corresponding to position 910 of SEQ ID NO: 390, 396, 397, 398, 399, 400, 401, 402, 403, 404, 405, 406, 407, 408, 409, or 410; and ix) 33 Atty Dkt No: L1034381430WO (00376)

[0034] amino acid position corresponding to position 1077 of SEQ ID NO: 390, 396, 397, 398, 399, 400, 401, 402, 403, 404, 405, 406, 407, 408, 409, or 410. VI. Polymerase Editors (PEs) 5 The presently disclosed polymerase editors (PEs) comprise an RT and a DNA-binding polypeptide (e.g., RGN polypeptide). In some embodiments, a PE can further comprise a PE- enhancing polypeptide. The RT includes the RTs, or active variants or fragments thereof, as described herein, including but not limited to an RT having at least 40%, at least 50%, at least 60%, at least 70%, at 10 least 80%, at least 85%, at least 86%, at least 87%, at least 88%, at least 89%, at least 90%, at least 91%, at least 92%, at least 93%, at least 94%, at least 95%, at least 96%, at least 97%, at least 98%, at least 99%, or more sequence identity to any one of SEQ ID NOs: 1-41, 45-228, 233-334, 492-511, 807, 823-871, 881-898, and 917-934. In some embodiments, an RT, or active variant or fragment thereof, of the disclosure includes but is not limited to an RT having at least 40%, at least 50%, at 15 least 60%, at least 70%, at least 80%, at least 85%, at least 86%, at least 87%, at least 88%, at least 89%, at least 90%, at least 91%, at least 92%, at least 93%, at least 94%, at least 95%, at least 96%, at least 97%, at least 98%, at least 99%, or more sequence identity to any one of SEQ ID NOs: 1-41, 45- 133, 242-271, 311-314, 807, 823-871, and 881-898. The DNA-binding polypeptide (e.g., RGN polypeptide) can include any DNA-binding 20 polypeptide known in the art (including any RGN known in the art), including but not limited to the DNA-binding polypeptides, or active variants or fragments thereof, described herein. In some embodiments, the RGN polypeptide can include but is not limited to the RGN polypeptides, or variants or fragments thereof, described herein and includes but not limited to an RGN having at least 50%, at least 60%, at least 70%, at least 80%, at least 85%, at least 86%, at least 87%, at least 88%, at 25 least 89%, at least 90%, at least 91%, at least 92%, at least 93%, at least 94%, at least 95%, at least 96%, at least 97%, at least 98%, at least 99%, or more identity to any one of the RGN polypeptides of Table 1 and / or SEQ ID NOs: 387-420. The PE-enhancing polypeptides include the PE-enhancing polypeptides, or active variants or fragments thereof, as described herein, including but not limited to a PE-enhancing polypeptide 30 having at least 50%, at least 60%, at least 70%, at least 80%, at least 85%, at least 86%, at least 87%, at least 88%, at least 89%, at least 90%, at least 91%, at least 92%, at least 93%, at least 94%, at least 95%, at least 96%, at least 97%, at least 98%, at least 99%, or more sequence identity to any one of SEQ ID NOs: 335-344, 359-368, 370-372, 482, and 483. In some embodiments, the PE-enhancing polypeptides, or active variants or fragments thereof, as described herein, include but is not limited to 35 a PE-enhancing polypeptide having at least 50%, at least 60%, at least 70%, at least 80%, at least 85%, at least 86%, at least 87%, at least 88%, at least 89%, at least 90%, at least 91%, at least 92%, at 34 Atty Dkt No: L1034381430WO (00376)

[0035] least 93%, at least 94%, at least 95%, at least 96%, at least 97%, at least 98%, at least 99%, or more sequence identity to any one of SEQ ID NOs: 335-344, 359-365, 371, 482, and 483. A. Various Formats of Polymerase Editors 5 The presently disclosed polymerase editors can be provided in trans, wherein the RT and DNA-binding polypeptide (e.g., RGN polypeptide), and / or PE-enhancing polypeptides are separate polypeptides. In some embodiments, the RT and the DNA-binding polypeptide (e.g., RGN polypeptide) are transcribed together and have a sequence encoding a self-cleaving peptide (e.g., 2A peptide such as P2A) in between, such that translation results in two separate polypeptides. Any self- 10 cleaving peptide known in the art can be used in such embodiments, including but not limited to, 2A peptides, which is a class of 18-22 amino acid long peptides that may function through ribosomal skipping during translation. Non-limiting examples of 2A peptides are T2A, P2A, E2A, and F2A. The PE-enhancing polypeptide of the presently disclosed PEs can also be provided in trans as a separate polypeptide, wherein the PE comprises three polypeptides: the RT, the DNA-binding polypeptide 15 (e.g., RGN polypeptide), and the PE-enhancing polypeptide. Alternatively, the PE-enhancing polypeptide and RT and / or DNA-binding polypeptide (e.g., RGN polypeptide) can be transcribed together and have a sequence encoding a self-cleaving peptide in between the PE-enhancing polypeptide and the RT, the PE-enhancing polypeptide and the DNA-binding polypeptide (e.g., RGN polypeptide), or in between the PE-enhancing polypeptide and the RT and in between the PE- 20 enhancing polypeptide and the DNA-binding polypeptide (e.g., RGN polypeptide). In some embodiments, the presently disclosed PEs can comprise an RT operably fused to a DNA-binding polypeptide (e.g., RGN polypeptide), wherein the RT and DNA-binding polypeptide (e.g., RGN polypeptide) are fused to each other end-to-end or wherein the RT is inserted into the DNA-binding polypeptide (e.g., RGN polypeptide), such as those inlaid base editors described in 25 International Appl. Publ. No. WO 2024 / 095245, which is herein incorporated by reference in its entirety. In an end-to-end fusion, the RT can be fused to the amino terminus of the DNA-binding polypeptide (e.g., RGN polypeptide) or the carboxy terminus of the DNA-binding polypeptide (e.g., RGN polypeptide). The presently disclosed PEs can comprise from amino terminus to carboxy terminus: a) the PE-enhancing polypeptide, the RT, and the DNA-binding polypeptide (e.g., RGN 30 polypeptide); b) the PE-enhancing polypeptide, the DNA-binding polypeptide (e.g., RGN polypeptide), and the RT; c) the RT, the DNA-binding polypeptide (e.g., RGN polypeptide), and the PE-enhancing polypeptide; d) the RT, the PE-enhancing polypeptide, and the DNA-binding polypeptide (e.g., RGN polypeptide); e) the DNA-binding polypeptide (e.g., RGN polypeptide), the RT, and the PE-enhancing polypeptide; or f) the DNA-binding polypeptide (e.g., RGN polypeptide), 35 the PE-enhancing polypeptide, and the RT. In those embodiments wherein the RT and / or PE-enhancing polypeptide is inserted within an RGN polypeptide, the RT and / or PE-enhancing polypeptide is inserted between surface amino acid 35 Atty Dkt No: L1034381430WO (00376)

[0036] residues. The RT and / or PE-enhancing polypeptide can be inserted within or between a linker domain 2, a wedge (WED) domain, a RuvC domain, an HNH domain, a Rec-2 domain, or a PAM-interacting (PI) domain. In some embodiments, the RuvC domain is the RuvCIII domain. A Rec or recognition lobe mediates nucleic acid binding through multiple Rec domains (e.g., Rec1-3) by sensing nucleic 5 acids, regulates the HNH conformational transition, and locks the catalytic HNH domain at the cleavage site. A wedge domain is responsible for the recognition of guide RNA scaffolds. Non- limiting examples of domains within an RGN include: RuvC-I from amino acid residues 1-54; BH from amino acid residues 55-83; REC1 from amino acid residues 84-244; REC2 from amino acid residues 245-462; RuvC-II from amino acid residues 463-521; L1 from amino acid residues 522-552; 10 HNH from amino acid residues 553-672; L2 from amino acid residues 673-685; RuvC-III from amino acid residues 686-833; WED from amino acid residues 834-938; and PI from amino acid residues 939-1071; all in reference to LPG10221 and APG07433.1 (and variants thereof), which are set forth as SEQ ID NOs: 387 and 389 (and 392-395), respectively. APG05586 (set forth as SEQ ID NO: 388) has the following domains: RuvC-I from amino acid residues 1-33; BH from amino acid residues 34- 15 71; REC1 from amino acid residues 72-232; REC2 from amino acid residues 233-468; RuvC-II from amino acid residues 469-517; L1 from amino acid residues 518-552; HNH from amino acid residues 553-672; L2 from amino acid residues 673-687; RuvC-III from amino acid residues 688-837; WED from amino acid residues 838-998; and PI from amino acid residues 999-1150. LPG10145 (set forth as SEQ ID NO: 390) and variants thereof (set forth as SEQ ID NOs: 396-410) have the following 20 domains: RuvC-I from amino acid residues 1-42; BH from amino acid residues 43-79; REC1 from amino acid residues 80-236; REC2 from amino acid residues 237-476; RuvC-II from amino acid residues 477-524; L1 from amino acid residues 525-560; HNH from amino acid residues 561-676; L2 from amino acid residues 677-690; RuvC-III from amino acid residues 691-828; WED from amino acid residues 829-976; and PI from amino acid residues 977-1130. APG01604 (set forth as SEQ ID 25 NO: 391) has the following domains: RuvC-I from amino acid residues 1-40; BH from amino acid residues 41-74; REC1 from amino acid residues 75-223; REC2 from amino acid residues 224-430; RuvC-II from amino acid residues 431-483; L1 from amino acid residues 484-516; HNH from amino acid residues 517-631; L2 from amino acid residues 632-651; RuvC-III from amino acid residues 652-775; WED from amino acid residues 776-909; and PI from amino acid residues 910-1052. 30 A PAM-interacting domain is the domain of an RGN polypeptide that binds to a PAM site. The general domains of RGN polypeptides can be determined via structural comparison to RGN polypeptides with defined domains. In those embodiments wherein the PE comprises an RGN having at least 90% sequence identity to SEQ ID NO: 387, 389, 392, 393, 394, or 395, the RT and / or PE-enhancing polypeptide can 35 be inserted within the RGN immediately after the amino acid position selected from the group consisting of: i) amino acid position corresponding to position 30 of SEQ ID NO: 387, 389, 392, 393, 394, or 395; ii) amino acid position corresponding to position 642 of SEQ ID NO: 387, 389, 392, 393, 36 Atty Dkt No: L1034381430WO (00376)

[0037] 394, or 395; iii) amino acid position corresponding to position 670 of SEQ ID NO: 387, 389, 392, 393, 394, or 395; iv) amino acid position corresponding to position 737 of SEQ ID NO: 387, 389, 392, 393, 394, or 395; v) amino acid position corresponding to position 772 of SEQ ID NO: 387, 389, 392, 393, 394, or 395; vi) amino acid position corresponding to position 775 of SEQ ID NO: 387, 5 389, 392, 393, 394, or 395; vii) amino acid position corresponding to position 778 of SEQ ID NO: 387, 389, 392, 393, 394, or 395; viii) amino acid position corresponding to position 802 of SEQ ID NO: 387, 389, 392, 393, 394, or 395; ix) amino acid position corresponding to position 900 of SEQ ID NO: 387, 389, 392, 393, 394, or 395; and x) amino acid position corresponding to position 910 of SEQ ID NO: 387, 389, 392, 393, 394, or 395. 10 In those embodiments wherein the PE comprises an RGN having at least 90% sequence identity to SEQ ID NO: 388, the RT and / or PE-enhancing polypeptide can be inserted within the RGN immediately after the amino acid position selected from the group consisting of: i) amino acid position corresponding to position 342 of SEQ ID NO: 388; ii) amino acid position corresponding to position 518 of SEQ ID NO: 388; iii) amino acid position corresponding to position 630 of SEQ ID 15 NO: 388; iv) amino acid position corresponding to position 661 of SEQ ID NO: 388; v) amino acid position corresponding to position 678 of SEQ ID NO: 388; vi) amino acid position corresponding to position 736 of SEQ ID NO: 388; vii) amino acid position corresponding to position 778 of SEQ ID NO: 388; viii) amino acid position corresponding to position 788 of SEQ ID NO: 388; ix) amino acid position corresponding to position 922 of SEQ ID NO: 388; and x) amino acid position corresponding 20 to position 1109 of SEQ ID NO: 388. In those embodiments wherein the PE comprises an RGN having at least 90% sequence identity to SEQ ID NO: 391, the RT and / or PE-enhancing polypeptide can be inserted within the RGN immediately after the amino acid position selected from the group consisting of: i) amino acid position corresponding to position 597 of SEQ ID NO: 391; ii) amino acid position corresponding to 25 position 631 of SEQ ID NO: 391; iii) amino acid position corresponding to position 725 of SEQ ID NO: 391; iv) amino acid position corresponding to position 739 of SEQ ID NO: 391; and v) amino acid position corresponding to position 744 of SEQ ID NO: 391. In those embodiments wherein the PE comprises an RGN having at least 90% sequence identity to SEQ ID NO: 390, 396, 397, 398, 399, 400, 401, 402, 403, 404, 405, 406, 407, 408, 409, or 30 410, the RT and / or PE-enhancing polypeptide can be inserted within the RGN immediately after the amino acid position selected from the group consisting of: i) amino acid position corresponding to position 347 of SEQ ID NO: 390, 396, 397, 398, 399, 400, 401, 402, 403, 404, 405, 406, 407, 408, 409, or 410; ii) amino acid position corresponding to position 524 of SEQ ID NO: 390, 396, 397, 398, 399, 400, 401, 402, 403, 404, 405, 406, 407, 408, 409, or 410; iii) amino acid position corresponding 35 to position 640 of SEQ ID NO: 390, 396, 397, 398, 399, 400, 401, 402, 403, 404, 405, 406, 407, 408, 409, or 410; iv) amino acid position corresponding to position 666 of SEQ ID NO: 390, 396, 397, 398, 399, 400, 401, 402, 403, 404, 405, 406, 407, 408, 409, or 410; v) amino acid position 37 Atty Dkt No: L1034381430WO (00376)

[0038] corresponding to position 680 of SEQ ID NO: 390, 396, 397, 398, 399, 400, 401, 402, 403, 404, 405, 406, 407, 408, 409, or 410; vi) amino acid position corresponding to position 740 of SEQ ID NO: 390, 396, 397, 398, 399, 400, 401, 402, 403, 404, 405, 406, 407, 408, 409, or 410; vii) amino acid position corresponding to position 785 of SEQ ID NO: 390, 396, 397, 398, 399, 400, 401, 402, 403, 5 404, 405, 406, 407, 408, 409, or 410; viii) amino acid position corresponding to position 910 of SEQ ID NO: 390, 396, 397, 398, 399, 400, 401, 402, 403, 404, 405, 406, 407, 408, 409, or 410; and ix) amino acid position corresponding to position 1077 of SEQ ID NO: 390, 396, 397, 398, 399, 400, 401, 402, 403, 404, 405, 406, 407, 408, 409, or 410. The RT may be fused directly to the DNA-binding polypeptide (e.g., RGN polypeptide) 10 and / or the PE-enhancing polypeptide or a peptide linker can connect the RT and the DNA-binding polypeptide (e.g., RGN polypeptide) and / or the PE-enhancing polypeptide. In those embodiments wherein the RT and / or PE-enhancing polypeptide is inserted into the RGN polypeptide, there can be peptide linkers on one or both ends of the RT and / or PE-enhancing polypeptide. Any suitable peptide linker can be used to connect the RT and DNA-binding polypeptide (e.g., RGN polypeptide) (or a 15 fragment thereof) and / or PE-enhancing polypeptide, but one suitable peptide linker comprises one or more copies of SGGS. In some embodiments, the peptide linker comprises 1 SGGS sequence, 2 SGGS sequences, 3 SGGS sequences, 4 SGGS sequences, or more, such that the linker sequence can be 4, 8, 12, or 16 amino acids long. The linker between the RT and DNA-binding polypeptide (e.g., RGN polypeptide) (or fragments thereof) and / or PE-enhancing polypeptide can be 3, 4, 5, 6, 7, 8, 9, 20 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30, 31, 32, 33, 34, 35, 36, 37, 38, 39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 59, 60, 61, 62, 63, 64, 65, 66, 67, 68, 69, 70, or more nucleotides in length. The peptide linker separating the RT and DNA-binding polypeptide (e.g., RGN polypeptide) (or a fragment thereof) and / or the PE-enhancing polypeptide can also comprise an NLS, such as but not limited to those disclosed elsewhere herein, 25 including SEQ ID NO: 425, 426, or 427, wherein the NLSs can be connected by peptide linkers (such as SGGS). In some embodiments, the peptide linker separating the RT and DNA-binding polypeptide (e.g., RGN polypeptide) (or a fragment thereof) and / or PE-enhancing polypeptide comprises more than one localization sequences, such as 2, 3, or more localization sequences. In some embodiments, a peptide linker has a formula of –[(SGGS)x-NLS]m-(SGGS)y-, wherein x or y is 0, 1, 2, 3, or 4, and m 30 is 1, 2, 3, or 4. In some embodiments, a peptide linker has a formula of –[(SGGS)x-NLS]m-(SGGS)y-, wherein x or y is 1, and m is 1, 2, 3, or 4. In some embodiments, a peptide linker has a formula of – [(SGGS)x-NLS]m-(SGGS)y-, wherein x is 1, y is 1, and m is 1, 2, 3, or 4. In some embodiments, a peptide linker has a formula of –[(SGGS)x-NLS]m-(SGGS)y-, wherein x is 1, y is 1, and m is 1. In some embodiments, a peptide linker has a formula of –[(SGGS)x-NLS]m-(SGGS)y-, wherein x is 1, y 35 is 1, and m is 2. In some embodiments, a peptide linker has a formula of –[(SGGS)x-NLS]m-(SGGS)y-, wherein x is 1, y is 1, and m is 3. In some embodiments, a peptide linker has a formula of –[(SGGS)x- NLS]m-(SGGS)y-, wherein x is 1, y is 1, and m is 4. In some embodiments, a peptide linker has a 38 Atty Dkt No: L1034381430WO (00376)

[0039] formula of -(SGGS)x-NLSm-(SGGS)y-NLSn-(SGGS)z-, wherein each of x, y, or z is 0, 1, 2, 3, or 4; and wherein each of m or n is 0 or 1. In certain embodiments, a peptide linker has a formula of - (SGGS)x-NLSm-(SGGS)y-NLSn-(SGGS)z-, wherein each of x or z is 0, 1, 2, 3, or 4, and y is 0; and wherein one of m or n is 0, and the other is 1. In other embodiments, the peptide linker has a formula 5 of -(SGGS)x-NLSm-(SGGS)y-NLSn-(SGGS)z-, wherein each of x, y, or z is 0, 1, 2, 3, or 4; and wherein each of m or n is 1, and y is not 0. In some embodiments, x, y, or z are not all 0. The presently disclosed RTs, DNA-binding polypeptides (e.g., RGN polypeptides), PE- enhancing polypeptides, fusion proteins, or PEs can comprise at least one nuclear localization signal (NLS) to enhance transport of the protein to the nucleus of a cell. Nuclear localization signals are 10 known in the art and generally comprise a stretch of basic amino acids (see, e.g., Lange et al., J. Biol. Chem. (2007) 282:5101-5105). In some embodiments, the RT, DNA-binding polypeptide (e.g., RGN polypeptide), PE-enhancing polypeptide, fusion protein, or PE comprises 2, 3, 4, 5, 6 or more nuclear localization signals. The nuclear localization signal(s) can be a heterologous NLS. Non-limiting examples of nuclear localization signals useful for the presently disclosed RTs, DNA-binding 15 polypeptides (e.g., RGN polypeptides), PE-enhancing polypeptides, fusion proteins, or PEs are the nuclear localization signals of SV40 Large T-antigen, nucleoplasmin, and c-Myc (see, e.g., Ray et al. (2015) Bioconjug Chem 26(6):1004-7). In some embodiments, the RT, DNA-binding polypeptide (e.g., RGN polypeptide), PE-enhancing polypeptide, fusion protein, or PE comprises the NLS sequence set forth as SEQ ID NO: 425, 426, and / or 427. In some embodiments, the RT, DNA-binding 20 polypeptide (e.g., RGN polypeptide), PE-enhancing polypeptide, fusion protein, or PE comprises the NLS sequence set forth as any one of SEQ ID NOs: 425-430. The RT, DNA-binding polypeptide (e.g., RGN polypeptide), PE-enhancing polypeptide, fusion protein, or PE can comprise one or more NLS sequences at its N-terminus, C- terminus, or both the N-terminus and C-terminus. For example, the RT, DNA-binding polypeptide (e.g., RGN polypeptide), PE-enhancing polypeptide, fusion 25 protein, or PE can comprise two NLS sequences at the N-terminal region and four NLS sequences at the C-terminal region. In some embodiments, a peptide linker can connect the NLS to the RT, DNA- binding polypeptide (e.g., RGN polypeptide), PE-enhancing polypeptide, or fusion protein. Other localization signal sequences known in the art that localize polypeptides to particular subcellular location(s) can also be used to target the RTs, DNA-binding polypeptides (e.g., RGN 30 polypeptides), PE-enhancing polypeptides, fusion proteins, or PEs, including, but not limited to, plastid localization sequences, mitochondrial localization sequences, and dual-targeting signal sequences that target to both the plastid and mitochondria (see, e.g., Nassoury and Morse (2005) Biochim Biophys Acta 1743:5-19; Kunze and Berger (2015) Front Physiol dx.doi.org / 10.3389 / fphys.2015.00259; Herrmann and Neupert (2003) IUBMB Life 55:219-225; Soll35 (2002) Curr Opin Plant Biol 5:529-535; Carrie and Small (2013) Biochim Biophys Acta 1833:253- 259; Carrie et al. (2009) FEBS J 276:1187-1195; Silva-Filho (2003) Curr Opin Plant Biol 6:589-595; Peeters and Small (2001) Biochim Biophys Acta 1541:54-63; Murcha et al. (2014) J Exp Bot 65:6301- 39 Atty Dkt No: L1034381430WO (00376)

[0040] 6335; Mackenzie (2005) Trends Cell Biol 15:548-554; Glaser et al. (1998) Plant Mol Biol 38:311- 338). RTs, DNA-binding polypeptides (e.g., RGN polypeptides), PE-enhancing polypeptides, fusion proteins, or PEs can comprise at least one cell-penetrating domain that facilitates cellular 5 uptake of the RTs, DNA-binding polypeptides (e.g., RGN polypeptides), PE-enhancing polypeptides, fusion proteins, or PEs. Cell-penetrating domains are known in the art and generally comprise stretches of positively charged amino acid residues (i.e., polycationic cell-penetrating domains), alternating polar amino acid residues and non-polar amino acid residues (i.e., amphipathic cell- penetrating domains), or hydrophobic amino acid residues (i.e., hydrophobic cell-penetrating 10 domains) (see, e.g., Milletti F. (2012) Drug Discov Today 17:850-860). A non-limiting example of a cell-penetrating domain is the trans-activating transcriptional activator (TAT) from the human immunodeficiency virus 1. The nuclear localization signal, plastid localization signal, mitochondrial localization signal, dual-targeting localization signal, and / or cell-penetrating domain can be located at the amino-terminus15 (N-terminus), the carboxyl-terminus (C-terminus), and / or in an internal location of the RT, DNA- binding polypeptide (e.g., RGN polypeptide), PE-enhancing polypeptide, fusion protein, or PE. RTs, DNA-binding polypeptides (e.g., RGN polypeptides), PE-enhancing polypeptides, fusion proteins, or PEs can also comprise a purification tag, which is any molecule that can be utilized to isolate a protein or fused protein from a mixture (e.g., biological sample, culture medium). Non- 20 limiting examples of purification tags include biotin, myc, maltose binding protein (MBP), glutathione-S-transferase (GST), and 3X FLAG tag. B. Guide RNA The present disclosure provides PE systems comprising guide RNAs and polynucleotides 25 encoding the same that target an associated RNA-guided nuclease (RGN) or a PE comprising such an RGN to a target sequence. The term “guide RNA” refers to a nucleotide sequence having sufficient complementarity with a target nucleotide sequence to hybridize with the target sequence and direct sequence-specific binding of an associated RGN to the target nucleotide sequence. More specifically, when the target nucleotide sequence is double-stranded as is the case with DNA, the target nucleotide 30 sequence comprises a target strand and a non-target strand (which comprises the PAM sequence). In these embodiments, the guide RNA has sufficient complementarity with the target strand of a double- stranded target sequence (e.g., target DNA sequence) such that the guide RNA hybridizes with the target strand and directs sequence-specific binding of an associated RGN to the target sequence (e.g., target DNA sequence). Therefore, in some embodiments, a guide RNA includes a spacer that is 35 identical to the sequence of the non-target strand except that uracil (U) replaces thymidine (T) in the guide RNA. In embodiments where multiplex gene editing is used and there are multiple guide RNAs, each of the one or more guide RNA has sufficient complementarity with the target strand of a 40 Atty Dkt No: L1034381430WO (00376)

[0041] particular target sequence and is capable of hybridizing to the target strand of that target sequence. Thus, “a corresponding target sequence” for a guide RNA refers to the target sequence that the guide RNA has sufficient complementarity with and is capable of hybridizing to. An RGN’s respective guide RNA is one or more RNA molecules (generally, one or two), that 5 can bind to the RGN and guide the RGN to bind to a particular target sequence, and in those embodiments wherein the RGN has nickase or nuclease activity, also cleave the target strand and / or the non-target strand. In general, a guide RNA comprises a CRISPR RNA (crRNA) and a trans- activating CRISPR RNA (tracrRNA), although some RGNs do not require a tracrRNA. A guide RNA of the PE systems of the disclosure (e.g., a crRNA) can comprise at least one 10 chemical modification. The at least one chemical modification includes: a bridged nucleic acid (BNA) modification; 2'-O-methyl (2'-O-Me) modification; 2'-O-methoxy-ethyl (2'MOE) modification; 2'- fluoro (2'-F) modification; 2'F-4'Cα-OMe modification; 2',4'-di-Cα-OMe modification; 2'-O-methyl 3'phosphorothioate (MS) modification; 2'-O-methyl 3'thiophosphonoacetate (MSP) modification; 2'- O-methyl 3'phosphonoacetate (MP) modification; and phosphorothioate (PS) modification; or a 15 combination thereof. In some embodiments, the BNA comprises a 2′,4′ BNA modification. In some embodiments, the 2′,4′ BNA modification is selected from the group consisting of: locked nucleic acid (LNA) modification, BNANC[N-Me] modification, 2′-O,4′-C-ethylene bridged nucleic acid (2′,4′- ENA) modification, and S-constrained ethyl (cEt) modification. In some embodiments, the 2′,4′ BNA is a LNA modification. In some embodiments, the 2′,4′ BNA is a cEt modification. In some 20 embodiments, the at least one chemical modification comprises a BNA modification, 2'-O-Me modification, or PS modification. Chemical modifications of spacers, crRNA repeats, crRNAs, tracrRNAs, and guide RNAs are described in International Application Publication No. WO 2024 / 042489, which is hereby incorporated by reference in its entirety herein. The present disclosure provides PE systems comprising guide RNAs comprising CRISPR 25 RNAs (crRNAs). A crRNA comprises a spacer and a CRISPR repeat. The “spacer” has a nucleotide sequence that directly hybridizes with the target strand of a target sequence (e.g., target DNA sequence) of interest. The spacer is engineered to have full or partial complementarity with the target strand of a target sequence of interest. In some embodiments, the spacer can comprise from about 8 nucleotides to about 30 nucleotides, or more. For example, the spacer can be about 8, about 9, about 30 10, about 11, about 12, about 13, about 14, about 15, about 16, about 17, about 18, about 19, about 20, about 21, about 22, about 23, about 24, about 25, about 26, about 27, about 28, about 29, about 30, or more nucleotides in length. In some embodiments, the spacer is 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30, or more nucleotides in length. In some embodiments, the spacer is about 10 to about 26 nucleotides in length, or about 12 to about 30 nucleotides in length. In 35 some embodiments, the spacer is about 25 nucleotides in length. In some embodiments, the degree of complementarity between a spacer and the target strand of a target sequence (e.g., target DNA sequence), when optimally aligned using a suitable alignment algorithm, is between 50% and 99% or 41 Atty Dkt No: L1034381430WO (00376)

[0042] more, including but not limited to about or more than about 50%, about 60%, about 70%, about 75%, about 80%, about 81%, about 82%, about 83%, about 84%, about 85%, about 86%, about 87%, about 88%, about 89%, about 90%, about 91%, about 92%, about 93%, about 94%, about 95%, about 96%, about 97%, about 98%, about 99%, or more. In some embodiments, the degree of complementarity 5 between a spacer and the target strand of a target sequence (e.g., target DNA sequence), when optimally aligned using a suitable alignment algorithm, is 50%, 60%, 70%, 75%, 80%, 81%, 82%, 83%, 84%, 85%, 86%, 87%, 88%, 89%, 90%, 91%, 92%, 93%, 94%, 95%, 96%, 97%, 98%, 99%, or more. In some embodiments, the spacer can be identical in sequence to the non-target strand of a target sequence. In some of those embodiments wherein the target sequence is a target DNA 10 sequence, the spacer can be identical in sequence to the non-target strand of the target DNA sequence, with the exception of the thymidines (Ts) in the non-target strand being replaced by uracils (Us) in the spacer. In particular embodiments, the spacer is free of secondary structure, which can be predicted using any suitable polynucleotide folding algorithm known in the art, including but not limited to mFold (see, e.g., Zuker and Stiegler (1981) Nucleic Acids Res.9:133-148) and RNAfold (see, e.g., 15 Gruber et al. (2008) Cell 106(1):23-24). Along with a spacer, a crRNA further comprises a CRISPR RNA (crRNA) repeat. Generally, a crRNA repeat comprises a nucleotide sequence that forms a structure, either on its own or in concert with a hybridized tracrRNA, that is recognized by the RGN polypeptide. For LPG10221, APG07433.1, APG05586, APG01604, and LPG10145 guide crRNAs, the spacer is 5′ of the crRNA 20 repeat. In various embodiments, the crRNA repeat can comprise from about 8 nucleotides to about 30 nucleotides, or more. For example, the crRNA repeat can be about 8, about 9, about 10, about 11, about 12, about 13, about 14, about 15, about 16, about 17, about 18, about 19, about 20, about 21, about 22, about 23, about 24, about 25, about 26, about 27, about 28, about 29, about 30, or more nucleotides in length. In particular embodiments, the crRNA repeat is 8, 9, 10, 11, 12, 13, 14, 15, 16, 25 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30, or more nucleotides in length. In some embodiments, a crRNA repeat comprises a total length of 19 to 40 nucleotides (nt). In some embodiments, a crRNA repeat comprises a total length of at most 19 nt, 20 nt, 21 nt, 22 nt, 23 nt, 24 nt, 25 nt, 26 nt, 27 nt, 28 nt, 29 nt, or 30 nt. In some embodiments, the crRNA repeat is about 19 nt or 21 nt. A crRNA repeat can include a consensus repeat of the CRISPR array found in the genome of 30 the organism from which the crRNA repeat is obtained. In some embodiments, the crRNA repeat comprises the nucleotide sequence set forth as SEQ ID NO: 444, 445, 446, 455, 456, 457, 468, 471, or 472, or an active variant or fragment thereof, that when comprised within a guide RNA, is capable of directing the sequence-specific binding of an associated RGN provided herein to a target sequence of interest. In some embodiments, an active 35 crRNA repeat variant of a wild-type sequence comprises a nucleotide sequence having at least 40%, 45%, 50%, 55%, 60%, 65%, 70%, 75%, 80%, 85%, 90%, 91%, 92%, 93%, 94%, 95%, 96%, 97%, 98%, 99% or more sequence identity to the nucleotide sequence set forth as SEQ ID NO: 444, 445, 42 Atty Dkt No: L1034381430WO (00376)

[0043] 446, 455, 456, 457, 468, 471, or 472. In some embodiments, an active crRNA repeat fragment of a wild-type sequence comprises at least 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, or 20 contiguous nucleotides of the nucleotide sequence set forth as SEQ ID NO: 444, 445, 446, 455, 456, 457, 468, 471, or 472. 5 In some embodiments, a crRNA repeat has the nucleotide sequence set forth as SEQ ID NO: 444, 445, 446, 455, 456, 457, 468, 471, or 472 or differs from SEQ ID NO: 444, 445, 446, 455, 456, 457, 468, 471, or 472 by 1 to 5 nucleotides. In some embodiments, a crRNA repeat has a nucleotide sequence that differs from SEQ ID NO: 444, 445, 446, 455, 456, 457, 468, 471, or 472 by 5 nucleotides. In some embodiments, a crRNA repeat has a nucleotide sequence that differs from SEQ 10 ID NO: 444, 445, 446, 455, 456, 457, 468, 471, or 472 by 4 nucleotides. In some embodiments, a crRNA repeat has a nucleotide sequence that differs from SEQ ID NO: 444, 445, 446, 455, 456, 457, 468, 471, or 472 by 3 nucleotides. In some embodiments, a crRNA repeat has a nucleotide sequence that differs from SEQ ID NO: 444, 445, 446, 455, 456, 457, 468, 471, or 472 by 2 nucleotides. In some embodiments, a crRNA repeat has a nucleotide sequence that differs from SEQ ID NO: 444, 15 445, 446, 455, 456, 457, 468, 471, or 472 by 1 nucleotide. In some embodiments, a crRNA repeat has the nucleotide sequence set forth as SEQ ID NO: 444, 445, 446, 455, 456, 457, 468, 471, or 472. In those embodiments wherein the RGN has the amino acid sequence set forth as SEQ ID NO: 388, 413, or 414, the crRNA repeat of the associated gRNA can have the nucleotide sequence set forth as SEQ ID NO: 455, 456, or 457, or an active variant or fragment thereof. In those embodiments 20 wherein the RGN has the amino acid sequence set forth as SEQ ID NO: 387, 389, 392, 393, 394, 395, 411, 412, 415, or 416, the crRNA repeat of the associated gRNA can have the nucleotide sequence set forth as SEQ ID NO: 444, 445, or 446, or an active variant or fragment thereof. In those embodiments wherein the RGN has the amino acid sequence set forth as SEQ ID NO: 391, 419, or 420, the crRNA repeat of the associated gRNA can have the nucleotide sequence set forth as SEQ ID NO: 468, or an 25 active variant or fragment thereof. In those embodiments wherein the RGN has the amino acid sequence set forth as SEQ ID NO: 390, 396, 397, 398, 399, 400, 401, 402, 403, 404, 405, 406, 407, 408, 409, 410, 417, or 418, the crRNA repeat of the associated gRNA can have the nucleotide sequence set forth as SEQ ID NO: 471 or 472 or an active variant or fragment thereof. In some embodiments, the crRNA is not naturally-occurring. In some of these embodiments, 30 the specific crRNA repeat is not linked to the engineered spacer in nature and the crRNA repeat is considered heterologous to the spacer. In certain embodiments, the spacer is an engineered sequence that is not naturally occurring. The guide RNA can further comprise a trans-activating CRISPR RNA (tracrRNA). A tracrRNA molecule comprises a nucleotide sequence comprising a region that has sufficient 35 complementarity to hybridize to a CRISPR repeat of a crRNA, which is referred to herein as the anti- repeat. In some embodiments, the tracrRNA molecule further comprises a region with secondary structure (e.g., stem-loop) or forms secondary structure upon hybridizing with its corresponding 43 Atty Dkt No: L1034381430WO (00376)

[0044] crRNA. In particular embodiments, the region of the tracrRNA that is fully or partially complementary to a CRISPR repeat is at the 5' end of the molecule and the 3' end of the tracrRNA comprises secondary structure. This region of secondary structure generally comprises several hairpin structures, including the nexus hairpin, which is found adjacent to the anti-repeat. The nexus forms 5 the core of the interactions between the guide RNA and the RGN, and is at the intersection between the guide RNA, the RGN, and the target DNA. The nexus hairpin often has a conserved nucleotide sequence in the base of the hairpin stem, with the motif UNANNC found in many nexus hairpins in tracrRNAs. In some embodiments, guide RNAs or RGN systems use tracrRNAs that comprise non- canonical sequences in the base of the hairpin stem of their nexus hairpins, including UNANNG, 10 CNANNC, CNANNU, UNANNU, CNANNG, and CNCNNU. There are often terminal hairpins at the 3' end of the tracrRNA that can vary in structure and number, but often comprise a GC-rich Rho- independent transcriptional terminator hairpin followed by a string of U’s at the 3' end. See, for example, Briner et al. (2014) Molecular Cell 56:333-339, Briner and Barrangou (2016) Cold Spring Harb Protoc; doi: 10.1101 / pdb.top090902, and U.S. Publication No.2017 / 0275648, each of which is 15 herein incorporated by reference in its entirety. In various embodiments, the anti-repeat region of the tracrRNA that is fully or partially complementary to the CRISPR repeat comprises from about 8 nucleotides to about 30 nucleotides, or more. For example, the region of base pairing between the tracrRNA anti-repeat and the CRISPR repeat can be about 8, about 9, about 10, about 11, about 12, about 13, about 14, about 15, about 16, 20 about 17, about 18, about 19, about 20, about 21, about 22, about 23, about 24, about 25, about 26, about 27, about 28, about 29, about 30, or more nucleotides in length. In particular embodiments, the region of base pairing between the tracrRNA anti-repeat and the CRISPR repeat is 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30, or more nucleotides in length. In some embodiments, the degree of complementarity between a CRISPR repeat and its 25 corresponding tracrRNA anti-repeat, when optimally aligned using a suitable alignment algorithm, is about or more than about 50%, about 60%, about 70%, about 75%, about 80%, about 81%, about 82%, about 83%, about 84%, about 85%, about 86%, about 87%, about 88%, about 89%, about 90%, about 91%, about 92%, about 93%, about 94%, about 95%, about 96%, about 97%, about 98%, about 99%, or more. In particular embodiments, the degree of complementarity between a CRISPR repeat 30 and its corresponding tracrRNA anti-repeat, when optimally aligned using a suitable alignment algorithm, is 50%, 60%, 70%, 75%, 80%, 81%, 82%, 83%, 84%, 85%, 86%, 87%, 88%, 89%, 90%, 91%, 92%, 93%, 94%, 95%, 96%, 97%, 98%, 99%, or more. In various embodiments, the entire tracrRNA can comprise from about 60 nucleotides to more than about 210 nucleotides. For example, the tracrRNA can be about 50, about 55, about 60, about 35 65, about 70, about 75, about 80, about 85, about 90, about 95, about 100, about 105, about 110, about 115, about 120, about 125, about 130, about 135, about 140, about 150, about 160, about 170, about 180, about 190, about 200, about 210, or more nucleotides in length. In particular embodiments, the 44 Atty Dkt No: L1034381430WO (00376)

[0045] tracrRNA is 50, 55, 60, 65, 70, 75, 80, 85, 90, 95, 100, 105, 110, 115, 120, 125, 130, 135, 140, 150, 160, 170, 180, 190, 200, 210 or more nucleotides in length. In particular embodiments, the tracrRNA is about 57 to about 115 nucleotides in length, including about 57, about 58, about 59, about 60, about 61, about 62, about 63, about 64, about 65, about 66, about 67, about 68, about 69, about 70, about 71, 5 about 72, about 73, about 74, about 75, about 76, about 77, about 78, about 79, about 80, about 81, about 82, about 83, about 84, about 85, about 86, about 87, about 88, about 89, about 90, about 91, about 92, about 93, about 94, about 95, about 96, about 97, about 98, about 99, about 100, about 101, about 102, about 103, about 104, about 105, about 106, about 107, about 108, about 109, about 110, about 111, about 112, about 113, about 114, and about 115 nucleotides in length. In particular 10 embodiments, the tracrRNA is 59 to 115 nucleotides in length, including 57, 58, 59, 60, 61, 62, 63, 64, 65, 66, 67, 68, 69, 70, 71, 72, 73, 74, 75, 76, 77, 78, 79, 80, 81, 82, 83, 84, 85, 86, 87, 88, 89, 90, 91, 92, 93, 94, 95, 96, 97, 98, 99, 100, 101, 102, 103, 104, 105, 106, 107, 108, 109, 110, 111, 112, 113, 114, and 115 nucleotides in length. In particular embodiments, the tracrRNA comprises the nucleotide sequence of SEQ ID NO: 15 447, 448, 449, 450, 458, 459, 460, 461, 462, 469, 473, or 474, or an active variant or fragment thereof that when comprised within a guide RNA is capable of directing the sequence-specific binding of an associated RNA-guided nuclease provided herein to a target DNA sequence of interest. In certain embodiments, an active tracrRNA sequence variant comprises a nucleotide sequence having at least 40%, 45%, 50%, 55%, 60%, 65%, 70%, 75%, 80%, 85%, 90%, 91%, 92%, 93%, 94%, 95%, 96%, 20 97%, 98%, 99% or more sequence identity to the nucleotide sequence set forth as SEQ ID NO: 447, 448, 449, 450, 458, 459, 460, 461, 462, 469, 473, or 474. In certain embodiments, an active tracrRNA sequence fragment comprises at least 5, 10, 15, 20, 25, 30, 35, 40, 45, 50, 55, 60, 65, 70, or 75, or more contiguous nucleotides of the nucleotide sequence set forth as SEQ ID NO: 447, 448, 449, 450, 458, 459, 460, 461, 462, 469, 473, or 474. 25 In those embodiments wherein the RGN has the amino acid sequence set forth as SEQ ID NO: 388, 413, or 414, the tracrRNA of the associated gRNA can have the nucleotide sequence set forth as SEQ ID NOs: 458, 459, 460, 461, 462, or an active variant or fragment thereof. In those embodiments wherein the RGN has the amino acid sequence set forth as SEQ ID NO: 387, 389, 392, 393, 394, 395, 411, 412, 415, or 416, the tracrRNA of the associated gRNA can have the nucleotide 30 sequence set forth as SEQ ID NO: 447, 448, 449, 450, or an active variant or fragment thereof. In those embodiments wherein the RGN has the amino acid sequence set forth as SEQ ID NO: 391, 419, or 420, the tracrRNA of the associated gRNA can have the nucleotide sequence set forth as SEQ ID NO: 469, or an active variant or fragment thereof. In those embodiments wherein the RGN has the amino acid sequence set forth as SEQ ID NO: 390, 396, 397, 398, 399, 400, 401, 402, 403, 404, 405, 35 406, 407, 408, 409, 410, 417, or 418, the tracrRNA of the associated gRNA can have the nucleotide sequence set forth as SEQ ID NO: 473 or 474, or an active variant or fragment thereof. 45 Atty Dkt No: L1034381430WO (00376)

[0046] The guide RNA can be a single guide RNA or a dual-guide RNA system. A single guide RNA comprises the crRNA and optionally tracrRNA on a single molecule of RNA, whereas a dual- guide RNA system comprises a crRNA and a tracrRNA present on two distinct RNA molecules, hybridized to one another through at least a portion of the CRISPR repeat sequence of the crRNA and 5 at least a portion of the tracrRNA, which may be fully or partially complementary to the CRISPR repeat sequence of the crRNA. In some of those embodiments wherein the guide RNA is a single guide RNA, the crRNA and optionally tracrRNA are connected by a linker nucleotide sequence. In general, the linker nucleotide sequence between a crRNA and a tracrRNA is one that does not include complementary bases in order to avoid the formation of secondary structure within or 10 comprising nucleotides of the linker nucleotide sequence. In some embodiments, the linker nucleotide sequence between the crRNA and tracrRNA is at least 3, at least 4, at least 5, at least 6, at least 7, at least 8, at least 9, at least 10, at least 11, at least 12, or more nucleotides in length. In some embodiments, the linker nucleotide sequence between the crRNA and tracrRNA is 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, or more nucleotides in length. In some embodiments, the linker nucleotide sequence of a 15 single guide RNA is at least 4 nucleotides in length. In some embodiments, the linker nucleotide sequence of a single guide RNA is 4 nucleotides in length. In some embodiments, the linker nucleotide sequence is AAAG. In some embodiments, the guide RNA is a single guide RNA (sgRNA) having the backbone sequence (comprising a crRNA repeat, an optional linker nucleotide sequence, and a tracrRNA) of 20 any one of SEQ ID NOs: 451, 452, 453, 454, 463, 464, 465, 466, 467, 470, 475, and 476, or an active variant or fragment thereof. In certain embodiments, an active sgRNA backbone sequence variant comprises a nucleotide sequence having at least 40%, 45%, 50%, 55%, 60%, 65%, 70%, 75%, 80%, 85%, 90%, 91%, 92%, 93%, 94%, 95%, 96%, 97%, 98%, 99% or more sequence identity to any one of the nucleotide sequences set forth as SEQ ID NO: 451, 452, 453, 454, 463, 464, 465, 466, 467, 25 470, 475, and 476. In certain embodiments, an active sgRNA backbone sequence fragment comprises at least 5, 10, 15, 20, 25, 30, 35, 40, 45, 50, 55, 60, 65, 70, 75, 80, 85, 90, 95, 100, 105, or more contiguous nucleotides of any one of the nucleotide sequences set forth as SEQ ID NO: 451, 452, 453, 454, 463, 464, 465, 466, 467, 470, 475, and 476. In those embodiments wherein the RGN has the amino acid sequence set forth as SEQ ID 30 NO: 388, 413, or 414, the sgRNA backbone can have any one of the nucleotide sequences set forth as SEQ ID NOs: 463, 464, 465, 466, and 467, or an active variant or fragment thereof. In those embodiments wherein the RGN has the amino acid sequence set forth as SEQ ID NO: 387, 389, 392, 393, 394, 395, 411, 412, 415, or 416, the sgRNA backbone can have any one of the nucleotide sequences set forth as SEQ ID NOs: 451, 452, 453, 454, or an active variant or fragment thereof. In 35 those embodiments wherein the RGN has the amino acid sequence set forth as SEQ ID NO: 391, 419, or 420, the sgRNA backbone can have the nucleotide sequence set forth as SEQ ID NO: 470, or an active variant or fragment thereof. In those embodiments wherein the RGN has the amino acid 46 Atty Dkt No: L1034381430WO (00376)

[0047] sequence set forth as SEQ ID NO: 390, 396, 397, 398, 399, 400, 401, 402, 403, 404, 405, 406, 407, 408, 409, 410, 417, or 418, the sgRNA backbone can have the nucleotide sequence set forth as SEQ ID NO: 475 or 476, or an active variant or fragment thereof. Two polynucleotide sequences can be considered to be substantially complementary when the 5 two sequences hybridize to each other under stringent conditions. Likewise, a DNA-binding polypeptide (e.g., RGN polypeptide) is considered to bind to a particular target sequence within a sequence-specific manner if the guide RNA bound to the DNA-binding polypeptide (e.g., RGN polypeptide) binds to a target sequence under stringent conditions. By "stringent conditions" or "stringent hybridization conditions" is intended conditions under which the two polynucleotide 10 sequences will hybridize to each other to a detectably greater degree than to other sequences (e.g., at least 2-fold over background). Stringent conditions are sequence-dependent and will be different in different circumstances. Typically, stringent conditions will be those in which the salt concentration is less than about 1.5 M Na ion, typically about 0.01 to 1.0 M Na ion concentration (or other salts) at pH 7.0 to 8.3, and the temperature is at least about 30°C for short sequences (e.g., 10 to 50 15 nucleotides) and at least about 60°C for long sequences (e.g., greater than 50 nucleotides). Stringent conditions may also be achieved with the addition of destabilizing agents such as formamide. Exemplary low stringency conditions include hybridization with a buffer solution of 30 to 35% formamide, 1 M NaCl, 1% SDS (sodium dodecyl sulfate) at 37°C, and a wash in 1X to 2X SSC (20X SSC = 3.0 M NaCl / 0.3 M trisodium citrate) at 50 to 55°C. Exemplary moderate stringency conditions 20 include hybridization in 40 to 45% formamide, 1.0 M NaCl, 1% SDS at 37°C, and a wash in 0.5X to 1X SSC at 55 to 60°C. Exemplary high stringency conditions include hybridization in 50% formamide, 1 M NaCl, 1% SDS at 37°C, and a wash in 0.1X SSC at 60 to 65°C. Optionally, wash buffers may comprise about 0.1% to about 1% SDS. Duration of hybridization is generally less than about 24 hours, usually about 4 to about 12 hours. The duration of the wash time will be at least a 25 length of time sufficient to reach equilibrium. The Tm is the temperature (under defined ionic strength and pH) at which 50% of a complementary target sequence hybridizes to a perfectly matched sequence. For DNA-DNA hybrids, the Tm can be approximated from the equation of Meinkoth and Wahl (1984) Anal. Biochem. 138:267-284: Tm = 81.5°C + 16.6 (log M) + 0.41 (%GC) - 0.61 (% form) - 500 / L; where M is the 30 molarity of monovalent cations, %GC is the percentage of guanosine and cytosine nucleotides in the DNA, % form is the percentage of formamide in the hybridization solution, and L is the length of the hybrid in base pairs. Generally, stringent conditions are selected to be about 5°C lower than the thermal melting point (Tm) for the specific sequence and its complement at a defined ionic strength and pH. However, severely stringent conditions can utilize a hybridization and / or wash at 1, 2, 3, or 35 4°C lower than the thermal melting point (Tm); moderately stringent conditions can utilize a hybridization and / or wash at 6, 7, 8, 9, or 10°C lower than the thermal melting point (Tm); low stringency conditions can utilize a hybridization and / or wash at 11, 12, 13, 14, 15, or 20°C lower than 47 Atty Dkt No: L1034381430WO (00376)

[0048] the thermal melting point (Tm). Using the equation, hybridization and wash compositions, and desired Tm, those of ordinary skill will understand that variations in the stringency of hybridization and / or wash solutions are inherently described. An extensive guide to the hybridization of nucleic acids is found in Tijssen (1993) Laboratory Techniques in Biochemistry and Molecular Biology— 5 Hybridization with Nucleic Acid Probes, Part I, Chapter 2 (Elsevier, New York); and Ausubel et al., eds. (1995) Current Protocols in Molecular Biology, Chapter 2 (Greene Publishing and Wiley- Interscience, New York). See Sambrook et al. (1989) Molecular Cloning: A Laboratory Manual (2d ed., Cold Spring Harbor Laboratory Press, Plainview, New York). The term “sequence specific” can also refer to the binding of a DNA-binding polypeptide 10 (e.g., RGN polypeptide) or PE to a target sequence at a greater affinity than binding to a randomized background sequence. The guide RNA can be synthesized chemically or via in vitro transcription. Assays for determining sequence-specific binding between an RGN and a guide RNA are known in the art and include, but are not limited to, in vitro binding assays between an expressed RGN and the guide RNA, 15 which can be tagged with a detectable label (e.g., biotin) and used in a pull-down detection assay in which the guide RNA:RGN complex is captured via the detectable label (e.g., with streptavidin beads). A control guide RNA with an unrelated sequence or structure to the guide RNA can be used as a negative control for non-specific binding of the RGN to RNA. The guide RNA can be introduced into a target cell, organelle, or embryo as an RNA 20 molecule. In some embodiments, a nucleotide sequence encoding the guide RNA is introduced into a target cell, organelle, or embryo. In some embodiments, the nucleotide sequence encoding a guide RNA is operably linked to a promoter (e.g., an RNA polymerase III promoter). The promoter can be a native promoter or heterologous to the guide RNA-encoding nucleotide sequence. In some embodiments, the guide RNA can be introduced into a target cell, organelle, or embryo as a 25 ribonucleoprotein complex, as described herein, wherein the guide RNA is bound to an RGN polypeptide. The guide RNA directs an associated RGN to a particular target nucleotide sequence of interest through hybridization of the guide RNA to the target sequence of interest. The target sequence can be bound (and in some embodiments, cleaved) by an RGN in vitro or in a cell. A target sequence 30 is within a target polynucleotide and can comprise DNA, RNA, or a combination of both and can be single-stranded or double-stranded. A target sequence can be genomic DNA (i.e., chromosomal DNA), plasmid DNA, or an RNA molecule (e.g., messenger RNA, ribosomal RNA, transfer RNA, micro RNA, small interfering RNA). In those embodiments wherein the target sequence is a chromosomal sequence, the chromosomal sequence can be a nuclear, plastid, or mitochondrial 35 chromosomal sequence. In the presently disclosed compositions and methods, the target sequence is within a target polynucleotide that is double-stranded (e.g., a target DNA sequence). In some 48 Atty Dkt No: L1034381430WO (00376)

[0049] embodiments, the target sequence is unique in the target genome. In some embodiments, the target sequence is double-stranded and comprises a target strand and a non-target strand. The target sequence is adjacent to a protospacer adjacent motif (PAM) and the non-target strand of the target sequence is the strand that comprises the PAM. The PAM is immediately adjacent 5 to the target sequence and often comprise Ns, which represent any nucleotide. In some embodiments, the PAM comprises about 1 to about 10 Ns, including about 1, about 2, about 3, about 4, about 5, about 6, about 7, about 8, about 9, or about 10 Ns. In particular embodiments, a PAM comprises 1 to 10 Ns, including 1, 2, 3, 4, 5, 6, 7, 8, 9, or 10 Ns. In general, the PAM can be 5' or 3' of the target sequence on its non-target strand. In some embodiments, the PAM of the RGN of the PE or PE 10 system is immediately 3' of the target sequence on its non-target strand. Generally, the PAM is a consensus sequence of about 3-4 nucleotides, but in particular embodiments it can be 2, 3, 4, 5, 6, 7, 8, 9, or more nucleotides in length. The PAM recognized by the non-limiting examples of RGNs that can be used in the presently disclosed PE and PE systems is outlined in Table 1. In some embodiments, an RGN having the amino acid sequence set forth as SEQ ID NO: 388, 15 413, or 414, or an active variant or fragment thereof, binds a target nucleotide sequence adjacent to and 5′ of a PAM sequence set forth as NNRYA. In some embodiments, an RGN having the amino acid sequence set forth as SEQ ID NO: 388, 413, or 414, or an active variant or fragment thereof, binds a target nucleotide sequence adjacent to and 5′ of a PAM sequence set forth as NNRYA, when bound to a guide RNA comprising a crRNA repeat sequence of any one of SEQ ID NOs: 455, 456, 20 457, or an active variant or fragment thereof, and a tracrRNA sequence of any one of SEQ ID NOs: 458, 459, 460, 461, 462, or an active variant or fragment thereof. In some embodiments, an RGN having the amino acid sequence set forth as SEQ ID NO: 387, 411, or 412, or an active variant or fragment thereof, binds a target nucleotide sequence adjacent to and 5′ of a PAM sequence set forth as NNNNCY. In some embodiments, an RGN having the amino 25 acid sequence set forth as SEQ ID NO: 387, 411, or 412, or an active variant or fragment thereof, binds a target nucleotide sequence adjacent to and 5′ of a PAM sequence set forth as NNNNCY, when bound to a guide RNA comprising a crRNA repeat sequence of any one of SEQ ID NOs: 444, 445, 446, or an active variant or fragment thereof, and a tracrRNA sequence of any one of SEQ ID NOs: 447, 448, 449, 450, or an active variant or fragment thereof. 30 In some embodiments, an RGN having the amino acid sequence set forth as SEQ ID NO: 389, 415, or 416, or an active variant or fragment thereof, binds a target nucleotide sequence adjacent to and 5′ of a PAM sequence set forth as NNNNCC. In some embodiments, an RGN having the amino acid sequence set forth as SEQ ID NO: 389, 415, or 416, or an active variant or fragment thereof, binds a target nucleotide sequence adjacent to and 5′ of a PAM sequence set forth as NNNNCC, when 35 bound to a guide RNA comprising a crRNA repeat sequence of any one of SEQ ID NOs: 444, 445, 446, or an active variant or fragment thereof, and a tracrRNA sequence of any one of SEQ ID NOs: 447, 448, 449, 450, or an active variant or fragment thereof. 49 Atty Dkt No: L1034381430WO (00376)

[0050] In some embodiments, an RGN having the amino acid sequence set forth as SEQ ID NO: 391, 419, or 420, or an active variant or fragment thereof, binds a target nucleotide sequence adjacent to and 5′ of a PAM sequence set forth as NNGRR. In some embodiments, an RGN having the amino acid sequence set forth as SEQ ID NO: 391, 419, or 420, or an active variant or fragment thereof, 5 binds a target nucleotide sequence adjacent to and 5′ of a PAM sequence set forth as NNGRR, when bound to a guide RNA comprising a crRNA repeat sequence of SEQ ID NO: 468, or an active variant or fragment thereof, and a tracrRNA sequence of SEQ ID NO: 469, or an active variant or fragment thereof. In some embodiments, an RGN having the amino acid sequence set forth as SEQ ID NO: 390, 10 417, or 418, or an active variant or fragment thereof, binds a target nucleotide sequence adjacent to and 5′ of a PAM sequence set forth as NNGG. In some embodiments, an RGN having the amino acid sequence set forth as SEQ ID NO: 390, 417, or 418, or an active variant or fragment thereof, binds a target nucleotide sequence adjacent to and 5′ of a PAM sequence set forth as NNGG, when bound to a guide RNA comprising a crRNA repeat sequence of SEQ ID NO: 471 or 472, or an active variant or 15 fragment thereof, and a tracrRNA sequence of SEQ ID NO: 473 or 474, or an active variant or fragment thereof. It is well-known in the art that PAM sequence specificity for a given nuclease enzyme is affected by enzyme concentration (see, e.g., Karvelis et al. (2015) Genome Biol 16:253), which may be modified by altering the promoter used to express the RGN, or the amount of ribonucleoprotein 20 complex delivered to a target cell, organelle, or embryo. Upon recognizing its corresponding PAM sequence, the RGN, if active, may cleave one or both strands of a target sequence at a specific cleavage site. As used herein, a cleavage site comprises particular nucleotides within a target sequence at which the target strand, non-target strand, or both strands of a target sequence are cleaved by an RGN. The cleavage site can comprise the 1stand 2nd, 2nd25 and 3rd, 3rdand 4th, 4thand 5th, 5thand 6th, 7thand 8th, or 8thand 9thnucleotides from the PAM in either the 5' or 3' direction. In some embodiments, the cleavage site may be over 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, or 20 nucleotides from the PAM in either the 5' or 3' direction. As RGNs can cleave a target sequence resulting in staggered ends, in some embodiments, the cleavage site is defined based on the distance of the two nucleotides from the PAM on the non-target strand of the target sequence 30 and for the target strand, the distance of the two nucleotides from the complement of the PAM. 1. PEgRNA PE systems utilizes a polymerase editing guide RNA (“PEgRNA”). The PEgRNA is a guide RNA that both specifies the target sequence and provides the template for polymerization of the 35 replacement strand containing a desired edit by way of an extension engineered onto the RGN guide RNA or a part thereof, referred to herein as an extension arm. The PEgRNA can be a single guide RNA, wherein the extension arm can be at the 5' or 3' end, or at an internal portion of the guide RNA, 50 Atty Dkt No: L1034381430WO (00376)

[0051] or multiple polynucleotides (e.g., a dual guide RNA). In embodiments wherein the PEgRNA is a dual guide RNA, the extension arm can be at the 5' or 3' end, or at an internal portion of the crRNA or tracrRNA molecule. The template for polymerization within an extension arm is referred to herein as the DNA synthesis template. In those embodiments wherein the polymerase of the PE is an RT, the 5 DNA synthesis template can be referred to as the reverse transcriptase template (RTT). The RGN is guided to the target sequence by the PEgRNA and in those embodiments wherein the RGN is a nickase with an inactivated HNH domain and active RuvC domain, the RGN nickase nicks the non- target strand upstream of the sequence to be edited and upstream of the PAM, creating a 3' flap on the non-target strand. The PEgRNA includes a primer binding site (PBS) that is complementary to the 3' 10 flap of the non-target strand. The PBS can be at least about 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30, 31, 32, 33, 34, 35, 36, 37, 38, 39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, or 50 nucleotides in length. In certain embodiments, the PEgRNA comprises a PBS that is at least 5 (e.g., 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, or 20) nucleotides in length. In some embodiments, the PEgRNA may comprise a PBS that is 9, 11, 12, 13, or 15 nucleotides in 15 length. Hybridization of the PBS and 3′ flap of the non-target strand allows polymerization of the replacement strand containing the edit using the DNA synthesis template in the extension of the PEgRNA. The DNA synthesis template can be at least about 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30, 31, 32, 33, 34, 35, 36, 37, 38, 39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, or more nucleotides in length. In certain embodiments, the PEgRNA 20 comprises a DNA synthesis template that is at least 19, at least 20, at least 21, at least 22, at least 23, at least 24, at least 25, at least 26, at least 27, at least 28, at least 29, at least 30, at least 31, at least 32, at least 33, at least 34, at least 35, at least 36, at least 37, at least 38, at least 39, at least 40, at least 41, at least 42, at least 43, at least 44, at least 45, at least 46, at least 47, at least 48, at least 49, or at least 50 nucleotides in length. In some embodiments, the PEgRNA comprises a DNA synthesis template 25 that is 19, 22, 23, 24, 25, 26, 29, 30, 32, 34, 37, 38, 39, 40, 42, or 46 nucleotides in length. The DNA synthesis template comprises the desired edit, which can be a substitution of one or more nucleotides, a deletion of one or more nucleotides, or an addition of one or more nucleotides. The extension arm of the PEgRNA can be formed from RNA or DNA. In the case of an RNA extension, the polymerase of the polymerase editor can be an RNA-dependent DNA polymerase (such 30 as a reverse transcriptase). In the case of a DNA extension, the polymerase of the polymerase editor may be a DNA-dependent DNA polymerase. The replacement strand containing the desired edit (e.g., substitution, deletion, or addition) shares the same sequence as the non-target strand of the target sequence to be edited (with the exception that it includes the desired edit). Through DNA repair and / or replication machinery, the 35 non-target strand of the target sequence is replaced by the newly synthesized replacement strand containing the desired edit. In some cases, polymerase editing may be thought of as a “search-and- replace” genome editing technology since the polymerase editors not only search and locate the 51 Atty Dkt No: L1034381430WO (00376)

[0052] desired target sequence to be edited, but at the same time, encode a replacement strand containing a desired edit which is installed in place of the corresponding non-target strand of the target sequence. Thus, in some embodiments, a guide RNA of the disclosure comprises an extension comprising an edit template for polymerase editing. 5 2. Nicking guide RNA In order to reduce the possibility that the edit introduced by a polymerase editor is removed due to mismatch repair of the edited strand, a nicking guide RNA can be used. A “nicking guide RNA” is a guide RNA that targets a sequence within the unedited strand at a site nearby and opposite 10 to the original nick and guides the RGN nickase of the PE system to this unedited strand to introduce a single-stranded nick. The nicking guide RNA can be designed to match the edited sequence introduced by the PEgRNA, but not the original unedited sequence, to ensure that the nicking occurs after the editing event on the non-target strand takes place. 15 VII. Polynucleotides encoding RTs, DNA-binding polypeptides, PE-enhancing polypeptides, fusion proteins, polymerase editors, polymerase editor systems, and guide RNAs The present disclosure provides polynucleotides encoding the presently disclosed RTs and fusion proteins comprising the same. PEs and PE systems can comprise polynucleotides comprising or encoding PEgRNAs and polynucleotides comprising a nucleotide sequence encoding RTs, DNA- 20 binding polypeptides (e.g., RGN polypeptides), PE-enhancing polypeptides, fusion proteins, and / or PEs. The use of the term "polynucleotide" or “nucleic acid molecule” is not intended to limit the present disclosure to polynucleotides comprising DNA. Those of ordinary skill in the art will recognize that polynucleotides can comprise ribonucleotides (RNA) and combinations of 25 ribonucleotides and deoxyribonucleotides. Such deoxyribonucleotides and ribonucleotides include both naturally occurring molecules and synthetic analogues. These include peptide nucleic acids (PNAs), PNA-DNA chimers, locked nucleic acids (LNAs), and phosphothiorate linked sequences. The polynucleotides disclosed herein also encompass all forms of sequences including, but not limited to, single-stranded forms, double-stranded forms, DNA-RNA hybrids, triplex structures, stem-and- 30 loop structures, circular RNA (circRNA), and the like. In some of those embodiments wherein the presently disclosed compositions and methods comprise a polynucleotide encoding an RT, DNA-binding polypeptide (e.g., RGN polypeptide), PE- enhancing polypeptide, fusion protein, and / or PE, the polynucleotide is an RNA polynucleotide (e.g., an mRNA (messenger RNA) molecule). An mRNA refers to any polynucleotide which encodes a 35 polypeptide of interest and which is capable of being translated to produce the encoded polypeptide of interest in vitro, in vivo, in situ, or ex vivo. In some embodiments, the basic components of an mRNA molecule include at least a coding region, a 5′ untranslated region (UTR), a 3′ UTR, a 5′ 52 Atty Dkt No: L1034381430WO (00376)

[0053] cap and a poly-A tail. A 5′ UTR, situated 5′ of a coding sequence and transcribed as part of an mRNA, may comprise various regulatory elements, including, e.g., 5′ cap structure, G-quadruplex structure (G4), stem-loop structure, and internal ribosome entry sites (IRES), which can control translation initiation of the mRNA. A 3′ UTR, situated 3′ of a coding sequence and transcribed as part of an 5 mRNA, can be involved in numerous regulatory processes including transcript cleavage, stability and polyadenylation, translation, and mRNA localization. The 3′ UTR can serve as a binding site for numerous regulatory proteins and small non-coding RNAs, e.g., microRNAs. A 5′ UTR and / or a 3′ UTR heterologous to an mRNA originates from an organism or species that is different from that of the mRNA, or if from the same organism or species as the mRNA, is substantially modified from its 10 native form in composition and / or genomic locus by deliberate human intervention. In some embodiments, inclusion of a 5′ UTR and / or a 3′ UTR heterologous to an mRNA encoding an RT, DNA-binding polypeptide (e.g., RGN polypeptide), PE-enhancing polypeptide, fusion protein, and / or PE of the disclosure improves polypeptide synthesis from the mRNA in a tissue (e.g., liver, or cells in vitro, such as stem cells, hepatocytes or lymphocytes). Heterologous 5′ UTRs 15 and / or 3′ UTRs may, for example, increase protein synthesis by increasing the time that the mRNA remains in translating polysomes (message stability) and / or the rate at which ribosomes initiate translation on the mRNA (message translation efficiency). Thus, inclusion of a 5′ UTR and / or a 3′ UTR heterologous to an mRNA encoding an RT, DNA-binding polypeptide (e.g., RGN polypeptide), PE-enhancing polypeptide, fusion protein, and / or PE of the disclosure can lead to 20 prolonged and / or increased polypeptide synthesis, enabling improved editing of a target polynucleotide by the PE or PE system. In some embodiments, the enhanced polypeptide synthesis from an mRNA occurs in a tissue-specific manner. Heterologous UTR sequences are described, for example, in US 2023 / 0050143 and US 2017 / 0252461. In some embodiments, an mRNA encoding an RT, DNA-binding polypeptide (e.g., RGN 25 polypeptide), PE-enhancing polypeptide, fusion protein, and / or PE useful in the presently disclosed methods and compositions can include one or more structural and / or chemical modifications or alterations which impart useful properties to the polynucleotide. For instance, a useful property of an mRNA includes the lack of a substantial induction of the innate immune response of a cell into which the mRNA is introduced. A “structural” feature or modification is one in which two or more linked 30 nucleotides are inserted, deleted, duplicated, inverted or randomized in an mRNA without significant chemical modification to the nucleotides themselves. Because chemical bonds will necessarily be broken and reformed to effect a structural modification, structural modifications are of a chemical nature and hence are chemical modifications. However, structural modifications will result in a different sequence of nucleotides. Chemical modifications to mRNA can involve inclusion of 5-35 methylcytosine, N1-methyl-pseudouridine, pseudouridine, 2-thiouridine, 4-thiouridine, 5- methoxyuridine, 2′Fluoroguanosine, 2′Fluorouridine, 5-bromouridine, 5-(2-carbomethoxyvinyl) uridine, 5-[3(1-E-propenylamino)] uridine, α-thiocytidine, N6-methyladenosine, 5-methylcytidine, 53 Atty Dkt No: L1034381430WO (00376)

[0054] N4-acetylcytidine, 5-formylcytidine, or combinations thereof, in an mRNA. The polynucleotides encoding RTs, DNA-binding polypeptides (e.g., RGN polypeptides), PE- enhancing polypeptides, fusion proteins, PEs, and / or guide RNAs can be codon optimized for expression in an organism of interest. A "codon-optimized” coding sequence is a polynucleotide 5 coding sequence having its frequency of codon usage designed to mimic the frequency of preferred codon usage or transcription conditions of a particular host cell. Expression in the particular host cell or organism is enhanced as a result of the alteration of one or more codons at the nucleic acid level such that the translated amino acid sequence is not changed. Polynucleotides can be codon optimized, either wholly or in part. Codon tables and other references providing preference information for a 10 wide range of organisms are available in the art (see, e.g., Campbell and Gowri (1990) Plant Physiol. 92:1-11 for a discussion of plant-preferred codon usage). Methods are available in the art for synthesizing plant-preferred genes or mammalian (for example human) codon-optimized coding sequences. See, for example, U.S. Patent Nos.5,380,831, and 5,436,391, and Murray et al. (1989) Nucleic Acids Res.17:477-498, herein incorporated by reference. 15 Polynucleotides encoding the RTs, DNA-binding polypeptides (e.g., RGN polypeptides), PE- enhancing polypeptides, fusion proteins, PEs, and / or gRNAs provided herein can be provided in expression cassettes for in vitro expression or expression in a cell, organelle, embryo, or organism of interest. The cassette will include 5' and 3' regulatory sequences operably linked to a polynucleotide encoding an RT, DNA-binding polypeptide (e.g., RGN polypeptide), PE-enhancing polypeptide, 20 fusion protein, PE, and / or gRNA provided herein that allows for expression of the polynucleotide. The cassette may additionally contain at least one additional gene or genetic element to be cotransformed into the organism. Where additional genes or elements are included, the components are operably linked. The term “operably linked” is intended to mean a functional linkage between two or more elements. For example, an operable linkage between a promoter and a coding region of 25 interest (e.g., region coding for a DNA-binding polypeptide and / or gRNA) is a functional link that allows for expression of the coding region of interest. Operably linked elements may be contiguous or non-contiguous. When used to refer to the joining of two protein coding regions (either by fusion or insertion), by “operably linked” or “operably fused” is intended that the coding regions are in the same reading frame, even if one is inserted into another. In some embodiments, polypeptides that are 30 “operably fused” or “operably linked” means that the structure and / or biological activity of each individual peptide is also present in the fusion. Alternatively, the additional gene(s) or element(s) can be provided on multiple expression cassettes. For example, the nucleotide sequence encoding a presently disclosed RT, DNA-binding polypeptide (e.g., RGN polypeptide), PE-enhancing polypeptide, fusion protein, or PE can be present on one expression cassette, whereas the nucleotide 35 sequence encoding a guide RNA can be on a separate expression cassette. Such an expression cassette is provided with a plurality of restriction sites and / or recombination sites for insertion of the polynucleotides to be under the transcriptional regulation of the regulatory regions. The expression 54 Atty Dkt No: L1034381430WO (00376)

[0055] cassette may additionally contain a selectable marker gene. The expression cassette will include in the 5'-3' direction of transcription, a transcriptional (and, in some embodiments, translational) initiation region (i.e., a promoter), an RT-, a DNA-binding polypeptide (e.g., RGN polypeptide) -, a PE-enhancing polypeptide -, a fusion protein-, a PE-, and / or 5 a gRNA-encoding polynucleotide of the invention, and a transcriptional (and in some embodiments, translational) termination region (i.e., termination region) functional in the cell or organism of interest. The promoters of the disclosure are capable of directing or driving expression of a coding sequence in a host cell. The regulatory regions (e.g., promoters, transcriptional regulatory regions, and translational termination regions) may be endogenous or heterologous to the host cell or to each other. 10 As used herein, “heterologous”, in reference to a regulatory region that is heterologous to another regulatory region or to the host cell, is a regulatory region that is not found with another regulatory region or in the host cell in nature. The heterologous regulatory region can originate from a foreign species or from the same species. The heterologous regulatory region can be in its native form or is substantially modified from its native form in composition and / or genomic locus by deliberate human 15 intervention. For example, a chimeric gene comprises a coding sequence operably linked to a transcription initiation region that is heterologous to the coding sequence. Convenient termination regions include ones from simian virus (SV40), human growth hormone (hGH), bovine growth hormone (BGH), and rabbit beta-globin (rbGlob). See also Proudfoot (1991) Cell 64:671-674; Munroe et al. (1990) Gene 91:151-158; Schek et al. (1992) Molecular and 20 Cellular Biology 12(12):5386-5393; Gil and Proudfoot (1987) Cell 49(3):399-406; Goodwin and Rottman (1992) The Journal of Biological Chemistry 267(23):16330-16334; and Lanoix and Acheson (1988) EMBO J.7(8): 2515-2522. Additional termination regions are available from the Ti-plasmid of A. tumefaciens, such as the octopine synthase and nopaline synthase termination regions. See also Guerineau et al. (1991) Mol. Gen. Genet.262:141-144; Proudfoot (1991) Cell 64:671-674; Sanfacon 25 et al. (1991) Genes Dev.5:141-149; Mogen et al. (1990) Plant Cell 2:1261-1272; Munroe et al. (1990) Gene 91:151-158; Ballas et al. (1989) Nucleic Acids Res.17:7891-7903; and Joshi et al. (1987) Nucleic Acids Res.15:9627-9639. Additional regulatory signals include, but are not limited to, transcriptional initiation start sites, operators, activators, enhancers, other regulatory elements, ribosomal binding sites, an initiation 30 codon, termination signals, and the like. See, for example, U.S. Pat. Nos.5,039,523 and 4,853,331; EPO 0480762A2; Sambrook et al. (1992) Molecular Cloning: A Laboratory Manual, ed. Maniatis et al. (Cold Spring Harbor Laboratory Press, Cold Spring Harbor, N.Y.), hereinafter “Sambrook 11”; Davis et al., eds. (1980) Advanced Bacterial Genetics (Cold Spring Harbor Laboratory Press), Cold Spring Harbor, N.Y., and the references cited therein. 35 In preparing the expression cassette, the various DNA fragments may be manipulated, so as to provide for the DNA sequences in the proper orientation and, as appropriate, in the proper reading frame. Toward this end, adapters or linkers may be employed to join the DNA fragments or other 55 Atty Dkt No: L1034381430WO (00376)

[0056] manipulations may be involved to provide for convenient restriction sites, removal of superfluous DNA, removal of restriction sites, or the like. For this purpose, in vitro mutagenesis, primer repair, restriction, annealing, resubstitutions, e.g., transitions and transversions, may be involved. A number of promoters can be used in the practice of the disclosure. The promoters can be 5 selected based on the desired outcome. The nucleic acids can be combined with constitutive, inducible, growth stage-specific, cell type-specific, tissue-preferred, tissue-specific, or other promoters for expression in the organism of interest. See, for example, promoters set forth in WO 99 / 43838 and in US Patent Nos: 8,575,425; 7,790,846; 8,147,856; 8,586832; 7,772,369; 7,534,939; 6,072,050; 5,659,026; 5,608,149; 5,608,144; 5,604,121; 5,569,597; 5,466,785; 5,399,680; 5,268,463; 10 5,608,142; and 6,177,611; herein incorporated by reference. Exemplary constitutive promoters for expression in cells of the present disclosure include: an SV40 early promoter; a mouse mammary tumor virus long terminal repeat (LTR) promoter; adenovirus major late promoter (Ad MLP); a herpes simplex virus (HSV) promoter; a cytomegalovirus (CMV) promoter such as the CMV immediate early promoter region (CMVIE); a 15 rous sarcoma virus (RSV) promoter; a human ubiquitin C promoter (UBC); a human U6 small nuclear promoter (U6); an enhanced U6 promoter; a human H1 promoter from RNA polymerase III (H1); a human elongation factor 1α promoter (EF1A); a human beta-actin promoter (ACTB); a human or mouse phosphoglycerate kinase 1 promoter (PGK); a chicken β-Actin promoter coupled with CMV early enhancer (CAGG); a yeast transcription elongation factor promoter (TEF1); and the like. See, 20 for example, Miyagishi et al. (2002) Nature Biotechnology 20:497-500; Xia et al. (2003) Nucleic Acids Res.31(17):e100-e100; Pasleau et al. (1985) Gene 38:227–232; Martin-Gallardo et al. (1988) Gene 70: 51–56; Oellig and Seliger (1990) J Neurosci Res 26: 390–396; Manthorpe et al. (1993) Hum Gene Ther 4: 419–431; Yew et al. (1997) Hum Gene Ther 8: 575–584; Xu et al. (2001) Gene 272: 149–156; Nguyen et al. (2008) J Surg Res 148: 60–66; Costa et al. (2005) Nat Meth.2:259–260; Lam 25 and Truong (2020) ACS Synth. Biol. 9(10):2625–2631. For expression in plants, constitutive promoters also include CaMV 35S promoter (Odell et al. (1985) Nature 313:810-812); rice actin (McElroy et al. (1990) Plant Cell 2:163-171); ubiquitin (Christensen et al. (1989) Plant Mol. Biol.12:619-632 and Christensen et al. (1992) Plant Mol. Biol. 18:675-689); pEMU (Last et al. (1991) Theor. Appl. Genet.81:581-588); and MAS (Velten et al. 30 (1984) EMBO J.3:2723-2730). Examples of inducible promoters include: stress-regulated promoters such as Adh1 promoter, Hsp70 promoter, and Hsp90 promoter (Wurm et al. (1986) Proc. Natl. Acad. Sci. USA.83:5414– 5418; Nover L. Heat Shock Response. CRC Press; Boca Raton, FL, USA: 1991); light-inducible promoters such as PPDK promoter and pepcarboxylase promoter; metal-regulated promoters (Mayo et 35 al. (1982) Cell.29:99–108; Searle et al. (1985) Mol. Cell. Biol.5:1480–1489); hormone-responsive promoters including a glucocorticoid-responsive promoter (Hynes et al. (1981) Proc. Natl. Acad. Sci. USA.78:2038–2042; Klock et al. (1987) Nature.329:734–736). Chemically regulated promoters 56 Atty Dkt No: L1034381430WO (00376)

[0057] include: In2-2 promoter which is safener induced (U.S. Pat. No.5,364,780); the Axig1 promoter which is auxin induced and tapetum specific but also active in callus (PCT US01 / 22169); the steroid- responsive promoters (see, for example, the ERE promoter which is estrogen induced, and the glucocorticoid-inducible promoter in Schena et al. (1991) Proc. Natl. Acad. Sci. USA 88:10421-10425 5 and McNellis et al. (1998) Plant J.14(2):247-257); tetracycline-inducible and tetracycline-repressible promoters (see, for example, Gatz et al. (1991) Mol. Gen. Genet.227:229-237; Gossen et al. (1993) Trends Biochem Sci.18:471–475; Gossen and Bujard (1992) Proc. Natl Acad. Sci. USA 89:5547– 5551; Zhou et al. (2006) Gene Ther.13:1382–1390; and U.S. Pat. Nos.5,814,618 and 5,789,156); isopropyl-beta-D-thiogalactopyranoside (IPTG)-regulated promoters; and lactose-regulated 10 promoters. Inducible expression can be obtained using operator systems including AlcR / acetaldehyde, ArgR / L-arginine, BirA / biotinyl-AMP, CymR / cumate, EthR / 2-phenylethylbutyrate, HdnoR / 6- hydroxynicotine, HucR / uric acid, MphR(A) / macrolides, PIP / Streptogramins, Rex / NADH, RheA / heat, ScbR / SCB1, TraR / 3-oxo-C8-HSL, and TtgR / phloretin; see, for example, U.S. Patent No. 8,728,759B2; U.S. Patent No.7,745,592B2; Weber and Fussenegger (2004) Methods Mol. Biol. 15 267:451–466; Hartenbach et al. (2007) Nucleic Acids Res.35:e136; Weber et al. (2009) Metab. Eng. 11:117–124; Weber et al. (2008) Proc. Natl. Acad. Sci. USA.105:9994–9998; Malphettes et al. (2005) Nucleic Acids Res.33:e107; Kemmer et al. (2010) Nat. Biotechnol.28:355–360; Weber et al. (2002) Nat. Biotechnol.20:901–907; Fussenegger et al. (2000) Nat. Biotechnol.18:1203–1208; Weber et al. (2006) Metab. Eng.8:273–280; Weber et al. (2003) Nucleic Acids Res.31:e69; Weber et 20 al. (2003) Nucleic Acids Res.31:e71; Neddermann et al. (2003) EMBO Rep.4:159–165; and Gitzinger et al. (2009) Proc. Natl. Acad. Sci. USA.106:10638–10643. Inducible expression can be obtained using protein-protein interaction systems including: rapamycin-induced interaction between FKBP12 (FK506 binding protein 12) and mTOR (Rivera et al. (1996) Nat. Med.2:1028–1032; Belshaw et al. (1996) Proc. Natl. Acad. Sci. USA.93:4604–46077); abscisic acid (ABA)-regulated 25 interaction between PYL1 (abscisic acid receptor) and ABI1 (protein phosphatase 2C56) (Liang et al. (2011) Sci. Signal.4(164):rs2-rs2); and light-induced protein–protein interaction systems (Wang et al. (2012) Nat. Methods.9:266–269; Yamada et al. (2018) Cell. Rep.25:487–500). Tissue-specific or tissue-preferred promoters can be utilized to target expression of an expression construct within a particular tissue. In some embodiments, the tissue-specific or tissue- 30 preferred promoters are active in mammalian tissue. Examples of tissue-specific or tissue-preferred promoters include promoters that initiate transcription preferentially in certain tissues, such as white blood cells (e.g., CD4 T cell), heart, kidney, liver, CNS, eye, pancreas, skeletal muscle, and testis. In some embodiments, the tissue-specific or tissue-preferred promoters are active in plant tissue. Examples of promoters under developmental control in plants include promoters that initiate 35 transcription preferentially in certain tissues, such as leaves, roots, fruit, seeds, or flowers. A “tissue specific” promoter is a promoter that initiates transcription only in certain tissues. Unlike constitutive expression of genes, tissue-specific expression is the result of several interacting levels of gene 57 Atty Dkt No: L1034381430WO (00376)

[0058] regulation. As such, promoters from homologous or closely related plant species can be preferable to use to achieve efficient and reliable expression of transgenes in particular tissues. In some embodiments, the expression comprises a tissue-preferred promoter. A “tissue preferred” promoter is a promoter that initiates transcription preferentially, but not necessarily entirely or solely in certain 5 tissues. In some embodiments, the polynucleotides encoding a RT, DNA-binding polypeptide (e.g., RGN polypeptide), PE-enhancing polypeptide, fusion protein, PE, and / or gRNA comprise a cell type- specific promoter. A "cell type specific" promoter is a promoter that primarily drives expression in certain cell types in one or more organs. Some examples of cells in which cell type specific promoters 10 may be primarily active include, for example, a primary cell, a neuronal cell, a glial cell, an adipocyte, a cardiomyocyte, a smooth muscle cell, a photoreceptor cell, and a retinal ganglia cell. Some examples of plant cells in which cell type specific promoters functional in plants may be primarily active include, for example, BETL cells, vascular cells in roots, leaves, stalk cells, and stem cells. The polynucleotides can also include cell type preferred promoters. A "cell type preferred" promoter is a 15 promoter that primarily drives expression mostly, but not necessarily entirely or solely in certain cell types in one or more organs. Some examples of cells in which cell type preferred promoters may be preferentially active include, for example, a primary cell, a neuron, an adipocyte, a cardiomyocyte, a smooth muscle cell, and a photoreceptor cell. Some examples of plant cells in which cell type preferred promoters functional in plants may be preferentially active include, for example, BETL 20 cells, vascular cells in roots, leaves, stalk cells, and stem cells. The nucleic acid sequences encoding the RTs, DNA-binding polypeptides (e.g., RGN polypeptides), PE-enhancing polypeptides, fusion proteins, PEs, and / or gRNAs can be operably linked to a promoter sequence that is recognized by a phage RNA polymerase for example, for in vitro mRNA synthesis. In such embodiments, the in vitro-transcribed RNA can be purified for use in 25 the methods described herein. For example, the promoter sequence can be a T7, T3, or SP6 promoter sequence or a variation of a T7, T3, or SP6 promoter sequence. In such embodiments, the expressed protein and / or RNAs can be purified for use in the methods of genome editing described herein. In some embodiments, the polynucleotide encoding the RT, DNA-binding polypeptide (e.g., RGN polypeptide), PE-enhancing polypeptide, fusion protein, PE, and / or gRNA can be linked to a 30 polyadenylation signal (e.g., SV40 polyA signal and other signals functional in plants) and / or at least one transcriptional termination sequence. Additionally, the sequence encoding the RT, DNA-binding polypeptide (e.g., RGN polypeptide), PE-enhancing polypeptide, fusion protein, or PE also can be linked to sequence(s) encoding at least one nuclear localization signal, at least one cell-penetrating domain, and / or at least one signal peptide capable of trafficking proteins to particular subcellular 35 locations, as described elsewhere herein. The polynucleotide encoding the RT, DNA-binding polypeptide (e.g., RGN polypeptide), PE- enhancing polypeptide, fusion protein, PE, and / or gRNA can be present in a vector or multiple 58 Atty Dkt No: L1034381430WO (00376)

[0059] vectors. A “vector” refers to a polynucleotide composition for transferring, delivering, or introducing a nucleic acid into a host cell. Suitable vectors include plasmid vectors, phagemids, cosmids, artificial / mini-chromosomes, transposons, and viral vectors (e.g., lentiviral vectors, adeno-associated viral vectors, baculoviral vector). The vector can comprise additional expression control sequences 5 (e.g., enhancer sequences, Kozak sequences, polyadenylation sequences, transcriptional termination sequences), selectable marker sequences (e.g., antibiotic resistance genes), origins of replication, and the like. Additional information can be found in "Current Protocols in Molecular Biology" Ausubel et al., John Wiley & Sons, New York, 2003 or "Molecular Cloning: A Laboratory Manual" Sambrook & Russell, Cold Spring Harbor Press, Cold Spring Harbor, N.Y., 3rdedition, 2001. 10 The vector can also comprise a selectable marker gene for the selection of transformed cells. Selectable marker genes are utilized for the selection of transformed cells or tissues. Marker genes include genes encoding antibiotic resistance, such as those encoding neomycin phosphotransferase II (NEO) and hygromycin phosphotransferase (HPT), as well as genes conferring resistance to herbicidal compounds, such as glufosinate ammonium, bromoxynil, imidazolinones, and 2,4- 15 dichlorophenoxyacetate (2,4-D). Marker genes can include genes that allow selection for growth on a particular nutrient or substance, such as dihydrofolate reductase (DHFR; Simonsen and Levinson (1983) Proc. Natl. Acad. Sci. U.S.A.80:2495-2499), histidinol dehydrogenase (hisD; Hartman and Mulligan (1988) Proc. Natl. Acad. Sci. U.S.A.85:8047-8051), puromycin-N-acetyl transferase (PAC or puro; de la Luna et al. (1988) Gene 62:121- 126), thymidine kinase (TK; Littlefield (1964) Science 20 145:709-710), and xanthine-guanine phosphoribosyltransferase (XGPRT or gpt; Mulligan and Berg (1981) Proc. Natl. Acad. Sci. U.S.A.78:2072- 2076). The expression cassette or vector comprising the polynucleotide encoding a RT, DNA- binding polypeptide (e.g., RGN polypeptide), PE-enhancing polypeptide, fusion protein, and / or PE can further comprise a polynucleotide encoding a gRNA. The polynucleotide sequence encoding the 25 gRNA can be operably linked to at least one transcriptional control sequence for expression of the gRNA in the organism or host cell of interest. For example, the polynucleotide encoding the gRNA can be operably linked to a promoter sequence that is recognized by RNA polymerase III (Pol III). Examples of suitable Pol III promoters include, but are not limited to, mammalian U6, U3, H1, and 7SL RNA promoters and rice U6 and U3 promoters, such as the promoter set forth as SEQ ID NO: 30 480 and those disclosed in International Appl. Publ. No. WO 2022 / 261394, which is herein incorporated by reference in its entirety. Without being bound by any particular theory or mechanism of action, it is believed that the presently disclosed PE-enhancing polypeptides bind to the polyU on the 3' end of RNA polymerase III transcripts, shielding them from exonucleolytic degradation. As indicated, expression constructs comprising nucleotide sequences encoding the RTs, 35 DNA-binding polypeptides (e.g., RGN polypeptides), PE-enhancing polypeptides, fusion proteins, PEs, and / or gRNAs can be used to transform organisms of interest. Methods for transformation involve introducing a nucleotide construct into an organism of interest. By "introducing" is intended 59 Atty Dkt No: L1034381430WO (00376)

[0060] to introduce the nucleotide construct to the host cell in such a manner that the construct gains access to the interior of the host cell. The methods of the invention do not require a particular method for introducing a nucleotide construct to a host organism, only that the nucleotide construct gains access to the interior of at least one cell of the host organism. The host cell can be a eukaryotic or prokaryotic 5 cell. In some embodiments, the eukaryotic host cell is a plant cell, a mammalian cell, an avian cell, or an insect cell. In some embodiments, the eukaryotic cell that comprises or expresses a presently disclosed RT, DNA-binding polypeptide (e.g., RGN polypeptide), PE-enhancing polypeptide, fusion protein, PE, and / or gRNA is a human cell. In some embodiments, the eukaryotic cell that comprises or expresses a presently disclosed RT, DNA-binding polypeptide (e.g., RGN polypeptide), PE- 10 enhancing polypeptide, fusion protein, PE, and / or gRNA is a primary cell. The term "primary cell" refers to a cell isolated directly from a multicellular organism. Primary cells typically have undergone very few population doublings and are therefore more representative of the main functional component of the tissue from which they are derived in comparison to continuous (tumor or artificially immortalized) cell lines. In some cases, primary cells are cells that have been isolated and 15 then used immediately. In other cases, primary cells cannot divide indefinitely and thus cannot be cultured for long periods of time in vitro. In some embodiments, a primary cell is a primary T cell. In some embodiments, the eukaryotic cell that comprises or expresses a presently disclosed RT, DNA- binding polypeptide (e.g., RGN polypeptide), PE-enhancing polypeptide, fusion protein, PE, and / or gRNA is a cell of hematopoietic origin, such as an immune cell (i.e., a cell of the innate or adaptive 20 immune system) including but not limited to a B cell, a T cell, a natural killer (NK) cell, a chimeric antigen receptor T (CAR-T) cell, a monocyte, a macrophage, and a dendritic cell. In some embodiments, the eukaryotic cell is a pluripotent stem cell or an induced pluripotent stem cell. In some embodiments, the eukaryotic cell that comprises or expresses a presently disclosed RT, DNA- binding polypeptide (e.g., RGN polypeptide), PE-enhancing polypeptide, fusion protein, PE, and / or 25 gRNA is an ocular cell, muscle cell (e.g., skeletal muscle cell), epithelial cell (e.g., lung epithelial cell), or a diseased cell (e.g., tumor cell). Methods for introducing nucleotide constructs into plants and other host cells are known in the art including, but not limited to, stable transformation methods, transient transformation methods, and virus-mediated methods. 30 The methods result in a transformed organism, such as a plant, including whole plants, as well as plant organs (e.g., leaves, stems, roots, etc.), seeds, plant cells, propagules, embryos and progeny of the same. Plant cells can be differentiated or undifferentiated (e.g., callus, suspension culture cells, protoplasts, leaf cells, root cells, phloem cells, pollen). In some embodiments, the presently disclosed methods can result in a transformed organism or cell line derived from these transformed cells. 35 "Transgenic organisms" or "transformed organisms" or "stably transformed" organisms or cells or tissues refers to organisms that have incorporated or integrated a polynucleotide encoding a RT, DNA-binding polypeptide (e.g., RGN polypeptide), PE-enhancing polypeptide, fusion protein, 60 Atty Dkt No: L1034381430WO (00376)

[0061] PE, and / or gRNA of the disclosure. It is recognized that other exogenous or endogenous nucleic acid sequences or DNA fragments may also be incorporated into the host cell. Agrobacterium-and biolistic-mediated transformation remain the two predominantly employed approaches for transformation of plant cells. However, transformation of a host cell may be performed by infection, 5 transfection, microinjection, electroporation, microprojection, biolistics or particle bombardment, electroporation, silica / carbon fibers, ultrasound mediated, PEG mediated, calcium phosphate co- precipitation, polycation DMSO technique, DEAE dextran procedure, and viral mediated, liposome mediated and the like. Viral-mediated introduction of a polynucleotide encoding an RT, DNA-binding polypeptide (e.g., RGN polypeptide), PE-enhancing polypeptide, fusion protein, PE, and / or gRNA 10 includes retroviral, lentiviral, adenoviral, and adeno-associated viral mediated introduction and expression, as well as the use of Caulimoviruses (e.g., cauliflower mosaic virus), Geminiviruses (e.g., bean golden yellow mosaic virus or maize streak virus), and RNA plant viruses (e.g., tobacco mosaic virus). Transformation protocols as well as protocols for introducing polypeptides or polynucleotide 15 sequences into plants may vary depending on the type of host cell (e.g., monocot or dicot plant cell) targeted for transformation. Methods for transformation are known in the art and include those set forth in US Patent Nos: 8,575,425; 7,692,068; 8,802,934; 7,541,517; each of which is herein incorporated by reference. See, also, Rakoczy-Trojanowska, M. (2002) Cell Mol Biol Lett.7:849- 858; Jones et al. (2005) Plant Methods 1:5; Rivera et al. (2012) Physics of Life Reviews 9:308-345; 20 Bartlett et al. (2008) Plant Methods 4:1-12; Bates, G.W. (1999) Methods in Molecular Biology 111:359-366; Binns and Thomashow (1988) Annual Reviews in Microbiology 42:575-606; Christou, P. (1992) The Plant Journal 2:275-281; Christou, P. (1995) Euphytica 85:13-27; Tzfira et al. (2004) TRENDS in Genetics 20:375-383; Yao et al. (2006) Journal of Experimental Botany 57:3737-3746; Zupan and Zambryski (1995) Plant Physiology 107:1041-1047; Jones et al. (2005) Plant Methods 1:5. 25 Transformation may result in stable or transient incorporation of the nucleic acid into the cell. "Stable transformation" is intended to mean that the nucleotide construct introduced into a host cell integrates into the genome of the host cell and is capable of being inherited by the progeny thereof. "Transient transformation" is intended to mean that a polynucleotide is introduced into the host cell and does not integrate into the genome of the host cell. 30 Methods for transformation of chloroplasts are known in the art. See, for example, Svab et al. (1990) Proc. Nail. Acad. Sci. USA 87:8526-8530; Svab and Maliga (1993) Proc. Natl. Acad. Sci. USA 90:913-917; Svab and Maliga (1993) EMBO J.12:601-606. The method relies on particle gun delivery of DNA containing a selectable marker and targeting of the DNA to the plastid genome through homologous recombination. Additionally, plastid transformation can be accomplished by 35 transactivation of a silent plastid-borne transgene by tissue-preferred expression of a nuclear-encoded and plastid-directed RNA polymerase. Such a system has been reported in McBride et al. (1994) Proc. Natl. Acad. Sci. USA 91:7301-7305. 61 Atty Dkt No: L1034381430WO (00376)

[0062] The cells that have been transformed may be grown into a transgenic organism, such as a plant, in accordance with conventional ways. See, for example, McCormick et al. (1986) Plant Cell Reports 5:81-84. These plants may then be grown, and either pollinated with the same transformed strain or different strains, and the resulting hybrid having constitutive expression of the desired 5 phenotypic characteristic identified. Two or more generations may be grown to ensure that the polynucleotide encoding a RT, DNA-binding polypeptide (e.g., RGN polypeptide), PE-enhancing polypeptide, fusion protein, PE, and / or gRNA is stably maintained and inherited and then seeds harvested to ensure the presence of the polynucleotide encoding a RT, DNA-binding polypeptide (e.g., RGN polypeptide), PE-enhancing polypeptide, fusion protein, PE, and / or gRNA. In this manner, 10 the present disclosure provides a transformed plant or plant part having a nucleotide construct of the disclosure, for example, an expression cassette of the disclosure, stably incorporated into their genome. Seed having an expression cassette of the disclosure stably incorporated into their genome can be referred to as "transgenic seed". Alternatively, cells that have been transformed may be introduced into an organism. These 15 cells could have originated from the organism, wherein the cells are transformed in an ex vivo approach. These cells can be autologous (originated and returned to the same subject), allogeneic (the donor and recipient subjects are of the same species). The sequences provided herein may be used for transformation of any plant species, including, but not limited to, monocots and dicots. Examples of plants of interest include, but are not 20 limited to, corn (maize), sorghum, wheat, sunflower, tomato, crucifers, peppers, potato, cotton, rice, soybean, sugarbeet, sugarcane, tobacco, barley, and oilseed rape, Brassica sp., alfalfa, rye, millet, safflower, peanuts, sweet potato, cassava, coffee, coconut, pineapple, citrus trees, cocoa, tea, banana, avocado, fig, guava, mango, olive, papaya, cashew, macadamia, almond, oats, vegetables, ornamentals, and conifers. 25 Vegetables include, but are not limited to, tomatoes, lettuce, green beans, lima beans, peas, and members of the genus Curcumis such as cucumber, cantaloupe, and musk melon. Ornamentals include, but are not limited to, azalea, hydrangea, hibiscus, roses, tulips, daffodils, petunias, carnation, poinsettia, and chrysanthemum. In specific embodiments, plants of the present invention are crop plants (for example, maize, sorghum, wheat, sunflower, tomato, crucifers, peppers, potato, cotton, 30 rice, soybean, sugarbeet, sugarcane, tobacco, barley, oilseed rape, etc.). As used herein, the term plant includes plant cells, plant protoplasts, plant cell tissue cultures from which plants can be regenerated, plant calli, plant clumps, and plant cells that are intact in plants or parts of plants such as embryos, pollen, ovules, seeds, leaves, flowers, branches, fruit, kernels, ears, cobs, husks, stalks, roots, root tips, anthers, and the like. Grain is intended to mean the mature seed 35 produced by commercial growers for purposes other than growing or reproducing the species. Progeny, variants, and mutants of the regenerated plants are also included within the scope of the invention, provided that these parts comprise the introduced polynucleotides. Further provided is a 62 Atty Dkt No: L1034381430WO (00376)

[0063] processed plant product or byproduct that retains the sequences disclosed herein, including for example, soymeal. The polynucleotides encoding the RTs, DNA-binding polypeptides (e.g., RGN polypeptides), PE-enhancing polypeptides, fusion proteins, PEs, and / or gRNAs or comprising the gRNAs can be 5 used to transform any eukaryotic species, including but not limited to animals (e.g., mammals, humans, insects, fish, birds, and reptiles), plants, fungi, amoeba, algae, and yeast. In some embodiments, the polynucleotides encoding the RTs, DNA-binding polypeptides (e.g., RGN polypeptides), PE-enhancing polypeptides, fusion proteins, PEs, and / or gRNAs or comprising the gRNAs can be used to transform any prokaryotic species, including but not limited to, archaea and 10 bacteria (e.g., Bacillus sp., Klebsiella sp. Streptomyces sp., Rhizobium sp., Escherichia sp., Pseudomonas sp., Salmonella sp., Shigella sp., Vibrio sp., Yersinia sp., Mycoplasma sp., Agrobacterium, Lactobacillus sp.). Conventional viral and non-viral based gene transfer methods can be used to introduce nucleic acids in mammalian, insect, or avian cells or target tissues. Such methods can be used to 15 administer nucleic acids encoding components of a PE system to cells in culture, or in a host organism. Non-viral vector delivery systems include DNA plasmids, RNA (e.g., a transcript of a vector described herein), naked nucleic acid, and nucleic acid complexed with a delivery vehicle, such as a liposome. Viral vector delivery systems include DNA and RNA viruses, which have either episomal or integrated genomes after delivery to the cell. Non-limiting examples include vectors 20 utilizing Caulimoviruses (e.g., cauliflower mosaic virus), Geminiviruses (e.g., bean golden yellow mosaic virus or maize steak virus), and RNA plant viruses (e.g., tobacco mosaic virus). For a review of gene therapy procedures, see Anderson, Science 256: 808- 813 (1992); Nabel & Feigner, TIBTECH 11:211-217 (1993); Mitani & Caskey, TIBTECH 11:162-166 (1993); Dillon, TIBTECH 11:167-175 (1993); Miller, Nature 357:455-460 (1992); Van Brunt, Biotechnology 6(10): 1149-1154 25 (1988); Vigne, Restorative Neurology and Neuroscience 8:35-36 (1995); Kremer & Perricaudet, British Medical Bulletin 51(1):31-44 (1995); Haddada et al., in Current Topics in Microbiology and Immunology, Doerfler and Bohm (eds) (1995); and Yu et al., Gene Therapy 1:13-26 (1994). Methods of non-viral delivery of nucleic acids include lipofection, nucleofection, microinjection, biolistics, virosomes, liposomes, immunoliposomes, polycation or lipid: nucleic acid 30 conjugates, naked DNA, artificial virions, and agent-enhanced uptake of DNA. Lipofection is described in e.g., U.S. Pat. Nos. 5,049,386, 4,946,787; and 4,897,355) and lipofection reagents are sold commercially (e.g., Transfectam ™ and Lipofectin™). Cationic and neutral lipids that are suitable for efficient receptor-recognition lipofection of polynucleotides include those of Feigner, WO 91 / 17424; WO 91 / 16024. Delivery can be to cells (e.g. in vitro or ex vivo administration) or target 35 tissues (e.g. in vivo administration). The preparation of lipid:nucleic acid complexes, including targeted liposomes such as immunolipid complexes, is well known to one of skill in the art (see, e.g., Crystal, Science 270:404-410 (1995); Blaese et al., Cancer Gene Ther. 2:291- 297 (1995); Behr et al., 63 Atty Dkt No: L1034381430WO (00376)

[0064] Bioconjugate Chem. 5:382-389 (1994); Remy et al., Bioconjugate Chem. 5:647-654 (1994); Gao et al., Gene Therapy 2:710-722 (1995); Ahmad et al., Cancer Res. 52:4817-4820 (1992); U.S. Pat. Nos. 4,186,183, 4,217,344, 4,235,871, 4,261,975, 4,485,054, 4,501,728, 4,774,085, 4,837,028, and 4,946,787). 5 The use of RNA or DNA viral based systems for the delivery of nucleic acids takes advantage of highly evolved processes for targeting a virus to specific cells in the body and trafficking the viral payload to the nucleus. Viral vectors can be administered directly to patients (in vivo) or they can be used to treat cells in vitro, and the edited cells may optionally be administered to patients (ex vivo). Conventional viral based systems could include retroviral, lentivirus, adenoviral, adeno-associated 10 and herpes simplex virus vectors for gene transfer. Integration in the host genome is possible with the retrovirus, lentivirus, and adeno-associated virus gene transfer methods, often resulting in long term expression of the inserted transgene. Additionally, high transduction efficiencies have been observed in many different cell types and target tissues. The tropism of a retrovirus can be altered by incorporating foreign envelope proteins, 15 expanding the potential target population of target cells. Lentiviral vectors are retroviral vectors that are able to transduce or infect non-dividing cells and typically produce high viral titers. Selection of a retroviral gene transfer system would therefore depend on the target tissue. Retroviral vectors are comprised of cis-acting long terminal repeats with packaging capacity for up to 6-10 kb of foreign sequence. The minimum cis-acting LTRs are sufficient for replication and packaging of the vectors, 20 which are then used to integrate the therapeutic gene into the target cell to provide permanent transgene expression. Widely used retroviral vectors include those based upon murine leukemia virus (MuLV), gibbon ape leukemia virus (GaLV), Simian Immuno deficiency virus (SIV), human immune deficiency virus (HIV), and combinations thereof (see, e.g., Buchscher et al., J. Viral. 66:2731-2739 (1992); Johann et al., J. Viral. 66:1635-1640 (1992); Sommnerfelt et al., J. Viral. 176:58-59 (1990); 25 Wilson et al., J. Viral. 63:2374-2378 (1989); Miller et al., J. Viral. 65:2220-2224 (1991); PCT / US94 / 05700). In applications where transient expression is preferred, adenoviral based systems may be used. Adenoviral based vectors are capable of very high transduction efficiency in many cell types and do not require cell division. With such vectors, high titer and levels of expression have been30 obtained. This vector can be produced in large quantities in a relatively simple system. Adeno- associated virus (“AAV”) vectors may also be used to transduce cells with target nucleic acids, e.g., in the in vitro production of nucleic acids and peptides, and for in vivo and ex vivo gene therapy procedures (see, e.g., West et al., Virology 160:38-47 (1987); U.S. Pat. No. 4,797,368; WO 93 / 24641; Katin, Human Gene Therapy 5:793-801 (1994); Muzyczka, J. Clin. Invest. 94:1351 35 (1994). The term “adeno-associated virus” or “AAV” as used herein refers to a member of the class of viruses associated with this name and belonging to the genus dependoparvovirus, family Parvoviridae. 64 Atty Dkt No: L1034381430WO (00376)

[0065] Multiple serotypes of this virus are known to be suitable for gene delivery; all known serotypes can infect cells from various tissue types. At least 11, sequentially numbered, have been described. Non- limiting exemplary serotypes useful in the compositions and methods disclosed herein include any of the 11 serotypes (e.g., AAV2, AAV5, AAV6, AAV8), or variant serotypes, e.g., AAV-DJ. AAV is 5 advantageous over other viral vectors for in vivo delivery of genes (e.g., encoding gene editing components) due to their low toxicity and low probability of causing insertional mutagenesis because it typically does not integrate into the host genome. AAV has a packaging limit of about 4.5 to 4.75 Kb. Construction of recombinant AAV vectors is described in a number of publications, including 10 U.S. Pat. No. 5,173,414; Tratschin et al., Mol. Cell. Biol. 5:3251-3260 (1985); Tratschin, et al., Mol. Cell. Biol. 4:2072-2081 (1984); Hermonat & Muzyczka, PNAS 81:6466-6470 (1984); and Samulski et al., 1. Viral. 63:03822-3828 (1989). Packaging cells are typically used to form virus particles that are capable of infecting a host cell. Such cells include 293 cells, which package adenovirus, and ψJ2 cells or PA317 cells, which package retrovirus. 15 Viral vectors used in gene therapy are usually generated by producing a cell line that packages a nucleic acid vector into a viral particle. The vectors typically contain the minimal viral sequences required for packaging and subsequent integration into a host, other viral sequences being replaced by an expression cassette for the polynucleotide(s) to be expressed. The missing viral functions are typically supplied in trans by the packaging cell line. For example, AAV vectors used in 20 gene therapy typically only possess ITR sequences from the AAV genome which are required for packaging and integration into the host genome. Viral DNA is packaged in a cell line, which contains a helper plasmid encoding the other AAV genes, namely rep and cap, but lacking ITR sequences. The cell line may also be infected with adenovirus as a helper. The helper virus promotes replication of the AAV vector and expression of AAV genes from the helper plasmid. The helper plasmid is not 25 packaged in significant amounts due to a lack of ITR sequences. Contamination with adenovirus can be reduced by, e.g., heat treatment to which adenovirus is more sensitive than AAV. Additional methods for the delivery of nucleic acids to cells are known to those skilled in the art. See, for example, US20030087817, incorporated herein by reference. In some embodiments, a host cell is transiently or non-transiently transfected with one or 30 more vectors described herein. In some embodiments, a cell is transfected as it naturally occurs in a subject. In some embodiments, a cell that is transfected is taken from a subject. In some embodiments, a cell that is transfected is a eukaryotic cell. In some embodiments, the eukaryotic cell is an animal cell (e.g., mammals, humans, insects, fish, birds, and reptiles). In some embodiments, a cell that is transfected is a human cell. In some embodiments, a cell that is transfected 35 is a cell of hematopoietic origin, such as an immune cell (i.e., a cell of the innate or adaptive immune system) including but not limited to a B cell, a T cell, a natural killer (NK) cell, a pluripotent stem cell, an induced pluripotent stem cell, a chimeric antigen receptor T (CAR-T) cell, a monocyte, a 65 Atty Dkt No: L1034381430WO (00376)

[0066] macrophage, and a dendritic cell. In some embodiments, the cell is derived from cells taken from a subject, such as a cell line. In some embodiments, the cell or cell line is prokaryotic. In some embodiments, the cell or cell line is eukaryotic. In further embodiments, the cell or cell line is derived from insect, avian, plant, or fungal 5 species. In some embodiments, the cell or cell line may be mammalian, such as for example human, monkey, mouse, cow, swine, goat, hamster, rat, cat, or dog. A wide variety of cell lines for tissue culture are known in the art. Examples of cell lines include, but are not limited to, C8161, CCRF- CEM, MOLT, mIMCD-3, NHDF, HeLaS3, Huhl, Huh4, Huh7, HUVEC, HASMC, HEKn, HEKa, MiaPaCell, Panel, PC-3, TFl, CTLL-2, CIR, Rat6, CVI, RPTE, AlO, T24, 182, A375, ARH-77, Calul, 10 SW480, SW620, SKOV3, SK-UT, CaCo2, P388Dl, SEM-K2, WEHI- 231, HB56, TIB55, lurkat, 145.01, LRMB, Bcl-1, BC-3, IC21, DLD2, Raw264.7, NRK, NRK-52E, MRC5, MEF, Hep G2, HeLa B, HeLa T4. COS, COS-1, COS-6, COS-M6A, BS-C-1 monkey kidney epithelial, BALB / 3T3 mouse embryo fibroblast, 3T3 Swiss, 3T3-Ll, 132-d5 human fetal fibroblasts; 10.1 mouse fibroblasts, 293-T, 3T3, 721, 9L, A2780, A2780ADR, A2780cis, A172, A20, A253, A431, A-549, ALC, B16, B35,15 BCP-I cells, BEAS-2B, bEnd.3, BHK-21, BR 293, BxPC3, C3H-10Tl / 2, C6 / 36, Cal-27, CHO, CHO- 7, CHO-IR, CHO-Kl, CHO-K2, CHO-T, CHO Dhfr- / -, COR-L23, COR-L23 / CPR, COR-L235010, CORL23 / R23, COS-7, COV-434, CML Tl, CMT, CT26, D17, DH82, DU145, DuCaP, EL4, EM2, EM3, EMT6 / AR1, EMT6 / AR10.0, FM3, H1299, H69, HB54, HB55, HCA2, HEK-293, HeLa, Hepalclc7, HL-60, HMEC, HT-29, lurkat, lY cells, K562 cells, Ku812, KCL22, KGl, KYOl, LNCap, 20 Ma-Mel 1-48, MC-38, MCF-7, MCF-l0A, MDA-MB-231, MDA-MB-468, MDA-MB-435, MDCKII, MDCKII, MOR / 0.2R, MONO-MAC 6, MTD-lA, MyEnd, NCI-H69 / CPR, NCI-H69 / LX10, NCI- H69 / LX20, NCI-H69 / LX4, NIH-3T3, NALM-1, NW-145, OPCN / OPCT cell lines, Peer, PNT-lA / PNT 2, RenCa, RIN-5F, RMA / RMAS, Saos-2 cells, Sf-9, SkBr3, T2, T-47D, T84, THPl cell line, U373, U87, U937, VCaP, Vero cells, WM39, WT-49, X63, YAC-1, YAR, and transgenic varieties 25 thereof. Cell lines are available from a variety of sources known to those with skill in the art (see, e.g., the American Type Culture Collection (ATCC) (Manassas, Va.)). In some embodiments, a cell transfected with one or more polynucleotides or vectors described herein is used to establish a new cell line comprising one or more vector-derived sequences. In some embodiments, a cell transiently transfected with the components of a PE system as described 30 herein (such as by transient transfection of one or more vectors, or transfection with RNA), and edited through the activity of a PE system, is used to establish a new cell line comprising cells containing the edit but lacking any other exogenous sequence. In some embodiments, cells transiently or non- transiently transfected with one or more vectors described herein, or cell lines derived from such cells are used in assessing one or more test compounds. 35 In some embodiments, one or more vectors described herein are used to produce a non-human transgenic animal or transgenic plant. In some embodiments, the transgenic animal is an insect. In further embodiments, the insect is an insect pest, such as a mosquito or tick. In some embodiments, 66 Atty Dkt No: L1034381430WO (00376)

[0067] the insect is a plant pest, such as a corn rootworm or a fall armyworm. In some embodiments, the transgenic animal is a bird, such as a chicken, turkey, goose, or duck. In some embodiments, the transgenic animal is a mammal, such as a human, mouse, rat, hamster, monkey, ape, rabbit, swine, cow, horse, goat, sheep, cat, or dog. 5 VIII. Variants and Fragments of Polypeptides and Polynucleotides The present disclosure provides active variants and fragments of a RT, DNA-binding polypeptide (e.g., RGN polypeptide), PE-enhancing polypeptide, or PE comprising the same. In some embodiments, the disclosure provides: active variants and fragments of an RT having the amino acid10 sequence set forth as any one of SEQ ID NOs: 1-41, 45-228, 233-334, 492-511, 807, 823-871, 881- 898, and 917-934; active variants and fragments of a DNA-binding polypeptide (e.g., RGN polypeptide) having the amino acid sequence set forth as any one of SEQ ID NOs: 387-420, and 484- 489, or having the amino acid sequence of any one of the RGN polypeptides of Table 1; active variants and fragments of a PE-enhancing polypeptide having the amino acid sequence set forth as 15 any one of SEQ ID NOs: 335-344, 359-365, 371, 482, and 483; active variants and fragments of CRISPR repeats, including the nucleotide sequence set forth as any one of SEQ ID NOs: 444, 445, 446, 455, 456, 457, 468, 471, or 472; active variants and fragments of tracrRNAs, including the sequence set forth as any one of SEQ ID NOs: 447, 448, 449, 450, 458, 459, 460, 461, 462, 469, 473, or 474; and polynucleotides encoding the same. 20 While the activity of a variant or fragment may be altered compared to the polynucleotide or polypeptide of interest, the active variant and fragment should retain the functionality of the polynucleotide or polypeptide of interest. For example, an active variant or fragment may have increased activity, decreased activity, different spectrum of activity or any other alteration in activity when compared to the polynucleotide or polypeptide of interest. 25 Active variants and fragments of RTs disclosed herein having the amino acid sequence of any one of SEQ ID NOs: 1-41, 45-228, 233-334, 492-511, 807, 823-871, 881-898, and 917-934 will retain the ability, when part of a PE, to catalyze the addition of nucleotides to a nicked polynucleotide strand, using a template. Active variants and fragments of DNA-binding polypeptides (e.g., RGN polypeptides) (or 30 PEs comprising the same) disclosed herein having the amino acid sequence of any one of SEQ ID NOs: 387-420, and 484-489, or having the amino acid sequence of any one of the RGN polypeptides of Table 1, will retain sequence-specific, RNA-guided DNA-binding activity. In some embodiments, active variants and fragments of RGN polypeptides disclosed herein, will retain nuclease (e.g., nickase) activity. 35 Active variants and fragments of PE-enhancing polypeptides (or PEs comprising the same) disclosed herein having the amino acid sequence of any one of SEQ ID NOs: 335-344, 359-368, 370- 67 Atty Dkt No: L1034381430WO (00376)

[0068] 372, 482, and 483 will retain the ability to enhance polymerase editors or polymerase editing, and in some embodiments, will retain the ability to bind to ssRNA or ssDNA. Active variants and fragments of CRISPR RNA (crRNA) repeats or tracrRNAs disclosed herein, will retain the ability, when part of a guide RNA, to bind to and guide an RGN (or a PE 5 comprising the same) to a target sequence (e.g., target DNA sequence) in a sequence-specific manner. Active variants and fragments of PEs disclosed herein, will retain the ability to, when associated with a PEgRNA, edit a double-stranded polynucleotide through the replacement of a target sequence using the template sequence of the PEgRNA. The term “fragment” refers to a portion of a polynucleotide or polypeptide sequence of the 10 disclosure. "Fragments", “active fragments”, or "biologically active portions" include polynucleotides comprising a sufficient number of contiguous nucleotides to retain the biological activity. "Fragments", “active fragments”, or "biologically active portions" include polypeptides comprising a sufficient number of contiguous amino acid residues to retain the biological activity. Such biologically active portions can be prepared by recombinant techniques and evaluated for activity. 15 A biologically active portion of an RT can be a polypeptide that comprises, for example, 10, 25, 50, 100, 150, 200, 250, 300, 350, 400, 450, 500, 550, 600, 650, or more contiguous amino acid residues of any one of SEQ ID NOs: 1-41, 45-228, 233-334, 492-511, 807, 823-871, 881-898, and 917-934. A biologically active portion of a DNA-binding polypeptide (e.g., RGN polypeptide) can be a 20 polypeptide that comprises, for example, 10, 25, 50, 100, 150, 200, 250, 300, 350, 400, 450, 500, 550, 600, 650, 700, 750, 800, 850, 900, 1000, or more contiguous amino acid residues of an RGN polypeptide of Table 1 or any one of SEQ ID NOs: 387-420, and 484-489. Fragments of the PE-enhancing polypeptides (or PEs comprising the same) include those that are shorter than the full-length sequences due to the use of an alternate downstream start site. A 25 biologically active portion of a PE-enhancing polypeptide can be a polypeptide that comprises, for example, 10, 20, 30, 40, 50, 60, 70, 80, 90, 100, 110, 120, 130, 140, 150, 160, 170, 180, 190, 200, 210, 220, 230, 240, 250, 260, 270, 280, 290, 300, 310, 320, 330, 340, 350, 360, 370, 380, 390, 400, or more contiguous amino acid residues of any one of SEQ ID NOs: 335-344, 359-368, 370-372, 482, and 483. 30 A biologically active fragment of a crRNA repeat can comprise at least 8 contiguous nucleotides of any one of SEQ ID NOs: 444, 445, 446, 455, 456, 457, 468, 471, and 472. A biologically active portion of a CRISPR repeat sequence can be a polynucleotide that comprises, for example, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, or 21 contiguous nucleotides of any one of SEQ ID NOs: 444, 445, 446, 455, 456, 457, 468, 471, and 472. 35 A biologically active fragment of a tracrRNA sequence can comprise at least 10 contiguous nucleotides of any one of SEQ ID NOs: 447, 448, 449, 450, 458, 459, 460, 461, 462, 469, 473, or 474. A biologically active portion of a tracrRNA sequence can be a polynucleotide that comprises, for 68 Atty Dkt No: L1034381430WO (00376)

[0069] example, 10, 15, 20, 25, 30, 35, 40, 45, 50, 55, 60, 65, 70, 75, 80, 85, 90, 95, 100, 105, or more contiguous nucleotides of any one of SEQ ID NOs: 447, 448, 449, 450, 458, 459, 460, 461, 462, 469, 473, or 474. In general, "variants" or “active variant” is intended to mean substantially similar sequences 5 that retain the activity of the original molecule. For polynucleotides, a variant comprises a deletion and / or addition of one or more nucleotides at one or more internal sites within the native polynucleotide and / or a substitution of one or more nucleotides at one or more sites in the native polynucleotide. As used herein, a "native" or “wild type” polynucleotide or polypeptide comprises a naturally occurring nucleotide sequence or amino acid sequence, respectively. For polynucleotides, 10 conservative variants include those sequences that, because of the degeneracy of the genetic code, encode the native amino acid sequence of the gene of interest. Naturally occurring allelic variants such as these can be identified with the use of well-known molecular biology techniques, as, for example, with polymerase chain reaction (PCR) and hybridization techniques as outlined below. Variant polynucleotides also include synthetically derived polynucleotides, such as those generated, 15 for example, by using site-directed mutagenesis but which still encode the polypeptide or the polynucleotide of interest. Generally, variants of a particular polynucleotide disclosed herein will have at least about 40%, 45%, 50%, 55%, 60%, 65%, 70%, 75%, 80%, 85%, 90%, 91%, 92%, 93%, 94%, 95%, 96%, 97%, 98%, 99% or more sequence identity to that particular polynucleotide as determined by sequence alignment programs and parameters described elsewhere herein. 20 Variants of a particular polynucleotide disclosed herein (i.e., the reference polynucleotide) can also be evaluated by comparison of the percent sequence identity between the polypeptide encoded by a variant polynucleotide and the polypeptide encoded by the reference polynucleotide. Percent sequence identity between any two polypeptides can be calculated using sequence alignment programs and parameters described elsewhere herein. Where any given pair of polynucleotides 25 disclosed herein is evaluated by comparison of the percent sequence identity shared by the two polypeptides they encode, the percent sequence identity between the two encoded polypeptides is at least about 40%, 45%, 50%, 55%, 60%, 65%, 70%, 75%, 80%, 85%, 90%, 91%, 92%, 93%, 94%, 95%, 96%, 97%, 98%, 99% or more sequence identity. The presently disclosed polynucleotides encode a RT, DNA-binding polypeptide (e.g., RGN 30 polypeptide), PE-enhancing polypeptide, or a PE comprising the same. In some embodiments, the presently disclosed polynucleotides encode a RT (or a PE comprising the same) comprising an amino acid sequence having at least 40%, 45%, 50%, 55%, 60%, 65%, 70%, 75%, 80%, 81%, 82%, 83%, 84%, 85%, 86%, 87%, 88%, 89%, 90%, 91%, 92%, 93%, 94%, 95%, 96%, 97%, 98%, 99%, or greater sequence identity to the amino acid sequence set forth as any one of SEQ ID NOs: 1-41, 45- 35 228, 233-334, 492-511, 807, 823-871, 881-898, and 917-934. In some embodiments, the presently disclosed polynucleotides encode a DNA-binding polypeptide (e.g., RGN polypeptide) (or a PE comprising the same) comprising an amino acid sequence having at least 40%, 45%, 50%, 55%, 60%, 69 Atty Dkt No: L1034381430WO (00376)

[0070] 65%, 70%, 75%, 80%, 81%, 82%, 83%, 84%, 85%, 86%, 87%, 88%, 89%, 90%, 91%, 92%, 93%, 94%, 95%, 96%, 97%, 98%, 99%, or greater sequence identity to the amino acid sequence set forth as any one of SEQ ID NOs: 387-420 or to the amino acid sequence of any one of the RGN polypeptides of Table 1. In some embodiments, the presently disclosed polynucleotides encode a PE-enhancing 5 polypeptide (or a PE comprising the same) comprising an amino acid sequence having at least 40%, 45%, 50%, 55%, 60%, 65%, 70%, 75%, 80%, 81%, 82%, 83%, 84%, 85%, 86%, 87%, 88%, 89%, 90%, 91%, 92%, 93%, 94%, 95%, 96%, 97%, 98%, 99%, or greater sequence identity to the amino acid sequence set forth as any one of SEQ ID NOs: 335-344, 359-368, 370-372, 482, and 483. A biologically active variant of a RT, DNA-binding polypeptide (e.g., RGN polypeptide), PE- 10 enhancing polypeptide, or PE of the disclosure may differ by as few as about 1-15 amino acid residues, as few as about 1-10, such as about 6-10, as few as 5, as few as 4, as few as 3, as few as 2, or as few as 1 amino acid residue. In some embodiments, the polypeptides can comprise an N-terminal or a C-terminal truncation, which can comprise at least a deletion of 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 15, 20, 25, 30, 35, 40, 45, 50, 55, 60, 65, 70, 75, 80, 85, 90, 95, 100, 150, 200, 250, 300 amino acids or more 15 from either the N- or C-terminus of the polypeptide. In some embodiments, the presently disclosed polynucleotides comprise or encode a crRNA repeat comprising a nucleotide sequence having at least 40%, 45%, 50%, 55%, 60%, 65%, 70%, 75%, 80%, 81%, 82%, 83%, 84%, 85%, 86%, 87%, 88%, 89%, 90%, 91%, 92%, 93%, 94%, 95%, 96%, 97%, 98%, 99%, or greater sequence identity to the nucleotide sequence set forth as any one of SEQ 20 ID NOs: 444, 445, 446, 455, 456, 457, 468, 471, and 472. In some embodiments, the presently disclosed polynucleotides comprise or encode a tracrRNA comprising a nucleotide sequence having at least 40%, 45%, 50%, 55%, 60%, 65%, 70%, 75%, 80%, 81%, 82%, 83%, 84%, 85%, 86%, 87%, 88%, 89%, 90%, 91%, 92%, 93%, 94%, 95%, 96%, 97%, 98%, 99%, or greater sequence identity to the nucleotide sequence set forth as any one of 25 SEQ ID NOs: 447, 448, 449, 450, 458, 459, 460, 461, 462, 469, 473, and 474. Variants of guide RNAs disclosed herein include guide RNAs that have modified nucleotides, sugars, phosphate backbone, and / or nucleobases. Variant guide RNAs can include modifications including: 2'-O-methyl (2'-O-Me) modification; 2'-fluoro (2'-F) modification; 2'F-4'Cα-OMe modification; 2',4'-di-Cα-OMe modification; 2'-O-methyl 3'-phosphorothioate (MS) modification; 2'- 30 O-methyl 3'thiophosphonoacetate (MSP; 2'-O-methyl 3'thioPACE) modification; 2'-O-methyl 3'phosphonoacetate (MP) modification; phosphorothioate (PS) modification; bridged nucleic acid (BNA) modification (e.g., 2',4' BNA, locked nucleic acid (LNA), N-methyl substituted bridged nucleic acid BNANC[N-Me], 2'-O,4'-C-ethylene bridged nucleic acid (2',4'-ENA), and S-constrained ethyl (cEt)); or a combination thereof. Chemical modifications of spacers, crRNA 35 repeats, crRNAs, tracrRNAs, and guide RNAs are described in International Application Publication No. WO 2024 / 042489, which is hereby incorporated by reference in its entirety herein. Biologically active variants of a guide RNA of the disclosure may differ by as few as about 1- 70 Atty Dkt No: L1034381430WO (00376)

[0071] 15 nucleotides, as few as about 1-10, such as about 6-10, as few as 5, as few as 4, as few as 3, as few as 2, or as few as 1 nucleotide. In some embodiments, the polynucleotides can comprise a 5' or 3' truncation, which can comprise at least a deletion of 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15 nucleotides or more from either the 5' or 3' end of the polynucleotide. 5 It is recognized that modifications may be made to the RTs, DNA-binding polypeptides (e.g., RGN polypeptides), PE-enhancing polypeptides (or PEs comprising the same), crRNA repeats, or tracrRNAs provided herein creating variant proteins and polynucleotides. Changes designed by man may be introduced through the application of site-directed mutagenesis techniques. Alternatively, native, as yet unknown or as yet unidentified polynucleotides and / or polypeptides structurally and / or 10 functionally related to the sequences disclosed herein may also be identified that fall within the scope of the present disclosure. Conservative amino acid substitutions may be made in nonconserved regions that do not alter the function of the RTs, DNA-binding polypeptides (e.g., RGN polypeptides), PE-enhancing polypeptides, or PEs. Alternatively, modifications may be made that improve the activity of the RTs, DNA-binding polypeptides (e.g., RGN polypeptides), PE-enhancing polypeptides, 15 or PEs. Variant polynucleotides and proteins also encompass sequences and proteins derived from a mutagenic and recombinogenic procedure such as DNA shuffling. With such a procedure, one or more different RTs, DNA-binding polypeptides (e.g., RGN polypeptides), PE-enhancing polypeptides, or PEs disclosed herein is manipulated to create a new RT, DNA-binding polypeptide 20 (e.g., RGN polypeptide), PE-enhancing polypeptide, or PE possessing the desired properties. In this manner, libraries of recombinant polynucleotides are generated from a population of related sequence polynucleotides comprising sequence regions that have substantial sequence identity and can be homologously recombined in vitro or in vivo. For example, using this approach, sequence motifs encoding a domain of interest may be shuffled between the RT, DNA-binding polypeptide (e.g., RGN 25 polypeptide), PE-enhancing polypeptide, or PE sequences provided herein and other known RT, DNA-binding polypeptide (e.g., RGN polypeptide), PE-enhancing polypeptide, or PE genes to obtain a new gene coding for a protein with an improved property of interest, such as an increased Kmin the case of an enzyme. Strategies for such DNA shuffling are known in the art. See, for example, Stemmer (1994) Proc. Natl. Acad. Sci. USA 91:10747-10751; Stemmer (1994) Nature 370:389-391; 30 Crameri et al. (1997) Nature Biotech.15:436-438; Moore et al. (1997) J. Mol. Biol.272:336-347; Zhang et al. (1997) Proc. Natl. Acad. Sci. USA 94:4504-4509; Crameri et al. (1998) Nature 391:288- 291; and U.S. Patent Nos.5,605,793 and 5,837,458. A "shuffled" nucleic acid is a nucleic acid produced by a shuffling procedure such as any shuffling procedure set forth herein. Shuffled nucleic acids are produced by recombining (physically or virtually) two or more nucleic acids (or character 35 strings), for example in an artificial, and optionally recursive, fashion. Generally, one or more screening steps are used in shuffling processes to identify nucleic acids of interest; this screening step can be performed before or after any recombination step. In some (but not all) shuffling embodiments, 71 Atty Dkt No: L1034381430WO (00376)

[0072] it is desirable to perform multiple rounds of recombination prior to selection to increase the diversity of the pool to be screened. The overall process of recombination and selection are optionally repeated recursively. Depending on context, shuffling can refer to an overall process of recombination and selection, or, alternately, can simply refer to the recombinational portions of the overall process. 5 As used herein, "sequence identity" or "identity" in the context of two polynucleotides or polypeptide sequences makes reference to the residues in the two sequences that are the same when aligned for maximum correspondence over a specified comparison window. It is recognized that residue positions which are not identical often differ by conservative amino acid substitutions, where amino acid residues are substituted for other amino acid residues with similar chemical properties 10 (e.g., charge or hydrophobicity) and therefore do not change the functional properties of the molecule. Protein sequences that differ by such conservative substitutions are said to have "sequence similarity" or "similarity". Means for measuring sequence similarity are well known to those of skill in the art. Typically, this involves scoring a conservative substitution as a partial rather than a full mismatch. Thus, for example, where an identical amino acid is given a score of 1 and a non-conservative 15 substitution is given a score of zero, a conservative substitution is given a score between zero and 1. The scoring of conservative substitutions is calculated, e.g., as implemented in the program PC / GENE (Intelligenetics, Mountain View, California). As used herein, "percentage of sequence identity" means the value determined by comparing two optimally aligned sequences over a comparison window, wherein the portion of the 20 polynucleotide sequence in the comparison window may comprise additions or deletions (i.e., gaps) as compared to the reference sequence (which does not comprise additions or deletions) for optimal alignment of the two sequences. The percentage is calculated by determining the number of positions at which the identical nucleic acid base or amino acid residue occurs in both sequences to yield the number of matched positions, dividing the number of matched positions by the total number of 25 positions in the window of comparison, and multiplying the result by 100 to yield the percentage of sequence identity. Unless otherwise stated, sequence identity / similarity values provided herein refer to the value obtained using GAP Version 10 using the following parameters: % identity and % similarity for a nucleotide sequence using GAP Weight of 50 and Length Weight of 3, and the nwsgapdna.cmp 30 scoring matrix; % identity and % similarity for an amino acid sequence using GAP Weight of 8 and Length Weight of 2, and the BLOSUM62 scoring matrix; or any equivalent program thereof. By "equivalent program" is intended any sequence comparison program that, for any two sequences in question, generates an alignment having identical nucleotide or amino acid residue matches and an identical percent sequence identity when compared to the corresponding alignment generated by GAP 35 Version 10. Two sequences are "optimally aligned" when they are aligned for similarity scoring using a defined amino acid substitution matrix (e.g., BLOSUM62), gap existence penalty and gap extension 72 Atty Dkt No: L1034381430WO (00376)

[0073] penalty so as to arrive at the highest score possible for that pair of sequences. Amino acid substitution matrices and their use in quantifying the similarity between two sequences are well-known in the art and described, e.g., in Dayhoff et al. (1978) "A model of evolutionary change in proteins." In "Atlas of Protein Sequence and Structure," Vol.5, Suppl.3 (ed. M. O. Dayhoff), pp.345-352. Natl. Biomed. 5 Res. Found., Washington, D.C. and Henikoff et al. (1992) Proc. Natl. Acad. Sci. USA 89:10915- 10919. The BLOSUM62 matrix is often used as a default scoring substitution matrix in sequence alignment protocols. The gap existence penalty is imposed for the introduction of a single amino acid gap in one of the aligned sequences, and the gap extension penalty is imposed for each additional empty amino acid position inserted into an already opened gap. The alignment is defined by the amino 10 acid positions of each sequence at which the alignment begins and ends, and optionally by the insertion of a gap or multiple gaps in one or both sequences, so as to arrive at the highest possible score. While optimal alignment and scoring can be accomplished manually, the process is facilitated by the use of a computer-implemented alignment algorithm, e.g., gapped BLAST 2.0, described in Altschul et al. (1997) Nucleic Acids Res.25:3389-3402, and made available to the public at the 15 National Center for Biotechnology Information Website (World Wide Web at ncbi.nlm.nih.gov). Optimal alignments, including multiple alignments, can be prepared using, e.g., PSI-BLAST, available through World Wide Web at ncbi.nlm.nih.gov and described by Altschul et al. (1997) Nucleic Acids Res.25:3389-3402. With respect to an amino acid sequence that is optimally aligned with a reference sequence, 20 an amino acid residue "corresponds to" the position in the reference sequence with which the residue is paired in the alignment. The "position" is denoted by a number that sequentially identifies each amino acid in the reference sequence based on its position relative to the N-terminus. Owing to deletions, insertion, truncations, fusions, etc., that must be taken into account when determining an optimal alignment, in general the amino acid residue number in a test sequence as determined by 25 simply counting from the N-terminal will not necessarily be the same as the number of its corresponding position in the reference sequence. For example, in a case where there is a deletion in an aligned test sequence, there will be no amino acid that corresponds to a position in the reference sequence at the site of deletion. Where there is an insertion in an aligned reference sequence, that insertion will not correspond to any amino acid position in the reference sequence. In the case of 30 truncations or fusions there can be stretches of amino acids in either the reference or aligned sequence that do not correspond to any amino acid in the corresponding sequence. IX. Antibodies Also encompassed in the disclosure are antibodies recognizing: the RTs, fusion proteins 35 comprising the RTs, PEs comprising the RTs, or ribonucleoprotein (RNP) complexes comprising the RTs, including RTs having the amino acid sequence set forth as any one of SEQ ID NOs: 1-41, 45- 73 Atty Dkt No: L1034381430WO (00376)

[0074] 228, 233-334, 492-511, 807, 823-871, 881-898, and 917-934, or active variants or fragments thereof; DNA-binding polypeptides (e.g., RGN polypeptides), fusion proteins comprising the DNA-binding polypeptides (e.g., RGN polypeptides), PEs comprising the DNA-binding polypeptides (e.g., RGN polypeptides), or ribonucleoprotein complexes comprising the DNA-binding polypeptides (e.g., RGN 5 polypeptides), including DNA-binding polypeptides (e.g., RGN polypeptides) of Table 1 and / or having the amino acid sequence set forth as any one of SEQ ID NOs: 387-420; and PE-enhancing polypeptides, PEs comprising the PE-enhancing polypeptides, or ribonucleoprotein complexes comprising the PE-enhancing polypeptides, including PE-enhancing polypeptides having the amino acid sequence set forth as any one of SEQ ID NOs: 335-344, 359-368, 370-372, 482, and 483. 10 Methods for producing antibodies are well known in the art (see, for example, Harlow and Lane (1988) Antibodies: A Laboratory Manual, Cold Spring Harbor Laboratory, Cold Spring Harbor, N.Y.; and U.S. Pat. No.4,196,265). These antibodies can be used in kits for the detection and isolation of RTs, DNA-binding polypeptides (e.g., RGN polypeptides), PE-enhancing polypeptides, and fusion proteins, PEs and ribonucleoprotein complexes comprising the same. Thus, this disclosure provides 15 kits comprising antibodies that specifically bind to the RTs, DNA-binding polypeptides (e.g., RGN polypeptides), PE-enhancing polypeptides, and fusion proteins, PEs and ribonucleoprotein complexes comprising the same described herein, including, for example, PE-enhancing proteins (or fusion proteins, PEs, or RNPs comprising the same). 20 X. PE Systems and Ribonucleoprotein Complexes for Binding and Editing a Target Sequence and Methods of Making the Same The present disclosure provides PE systems for binding and editing a target sequence of interest, wherein the PE system comprises a RT (or a polynucleotide encoding the same), a DNA- binding polypeptide (e.g., RGN polypeptide) (or a polynucleotide encoding the same), along with one 25 or more PEgRNAs (or one or more polynucleotide sequences encoding the same). The PE system may further comprise a PE-enhancing polypeptide (or a polynucleotide encoding the same). The PE system may comprise: a) a PE wherein the PE comprises a single fusion protein (or a polynucleotide encoding the same) comprising the RT and the DNA-binding polypeptide (e.g., RGN polypeptide); b) a PE wherein the RT and the DNA-binding polypeptide (e.g., RGN polypeptide) are two separate 30 polypeptides; c) a PE wherein the PE comprises a single fusion protein (or a polynucleotide encoding the same) comprising the RT, DNA-binding polypeptide (e.g., RGN polypeptide), and PE-enhancing polypeptide; d) a PE comprising a fusion protein (or a polynucleotide encoding the same) comprising the RT and the PE-enhancing polypeptide, and the DNA-binding polypeptide (e.g., RGN polypeptide) is provided as a separate polypeptide (or a separate polynucleotide encoding the same); e) a PE 35 comprising a fusion protein (or a polynucleotide encoding the same) comprising the DNA-binding polypeptide (e.g., RGN polypeptide) and the PE-enhancing polypeptide, and the RT is provided as a separate polypeptide (or a separate polynucleotide encoding the same); f) a PE comprising a fusion 74 Atty Dkt No: L1034381430WO (00376)

[0075] protein (or a polynucleotide encoding the same) comprising the RT and the DNA-binding polypeptide (e.g., RGN polypeptide), and the PE-enhancing polypeptide provided as a separate polypeptide (or a polynucleotide encoding the same); or g) a PE wherein the RT, the DNA-binding polypeptide (e.g., RGN polypeptide), and the PE-enhancing polypeptide, are three separate polypeptides. 5 In some embodiments, a dual PE (DPE) system for dual polymerase editing is provided, wherein the system comprises a first PE system comprising a first PE (or one or more polynucleotides encoding the same; or a combination of protein(s) and encoding polynucleotide(s)) and a first PEgRNA (or a polynucleotide encoding the same) and a second PE system comprising a second PE (or one or more polynucleotides encoding the same; or a combination of protein(s) and encoding 10 polynucleotide(s)) and a second PEgRNA (or a polynucleotide encoding the same). The first and second PE can be the same or different and can be any one of the PEs described herein. The DPE system can also comprise a PE (or one or more polynucleotides encoding the same; or a combination of protein(s) and encoding polynucleotide(s)) and a first PEgRNA (or a polynucleotide encoding the same) and a second PEgRNA (or a polynucleotide encoding the same). The first and second 15 PEgRNAs can bind to opposite strands of a target DNA so that the intended repair event is installed on both strands of the target DNA. The DNA synthesis template of the first PEgRNA and the DNA synthesis template of the second PEgRNA each encode a single-stranded DNA sequence that is complementary (full or partial) to each other so that the region of the DNA between the two nicked sites is replaced. 20 For large insertions, the DPE system comprises PEgRNAs wherein the DNA synthesis templates are designed such that the replacement sequence (comprising the complementary single- stranded DNA sequences encoded by the first and second DNA synthesis templates) comprises a first recombinase site, as well as a donor DNA comprising a second recombinase site and the corresponding site-specific recombinase that recognizes the first and second recombinase site. The 25 recombination of the replacement sequence and donor DNA results in an insertion of exogenous DNA. As used herein, the term “recombinase” refers to a site-specific enzyme that catalyzes the recombination of DNA between recombinase sites that results in the excision, integration, inversion, or exchange of DNA fragments between the recombinase sites. Non-limiting examples of 30 recombinases are serine recombinases (e.g., Hin, Gin, Tn3, β-six, CinH, ParA, γδ, Bxb1, ϕC31, TP901, TG1, φBT1, R4, φRV1, φFC1, MR11, A118, U153, and gp29) and tyrosine recombinases (e.g., Cre, FLP, R, Lambda, HK101, HK022, and pSAM2). See, e.g., Brown et al., “Serine recombinases as tools for genome engineering.” Methods.2011;53(4):372-9; Hirano et al., “Site- specific recombinases as tools for heterologous gene integration.” Appl. Microbiol. Biotechnol.2011; 35 92(2):227-39; Chavez and Calos, “Therapeutic applications of the ΦC31 integrase system.” Curr. Gene Ther.2011;11(5):375-81; Turan and Bode, “Site-specific recombinases: from tag-and-target- to tag-and-exchange-based genomic modifications.” FASEB J.2011; 25(12):4088-107; Venken and 75 Atty Dkt No: L1034381430WO (00376)

[0076] Bellen, “Genome-wide manipulations of Drosophila melanogaster with transposons, Flp recombinase, and ΦC31 integrase.” Methods Mol. Biol.2012; 859:203-28; Murphy, “Phage recombinases and their applications.” Adv. Virus Res.2012; 83:367-414; Zhang et al., “Conditional gene manipulation: Cre- ating a new biological era.” J. Zhejiang Univ. Sci. B.2012; 13(7):511-24; Karpenshif and Bernstein, 5 “From yeast to mammals: recent advances in genetic control of homologous recombination.” DNA Repair (Amst).2012; 1;11(10):781-8; each of which are hereby incorporated by reference in its entirety. Serine and tyrosine recombinases derive their name from the conserved nucleophilic amino acid residue that it uses to attack the DNA and is covalently linked to the DNA during strand exchange. 10 As used herein, the term “recombinase site” refers to a target nucleotide sequence recognized by a recombinase that undergoes strand exchange with another nucleotide sequence having a similar recombinase site. Non-limiting examples of recombinase sites are the attB / attP sites recognized by the HK022 and ϕC31 recombinases. The presently disclosed PE systems can include a ribonucleoprotein (RNP) complex, which is 15 at least one molecule of an RNA bound to at least one protein. The RNP complexes provided herein comprise at least one guide RNA as the RNA component and a PE as the protein component. The guide RNA of an RNP complex of the disclosure can comprise a spacer that hybridizes to a eukaryotic target sequence. In some embodiments, the eukaryotic target sequence comprises a mammalian target sequence. Such RNP complexes can be purified from a cell or organism that has been transformed 20 with one or more polynucleotides that encode a PE, and a PE guide RNA (or a polynucleotide that comprises a PE guide RNA) and cultured under conditions to allow for the expression of the PE and PE guide RNA. Methods are provided for making a RT, a DNA-binding polypeptide (e.g., RGN polypeptide), a PE-enhancing polypeptide, a fusion protein comprising one or more of these polypeptides, a PE 25 comprising one or more of these polypeptides, or an RNP complex comprising one or more of these polypeptides. Such methods comprise culturing a cell comprising a polynucleotide sequence encoding a RT, a DNA-binding polypeptide (e.g., RGN polypeptide), a PE-enhancing polypeptide, a fusion protein, or a PE, and in some embodiments a polynucleotide sequence encoding or comprising a guide RNA, under conditions in which the RT, DNA-binding polypeptide (e.g., RGN polypeptide), PE- 30 enhancing polypeptide, fusion protein, or PE (and in some embodiments, the guide RNA) is expressed. The RT, DNA-binding polypeptide (e.g., RGN polypeptide), PE-enhancing polypeptide, fusion protein, PE, or RNP complex can then be purified from a lysate of the cultured cells. In some embodiments, the polynucleotide sequence encoding an RT, a DNA-binding polypeptide (e.g., RGN polypeptide), a PE-enhancing polypeptide, a fusion protein, or a PE is a mRNA (messenger RNA). In 35 some embodiments, methods for assembling an RNP complex comprise combining one or more of the presently disclosed guide RNAs and one or more of the presently disclosed RTs, DNA-binding 76 Atty Dkt No: L1034381430WO (00376)

[0077] polypeptides (e.g., RGN polypeptides), PE-enhancing polypeptides, fusion proteins, or PEs under conditions suitable for formation of the RNP complex. Methods for purifying a RT, DNA-binding polypeptide (e.g., RGN polypeptide), PE- enhancing polypeptide, fusion protein, PE, or RNP complex from a lysate of a biological sample are 5 known in the art (e.g., size exclusion and / or affinity chromatography, 2D-PAGE, HPLC, reversed- phase chromatography, immunoprecipitation). In particular methods, the RT, DNA-binding polypeptide (e.g., RGN polypeptide), PE-enhancing polypeptide, fusion protein, PE, or RNP complex is recombinantly produced and comprises a purification tag to aid in its purification, including but not limited to, glutathione-S-transferase (GST), chitin binding protein (CBP), maltose binding protein, 10 thioredoxin (TRX), poly(NANP), tandem affinity purification (TAP) tag, myc, AcV5, AU1, AU5, E, ECS, E2, FLAG (e.g., 3X FLAG tag), HA, nus, Softag 1, Softag 3, Strep, SBP, Glu-Glu, HSV, KT3, S, S1, T7, V5, VSV-G, 6xHis, 10xHis, biotin carboxyl carrier protein (BCCP), and calmodulin. Generally, the tagged RT, DNA-binding polypeptide (e.g., RGN polypeptide), PE-enhancing polypeptide, fusion protein, PE, or RNP complex is purified using immobilized metal affinity 15 chromatography. It will be appreciated that other similar methods known in the art may be used, including other forms of chromatography or for example immunoprecipitation, either alone or in combination. An "isolated" or "purified" polypeptide, or biologically active portion thereof, is substantially or essentially free from components that normally accompany or interact with the polypeptide as 20 found in its naturally occurring environment. Thus, an isolated or purified polypeptide is substantially free of other cellular material, or culture medium when produced by recombinant techniques, or substantially free of chemical precursors or other chemicals when chemically synthesized. A protein that is substantially free of cellular material includes preparations of protein having less than about 30%, 20%, 10%, 5%, or 1% (by dry weight) of contaminating protein. When the protein of the 25 invention or biologically active portion thereof is recombinantly produced, optimally culture medium represents less than about 30%, 20%, 10%, 5%, or 1% (by dry weight) of chemical precursors or non- protein-of-interest chemicals. Similarly, an “isolated” polynucleotide or nucleic acid molecule is removed from its naturally occurring environment. An isolated polynucleotide is substantially free of chemical precursors or other chemicals when chemically synthesized or has been removed from a 30 genomic locus via the breaking of phosphodiester bonds. An isolated polynucleotide can be part of a vector, a composition of matter or can be contained within a cell so long as the cell is not the original environment of the polynucleotide. Particular methods provided herein for binding and / or cleaving a target polynucleotide comprising a target sequence of interest involve the use of an in vitro assembled RNP complex. In 35 vitro assembly of an RNP complex can be performed using any method known in the art in which a PE is contacted with a guide RNA under conditions that allow for binding of the PE to the guide RNA. As used herein, “contact”, “contacting”, or “contacted” refer to making one entity in touch with 77 Atty Dkt No: L1034381430WO (00376)

[0078] one or more other entities with or without any intermediate means. In some embodiments, “contact”, “contacting”, or “contacted” include but is not limited to placing the entities in the same container or the same solution, or transfection, transformation, viral delivery, or LNP delivery of the one entity and the one or more other entities. The PE or any of its components can be purified from a biological 5 sample, cell lysate, or culture medium, produced via in vitro translation, or chemically synthesized. The guide RNA can be purified from a biological sample, cell lysate, or culture medium, transcribed in vitro, or chemically synthesized. The PE and guide RNA can be brought into contact in solution (e.g., buffered saline solution) to allow for in vitro assembly of the RNP complex. Some aspects of this disclosure provide kits comprising one or more elements of a PE system 10 described herein, including: RTs, DNA-binding polypeptides (e.g., RGN polypeptides), PE-enhancing polypeptides, fusion proteins, guide RNAs, PEs, or polynucleotides encoding the same; cells; and complete PE systems. In some embodiments, the kit includes suitable reagents, buffers, and / or instructions for using one or more elements of a PE system, e.g., for in vitro or in vivo nucleic acid editing. Reagents may be provided in any suitable container, such as a vial, a bottle, or a tube. 15 Reagents may be used in a process utilizing one or more of the elements of a PE system. For example, restriction enzymes may be included for cloning of a polynucleotide encoding a RT, DNA-binding polypeptide (e.g., RGN polypeptide), PE-enhancing polypeptide, fusion protein, or PE into a vector. In some embodiments, the kit includes instructions regarding the design and use of suitable guide RNAs for targeted editing of a target sequence. Reagents may be provided in a form that is usable in a 20 particular assay, or in a form that requires addition of one or more other components before use (e.g. in concentrate or lyophilized form). A buffer can be any buffer, including but not limited to a sodium carbonate buffer, a sodium bicarbonate buffer, a borate buffer, a Tris buffer, a MOPS buffer, a HEPES buffer, and combinations thereof. In some embodiments, the buffer is alkaline. In some embodiments, the buffer has a pH from about 7 to about 10. 25 A kit including one or more elements of a PE system of the disclosure has utility in a wide variety of applications including editing a target sequence in a multiplicity of cell types. As such, kits including one or more elements of a PE system of the disclosure may be useful in, for example, gene therapy. In some embodiments, a kit of the disclosure includes a pharmaceutical kit including a 30 pharmaceutical composition described herein. In some embodiments, a pharmaceutical kit may include: (a) a container containing a composition of the disclosure in lyophilized form and (b) a second container containing a pharmaceutically acceptable diluent (e.g., sterile water) for injection. The pharmaceutically acceptable diluent can be used for reconstitution or dilution of the lyophilized compound of the disclosure. Optionally associated with such container(s) can be a notice in the form 35 prescribed by a governmental agency regulating the manufacture, use or sale of pharmaceuticals or biological products, which notice reflects approval by the agency of manufacture, use or sale for human administration. 78 Atty Dkt No: L1034381430WO (00376)

[0079] XI. Methods of Binding, Cleaving, or Editing a Target Polynucleotide The present disclosure provides methods for editing a target polynucleotide (e.g., target DNA) of interest comprising a target sequence. The methods include delivering a PE system comprising at 5 least one guide RNA or a polynucleotide encoding the same, and at least one PE (or one or more polynucleotides encoding the same, or a combination of protein(s) and encoding polynucleotide(s)), to the target sequence or a cell, organelle, or embryo comprising the target sequence. The methods for editing a target polynucleotide (e.g., target DNA) of interest comprising a target sequence can be performed ex vivo or in vitro. In some embodiments, the methods for editing a target polynucleotide 10 (e.g., target DNA) of interest are not methods for treatment of the human or animal body by therapy or are not processes for editing the germ line genetic identity of a human being. In particular embodiments, the RT, DNA-binding polypeptide (e.g., RGN polypeptide), PE- enhancing polypeptide, fusion protein, PE, and / or gRNA is heterologous to the cell, organelle, or embryo to which the RT, DNA-binding polypeptide (e.g., RGN polypeptide), PE-enhancing 15 polypeptide, fusion protein, PE, and / or gRNA (or polynucleotide(s) encoding at least one of the RT, DNA-binding polypeptide (e.g., RGN polypeptide), PE-enhancing polypeptide, fusion protein, PE, and gRNA) are introduced. Delivery of a polynucleotide encoding a RT, DNA-binding polypeptide (e.g., RGN polypeptide), PE-enhancing polypeptide, fusion protein, PE, and / or gRNA to a cell or embryo can be 20 delivered to a cell or embryo ex vivo, in vitro, or in vivo. The cell or embryo can be cultured under conditions in which the RT, DNA-binding polypeptide (e.g., RGN polypeptide), PE-enhancing polypeptide, fusion protein, PE, and / or gRNA are expressed. In some embodiments, the method comprises contacting a target polynucleotide or a cell comprising a target polynucleotide with an RNP complex. The contacting can be ex vivo, in vitro, or in vivo. In some embodiments, the method 25 comprises introducing into a cell, organelle, or embryo comprising a target polynucleotide a PE RNP complex. The RNP complex can be one that has been purified from a biological sample, recombinantly produced and subsequently purified, or in vitro-assembled as described herein. In those embodiments wherein the PE RNP complex that is contacted with the target polynucleotide, cell, organelle, or embryo, has been assembled in vitro, the method can further comprise the in vitro 30 assembly of the complex prior to contact with the target polynucleotide, cell, organelle, or embryo. A purified or in vitro assembled PE RNP complex can be introduced into a cell, organelle, or embryo using any method known in the art (e.g., electroporation). In some embodiments, delivery of a polynucleotide encoding a RT, DNA-binding polypeptide (e.g., RGN polypeptide), PE-enhancing polypeptide, fusion protein, PE, and / or gRNA to a cell or embryo is not a method for treatment of the 35 human or animal body by therapy or is not a process for editing the germ line genetic identity of a human being. In some embodiments, a method comprising contacting a target polynucleotide with an 79 Atty Dkt No: L1034381430WO (00376)

[0080] RNP complex is not a method for treatment of the human or animal body by therapy or is not a process for editing the germ line genetic identity of a human being. In some embodiments, the embryo is a non-human embryo. Upon delivery to or contact with the target polynucleotide or cell, organelle, or embryo 5 comprising the target polynucleotide, the guide RNA directs the PE to bind to the target sequence within the target polynucleotide in a sequence-specific manner. In those embodiments wherein the PE comprises an RGN nickase, a single strand of a double-stranded DNA target sequence is nicked and the DNA synthesis template within the extension arm of the associated PEgRNA is used as a template to introduce a desired edit into the target sequence. 10 Methods to measure binding of a PE or PE system to a target sequence are known in the art and include chromatin immunoprecipitation assays, gel mobility shift assays, DNA pull-down assays, reporter assays, microplate capture and detection assays. Likewise, methods to measure cleavage or editing of a target polynucleotide comprising a target sequence are known in the art and include in vitro or in vivo cleavage assays wherein cleavage is confirmed using PCR, sequencing, or gel 15 electrophoresis, with or without the attachment of an appropriate label (e.g., radioisotope, fluorescent substance) to the target sequence to facilitate detection of degradation products. Alternatively, the nicking triggered exponential amplification reaction (NTEXPAR) assay can be used (see, e.g., Zhang et al. (2016) Chem. Sci.7:4951-4957). In vivo cleavage can be evaluated using the Surveyor assay (Guschin et al. (2010) Methods Mol Biol 649:247-256). 20 In some embodiments, the methods involve the use of a single type of PE complexed with more than one guide RNA. The more than one guide RNA can target different regions of a single gene or can target multiple genes. In some embodiments, the methods comprise dual polymerase editing wherein a single PE (or one or more polynucleotides encoding the same, or a combination of protein(s) and encoding 25 polynucleotide(s)) and two PEgRNAs (or polynucleotides encoding the same) that associate with the PE are contacted with a target DNA molecule for the programmable replacement or excision of DNA sequences. Alternatively, a first PE (or one or more polynucleotides encoding the same, or a combination of protein(s) and encoding polynucleotide(s)) and its associated first PEgRNA (or a polynucleotide encoding the same) and a second PE (or one or more polynucleotides encoding the 30 same or a combination of protein(s) and polynucleotide(s)) and its associated second PEgRNA (or a polynucleotide encoding the same) are contacted with a target DNA molecule, wherein the first and second PEs are different from each other. In both scenarios, the two PEgRNAs can bind to opposite strands of a target DNA so that the intended repair event is installed on both strands of the target DNA. The DNA synthesis template of the first PEgRNA and the DNA synthesis template of the 35 second PEgRNA each encode a single-stranded DNA sequence that is complementary (full or partial) to each other so that the region of the DNA between the two nicked sites is replaced. 80 Atty Dkt No: L1034381430WO (00376)

[0081] For large insertions, the DPE DNA synthesis templates are designed such that the replacement sequence comprises a first recombinase site, and a donor DNA comprising a second recombinase site is introduced, as well as the corresponding site-specific recombinase that recognizes the first and second recombinase site, which results in site-specific integration of exogenous DNA into the target 5 DNA molecule. As used herein, an “edit” in reference to a polynucleotide refers to a change in the nucleotide sequence of the polynucleotide, which can be a deletion, insertion, or substitution of one or more nucleotides, or a combination thereof. Editing of the target polynucleotide comprising a target sequence can result in the expression of an altered protein product or inactivation of a coding 10 sequence. In those embodiments wherein a donor polynucleotide is present, the donor sequence in the donor polynucleotide can be integrated into or exchanged with the target nucleotide sequence, resulting in the introduction of the exogenous donor sequence. A donor polynucleotide thus comprises a donor sequence that is desired to be introduced into a target sequence of interest. In some 15 embodiments, the donor sequence alters the original target nucleotide sequence such that the newly integrated donor sequence will not be recognized and cleaved by the PE. In some embodiments, the donor polynucleotide is a single-stranded DNA. Integration of the donor sequence can be enhanced by the inclusion within the donor polynucleotide of flanking sequences, referred to herein as “homology arms” that have substantial sequence identity with the sequences flanking the target nucleotide 20 sequence, allowing for a homology-directed repair process. In some embodiments, homology arms have a length of at least 30 base pairs, at least 35 base pairs, at least 40 base pairs, at least 45 base pairs, at least 50 base pairs, at least 55 base pairs, at least 60 base pairs, at least 65 base pairs, at least 70 base pairs, at least 75 base pairs, at least 80 base pairs, at least 85 base pairs, at least 90 base pairs, at least 95 base pairs, at least 100 base pairs, and up to 2000 base pairs or more, and have at least 25 90%, at least 95%, or more, sequence homology to their corresponding sequence within the target nucleotide sequence. In some embodiments, the binding of the PE or PE system results in the editing of nucleotide(s) within or adjacent to the target sequence through the use of a DNA synthesis template of varying lengths such that the editing window using a polymerase editor can be 1, 2, 3, 4, 5, 6, 7, 8, 9, 30 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 25, 30, 35, 40, 45, 50, 55, 60, 65, 70, 75, 80, 85, 90, 95, or 100 base pairs from the 5’ or 3’ end of the target sequence. In order to minimize removal of the edit inserted by the polymerase editor by the DNA mismatch repair machinery, one or more components of the mismatch repair system can be inactivated using, for example, a dominant negative version thereof. A non-limiting example of a 35 component of the mismatch repair system that can be inactivated or have its activity reduced is MLH1. A dominant negative MLH1 or a polynucleotide encoding the same can be introduced into the cell, along with, preceding or subsequent to the introduction of the PE system. A non-limiting 81 Atty Dkt No: L1034381430WO (00376)

[0082] example of a dominant-negative MLH1 is the sequence set forth as SEQ ID NO: 481. In some embodiments, the DNA construct encoding the PE comprises the dominant-negative MLH1-encoding sequence on its N-terminus or its C-terminus and the dominant-negative MLH1-encoding sequence can connect to the PE-encoding sequence through a peptide linker and / or a NLS. 5 One of ordinary skill in the art will appreciate that any of the presently disclosed methods can be used to target a single target sequence or multiple target sequences. Thus, methods comprise the use of a single PE in combination with multiple, distinct guide RNAs, which can target multiple, distinct sequences within a single gene and / or multiple genes. Also encompassed herein are methods wherein multiple, distinct guide RNAs are introduced in combination with multiple, distinct PEs. 10 These guide RNAs and guide RNA / PE systems can target multiple, distinct sequences within a single gene and / or multiple genes. XII. Target Polynucleotides The disclosure provides for methods of editing a target polynucleotide comprising a target 15 sequence in a eukaryotic cell, which may be in vivo, ex vivo, or in vitro. In some embodiments, the method comprises sampling a cell or population of cells from a human or non-human animal or plant (including microalgae) and editing the cell or cells. Culturing may occur at any stage ex vivo. The cell or cells may even be re-introduced into the non-human animal or plant (including micro-algae). Using natural variability, plant breeders combine most useful genes for desirable qualities, 20 such as yield, quality, uniformity, hardiness, and resistance against pests. These desirable qualities also include growth, day length preferences, temperature requirements, initiation date of floral or reproductive development, fatty acid content, insect resistance, disease resistance, nematode resistance, fungal resistance, herbicide resistance, tolerance to various environmental factors including drought, heat, wet, cold, wind, and adverse soil conditions including high salinity. The sources of 25 these useful genes include native or foreign varieties, heirloom varieties, wild plant relatives, and induced mutations, e.g., treating plant material with mutagenic agents. Using the present disclosure, plant breeders are provided with a new tool to induce mutations. Accordingly, one skilled in the art can analyze the genome for sources of useful genes, and in varieties having desired characteristics or traits employ the present invention to induce the rise of useful genes, with more precision than 30 previous mutagenic agents and hence accelerate and improve plant breeding programs. The target polynucleotide of a PE system can be any polynucleotide endogenous or exogenous to the eukaryotic cell. For example, the target polynucleotide can be a polynucleotide residing in the nucleus of the eukaryotic cell. The target polynucleotide can be a sequence encoding a gene product (e.g., a protein) or can be a non-coding sequence (e.g., a regulatory polynucleotide or a 35 junk DNA). 82 Atty Dkt No: L1034381430WO (00376)

[0083] The target polynucleotide of a PE system of the disclosure may include a number of disease- associated genes and polynucleotides as well as signaling biochemical pathway-associated genes and polynucleotides. Examples of target polynucleotides include a sequence associated with a signaling biochemical pathway, e.g., a signaling biochemical pathway-associated gene or polynucleotide. 5 Examples of target polynucleotides include a disease associated gene or polynucleotide. A “disease- associated” gene or polynucleotide refers to any gene or polynucleotide which is yielding transcription or translation products at an abnormal level or in an abnormal form in cells derived from a disease-affected tissues compared with tissues or cells of a non-disease control. It may be a gene that becomes expressed at an abnormally high level; it may be a gene that becomes expressed at an 10 abnormally low level, where the altered expression correlates with the occurrence and / or progression of the disease. A disease-associated gene also refers to a gene possessing mutation(s) or genetic variation that is directly responsible or is in linkage disequilibrium with a gene(s) that is responsible for the etiology of a disease (e.g., a mutation). The transcribed or translated products may be known or unknown, and further may be at a normal or abnormal level. In some embodiments, the disease 15 may be an animal disease. In some embodiments, the disease may be an avian disease. In some embodiments, the disease may be a mammalian disease. In some embodiments, the disease may be a human disease. Non-limiting examples of disease-associated genes and polynucleotides in humans are available from McKusick-Nathans Institute of Genetic Medicine, Johns Hopkins University (Baltimore, Md.) and National Center for Biotechnology Information, National Library of Medicine 20 (Bethesda, Md.), available on the World Wide Web. The methods comprise contacting a target polynucleotide comprising a target sequence with a PE or PE system of the disclosure, wherein the target polynucleotide is contacted with the PE or PE system in an amount effective and under conditions suitable for editing of the target sequence. In some embodiments, the target sequence comprises a sequence associated with a disease or disorder, 25 and the editing of the target sequence results in a sequence that is not associated with a disease or disorder. In some embodiments, the target sequence resides in an allele of a crop plant, wherein the particular allele is associated with a trait that results in a plant of lesser agronomic value. The editing of the target sequence results in an allele that is associated with a trait that increases the agronomic value of the plant. 30 In some embodiments, the target DNA sequence comprises a T^C or A^G point mutation associated with a disease or disorder, and wherein the deamination of the mutant C or G base results in a sequence that is not associated with a disease or disorder. In some embodiments, the deamination corrects a point mutation in the sequence associated with the disease or disorder. In some embodiments, the sequence associated with the disease or disorder encodes a protein, 35 and the editing of the target sequence introduces a stop codon into the sequence associated with the disease or disorder, resulting in a truncation of the encoded protein. In some embodiments, the contacting is performed in vivo in a subject susceptible to having or diagnosed with the disease or 83 Atty Dkt No: L1034381430WO (00376)

[0084] disorder. In some embodiments, the disease or disorder is a disease associated with a point mutation, or a single-base mutation, in the genome. In some embodiments, the disease is a genetic disease, a cancer, a metabolic disease, or a lysosomal storage disease. 5 XIII. Cells Comprising a Polynucleotide Genetic Edit Provided herein are cells and organisms comprising a target polynucleotide that has been edited using a process mediated by a PE system, as described herein. The edited cells can be eukaryotic (e.g., mammalian, plant, insect, avian cell) or prokaryotic. Prokaryotic cells can be from species, including but not limited to, archaea and bacteria (e.g., Bacillus sp., Klebsiella sp. 10 Streptomyces sp., Rhizobium sp., Escherichia sp., Pseudomonas sp., Salmonella sp., Shigella sp., Vibrio sp., Yersinia sp., Mycoplasma sp., Agrobacterium, Lactobacillus sp.). Eukaryotic cells can include cells from animals (e.g., mammals, humans, insects, fish, birds, and reptiles), plants, fungi, amoeba, algae, and yeast. In some embodiments, the cell that is edited by the presently disclosed methods include cells of hematopoietic origin, such as cells of the immune 15 system including but not limited to B cells, T cells, natural killer (NK) cells, chimeric antigen receptor T (CAR-T) cells, monocytes, macrophages, and dendritic cells. In some embodiments, the cell is a pluripotent stem cell or induced pluripotent stem cell. In some embodiments, the cell that is edited by the presently disclosed methods include primary cells. In certain embodiments, the primary cells include primary T cells. 20 The methods provided herein may be used for editing of any plant species, including, but not limited to, monocots and dicots. Examples of plants of interest include, but are not limited to, corn (maize), sorghum, wheat, sunflower, tomato, crucifers, peppers, potato, cotton, rice, soybean, sugarbeet, sugarcane, tobacco, barley, and oilseed rape, Brassica sp., alfalfa, rye, millet, safflower, peanuts, sweet potato, cassava, coffee, coconut, pineapple, citrus trees, cocoa, tea, banana, avocado, 25 fig, guava, mango, olive, papaya, cashew, macadamia, almond, oats, vegetables, ornamentals, and conifers. Vegetables include, but are not limited to, tomatoes, lettuce, green beans, lima beans, peas, and members of the genus Curcumis such as cucumber, cantaloupe, and musk melon. Ornamentals include, but are not limited to, azalea, hydrangea, hibiscus, roses, tulips, daffodils, petunias, carnation, 30 poinsettia, and chrysanthemum. In specific embodiments, plants of the present invention are crop plants (for example, maize, sorghum, wheat, sunflower, tomato, crucifers, peppers, potato, cotton, rice, soybean, sugarbeet, sugarcane, tobacco, barley, oilseed rape, etc.). Also provided are organelles and embryos comprising at least one target sequence that has been edited by a process utilizing a PE or PE system as described herein. The genetically edited cells, 35 organisms, organelles, and embryos can be heterozygous or homozygous for the edited target sequence. 84 Atty Dkt No: L1034381430WO (00376)

[0085] The chromosomal editing of the cell, organism, organelle, or embryo can result in altered expression (up-regulation or down-regulation), inactivation, or the expression of an altered protein product or an integrated sequence. In those embodiments wherein the chromosomal editing results in either the inactivation of a gene or the expression of a non-functional protein product, the genetically 5 edited cell, organism, organelle, or embryo is referred to as a “knock out”. The knock out phenotype can be the result of a deletion mutation (i.e., deletion of at least one nucleotide), an insertion mutation (i.e., insertion of at least one nucleotide), or a nonsense mutation (i.e., substitution of at least one nucleotide such that a stop codon is introduced). In some embodiments, chromosomal editing results in upregulation of expression of a protein product that had been lacking or reduced due to mutation(s) 10 in a target sequence. Alternatively, the chromosomal editing of a cell, organism, organelle, or embryo can produce a “knock in”, which results from the chromosomal integration of a nucleotide sequence that encodes a protein. In some of these embodiments, the coding sequence is integrated into the chromosome such that the chromosomal sequence encoding the wild-type protein is inactivated, but the exogenously 15 introduced protein is expressed. In some embodiments, the mutation(s) introduced using the presently disclosed PE systems yields production of a variant protein product. The expressed variant protein product can have at least one amino acid substitution and / or the addition or deletion of at least one amino acid. The variant protein product encoded by the altered chromosomal sequence can exhibit modified characteristics or 20 activities when compared to the wild-type protein, including but not limited to altered enzymatic activity or substrate specificity. In some embodiments, the chromosomal editing can result in an altered expression pattern of a protein. As a non-limiting example, chromosomal alterations in the regulatory regions controlling the expression of a protein product can result in the overexpression or downregulation of the protein product or an altered tissue or temporal expression pattern. In some 25 embodiments, the mutation(s) introduced as a result of these PE systems yields a reduction or elimination in expression of a gene. Cells that have been edited may be introduced into an organism. These cells could have originated from the same organism (e.g., person) in the case of autologous cellular transplants, wherein the cells are edited in an ex vivo approach. Alternatively, the cells originated from another 30 organism within the same species (e.g., another person) in the case of allogeneic cellular transplants. The cells that have been edited can be grown into an organism, such as a plant, in accordance with conventional ways. See, for example, McCormick et al. (1986) Plant Cell Reports 5:81-84. These plants may then be grown, and either pollinated with the same edited strain or different strains, and the resulting hybrid having the genetic edit. The present disclosure provides genetically edited seed. 35 Progeny, variants, and mutants of the regenerated plants are also included within the scope of the disclosure, provided that these parts comprise the genetic edit. Further provided is a processed plant product or byproduct that retains the genetic edit, including for example, soymeal. 85 Atty Dkt No: L1034381430WO (00376)

[0086] XIV. Pharmaceutical Compositions Pharmaceutical compositions of the present disclosure can comprise: RTs, fusion proteins comprising the same, or PEs comprising the same; DNA-binding polypeptides (e.g., RGN 5 polypeptides), fusion proteins comprising the same, or PEs comprising the same; PE-enhancing polypeptides, fusion proteins comprising the same, or PEs comprising the same; or active variants and fragments thereof of any of these described herein, as well as polynucleotides encoding the same; gRNAs, or active variants and fragments thereof, described herein, or polynucleotides encoding the same; PE systems (including DPE systems); cells described herein comprising any of the RTs, DNA- 10 binding polypeptides (e.g., RGN polypeptides), PE-enhancing polypeptides, fusion proteins, PEs, and / or gRNAs; RNP complexes comprising the same; or RT-, DNA-binding polypeptide (e.g., RGN polypeptide)-, PE-enhancing polypeptide-, or PE-encoding polynucleotides, gRNA or gRNA- encoding polynucleotides; and a pharmaceutically acceptable carrier. A pharmaceutical composition is a composition that is employed to prevent, reduce in 15 intensity, cure or otherwise treat a target condition or disease that comprises an active ingredient (i.e. RTs, DNA-binding polypeptides (e.g., RGN polypeptides), PE-enhancing polypeptides, fusion proteins, PEs, and / or gRNAs; polynucleotides encoding any of these; PE systems (including DPE systems) comprising any of these; RNP complexes comprising any of these; or cells comprising any of these) and a pharmaceutically acceptable carrier. 20 As used herein, a “pharmaceutically acceptable carrier” refers to a material that does not cause significant irritation to an organism and does not abrogate the activity and properties of the active ingredient (i.e. RTs, DNA-binding polypeptides (e.g., RGN polypeptides), PE-enhancing polypeptides, fusion proteins, PEs, and / or gRNAs; polynucleotides encoding any of these; RNP complexes comprising any of these; PE systems (including DPE systems) comprising any of these; or 25 cells comprising any of these). Carriers must be of sufficiently high purity and of sufficiently low toxicity to render them suitable for administration to a subject being treated. The carrier can be inert, or it can possess pharmaceutical benefits. In some embodiments, a pharmaceutically acceptable carrier comprises one or more compatible solid or liquid filler, diluents or encapsulating substances which are suitable for administration to a human or other vertebrate animal. In some embodiments, the 30 pharmaceutically acceptable carrier is not naturally-occurring. In some embodiments, the pharmaceutically acceptable carrier and the active ingredient are not found together in nature. Pharmaceutical compositions used in the presently disclosed methods can be formulated with suitable carriers, excipients, and other agents that provide suitable transfer, delivery, tolerance, and the like. A multitude of appropriate formulations are known to those skilled in the art. See, e.g., 35 Remington, The Science and Practice of Pharmacy (21sted.2005). Suitable formulations include, for example, powders, pastes, ointments, jellies, waxes, oils, lipids, lipid (cationic or anionic) containing vesicles (such as LIPOFECTIN vesicles), lipid nanoparticles, DNA conjugates, anhydrous absorption 86 Atty Dkt No: L1034381430WO (00376)

[0087] pastes, oil-in-water and water-in-oil emulsions, emulsions carbowax (polyethylene glycols of various molecular weights), semi-solid gels, and semi-solid mixtures containing carbowax. Pharmaceutical compositions for oral or parenteral use may be prepared into dosage forms in a unit dose suited to fit a dose of the active ingredients. Such dosage forms in a unit dose include, for example, tablets, pills, 5 capsules, injections (ampoules), suppositories, etc. The disclosure provides for pharmaceutical compositions comprising lipid-based formulations including an active ingredient (i.e. RTs, DNA-binding polypeptides (e.g., RGN polypeptides), PE- enhancing polypeptides, fusion proteins, PEs, and / or gRNAs; polynucleotides encoding any of these; RNP complexes comprising any of these; PE systems (including DPE systems) comprising any of 10 these; or cells comprising any of these). The lipid-based formulations can include liposomes. The lipid-based formulations can include lipid nanoparticles (LNPs). In some embodiments, an active ingredient is encapsulated in the lipid particle and / or disposed on the surface of the lipid particle. In some embodiments, an active ingredient is covalently attached to the lipid particle. In some embodiments, an active ingredient is non-covalently associated with the lipid particle. A covalent 15 attachment includes the sharing of electrons in a chemical bond. Non-covalent interactions include dispersed electromagnetic interactions such as hydrogen bonds, ionic bonds, van der Waals interactions, and hydrophobic bonds. In some embodiments, an active ingredient is encapsulated in the lipid particle. The term “encapsulate” means to enclose, surround or encase. As it relates to the formulation of the compounds 20 of the disclosure, encapsulation may be substantial, complete or partial. The term “substantially encapsulated” or “substantial encapsulation” means that greater than 50%, 60%, 70%, 80%, 85%, 90%, 95%, 96%, 97%, 98%, 99%, 99.9%, or greater of the pharmaceutical composition or active ingredient of the disclosure may be enclosed, surrounded, or encased within a delivery agent (e.g., liposome or LNP). The term “partially encapsulated” or “partial encapsulation” means that less than 25 50%, 40%, 30%, 20%, 10%, or less of the pharmaceutical composition or active ingredient of the disclosure may be enclosed, surrounded, or encased within the delivery agent. Encapsulation may be determined by measuring the escape or the activity of the pharmaceutical composition or active ingredient of the disclosure using fluorescence and / or electron microscopy. For example, at least 1%, 5%, 10%, 20%, 30%, 40%, 50%, 60%, 70%, 80%, 85%, 90%, 95%, 96%, 97%, 98%, 99%, 99.9%, or 30 greater of the pharmaceutical composition or active ingredient of the disclosure is encapsulated in a delivery agent (e.g., liposome or LNP). Liposomes are spherical vesicle structures composed of a uni- or multilamellar lipid bilayer surrounding internal aqueous compartments and a relatively impermeable outer lipophilic phospholipid bilayer. Liposomes have gained considerable attention as drug delivery carriers because 35 they are biocompatible, nontoxic, can deliver both hydrophilic and lipophilic drug molecules, protect their cargo from degradation by plasma enzymes, and transport their load across biological 87 Atty Dkt No: L1034381430WO (00376)

[0088] membranes and the blood brain barrier (BBB) (see, e.g., Spuch and Navarro (2011) Journal of drug delivery 2011). Liposomes can be made from several different types of lipids (e.g. ionizable lipids, structural lipids, helper lipids, and pegylated lipids); however, phospholipids are most commonly used to 5 generate liposomes as drug carriers. Although liposome formation is spontaneous when a lipid film is mixed with an aqueous solution, it can also be expedited by applying force in the form of shaking by using a homogenizer, sonicator, or an extrusion apparatus (see, e.g., Spuch and Navarro (2011) Journal of drug delivery 2011). A conventional liposome formulation is mainly comprised of natural phospholipids and 10 phospholipids such as 1,2-distearoryl-sn-glycero-3-phosphatidyl choline (DSPC), sphingomyelin, egg phosphatidylcholines, and monosialoganglioside. In some embodiments, 1,2-dioleoyl-sn-glycero-3- phosphoethanolamine (DOPE) increases stability of a liposome. Additives may be added to liposomes in order to modify their structure and properties. In some embodiments, cholesterol and / or sphingomyelin may be added to a liposomal mixture to help 15 stabilize the liposomal structure and to prevent leakage of the liposomal inner cargo. In some embodiments, addition of cholesterol to a conventional liposome formulation reduces rapid release of the encapsulated active ingredient (i.e., RTs, DNA-binding polypeptides (e.g., RGN polypeptides), PE-enhancing polypeptides, fusion proteins, PEs, and / or gRNAs; polynucleotides encoding any of these; RNP complexes comprising any of these; PE systems (including DPE systems) comprising any 20 of these; or cells comprising any of these) into the plasma. In some embodiments, liposomes are prepared from hydrogenated egg phosphatidylcholine or egg phosphatidylcholine, cholesterol, and dicetyl phosphate. In some embodiments, mean liposome vesicle size is adjusted to about 50 or 100 nm. In some embodiments, Trojan Horse liposomes (also known as Molecular Trojan Horses or PEGylated immunoliposomes) may be used in pharmaceutical compositions for delivery of an active 25 ingredient across the BBB (described on World Wide Web at cshprotocols.cshlp.org / content / 2010 / 4 / pdb.prot5407.long). Without being bound by any theory, it is believed that neutral lipid particles with specific antibodies conjugated to the surface allows crossing of the BBB via endocytosis. In some embodiments, pharmaceutical compositions comprising Trojan Horse liposomes may be used to deliver an active ingredient (i.e., RTs, DNA-binding polypeptides 30 (e.g., RGN polypeptides), PE-enhancing polypeptides, fusion proteins, PEs, and / or gRNAs; polynucleotides encoding any of these; RNP complexes comprising any of these; PE systems (including DPE systems) comprising any of these; or cells comprising any of these) to the brain via an intravascular injection. In some embodiments, liposomes include stable nucleic-acid-lipid particles (SNALP) (see, 35 e.g., Morrissey et al. (2005) Nature Biotechnology 23(8):1002-1007; Zimmerman et al. (2006) Nature 441: 111-114). SNALPs include a mixture of cationic and fusogenic lipids and coated with polyethylene glycol (PEG) that allow cellular uptake and endosomal release of an active ingredient 88 Atty Dkt No: L1034381430WO (00376)

[0089] cargo. In some embodiments, a SNALP is a class of LNP and includes an ionizable lipid that is cationic at low pH (e.g., DLinDMA, COATSOME® SS-OC), a neutral helper lipid (e.g. DSPC), cholesterol, and a diffusible polyethylene glycol (PEG)-lipid (e.g. Brij S100). In some embodiments, a SNALP formulation includes the following lipids: 3-N-(-methoxy poly(ethylene glycol)2000) 5 carbamoyl-1,2-dimyrestyloxy-propylamine (PEG-cDMA); 1,2-dilinoleyloxy-N,N-dimethyl-3- aminopropane (DLinDMA); 1,2-distearoyl-sn-glycero-3-phosphocholine (DSPC); and cholesterol. In some embodiments, a SNALP includes synthetic cholesterol, dipalmitoylphosphatidylcholine (DOPC), PEG-cDMA, and DLinDMA (see, e.g., Geisbert et al. (2010) Lancet 375:1896-1905). In some embodiments, a SNALP includes synthetic cholesterol, DSPC, PEG-cDMA, and DLinDMA 10 (see, e.g., Judge et al. (2009) J. Clin. Invest.119:661-673). In some embodiments, a SNALP formulation includes COATSOME® SS-OC, DSPC, Brij S100, and cholesterol. In some embodiments, a SNALP formulation includes an ionizable lipid, DSPC, cholesterol, and a PEG lipid. In some embodiments, a SNALP formulation includes the ionizable lipids and / or PEG lipids disclosed in WO2022173531 or WO2022173531 each of which is herein incorporated by reference in its 15 entirety. In some embodiments, SNALP liposomes are about 80-100 nm in size. SNALPs have been used as effective delivery molecules to highly vascularized HepG2-derived liver tumors (see, e.g., Li et al. (2012) Gene Therapy 19:775- 780). Without being bound by any one theory, during formulation of SNALPs, the ionizable lipid 20 serves to condense lipid with an active ingredient (e.g., a polynucleotide) during particle formation. When positively charged under increasingly acidic endosomal conditions, the ionizable lipid may mediate the fusion of a SNALP with the endosomal membrane, enabling release of the active ingredient into the cytoplasm. The PEG-lipid may stabilize the particle and reduce aggregation during formulation, and subsequently may provide a neutral hydrophilic exterior that improves 25 pharmacokinetic properties. In some embodiments, SNALP liposomes are prepared by formulating DLinDMA and PEG-cDMA with DSPC, cholesterol and an active ingredient using a 25:1 lipid: active ingredient ratio and a 48:40:10:2 molar ratio of cholesterol: DLinDMA: DSPC: PEG-cDMA. In some embodiments, a pharmaceutical composition of the disclosure includes LNPs. In some embodiments, lipids may be formulated with an active ingredient of the present disclosure to 30 form LNPs. An LNP comprises a plurality of lipid molecules physically associated with each other by intermolecular forces. In some embodiments, LNPs include liposomes. In some embodiments, LNPs differ from liposomes in not having a continuous lipid bilayer. In some embodiments, LNPs comprise solid particles having a mixture of solid and liquid lipids. In some embodiments, LNPs include dendrimer lipid nanoparticles (DLNPs), SNALPs, and lipid-like nanoparticles (LLNPs). In general, a 35 “nanoparticle” refers to any particle having a diameter of less than 1000 nanometers (nm). In some embodiments, nanoparticles have a diameter of 500 nm or less. In some embodiments, nanoparticles have a diameter ranging between 25 nm and 200 nm, or 100 nm or less. In some embodiments, 89 Atty Dkt No: L1034381430WO (00376)

[0090] nanoparticles have a diameter ranging between 35 nm and 60 nm. In some embodiments, an LNP includes a lipid particle between about 1 and about 100 nm in size. LNPs include four components: ionizable cationic lipids, fusogenic zwitterionic phospholipids, cholesterol, and PEGylated (PEG) lipids. In some embodiments, the ionizable cationic 5 lipid component complexes a negatively charged polynucleotide and enhances endosomal escape). In some embodiments, the phospholipid component functions in modifying lipid bilayer structure. In some embodiments, the cholesterol component helps to stabilize an LNP. In some embodiments, the PEG lipid component decreases LNP aggregation and non-specific uptake. In some embodiments, the LNP includes an ionizable lipid that is cationic at low pH (e.g., 10 DLinDMA, COATSOME® SS-OC), a neutral helper lipid (e.g. DSPC), cholesterol, and a diffusible polyethylene glycol (PEG)-lipid (e.g. Brij S100). In some embodiments, the LNP includes the following lipids: 3-N-(-methoxy poly(ethylene glycol)2000) carbamoyl-1,2-dimyrestyloxy- propylamine (PEG-cDMA); 1,2-dilinoleyloxy-N,N-dimethyl-3-aminopropane (DLinDMA); 1,2- distearoyl-sn-glycero-3-phosphocholine (DSPC); and cholesterol. In some embodiments, the LNP 15 includes synthetic cholesterol, dipalmitoylphosphatidylcholine (DOPC), PEG-cDMA, and DLinDMA (see, e.g., Geisbert et al. (2010) Lancet 375:1896-1905). In some embodiments, the LNP includes synthetic cholesterol, DSPC, PEG-cDMA, and DLinDMA (see, e.g., Judge et al. (2009) J. Clin. Invest.119:661-673). Ionizable cationic lipids useful in LNPs include: COATSOME® SS-OC, 1,2-dilineoyl-3-20 dimethylammonium-propane (DLinDAP); DLinDMA; l,2-dilinoleyloxy-keto-N,N-dimethyl-3- aminopropane (DlinK-DMA); 1,2-dilinoleyl-4-(2-dimethylaminoethyl)-[1,3]-dioxolane (DlinKC2- DMA); 5A2-SC8 (Zhou et al. (2016) Proc. Natl Acad. Sci. USA 113:520–525); C12-200 (Love et al. (2010) Proc. Natl Acad. Sci. USA 107:1864–1869); 246C10 (Kim et al. (2021) Sci Adv 7(9): eabf4398); cKK-E12 (Fenton et al. (2016) Advanced Materials 28(15):2939-2943); 1,2-distearyloxy- 25 N,N-dimethyl-3-aminopropane (DSDMA); 1,2-dioleyloxy-N,N -dimethyl-3-aminopropane (DODMA); 1,2-dilinolenyloxy-N,N -dimethyl-3-aminopropane (DLenDMA); and dilinoleylmethyl-4- dimethylaminobutyrate (Dlin-MC3-DMA; Jayaraman et al. (2012) Angew Chem Int Ed Engl.51(34): 8529–8533). Cationic lipids are further described in International Publication Nos. WO2012040184, WO2011153120, WO2011149733, WO2011090965, WO2011043913, WO2011022460, 30 WO2012061259, WO2012054365, WO2012044638, WO2010080724, WO201021865, WO2022173531, WO2022150485 and WO2008103276, US Patent Nos.7,893,302 and 7,404,969 and US Patent Publication No. US20100036115, each of which is herein incorporated by reference in its entirety. Zwitterionic phospholipids useful for LNPs include DSPC, DOPE, and DOPC. PEG lipids35 useful for LNPs include: 1,2-dimyristoyl-rac-glycero-3-methoxypolyethylene glycol (PEG-DMG); (3- o-[2’’-(methoxypolyethyleneglycol 2000) succinoyl]-l,2-dimyristoyl-sn-glycol (PEG-S-DMG); R-3- [(ω-methoxy-poly(ethylene glycol)2000) carbamoyl]-1,2-dimyristyloxlpropyl-3-amine (PEG-C- 90 Atty Dkt No: L1034381430WO (00376)

[0091] DOMG); and C16 PEG-ceramide. In some embodiments, an LNP includes 50: 10: 38.5: 1.5 molar ratio of DlinKC2-DMA or C12-200: DSPC: cholesterol: PEG-DMG (see, e.g., Basha et al. (2011) Molecular Therapy 19(12):2186-2200). In some embodiments, an LNP includes 26.5: 20: 52: 1.5 ionizable lipid: DOPE: cholesterol: PEG lipid (see, e.g., Han et al. (2022) Sci Adv 8(3): eabj6901; 5 Kim et al. (2021) Sci Adv 7(9): eabf4398). PEG lipids are further described in WO2012099755, WO2022173531 and WO2022150485 each of which is herein incorporated by reference in its entirety. In some embodiments, the ratio of PEG in the LNP formulations may be increased or decreased and / or the carbon chain length of the PEG lipid may be modified from C14 to C18 to alter the pharmacokinetics and / or biodistribution of the LNP formulations. 10 In some embodiments, a LNP formulation includes COATSOME® SS-OC, DSPC, Brij S100, and cholesterol. In some embodiments, a LNP formulation includes an ionizable lipid, DSPC, cholesterol, and a PEG lipid. In some embodiments, a LNP formulation includes the ionizable lipids and / or PEG lipids disclosed in WO2022173531 or WO2022150485 each of which is herein incorporated by reference in its entirety. In some embodiments, a LNP formulation includes the 15 ionizable lipids and / or PEG lipids disclosed in WO2022173531 or WO2022150485 (each of which is herein incorporated by reference in its entirety), DSPC, and cholesterol. In some embodiments, a LNP formulation includes any one of CAT1-CAT35 and any one of CHM-001 to CHM-016 disclosed in WO2022173531 or WO2022150485 each of which is herein incorporated by reference in its entirety. In some embodiments, a LNP formulation includes any one of CAT1-CAT35 and any one of 20 CHM-001 to CHM-016 disclosed in WO2022173531 or WO2022150485 (each of which is herein incorporated by reference in its entirety), DSPC, and cholesterol. In some embodiments, the LNP of the disclosure comprises 44-60 mol % of the cationic lipid, 19-25 mol % of the helper lipid, 25-33 mol % of the structural lipid, and 0.2-0.8 mol % of the PEG- lipid, inclusive of the endpoints. In some embodiments, the LNP of the disclosure comprises 44-54 25 mol % of the cationic lipid, 19-25 mol % of the helper lipid, 24-32 mol % of the s...

Claims

THAT WHICH IS CLAIMED:

1. A polynucleotide encoding a reverse transcriptase (RT), wherein said RT comprises an amino acid sequence having at least 40% sequence identity to SEQ ID NO: 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30, 31, 32, 33, 34, 35, 36, 5 37, 38, 40, 41, 262, 837, 846, 881, 883, 885, 887, 888, 889, 891, 892, 893, 894, 895, 896, 897, or 898.

2. The polynucleotide of claim 1, wherein said RT comprises: (i) an amino acid sequence having at least 40% sequence identity to SEQ ID NO: 35 or 41; (ii) an amino acid sequence having at least 60% sequence identity to SEQ ID NO: 1, 34, or 40; 10 (iii) an amino acid sequence having at least 70% sequence identity to SEQ ID NO: 6, 8, 9, 36, 37, 837, or 846; (iv) an amino acid sequence having at least 75% sequence identity to SEQ ID NO: 4; (v) an amino acid sequence having at least 80% sequence identity to SEQ ID NO: 895 or 897; (vi) an amino acid sequence having at least 83% sequence identity to SEQ ID NO: 18, 19, 20, 15 21, 22, 23, 892, or 896; (vii) an amino acid sequence having at least 85% sequence identity to SEQ ID NO: 891; (viii) an amino acid sequence having at least 87% sequence identity to SEQ ID NO: 889 or 898; (ix) an amino acid sequence having at least 90% sequence identity to SEQ ID NO: 7, 38, 262, 20 881, 883, or 893; (x) an amino acid sequence having at least 92% sequence identity to SEQ ID NO: 887 or 888; (xi) an amino acid sequence having at least 95% sequence identity to SEQ ID NO: 24, 25, 26, 27, 28, 29, 30, 31, 32, 33, 885, or 894; or (xii) an amino acid sequence having at least 99.7% sequence identity to SEQ ID NO: 2, 3, or 25 5.

3. The polynucleotide of claim 1 or 2, wherein said RT comprises: (i) an amino acid sequence having at least 50% sequence identity to SEQ ID NO: 35 or 41; (ii) an amino acid sequence having at least 70% sequence identity to SEQ ID NO: 1, 34, or 40; 30 (iii) an amino acid sequence having at least 75% sequence identity to SEQ ID NO: 6, 8, 9, 36, 37, 837, or 846; (iv) an amino acid sequence having at least 80% sequence identity to SEQ ID NO: 4; (v) an amino acid sequence having at least 85% sequence identity to SEQ ID NO: 895 or 897; (vi) an amino acid sequence having at least 90% sequence identity to SEQ ID NO: 18, 19, 20, 35 21, 22, 23, 889, 891, 892, 896, or 898; or (vii) an amino acid sequence having at least 95% sequence identity to SEQ ID NO: 7, 38, 262, 881, 883, 887, 888, or 893. 354 Atty Dkt No: L1034381430WO (00376)4. The polynucleotide of any one of claims 1-3, wherein said RT comprises: (i) an amino acid sequence having at least 60% sequence identity to SEQ ID NO: 35 or 41; (ii) an amino acid sequence having at least 75% sequence identity to SEQ ID NO: 1, 34, or 40; 5 (iii) an amino acid sequence having at least 80% sequence identity to SEQ ID NO: 6, 8, 9, 36, 37, 837, or 846; (iv) an amino acid sequence having at least 85% sequence identity to SEQ ID NO: 4; (v) an amino acid sequence having at least 90% sequence identity to SEQ ID NO: 895 or 897; or 10 (vi) an amino acid sequence having at least 95% sequence identity to SEQ ID NO: 18, 19, 20, 21, 22, 23, 889, 891, 892, 896, or 898.

5. The polynucleotide of any one of claims 1-4, wherein said RT comprises: (i) an amino acid sequence having at least 70% sequence identity to SEQ ID NO: 35 or 41; (ii) an amino acid sequence having at least 80% sequence identity to SEQ ID NO: 1, 34, or 15 40; (iii) an amino acid sequence having at least 85% sequence identity to SEQ ID NO: 6, 8, 9, 36, 37, 837, or 846; (iv) an amino acid sequence having at least 90% sequence identity to SEQ ID NO: 4; or (v) an amino acid sequence having at least 95% sequence identity to SEQ ID NO: 895 or 897. 20 6. The polynucleotide of any one of claims 1-5, wherein said RT comprises: (i) an amino acid sequence having at least 80% sequence identity to SEQ ID NO: 35 or 41; (ii) an amino acid sequence having at least 85% sequence identity to SEQ ID NO: 1, 34, or 40; (iii) an amino acid sequence having at least 90% sequence identity to SEQ ID NO: 6, 8, 9, 36, 25 37, 837, or 846; or (iv) an amino acid sequence having at least 95% sequence identity to SEQ ID NO:

4.

7. The polynucleotide of any one of claims 1-6, wherein said RT comprises: (i) an amino acid sequence having at least 85% sequence identity to SEQ ID NO: 35 or 41; (ii) an amino acid sequence having at least 90% sequence identity to SEQ ID NO: 1, 34, or 30 40; or (iii) an amino acid sequence having at least 95% sequence identity to SEQ ID NO: 6, 8, 9, 36, 37, 837, or 846.

8. The polynucleotide of any one of claims 1-7, wherein said RT comprises: (i) an amino acid sequence having at least 90% sequence identity to SEQ ID NO: 35 or 41; or 35 (ii) an amino acid sequence having at least 95% sequence identity to SEQ ID NO: 1, 34, or 40. 355 Atty Dkt No: L1034381430WO (00376)9. The polynucleotide of any one of claims 1-8, wherein said RT comprises an amino acid sequence having at least 95% sequence identity to SEQ ID NO: 35 or 41.

10. The polynucleotide of any one of claims 1-9, wherein said RT comprises the amino acid sequence of any one of SEQ ID NO: 1-9, 18-41, 262, 837, 846, 881, 883, 885, 887, 888, 889, 5 891, 892, 893, 894, 895, 896, 897, and 898.

11. The polynucleotide of any one of claims 1-10, wherein said RT lacks an RNase H domain.

12. The polynucleotide of any one of claims 1-11, wherein said RT comprises at least one of: 10 a) an N at a position corresponding to 200 of SEQ ID NO: 42; b) a P at a position corresponding to 330 of SEQ ID NO: 42; c) a K at a position corresponding to 306 of SEQ ID NO: 42; and d) an F at a position corresponding to 313 of SEQ ID NO:

42.

13. The polynucleotide of any one of claims 1-12, wherein said RT comprises: 15 a) an amino acid sequence having at least 60% sequence identity to SEQ ID NO: 10, wherein said RT comprises at least one of: i) an N at a position corresponding to 198 of SEQ ID NO: 10; ii) a K at a position corresponding to 304 of SEQ ID NO: 10; iii) an F at a position corresponding to 311 of SEQ ID NO: 10; and 20 iv) a P at a position corresponding to 328 of SEQ ID NO: 10; b) an amino acid sequence having at least 99.5% sequence identity to SEQ ID NO: 11 or 12, wherein said RT comprises at least one of: i) an N at a position corresponding to 199 of SEQ ID NO: 11 or 12; ii) a K at a position corresponding to 305 of SEQ ID NO: 11 or 12; 25 iii) an F at a position corresponding to 312 of SEQ ID NO: 11 or 12; and iv) a P at a position corresponding to 329 of SEQ ID NO: 11 or 12; c) an amino acid sequence having at least 72% sequence identity to SEQ ID NO: 13, wherein said RT comprises at least one of: i) a K at a position corresponding to 306 of SEQ ID NO: 13; 30 ii) an F at a position corresponding to 313 of SEQ ID NO: 13; and iii) a P at a position corresponding to 330 of SEQ ID NO: 13; d) an amino acid sequence having at least 99.5% sequence identity to SEQ ID NO: 14, wherein said RT comprises at least one of: i) an N at a position corresponding to 198 of SEQ ID NO: 14; 35 ii) a K at a position corresponding to 304 of SEQ ID NO: 14; iii) an F at a position corresponding to 311 of SEQ ID NO: 14; and iv) a P at a position corresponding to 328 of SEQ ID NO: 14; 356 Atty Dkt No: L1034381430WO (00376)or e) an amino acid sequence having at least 87% sequence identity to SEQ ID NO: 15, 16 or 17, wherein said RT comprises at least one of: i) an N at a position corresponding to 198 of SEQ ID NO: 15, 16 or 17; 5 ii) a K at a position corresponding to 304 of SEQ ID NO: 15, 16 or 17; iii) an F at a position corresponding to 311 of SEQ ID NO: 15, 16 or 17; and iv) a P at a position corresponding to 328 of SEQ ID NO: 15, 16 or 17.

14. The polynucleotide of claim 13, wherein said RT comprises: a) an amino acid sequence having at least 70% sequence identity to SEQ ID NO: 10, wherein 10 said RT comprises at least one of: i) an N at a position corresponding to 198 of SEQ ID NO: 10; ii) a K at a position corresponding to 304 of SEQ ID NO: 10; iii) an F at a position corresponding to 311 of SEQ ID NO: 10; and iv) a P at a position corresponding to 328 of SEQ ID NO: 10; 15 b) an amino acid sequence having at least 80% sequence identity to SEQ ID NO: 13, wherein said RT comprises at least one of: i) a K at a position corresponding to 306 of SEQ ID NO: 13; ii) an F at a position corresponding to 313 of SEQ ID NO: 13; and iii) a P at a position corresponding to 330 of SEQ ID NO: 13; 20 or c) an amino acid sequence having at least 90% sequence identity to SEQ ID NO: 15, 16 or 17, wherein said RT comprises at least one of: i) an N at a position corresponding to 198 of SEQ ID NO: 15, 16 or 17; ii) a K at a position corresponding to 304 of SEQ ID NO: 15, 16 or 17; 25 iii) an F at a position corresponding to 311 of SEQ ID NO: 15, 16 or 17; and iv) a P at a position corresponding to 328 of SEQ ID NO: 15, 16 or 17.

15. The polynucleotide of claim 13 or 14, wherein said RT comprises: a) an amino acid sequence having at least 75% sequence identity to SEQ ID NO: 10, wherein said RT comprises at least one of: 30 i) an N at a position corresponding to 198 of SEQ ID NO: 10; ii) a K at a position corresponding to 304 of SEQ ID NO: 10; iii) an F at a position corresponding to 311 of SEQ ID NO: 10; and iv) a P at a position corresponding to 328 of SEQ ID NO: 10; b) an amino acid sequence having at least 85% sequence identity to SEQ ID NO: 13, wherein 35 said RT comprises at least one of: i) a K at a position corresponding to 306 of SEQ ID NO: 13; ii) an F at a position corresponding to 313 of SEQ ID NO: 13; and 357 Atty Dkt No: L1034381430WO (00376)iii) a P at a position corresponding to 330 of SEQ ID NO: 13; or c) an amino acid sequence having at least 95% sequence identity to SEQ ID NO: 15, 16 or 17, wherein said RT comprises at least one of: 5 i) an N at a position corresponding to 198 of SEQ ID NO: 15, 16 or 17; ii) a K at a position corresponding to 304 of SEQ ID NO: 15, 16 or 17; iii) an F at a position corresponding to 311 of SEQ ID NO: 15, 16 or 17; and iv) a P at a position corresponding to 328 of SEQ ID NO: 15, 16 or 17.

16. The polynucleotide of any one of claims 13-15, wherein said RT comprises: 10 a) an amino acid sequence having at least 80% sequence identity to SEQ ID NO: 10, wherein said RT comprises at least one of: i) an N at a position corresponding to 198 of SEQ ID NO: 10; ii) a K at a position corresponding to 304 of SEQ ID NO: 10; iii) an F at a position corresponding to 311 of SEQ ID NO: 10; and 15 iv) a P at a position corresponding to 328 of SEQ ID NO: 10; or b) an amino acid sequence having at least 90% sequence identity to SEQ ID NO: 13, wherein said RT comprises at least one of: i) a K at a position corresponding to 306 of SEQ ID NO: 13; 20 ii) an F at a position corresponding to 313 of SEQ ID NO: 13; and iii) a P at a position corresponding to 330 of SEQ ID NO:

13.

17. The polynucleotide of any one of claims 13-16, wherein said RT comprises: a) an amino acid sequence having at least 85% sequence identity to SEQ ID NO: 10, wherein said RT comprises at least one of: 25 i) an N at a position corresponding to 198 of SEQ ID NO: 10; ii) a K at a position corresponding to 304 of SEQ ID NO: 10; iii) an F at a position corresponding to 311 of SEQ ID NO: 10; and iv) a P at a position corresponding to 328 of SEQ ID NO: 10; or 30 b) an amino acid sequence having at least 95% sequence identity to SEQ ID NO: 13, wherein said RT comprises at least one of: i) a K at a position corresponding to 306 of SEQ ID NO: 13; ii) an F at a position corresponding to 313 of SEQ ID NO: 13; and iii) a P at a position corresponding to 330 of SEQ ID NO:

13. 35 18. The polynucleotide of any one of claims 13-17, wherein said RT comprises an amino acid sequence having at least 90% sequence identity to SEQ ID NO: 10, wherein said RT comprises at least one of: 358 Atty Dkt No: L1034381430WO (00376)i) an N at a position corresponding to 198 of SEQ ID NO: 10; ii) a K at a position corresponding to 304 of SEQ ID NO: 10; iii) an F at a position corresponding to 311 of SEQ ID NO: 10; and iv) a P at a position corresponding to 328 of SEQ ID NO:

10. 5 19. The polynucleotide of any one of claims 13-18, wherein said RT comprises an amino acid sequence having at least 95% sequence identity to SEQ ID NO: 10, wherein said RT comprises at least one of: i) an N at a position corresponding to 198 of SEQ ID NO: 10; ii) a K at a position corresponding to 304 of SEQ ID NO: 10; 10 iii) an F at a position corresponding to 311 of SEQ ID NO: 10; and iv) a P at a position corresponding to 328 of SEQ ID NO:

10.

20. The polynucleotide of any one of claims 13-19, wherein said RT comprises the amino acid sequence of any one of SEQ ID NOs: 10-17.

21. A reverse transcriptase (RT), wherein said RT comprises an amino acid sequence 15 having at least 40% sequence identity to SEQ ID NO: 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30, 31, 32, 33, 34, 35, 36, 37, 38, 40, 41, 262, 837, 846, 881, 883, 885, 887, 888, 889, 891, 892, 893, 894, 895, 896, 897, or 898.

22. The RT of claim 21, wherein said RT comprises: (i) an amino acid sequence having at least 40% sequence identity to SEQ ID NO: 35 or 41; 20 (ii) an amino acid sequence having at least 60% sequence identity to SEQ ID NO: 1, 34, or 40; (iii) an amino acid sequence having at least 70% sequence identity to SEQ ID NO: 6, 8, 9, 36, 37, 837, or 846; (iv) an amino acid sequence having at least 75% sequence identity to SEQ ID NO: 4; 25 (v) an amino acid sequence having at least 80% sequence identity to SEQ ID NO: 895 or 897; (vi) an amino acid sequence having at least 83% sequence identity to SEQ ID NO: 18, 19, 20, 21, 22, 23, 892, or 896; (vii) an amino acid sequence having at least 85% sequence identity to SEQ ID NO: 891; (viii) an amino acid sequence having at least 87% sequence identity to SEQ ID NO: 889 or 30 898; (ix) an amino acid sequence having at least 90% sequence identity to SEQ ID NO: 7, 38, 262, 881, 883, or 893; (x) an amino acid sequence having at least 92% sequence identity to SEQ ID NO: 887 or 888; (xi) an amino acid sequence having at least 95% sequence identity to SEQ ID NO: 24, 25, 26, 35 27, 28, 29, 30, 31, 32, 33, 885, or 894; or (xii) an amino acid sequence having at least 99.7% sequence identity to SEQ ID NO: 2, 3, or 5. 59Atty Dkt No: L1034381430WO (00376)23. The RT of claim 21 or 22, wherein said RT comprises: (i) an amino acid sequence having at least 50% sequence identity to SEQ ID NO: 35 or 41; (ii) an amino acid sequence having at least 70% sequence identity to SEQ ID NO: 1, 34, or 40; 5 (iii) an amino acid sequence having at least 75% sequence identity to SEQ ID NO: 6, 8, 9, 36, 37, 837, or 846; (iv) an amino acid sequence having at least 80% sequence identity to SEQ ID NO: 4; (v) an amino acid sequence having at least 85% sequence identity to SEQ ID NO: 895 or 897; (vi) an amino acid sequence having at least 90% sequence identity to SEQ ID NO: 18, 19, 20, 10 21, 22, 23, 889, 891, 892, 896, or 898; or (vii) an amino acid sequence having at least 95% sequence identity to SEQ ID NO: 7, 38, 262, 881, 883, 887, 888, or 893.

24. The RT of any one of claims 21-23, wherein said RT comprises: (i) an amino acid sequence having at least 60% sequence identity to SEQ ID NO: 35 or 41; 15 (ii) an amino acid sequence having at least 75% sequence identity to SEQ ID NO: 1, 34, or 40; (iii) an amino acid sequence having at least 80% sequence identity to SEQ ID NO: 6, 8, 9, 36, 37, 837, or 846; (iv) an amino acid sequence having at least 85% sequence identity to SEQ ID NO: 4; 20 (v) an amino acid sequence having at least 90% sequence identity to SEQ ID NO: 895 or 897; or (vi) an amino acid sequence having at least 95% sequence identity to SEQ ID NO: 18, 19, 20, 21, 22, 23, 889, 891, 892, 896, or 898.

25. The RT of any one of claims 21-24, wherein said RT comprises: 25 (i) an amino acid sequence having at least 70% sequence identity to SEQ ID NO: 35 or 41; (ii) an amino acid sequence having at least 80% sequence identity to SEQ ID NO: 1, 34, or 40; (iii) an amino acid sequence having at least 85% sequence identity to SEQ ID NO: 6, 8, 9, 36, 37, 837, or 846; 30 (iv) an amino acid sequence having at least 90% sequence identity to SEQ ID NO: 4; or (v) an amino acid sequence having at least 95% sequence identity to SEQ ID NO: 895 or 897.

26. The RT of any one of claims 21-25, wherein said RT comprises: (i) an amino acid sequence having at least 80% sequence identity to SEQ ID NO: 35 or 41; (ii) an amino acid sequence having at least 85% sequence identity to SEQ ID NO: 1, 34, or 35 40; (iii) an amino acid sequence having at least 90% sequence identity to SEQ ID NO: 6, 8, 9, 36, 37, 837, or 846; or 360 Atty Dkt No: L1034381430WO (00376)(iv) an amino acid sequence having at least 95% sequence identity to SEQ ID NO:

4.

27. The RT of any one of claims 21-26, wherein said RT comprises: (i) an amino acid sequence having at least 85% sequence identity to SEQ ID NO: 35 or 41; (ii) an amino acid sequence having at least 90% sequence identity to SEQ ID NO: 1, 34, or 5 40; or (iii) an amino acid sequence having at least 95% sequence identity to SEQ ID NO: 6, 8, 9, 36, 37, 837, or 846.

28. The RT of any one of claims 21-27, wherein said RT comprises: (i) an amino acid sequence having at least 90% sequence identity to SEQ ID NO: 35 or 41; or 10 (ii) an amino acid sequence having at least 95% sequence identity to SEQ ID NO: 1, 34, or 40.

29. The RT of any one of claims 21-28, wherein said RT comprises an amino acid sequence having at least 95% sequence identity to SEQ ID NO: 35 or 41.

30. The RT of any one of claims 21-29, wherein said RT comprises the amino acid 15 sequence of any one of SEQ ID NOs: 1-9, 18-41, 262, 837, 846, 881, 883, 885, 887, 888, 889, 891, 892, 893, 894, 895, 896, 897, and 898.

31. The RT of any one of claims 21-30, wherein said RT lacks an RNase H domain.

32. The RT of any one of claims 21-31, wherein said RT comprises at least one of: a) an N at a position corresponding to 200 of SEQ ID NO: 42; 20 b) a P at a position corresponding to 330 of SEQ ID NO: 42; c) a K at a position corresponding to 306 of SEQ ID NO: 42; and d) an F at a position corresponding to 313 of SEQ ID NO:

42.

33. The RT of any one of claims 21-32, wherein said RT comprises: a) an amino acid sequence having at least 60% sequence identity to SEQ ID NO: 10, wherein 25 said RT comprises at least one of: i) an N at a position corresponding to 198 of SEQ ID NO: 10; ii) a K at a position corresponding to 304 of SEQ ID NO: 10; iii) an F at a position corresponding to 311 of SEQ ID NO: 10; and iv) a P at a position corresponding to 328 of SEQ ID NO: 10; 30 b) an amino acid sequence having at least 99.5% sequence identity to SEQ ID NO: 11 or 12, wherein said RT comprises at least one of: i) an N at a position corresponding to 199 of SEQ ID NO: 11 or 12; ii) a K at a position corresponding to 305 of SEQ ID NO: 11 or 12; iii) an F at a position corresponding to 312 of SEQ ID NO: 11 or 12; and 35 iv) a P at a position corresponding to 329 of SEQ ID NO: 11 or 12; c) an amino acid sequence having at least 72% sequence identity to SEQ ID NO: 13, wherein said RT comprises at least one of: 361 Atty Dkt No: L1034381430WO (00376)i) a K at a position corresponding to 306 of SEQ ID NO: 13; ii) an F at a position corresponding to 313 of SEQ ID NO: 13; and iii) a P at a position corresponding to 330 of SEQ ID NO: 13; d) an amino acid sequence having at least 99.5% sequence identity to SEQ ID NO: 14, 5 wherein said RT comprises at least one of: i) an N at a position corresponding to 198 of SEQ ID NO: 14; ii) a K at a position corresponding to 304 of SEQ ID NO: 14; iii) an F at a position corresponding to 311 of SEQ ID NO: 14; and iv) a P at a position corresponding to 328 of SEQ ID NO: 14; 10 or e) an amino acid sequence having at least 87% sequence identity to SEQ ID NO: 15, 16 or 17, wherein said RT comprises at least one of: i) an N at a position corresponding to 198 of SEQ ID NO: 15, 16 or 17; ii) a K at a position corresponding to 304 of SEQ ID NO: 15, 16 or 17; 15 iii) an F at a position corresponding to 311 of SEQ ID NO: 15, 16 or 17; and iv) a P at a position corresponding to 328 of SEQ ID NO: 15, 16 or 17.

34. The RT of claim 33, wherein said RT comprises: a) an amino acid sequence having at least 70% sequence identity to SEQ ID NO: 10, wherein said RT comprises at least one of: 20 i) an N at a position corresponding to 198 of SEQ ID NO: 10; ii) a K at a position corresponding to 304 of SEQ ID NO: 10; iii) an F at a position corresponding to 311 of SEQ ID NO: 10; and iv) a P at a position corresponding to 328 of SEQ ID NO: 10; b) an amino acid sequence having at least 80% sequence identity to SEQ ID NO: 13, wherein 25 said RT comprises at least one of: i) a K at a position corresponding to 306 of SEQ ID NO: 13; ii) an F at a position corresponding to 313 of SEQ ID NO: 13; and iii) a P at a position corresponding to 330 of SEQ ID NO: 13; or 30 c) an amino acid sequence having at least 90% sequence identity to SEQ ID NO: 15, 16 or 17, wherein said RT comprises at least one of: i) an N at a position corresponding to 198 of SEQ ID NO: 15, 16 or 17; ii) a K at a position corresponding to 304 of SEQ ID NO: 15, 16 or 17; iii) an F at a position corresponding to 311 of SEQ ID NO: 15, 16 or 17; and 35 iv) a P at a position corresponding to 328 of SEQ ID NO: 15, 16 or 17.

35. The RT of claim 33 or 34, wherein said RT comprises: 362 Atty Dkt No: L1034381430WO (00376)a) an amino acid sequence having at least 75% sequence identity to SEQ ID NO: 10, wherein said RT comprises at least one of: i) an N at a position corresponding to 198 of SEQ ID NO: 10; ii) a K at a position corresponding to 304 of SEQ ID NO: 10; 5 iii) an F at a position corresponding to 311 of SEQ ID NO: 10; and iv) a P at a position corresponding to 328 of SEQ ID NO: 10; b) an amino acid sequence having at least 85% sequence identity to SEQ ID NO: 13, wherein said RT comprises at least one of: i) a K at a position corresponding to 306 of SEQ ID NO: 13; 10 ii) an F at a position corresponding to 313 of SEQ ID NO: 13; and iii) a P at a position corresponding to 330 of SEQ ID NO: 13; or c) an amino acid sequence having at least 95% sequence identity to SEQ ID NO: 15, 16 or 17, wherein said RT comprises at least one of: 15 i) an N at a position corresponding to 198 of SEQ ID NO: 15, 16 or 17; ii) a K at a position corresponding to 304 of SEQ ID NO: 15, 16 or 17; iii) an F at a position corresponding to 311 of SEQ ID NO: 15, 16 or 17; and iv) a P at a position corresponding to 328 of SEQ ID NO: 15, 16 or 17.

36. The RT of any one of claims 33-35, wherein said RT comprises: 20 a) an amino acid sequence having at least 80% sequence identity to SEQ ID NO: 10, wherein said RT comprises at least one of: i) an N at a position corresponding to 198 of SEQ ID NO: 10; ii) a K at a position corresponding to 304 of SEQ ID NO: 10; iii) an F at a position corresponding to 311 of SEQ ID NO: 10; and 25 iv) a P at a position corresponding to 328 of SEQ ID NO: 10; or b) an amino acid sequence having at least 90% sequence identity to SEQ ID NO: 13, wherein said RT comprises at least one of: i) a K at a position corresponding to 306 of SEQ ID NO: 13; 30 ii) an F at a position corresponding to 313 of SEQ ID NO: 13; and iii) a P at a position corresponding to 330 of SEQ ID NO:

13.

37. The RT of any one of claims 33-36, wherein said RT comprises: a) an amino acid sequence having at least 85% sequence identity to SEQ ID NO: 10, wherein said RT comprises at least one of: 35 i) an N at a position corresponding to 198 of SEQ ID NO: 10; ii) a K at a position corresponding to 304 of SEQ ID NO: 10; iii) an F at a position corresponding to 311 of SEQ ID NO: 10; and 363 Atty Dkt No: L1034381430WO (00376)iv) a P at a position corresponding to 328 of SEQ ID NO: 10; or b) an amino acid sequence having at least 95% sequence identity to SEQ ID NO: 13, wherein said RT comprises at least one of: 5 i) a K at a position corresponding to 306 of SEQ ID NO: 13; ii) an F at a position corresponding to 313 of SEQ ID NO: 13; and iii) a P at a position corresponding to 330 of SEQ ID NO:

13.

38. The RT of any one of claims 33-37, wherein said RT comprises an amino acid sequence having at least 90% sequence identity to SEQ ID NO: 10, wherein said RT comprises at 10 least one of: i) an N at a position corresponding to 198 of SEQ ID NO: 10; ii) a K at a position corresponding to 304 of SEQ ID NO: 10; iii) an F at a position corresponding to 311 of SEQ ID NO: 10; and iv) a P at a position corresponding to 328 of SEQ ID NO:

10. 15 39. The RT of any one of claims 33-38, wherein said RT comprises an amino acid sequence having at least 95% sequence identity to SEQ ID NO: 10, wherein said RT comprises at least one of: i) an N at a position corresponding to 198 of SEQ ID NO: 10; ii) a K at a position corresponding to 304 of SEQ ID NO: 10; 20 iii) an F at a position corresponding to 311 of SEQ ID NO: 10; and iv) a P at a position corresponding to 328 of SEQ ID NO:

10.

40. The RT of any one of claims 33-39, wherein said RT comprises the amino acid sequence of any one of SEQ ID NOs: 10-17.

41. A polynucleotide encoding a fusion protein comprising a reverse transcriptase (RT) 25 operably fused to at least one heterologous polypeptide, wherein said RT comprises an amino acid sequence having at least 40% sequence identity to SEQ ID NO: 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30, 31, 32, 33, 34, 35, 36, 37, 38, 40, 41, 262, 837, 846, 881, 883, 885, 887, 888, 889, 891, 892, 893, 894, 895, 896, 897, or 898.

42. The polynucleotide of claim 41, wherein said RT comprises: 30 (i) an amino acid sequence having at least 40% sequence identity to SEQ ID NO: 35 or 41; (ii) an amino acid sequence having at least 60% sequence identity to SEQ ID NO: 1, 34, or 40; (iii) an amino acid sequence having at least 70% sequence identity to SEQ ID NO: 6, 8, 9, 36, 37, 837, or 846; 35 (iv) an amino acid sequence having at least 75% sequence identity to SEQ ID NO: 4; (v) an amino acid sequence having at least 80% sequence identity to SEQ ID NO: 895 or 897; 364 Atty Dkt No: L1034381430WO (00376)(vi) an amino acid sequence having at least 83% sequence identity to SEQ ID NO: 18, 19, 20, 21, 22, 23, 892, or 896; (vii) an amino acid sequence having at least 85% sequence identity to SEQ ID NO: 891; (viii) an amino acid sequence having at least 87% sequence identity to SEQ ID NO: 889 or 5 898; (ix) an amino acid sequence having at least 90% sequence identity to SEQ ID NO: 7, 38, 262, 881, 883, or 893; (x) an amino acid sequence having at least 92% sequence identity to SEQ ID NO: 887 or 888; (xi) an amino acid sequence having at least 95% sequence identity to SEQ ID NO: 24, 25, 26, 10 27, 28, 29, 30, 31, 32, 33, 885, or 894; or (xii) an amino acid sequence having at least 99.7% sequence identity to SEQ ID NO: 2, 3, or 5.

43. The polynucleotide of claim 41 or 42, wherein said RT comprises: (i) an amino acid sequence having at least 50% sequence identity to SEQ ID NO: 35 or 41; 15 (ii) an amino acid sequence having at least 70% sequence identity to SEQ ID NO: 1, 34, or 40; (iii) an amino acid sequence having at least 75% sequence identity to SEQ ID NO: 6, 8, 9, 36, 37, 837, or 846; (iv) an amino acid sequence having at least 80% sequence identity to SEQ ID NO: 4; 20 (v) an amino acid sequence having at least 85% sequence identity to SEQ ID NO: 895 or 897; (vi) an amino acid sequence having at least 90% sequence identity to SEQ ID NO: 18, 19, 20, 21, 22, 23, 889, 891, 892, 896, or 898; or (vii) an amino acid sequence having at least 95% sequence identity to SEQ ID NO: 7, 38, 262, 881, 883, 887, 888, or 893. 25 44. The polynucleotide of any one of claims 41-43, wherein said RT comprises: (i) an amino acid sequence having at least 60% sequence identity to SEQ ID NO: 35 or 41; (ii) an amino acid sequence having at least 75% sequence identity to SEQ ID NO: 1, 34, or 40; (iii) an amino acid sequence having at least 80% sequence identity to SEQ ID NO: 6, 8, 9, 36, 30 37, 837, or 846; (iv) an amino acid sequence having at least 85% sequence identity to SEQ ID NO: 4; (v) an amino acid sequence having at least 90% sequence identity to SEQ ID NO: 895 or 897; or (vi) an amino acid sequence having at least 95% sequence identity to SEQ ID NO: 18, 19, 20, 35 21, 22, 23, 889, 891, 892, 896, or 898.

45. The polynucleotide of any one of claims 41-44, wherein said RT comprises: (i) an amino acid sequence having at least 70% sequence identity to SEQ ID NO: 35 or 41; 365 Atty Dkt No: L1034381430WO (00376)(ii) an amino acid sequence having at least 80% sequence identity to SEQ ID NO: 1, 34, or 40; (iii) an amino acid sequence having at least 85% sequence identity to SEQ ID NO: 6, 8, 9, 36, 37, 837, or 846; 5 (iv) an amino acid sequence having at least 90% sequence identity to SEQ ID NO: 4; or (v) an amino acid sequence having at least 95% sequence identity to SEQ ID NO: 895 or 897.

46. The polynucleotide of any one of claims 41-45, wherein said RT comprises: (i) an amino acid sequence having at least 80% sequence identity to SEQ ID NO: 35 or 41; (ii) an amino acid sequence having at least 85% sequence identity to SEQ ID NO: 1, 34, or 10 40; (iii) an amino acid sequence having at least 90% sequence identity to SEQ ID NO: 6, 8, 9, 36, 37, 837, or 846; or (iv) an amino acid sequence having at least 95% sequence identity to SEQ ID NO:

4.

47. The polynucleotide of any one of claims 41-46, wherein said RT comprises: 15 (i) an amino acid sequence having at least 85% sequence identity to SEQ ID NO: 35 or 41; (ii) an amino acid sequence having at least 90% sequence identity to SEQ ID NO: 1, 34, or 40; or (iii) an amino acid sequence having at least 95% sequence identity to SEQ ID NO: 6, 8, 9, 36, 37, 837, or 846. 20 48. The polynucleotide of any one of claims 41-47, wherein said RT comprises: (i) an amino acid sequence having at least 90% sequence identity to SEQ ID NO: 35 or 41; or (ii) an amino acid sequence having at least 95% sequence identity to SEQ ID NO: 1, 34, or 40.

49. The polynucleotide of any one of claims 41-48, wherein said RT comprises an amino 25 acid sequence having at least 95% sequence identity to SEQ ID NO: 35 or 41.

50. The polynucleotide of any one of claims 41-49, wherein said RT comprises the amino acid sequence of any one of SEQ ID NO: 1-9, 18-41, 262, 837, 846, 881, 883, 885, 887, 888, 889, 891, 892, 893, 894, 895, 896, 897, and 898.

51. The polynucleotide of any one of claims 41-50, wherein said RT lacks an RNase H 30 domain.

52. The polynucleotide of any one of claims 41-51, wherein said RT comprises: a) an N at a position corresponding to 200 of SEQ ID NO: 42; b) a P at a position corresponding to 330 of SEQ ID NO: 42; c) a K at a position corresponding to 306 of SEQ ID NO: 42; and 35 d) an F at a position corresponding to 313 of SEQ ID NO:

42.

53. The polynucleotide of any one of claims 41-52, wherein said RT comprises: 366 Atty Dkt No: L1034381430WO (00376)a) an amino acid sequence having at least 60% sequence identity to SEQ ID NO: 10, wherein said RT comprises at least one of: i) an N at a position corresponding to 198 of SEQ ID NO: 10; ii) a K at a position corresponding to 304 of SEQ ID NO: 10; 5 iii) an F at a position corresponding to 311 of SEQ ID NO: 10; and iv) a P at a position corresponding to 328 of SEQ ID NO: 10; b) an amino acid sequence having at least 99.5% sequence identity to SEQ ID NO: 11 or 12, wherein said RT comprises at least one of: i) an N at a position corresponding to 199 of SEQ ID NO: 11 or 12; 10 ii) a K at a position corresponding to 305 of SEQ ID NO: 11 or 12; iii) an F at a position corresponding to 312 of SEQ ID NO: 11 or 12; and iv) a P at a position corresponding to 329 of SEQ ID NO: 11 or 12; c) an amino acid sequence having at least 72% sequence identity to SEQ ID NO: 13, wherein said RT comprises at least one of: 15 i) a K at a position corresponding to 306 of SEQ ID NO: 13; ii) an F at a position corresponding to 313 of SEQ ID NO: 13; and iii) a P at a position corresponding to 330 of SEQ ID NO: 13; d) an amino acid sequence having at least 99.5% sequence identity to SEQ ID NO: 14, wherein said RT comprises at least one of: 20 i) an N at a position corresponding to 198 of SEQ ID NO: 14; ii) a K at a position corresponding to 304 of SEQ ID NO: 14; iii) an F at a position corresponding to 311 of SEQ ID NO: 14; and iv) a P at a position corresponding to 328 of SEQ ID NO: 14; or 25 e) an amino acid sequence having at least 87% sequence identity to SEQ ID NO: 15, 16 or 17, wherein said RT comprises at least one of: i) an N at a position corresponding to 198 of SEQ ID NO: 15, 16 or 17; ii) a K at a position corresponding to 304 of SEQ ID NO: 15, 16 or 17; iii) an F at a position corresponding to 311 of SEQ ID NO: 15, 16 or 17; and 30 iv) a P at a position corresponding to 328 of SEQ ID NO: 15, 16 or 17.

54. The polynucleotide of claim 53, wherein said RT comprises: a) an amino acid sequence having at least 70% sequence identity to SEQ ID NO: 10, wherein said RT comprises at least one of: i) an N at a position corresponding to 198 of SEQ ID NO: 10; 35 ii) a K at a position corresponding to 304 of SEQ ID NO: 10; iii) an F at a position corresponding to 311 of SEQ ID NO: 10; and iv) a P at a position corresponding to 328 of SEQ ID NO: 10; 367 Atty Dkt No: L1034381430WO (00376)b) an amino acid sequence having at least 80% sequence identity to SEQ ID NO: 13, wherein said RT comprises at least one of: i) a K at a position corresponding to 306 of SEQ ID NO: 13; ii) an F at a position corresponding to 313 of SEQ ID NO: 13; and 5 iii) a P at a position corresponding to 330 of SEQ ID NO: 13; or c) an amino acid sequence having at least 90% sequence identity to SEQ ID NO: 15, 16 or 17, wherein said RT comprises at least one of: i) an N at a position corresponding to 198 of SEQ ID NO: 15, 16 or 17; 10 ii) a K at a position corresponding to 304 of SEQ ID NO: 15, 16 or 17; iii) an F at a position corresponding to 311 of SEQ ID NO: 15, 16 or 17; and iv) a P at a position corresponding to 328 of SEQ ID NO: 15, 16 or 17.

55. The polynucleotide of claim 53 or 54, wherein said RT comprises: a) an amino acid sequence having at least 75% sequence identity to SEQ ID NO: 10, wherein 15 said RT comprises at least one of: i) an N at a position corresponding to 198 of SEQ ID NO: 10; ii) a K at a position corresponding to 304 of SEQ ID NO: 10; iii) an F at a position corresponding to 311 of SEQ ID NO: 10; and iv) a P at a position corresponding to 328 of SEQ ID NO: 10; 20 b) an amino acid sequence having at least 85% sequence identity to SEQ ID NO: 13, wherein said RT comprises at least one of: i) a K at a position corresponding to 306 of SEQ ID NO: 13; ii) an F at a position corresponding to 313 of SEQ ID NO: 13; and iii) a P at a position corresponding to 330 of SEQ ID NO: 13; 25 or c) an amino acid sequence having at least 95% sequence identity to SEQ ID NO: 15, 16 or 17, wherein said RT comprises at least one of: i) an N at a position corresponding to 198 of SEQ ID NO: 15, 16 or 17; ii) a K at a position corresponding to 304 of SEQ ID NO: 15, 16 or 17; 30 iii) an F at a position corresponding to 311 of SEQ ID NO: 15, 16 or 17; and iv) a P at a position corresponding to 328 of SEQ ID NO: 15, 16 or 17.

56. The polynucleotide of any one of claims 53-55, wherein said RT comprises: a) an amino acid sequence having at least 80% sequence identity to SEQ ID NO: 10, wherein said RT comprises at least one of: 35 i) an N at a position corresponding to 198 of SEQ ID NO: 10; ii) a K at a position corresponding to 304 of SEQ ID NO: 10; iii) an F at a position corresponding to 311 of SEQ ID NO: 10; and 368 Atty Dkt No: L1034381430WO (00376)iv) a P at a position corresponding to 328 of SEQ ID NO: 10; or b) an amino acid sequence having at least 90% sequence identity to SEQ ID NO: 13, wherein said RT comprises at least one of: 5 i) a K at a position corresponding to 306 of SEQ ID NO: 13; ii) an F at a position corresponding to 313 of SEQ ID NO: 13; and iii) a P at a position corresponding to 330 of SEQ ID NO:

13.

57. The polynucleotide of any one of claims 53-56, wherein said RT comprises: a) an amino acid sequence having at least 85% sequence identity to SEQ ID NO: 10, wherein 10 said RT comprises at least one of: i) an N at a position corresponding to 198 of SEQ ID NO: 10; ii) a K at a position corresponding to 304 of SEQ ID NO: 10; iii) an F at a position corresponding to 311 of SEQ ID NO: 10; and iv) a P at a position corresponding to 328 of SEQ ID NO: 10; 15 or b) an amino acid sequence having at least 95% sequence identity to SEQ ID NO: 13, wherein said RT comprises at least one of: i) a K at a position corresponding to 306 of SEQ ID NO: 13; ii) an F at a position corresponding to 313 of SEQ ID NO: 13; and 20 iii) a P at a position corresponding to 330 of SEQ ID NO:

13.

58. The polynucleotide of any one of claims 53-57, wherein said RT comprises an amino acid sequence having at least 90% sequence identity to SEQ ID NO: 10, wherein said RT comprises at least one of: i) an N at a position corresponding to 198 of SEQ ID NO: 10; 25 ii) a K at a position corresponding to 304 of SEQ ID NO: 10; iii) an F at a position corresponding to 311 of SEQ ID NO: 10; and iv) a P at a position corresponding to 328 of SEQ ID NO:

10.

59. The polynucleotide of any one of claims 53-58, wherein said RT comprises an amino acid sequence having at least 95% sequence identity to SEQ ID NO: 10, wherein said RT comprises at 30 least one of: i) an N at a position corresponding to 198 of SEQ ID NO: 10; ii) a K at a position corresponding to 304 of SEQ ID NO: 10; iii) an F at a position corresponding to 311 of SEQ ID NO: 10; and iv) a P at a position corresponding to 328 of SEQ ID NO:

10. 35 60. The polynucleotide of any one of claims 53-59, wherein said RT comprises the amino acid sequence of any one of SEQ ID NOs: 10-17. 369 Atty Dkt No: L1034381430WO (00376)61. The polynucleotide of any one of claims 41-60, wherein said at least one heterologous polypeptide comprises a DNA-binding polypeptide or a polymerase editor (PE)-enhancing polypeptide.

62. The polynucleotide of any one of claims 41-60, wherein said at least one heterologous 5 polypeptide comprises a DNA-binding polypeptide and a PE-enhancing polypeptide.

63. The polynucleotide of claim 61 or 62, wherein said RT is operably fused to the N- terminus of said DNA-binding polypeptide or to the N-terminus of said PE-enhancing polypeptide.

64. The polynucleotide of claim 61 or 62, wherein said RT is operably fused to the C- terminus of said DNA-binding polypeptide or to the C-terminus of said PE-enhancing polypeptide. 10 65. The polynucleotide of claim 62, wherein said fusion protein comprises from amino terminus to carboxy terminus: said RT, said PE-enhancing polypeptide, and said DNA-binding polypeptide.

66. The polynucleotide of claim 62, wherein said fusion protein comprises from amino terminus to carboxy terminus: said RT, said DNA-binding polypeptide, and said PE-enhancing 15 polypeptide.

67. The polynucleotide of claim 62, wherein said PE comprises from amino terminus to carboxy terminus: said DNA-binding polypeptide, said RT, and said PE-enhancing polypeptide.

68. The polynucleotide of claim 62, wherein said PE comprises from amino terminus to carboxy terminus: said DNA-binding polypeptide, said PE-enhancing polypeptide, and said RT. 20 69. The polynucleotide of claim 62, wherein said fusion protein comprises from amino terminus to carboxy terminus: said PE-enhancing polypeptide, said RT, and said DNA-binding polypeptide.

70. The polynucleotide of claim 62, wherein said fusion protein comprises from amino terminus to carboxy terminus: said PE-enhancing polypeptide, said DNA-binding polypeptide, and 25 said RT.

71. The polynucleotide of claim 61 or 62, wherein said fusion protein comprises one or more nuclear localization signal (NLS).

72. The polynucleotide of claim 71, wherein said one or more NLS is operably fused at the N-terminus, C-terminus, or both the N-terminus and C-terminus of said RT, said DNA-binding 30 polypeptide, or said PE-enhancing polypeptide.

73. The polynucleotide of claim 71 or 72, wherein said one or more NLS is selected from the group consisting of SEQ ID NOs: 425-430.

74. The polynucleotide of claim 61 or 62, wherein said fusion protein further comprises one or more peptide linker. 35 75. The polynucleotide of claim 74, wherein said one or more peptide linker comprises at least one NLS. 370 Atty Dkt No: L1034381430WO (00376)76. The polynucleotide of claim 75, wherein said one or more peptide linker comprises two NLSs.

77. The polynucleotide of any one of claims 74-76, wherein said one or more peptide linker is operably fused at the N-terminus, C-terminus, or both the N-terminus and C-terminus of said 5 RT, said DNA-binding polypeptide, or said PE-enhancing polypeptide.

78. The polynucleotide of any one of claims 74-77, wherein said one or more peptide linker has a formula of –[(SGGS)x-NLS]m-(SGGS)y-, wherein x or y is 0, 1, 2, 3, or 4, and m is 1, 2, 3, or 4.

79. The polynucleotide of any one of claims 74-77, wherein said one or more peptide 10 linker has a formula of –[(SGGS)x-NLS]m-(SGGS)y-, wherein x or y is 1, and m is 1, 2, 3, or 4.

80. The polynucleotide of any one of claims 74-77, wherein said one or more peptide linker has a formula of –[(SGGS)x-NLS]m-(SGGS)y-, wherein x is 1, y is 1, and m is 1, 2, 3, or 4.

81. The polynucleotide of any one of claims 74-77, wherein said one or more peptide linker has a formula of –[(SGGS)x-NLS]m-(SGGS)y-, wherein x is 1, y is 1, and m is 1. 15 82. The polynucleotide of any one of claims 74-77, wherein said one or more peptide linker has a formula of –[(SGGS)x-NLS]m-(SGGS)y-, wherein x is 1, y is 1, and m is 2.

83. The polynucleotide of any one of claims 74-77, wherein said one or more peptide linker has a formula of –[(SGGS)x-NLS]m-(SGGS)y-, wherein x is 1, y is 1, and m is 3.

84. The polynucleotide of any one of claims 74-77, wherein said one or more peptide 20 linker has a formula of –[(SGGS)x-NLS]m-(SGGS)y-, wherein x is 1, y is 1, and m is 4.

85. The polynucleotide of any one of claims 74-77, wherein said one or more peptide linker has a formula of –(SGGS)x-NLSm-(SGGS)y-NLSn-(SGGS)z-, wherein each of x, y, or z is 0, 1, 2, 3, or 4; and wherein each of m or n is 0 or 1.

86. The polynucleotide of any one of claims 74-77, wherein said one or more peptide 25 linker has a formula of –(SGGS)x-NLSm-(SGGS)y-NLSn-(SGGS)z-, wherein each of x or z is 0, 1, 2, 3, or 4, and y is 0; and wherein one of m or n is 0, and the other is 1.

87. The polynucleotide of any one of claims 74-77, wherein said one or more peptide linker has a formula of –(SGGS)x-NLSm-(SGGS)y-NLSn-(SGGS)z-, wherein each of x, y, or z is 0, 1, 2, 3, or 4; and wherein each of m or n is 1, and y is not 0. 30 88. The polynucleotide of any one of claims 74-77, wherein said one or more peptide linker has a length of 42 amino acids.

89. The polynucleotide of any one of claims 74-77, wherein said one or more peptide linker has a length of more than or equal to 13 amino acids.

90. The polynucleotide of any one of claims 74-77, wherein said one or more peptide 35 linker comprises one or more copies of amino acid sequence SGGS.

91. The polynucleotide of claim 74, wherein said one or more peptide linker has the sequence of any one of SEQ ID NOs: 431-436, and 935-937. 371 Atty Dkt No: L1034381430WO (00376)92. The polynucleotide of any one of claims 41-91, wherein said DNA-binding polypeptide is an RNA-guided nuclease (RGN) polypeptide.

93. The polynucleotide of claim 92, wherein said RT is operably fused to an internal location of said RGN polypeptide. 5 94. The polynucleotide of claim 93, wherein said RT is operably fused within a linker domain 2, a wedge domain, a RuvC domain, an HNH domain, a Rec-2 domain, or a PAM-interacting domain of said RGN polypeptide, or wherein said RT is operably fused between a linker domain 2, a wedge domain, a RuvC domain, an HNH domain, a Rec-2 domain, or a PAM-interacting domain of said RGN polypeptide and another domain N-terminal or C-terminal to said linker domain 2, said 10 wedge domain, said RuvC domain, said HNH domain, said Rec-2 domain, or said PAM-interacting domain.

95. The polynucleotide of claim 94, wherein said RuvC domain is a RuvCIII domain.

96. The polynucleotide of claim 95, wherein said RT is operably fused within a linker domain 2, a wedge domain, or a RuvCIII domain of said RGN polypeptide. 15 97. The polynucleotide of claim 93, wherein said RT is operably fused within said RGN polypeptide immediately after an amino acid at a position selected from the group consisting of: a) an amino acid position corresponding to position 678 of SEQ ID NO: 388; b) an amino acid position corresponding to position 736 of SEQ ID NO: 388; c) an amino acid position corresponding to position 922 of SEQ ID NO: 388; 20 d) an amino acid position corresponding to position 642 of SEQ ID NO: 387, 389, 392, 393, 394, or 395; e) an amino acid position corresponding to position 772 of SEQ ID NO: 387, 389, 392, 393, 394, or 395; f) an amino acid position corresponding to position 739 of SEQ ID NO: 391; 25 g) an amino acid position corresponding to position 744 of SEQ ID NO: 391; h) an amino acid position corresponding to position 680 of SEQ ID NO: 390; i) an amino acid position corresponding to position 785 of SEQ ID NO: 390; and j) an amino acid position corresponding to position 910 of SEQ ID NO:

390.

98. The polynucleotide of any one of claims 92-97, wherein said RGN polypeptide is 30 capable of binding a target sequence in a target polynucleotide in an RNA-guided sequence specific manner when bound to a guide RNA (gRNA), wherein said target sequence comprises a target strand and a non-target strand, and wherein said gRNA is capable of hybridizing to the target strand of the target sequence.

99. The polynucleotide of claim 98, wherein said RGN polypeptide recognizes a 35 protospacer adjacent motif (PAM) that is 3′ of said target sequence.

100. The polynucleotide of claim 99, wherein: 372 Atty Dkt No: L1034381430WO (00376)a) said RGN polypeptide comprising an amino acid sequence having at least 90% sequence identity to SEQ ID NO: 388 recognizes a PAM having a consensus nucleotide sequence set forth as NNRYA; b) said RGN polypeptide comprising an amino acid sequence having at least 90% 5 sequence identity to SEQ ID NO: 389 recognizes a PAM having a consensus nucleotide sequence set forth as NNNNCC; c) said RGN polypeptide comprising an amino acid sequence having at least 90% sequence identity to SEQ ID NO: 391 recognizes a PAM having a consensus nucleotide sequence set forth as NNGRR; or 10 d) said RGN polypeptide comprising an amino acid sequence having at least 90% sequence identity to SEQ ID NO: 390 recognizes a PAM having a consensus nucleotide sequence set forth as NNGG.

101. The polynucleotide of any one of claims 98-100, wherein said RGN polypeptide is capable of cleaving said target polynucleotide upon binding. 15 102. The polynucleotide of claim 101, wherein said RGN polypeptide is capable of generating a double-stranded break.

103. The polynucleotide of claim 101, wherein said RGN polypeptide is capable of generating a single-stranded break.

104. The polynucleotide of any one of claims 92-100, wherein said RGN polypeptide 20 comprises an HNH domain with at least one mutation that reduces or eliminates its nuclease activity.

105. The polynucleotide of any one of claims 92-100, wherein said RGN polypeptide comprises an HNH domain with at least two mutations that reduces or eliminates its nuclease activity.

106. The polynucleotide of any one of claims 92-100, wherein said RGN polypeptide does not comprise an HNH domain. 25 107. The polynucleotide of claim 106, wherein said HNH domain of said RGN polypeptide has been replaced with said RT.

108. The polynucleotide of any one of claims 92-100, wherein said RGN polypeptide is nuclease inactive.

109. The polynucleotide of any one of claims 92-100, wherein said RGN polypeptide 30 comprises an RGN nickase.

110. The polynucleotide of claim 109, wherein said RGN nickase comprises an amino acid sequence having at least 90% sequence identity to any one of SEQ ID NOs: 411-420.

111. The polynucleotide of claim 110, wherein said RGN nickase comprises an amino acid sequence having at least 95% sequence identity to any one of SEQ ID NOs: 411-420. 35 112. The polynucleotide of claim 110 or 111, wherein said RGN nickase comprises the amino acid sequence of any one of SEQ ID NOs: 411-420. 373 Atty Dkt No: L1034381430WO (00376)113. The polynucleotide of any one of claims 92-112, wherein said RGN polypeptide comprises an amino acid sequence having at least 90% sequence identity to any one of SEQ ID NOs: 387-420.

114. The polynucleotide of claim 113, wherein said RGN polypeptide comprises an amino 5 acid sequence having at least 95% sequence identity to any one of SEQ ID NOs: 387-420.

115. The one or more polynucleotides of claim 113 or 114, wherein said RGN polypeptide comprises the amino acid sequence of any one of SEQ ID NOs: 387-420.

116. The polynucleotide of any one of claims 61-115, wherein said PE-enhancing polypeptide is a single-stranded RNA (ssRNA) binding protein. 10 117. The polynucleotide of claim 116, wherein said ssRNA binding protein comprises an amino acid sequence having at least 90% sequence identity to any one of SEQ ID NOs: 335, 336, 337, 338, 339, 340, 341, 342, 343, 344, 482, and 483.

118. The polynucleotide of claim 117, wherein said ssRNA binding protein comprises an amino acid sequence having at least 95% sequence identity to any one of SEQ ID NOs: 335, 336, 337, 15 338, 339, 340, 341, 342, 343, 344, 482, and 483.

119. The polynucleotide of claim 117 or 118, wherein said ssRNA binding protein comprises the amino acid sequence of any one of SEQ ID NOs: 335, 336, 337, 338, 339, 340, 341, 342, 343, 344, 482, and 483.

120. The polynucleotide of any one of claims 61-115, wherein said PE-enhancing 20 polypeptide is a single-stranded DNA (ssDNA) binding protein.

121. The polynucleotide of claim 120, wherein said ssDNA binding protein comprises an amino acid sequence having at least 90% sequence identity to any one of SEQ ID NOs: 359, 360, 361, 362, 363, 364, 365, and 371.

122. The polynucleotide of claim 121, wherein said ssDNA binding protein comprises an 25 amino acid sequence having at least 95% sequence identity to any one of SEQ ID NOs: 359, 360, 361, 362, 363, 364, 365, and 371.

123. The polynucleotide of claim 121 or 122, wherein said ssDNA binding protein comprises the amino acid sequence of any one of SEQ ID NOs: 359, 360, 361, 362, 363, 364, 365, and 371. 30 124. A polynucleotide encoding a fusion protein comprising a reverse transcriptase (RT) and a DNA-binding polypeptide, wherein the RT comprises an amino acid sequence having at least 40% sequence identity to SEQ ID NO: 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30, 31, 32, 33, 34, 35, 36, 37, 38, 40, 41, 262, 837, 846, 881, 883, 885, 887, 888, 889, 891, 892, 893, 894, 895, 896, 897, or 898, and wherein the DNA-binding 35 polypeptide has at least 90% identity to any one of SEQ ID NOs: 387-420, and 484-489.

125. The polynucleotide of claim 124, wherein the RT comprises: (i) an amino acid sequence having at least 40% sequence identity to SEQ ID NO: 35 or 41; 374 Atty Dkt No: L1034381430WO (00376)(ii) an amino acid sequence having at least 60% sequence identity to SEQ ID NO: 1, 34, or 40; (iii) an amino acid sequence having at least 70% sequence identity to SEQ ID NO: 6, 8, 9, 36, 37, 837, or 846; 5 (iv) an amino acid sequence having at least 75% sequence identity to SEQ ID NO: 4; (v) an amino acid sequence having at least 80% sequence identity to SEQ ID NO: 895 or 897; (vi) an amino acid sequence having at least 83% sequence identity to SEQ ID NO: 18, 19, 20, 21, 22, 23, 892, or 896; (vii) an amino acid sequence having at least 85% sequence identity to SEQ ID NO: 891; 10 (viii) an amino acid sequence having at least 87% sequence identity to SEQ ID NO: 889 or 898; (ix) an amino acid sequence having at least 90% sequence identity to SEQ ID NO: 7, 38, 262, 881, 883, or 893; (x) an amino acid sequence having at least 92% sequence identity to SEQ ID NO: 887 or 888; 15 (xi) an amino acid sequence having at least 95% sequence identity to SEQ ID NO: 24, 25, 26, 27, 28, 29, 30, 31, 32, 33, 885, or 894; or (xii) an amino acid sequence having at least 99.7% sequence identity to SEQ ID NO: 2, 3, or 5.

126. A polynucleotide encoding a fusion protein comprising a reverse transcriptase (RT) 20 and a PE-enhancing polypeptide, wherein the RT comprises an amino acid sequence having at least 40% sequence identity to SEQ ID NO: 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30, 31, 32, 33, 34, 35, 36, 37, 38, 40, 41, 262, 837, 846, 881, 883, 885, 887, 888, 889, 891, 892, 893, 894, 895, 896, 897, or 898, and wherein the PE-enhancing polypeptide has at least 90% sequence identity to any one of SEQ ID NOs: 335-344, 359-365, 371, 25 482, and 483.

127. The polynucleotide of claim 126, wherein the RT comprises: (i) an amino acid sequence having at least 40% sequence identity to SEQ ID NO: 35 or 41; (ii) an amino acid sequence having at least 60% sequence identity to SEQ ID NO: 1, 34, or 40; 30 (iii) an amino acid sequence having at least 70% sequence identity to SEQ ID NO: 6, 8, 9, 36, 37, 837, or 846; (iv) an amino acid sequence having at least 75% sequence identity to SEQ ID NO: 4; (v) an amino acid sequence having at least 80% sequence identity to SEQ ID NO: 895 or 897; (vi) an amino acid sequence having at least 83% sequence identity to SEQ ID NO: 18, 19, 20, 35 21, 22, 23, 892, or 896; (vii) an amino acid sequence having at least 85% sequence identity to SEQ ID NO: 891; 375 Atty Dkt No: L1034381430WO (00376)(viii) an amino acid sequence having at least 87% sequence identity to SEQ ID NO: 889 or 898; (ix) an amino acid sequence having at least 90% sequence identity to SEQ ID NO: 7, 38, 262, 881, 883, or 893; 5 (x) an amino acid sequence having at least 92% sequence identity to SEQ ID NO: 887 or 888; (xi) an amino acid sequence having at least 95% sequence identity to SEQ ID NO: 24, 25, 26, 27, 28, 29, 30, 31, 32, 33, 885, or 894; or (xii) an amino acid sequence having at least 99.7% sequence identity to SEQ ID NO: 2, 3, or 5. 10 128. A polynucleotide encoding a fusion protein comprising a reverse transcriptase (RT), a DNA-binding polypeptide, and a PE-enhancing polypeptide, wherein the RT comprises an amino acid sequence having at least 40% sequence identity to SEQ ID NO: 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30, 31, 32, 33, 34, 35, 36, 37, 38, 40, 41, 262, 837, 846, 881, 883, 885, 887, 888, 889, 891, 892, 893, 894, 895, 896, 897, or 898, wherein the15 DNA-binding polypeptide has at least 90% identity to any one of SEQ ID NOs: 387-420, and 484- 489, and wherein the PE-enhancing polypeptide has at least 90% sequence identity to any one of SEQ ID NOs: 335-344, 359-365, 371, 482, and 483.

129. The polynucleotide of claim 128, wherein the RT comprises: (i) an amino acid sequence having at least 40% sequence identity to SEQ ID NO: 35 or 41; 20 (ii) an amino acid sequence having at least 60% sequence identity to SEQ ID NO: 1, 34, or 40; (iii) an amino acid sequence having at least 70% sequence identity to SEQ ID NO: 6, 8, 9, 36, 37, 837, or 846; (iv) an amino acid sequence having at least 75% sequence identity to SEQ ID NO: 4; 25 (v) an amino acid sequence having at least 80% sequence identity to SEQ ID NO: 895 or 897; (vi) an amino acid sequence having at least 83% sequence identity to SEQ ID NO: 18, 19, 20, 21, 22, 23, 892, or 896; (vii) an amino acid sequence having at least 85% sequence identity to SEQ ID NO: 891; (viii) an amino acid sequence having at least 87% sequence identity to SEQ ID NO: 889 or 30 898; (ix) an amino acid sequence having at least 90% sequence identity to SEQ ID NO: 7, 38, 262, 881, 883, or 893; (x) an amino acid sequence having at least 92% sequence identity to SEQ ID NO: 887 or 888; (xi) an amino acid sequence having at least 95% sequence identity to SEQ ID NO: 24, 25, 26, 35 27, 28, 29, 30, 31, 32, 33, 885, or 894; or (xii) an amino acid sequence having at least 99.7% sequence identity to SEQ ID NO: 2, 3, or 5. 376 Atty Dkt No: L1034381430WO (00376)130. The polynucleotide of any one of claims 1-20 and 41-129, wherein said polynucleotide is codon optimized for expression in a eukaryotic cell.

131. The polynucleotide of claim 130, wherein said eukaryotic cell is a mammalian cell.

132. The polynucleotide of any one of claims 1-20 and 41-131, wherein said 5 polynucleotide is an RNA polynucleotide.

133. The polynucleotide of claim 132, wherein said RNA polynucleotide is an mRNA.

134. The polynucleotide of claim 12, wherein said RNA polynucleotide is a circRNA.

135. The polynucleotide of any one of claims 41-134, wherein said fusion protein comprises an amino acid sequence having at least 90% identical to any one of SEQ ID NOs: 808-812, 10 and 899-916.

136. The polynucleotide of claim 135, wherein said fusion protein comprises an amino acid sequence having at least 95% identical to any one of SEQ ID NOs: 808-812, and 899-916.

137. The polynucleotide of claim 135 or 136, wherein said fusion protein comprises the amino acid sequence of any one of SEQ ID NOs: 808-812, and 899-916. 15 138. A vector comprising the polynucleotide of any one of claims 1-20 and 41-131, and 135-137.

139. A vector comprising the polynucleotide of any one of claims 92-131, and 135-137.

140. The vector of claim 139, wherein said vector further comprises at least one nucleotide sequence encoding a polymerase editing guide RNA (PEgRNA), wherein said PEgRNA comprises an 20 extension arm, wherein said extension arm comprises a primer binding site and a DNA synthesis template sequence, and wherein said PEgRNA is capable of binding to said RGN polypeptide.

141. The vector of claim 140, wherein said extension arm is at the 3’ end of said PEgRNA.

142. The vector of claim 140 or 141, wherein said DNA synthesis template sequence is 19, 22, 23, 24, 25, 26, 29, 30, 32, 34, 37, 38, 40, 42, or 46 nucleotides in length. 25 143. The vector of any one of claims 140-142, wherein said DNA synthesis template sequence comprises an RT template (RTT) sequence.

144. The vector of any one of claims 140-143, wherein said primer binding site is 9, 11, 12, 13, or 15 nucleotides in length.

145. The vector of any one of claims 140-144, wherein the PEgRNA comprises a CRISPR 30 RNA comprising a CRISPR RNA (crRNA) repeat comprising a nucleotide sequence of any one of SEQ ID NOs: 444, 445, and 446, or that differs from any one of SEQ ID NOs: 444, 445, and 446 by 1 to 5 nucleotides, wherein said RGN polypeptide comprises an amino acid sequence having at least 90% sequence identity to the amino acid sequence of SEQ ID NO: 387 or 389.

146. The vector of claim 145, wherein the PEgRNA comprises a CRISPR RNA 35 comprising a CRISPR RNA (crRNA) repeat comprising the nucleotide sequence of any one of SEQ ID NOs: 444, 445, and 446, wherein said RGN polypeptide comprises the amino acid sequence of SEQ ID NO: 387 or 389. 377 Atty Dkt No: L1034381430WO (00376)147. The vector of claim 145 or 146, wherein the PEgRNA comprises a tracrRNA comprising a nucleotide sequence having at least 90% sequence identity to any one of SEQ ID NOs: 447, 448, 449, and 450.

148. The vector of claim 147, wherein the PEgRNA comprises a tracrRNA comprising a 5 nucleotide sequence having at least 95% sequence identity to any one of SEQ ID NOs: 447, 448, 449, and 450.

149. The vector of claim 147 or 148, wherein the PEgRNA comprises a tracrRNA comprising the nucleotide sequence of any one of SEQ ID NOs: 447, 448, 449, and 450.

150. The vector of any one of claims 140-144, wherein the PEgRNA comprises a CRISPR 10 RNA comprising a CRISPR RNA (crRNA) repeat comprising a nucleotide sequence of any one of SEQ ID NO: 455, 456, and 457, or that differs from any one of SEQ ID NO: 455, 456, and 457 by 1 to 5 nucleotides, wherein said RGN polypeptide comprises an amino acid sequence having at least 90% sequence identity to the amino acid sequence of SEQ ID NO:

388.

151. The vector of claim 150, wherein the PEgRNA comprises a CRISPR RNA 15 comprising a CRISPR RNA (crRNA) repeat comprising the nucleotide sequence of any one of SEQ ID NOs: 455, 456, and 457, wherein said RGN polypeptide comprises the amino acid sequence of SEQ ID NO:

388.

152. The vector of claim 150 or 151, wherein the PEgRNA comprises a tracrRNA comprising a nucleotide sequence having at least 90% sequence identity to any one of SEQ ID NOs: 20 458, 459, 460, 461, and 462.

153. The vector of claim 152, wherein the PEgRNA comprises a tracrRNA comprising a nucleotide sequence having at least 95% sequence identity to any one of SEQ ID NOs: 458, 459, 460, 461, and 462.

154. The vector of claim 152 or 153, wherein the PEgRNA comprises a tracrRNA 25 comprising the nucleotide sequence of any one of SEQ ID NOs: 458, 459, 460, 461, and 462.

155. The vector of any one of claims 140-144, wherein the PEgRNA comprises a CRISPR RNA comprising a CRISPR RNA (crRNA) repeat comprising a nucleotide sequence of SEQ ID NO: 468, or that differs from SEQ ID NO: 468 by 1 to 5 nucleotides, wherein said RGN polypeptide comprises an amino acid sequence having at least 90% sequence identity to the amino acid sequence 30 of SEQ ID NO:

391.

156. The vector of claim 155, wherein the PEgRNA comprises a CRISPR RNA comprising a CRISPR RNA (crRNA) repeat comprising the nucleotide sequence of SEQ ID NO: 468, wherein said RGN polypeptide comprises the amino acid sequence of SEQ ID NO:

391.

157. The vector of claim 155 or 156, wherein the PEgRNA comprises a tracrRNA 35 comprising a nucleotide sequence having at least 90% sequence identity to SEQ ID NO:

469.

158. The vector of claim 157, wherein the PEgRNA comprises a tracrRNA comprising a nucleotide sequence having at least 95% sequence identity to SEQ ID NO:

469. 378 Atty Dkt No: L1034381430WO (00376)159. The vector of claim 157 or 158, wherein the PEgRNA comprises a tracrRNA comprising the nucleotide sequence of SEQ ID NO:

469.

160. The vector of any one of claims 140-144, wherein the PEgRNA comprises a CRISPR RNA comprising a CRISPR RNA (crRNA) repeat comprising a nucleotide sequence of SEQ ID NO: 5 471 or 472, or that differs from SEQ ID NO: 471 or 472 by 1 to 5 nucleotides, wherein said RGN polypeptide comprises an amino acid sequence having at least 90% sequence identity to the amino acid sequence of SEQ ID NO:

390.

161. The vector of claim 160, wherein the PEgRNA comprises a CRISPR RNA comprising a CRISPR RNA (crRNA) repeat comprising the nucleotide sequence of SEQ ID NO: 471 10 or 472, wherein said RGN polypeptide comprises the amino acid sequence of SEQ ID NO:

390.

162. The vector of claim 160 or 161, wherein the PEgRNA comprises a tracrRNA comprising a nucleotide sequence having at least 90% sequence identity to SEQ ID NO: 473 or 474.

163. The vector of claim 162, wherein the PEgRNA comprises a tracrRNA comprising a nucleotide sequence having at least 95% sequence identity to SEQ ID NO: 473 or 474. 15 164. The vector of claim 162 or 163, wherein the PEgRNA comprises a tracrRNA comprising the nucleotide sequence of SEQ ID NO: 473 or 474.

165. The vector of any one of claims 139-164, wherein said vector further comprises a nucleotide sequence encoding a nicking guide RNA.

166. The vector of any one of claims 139-165, wherein said vector further comprises a 20 nucleotide sequence encoding a dominant negative MLH1.

167. The vector of any one of claims 138-166, wherein the vector is an adeno-associated viral (AAV) vector.

168. A cell comprising the polynucleotide of any one of claims 1-20 and 41-137 or the vector of any one of claims 138-167. 25 169. The cell of claim 168, wherein the cell is a prokaryotic cell.

170. The cell of claim 168, wherein the cell is a eukaryotic cell.

171. The cell of claim 170, wherein the eukaryotic cell is a mammalian cell.

172. The cell of claim 171, wherein the mammalian cell is a human cell.

173. The cell of claim 172, wherein the human cell is an immune cell. 30 174. The cell of claim 172, wherein the human cell is a stem cell.

175. The cell of claim 174, wherein the stem cell is an induced pluripotent stem cell.

176. The cell of claim 170, wherein the eukaryotic cell is an insect or avian cell.

177. The cell of claim 170, wherein the eukaryotic cell is a fungal cell.

178. The cell of claim 170, wherein the eukaryotic cell is a plant cell. 35 179. A plant or plant part comprising the plant cell of claim 178.

180. A method for making a RT or a fusion protein comprising culturing the cell of claim 168 under conditions in which said RT or fusion protein is expressed. 379 Atty Dkt No: L1034381430WO (00376)181. The method of claim 180, further comprising purifying said RT or fusion protein.

182. A fusion protein comprising a reverse transcriptase (RT) operably fused to at least one heterologous polypeptide, wherein said RT comprises an amino acid sequence having at least 40% sequence identity to SEQ ID NO: 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 5 21, 22, 23, 24, 25, 26, 27, 28, 29, 30, 31, 32, 33, 34, 35, 36, 37, 38, 40, 41, 262, 837, 846, 881, 883, 885, 887, 888, 889, 891, 892, 893, 894, 895, 896, 897, or 898.

183. The fusion protein of claim 182, wherein said RT comprises: (i) an amino acid sequence having at least 40% sequence identity to SEQ ID NO: 35 or 41; (ii) an amino acid sequence having at least 60% sequence identity to SEQ ID NO: 1, 34, or 10 40; (iii) an amino acid sequence having at least 70% sequence identity to SEQ ID NO: 6, 8, 9, 36, 37, 837, or 846; (iv) an amino acid sequence having at least 75% sequence identity to SEQ ID NO: 4; (v) an amino acid sequence having at least 80% sequence identity to SEQ ID NO: 895 or 897; 15 (vi) an amino acid sequence having at least 83% sequence identity to SEQ ID NO: 18, 19, 20, 21, 22, 23, 892, or 896; (vii) an amino acid sequence having at least 85% sequence identity to SEQ ID NO: 891; (viii) an amino acid sequence having at least 87% sequence identity to SEQ ID NO: 889 or 898; 20 (ix) an amino acid sequence having at least 90% sequence identity to SEQ ID NO: 7, 38, 262, 881, 883, or 893; (x) an amino acid sequence having at least 92% sequence identity to SEQ ID NO: 887 or 888; (xi) an amino acid sequence having at least 95% sequence identity to SEQ ID NO: 24, 25, 26, 27, 28, 29, 30, 31, 32, 33, 885, or 894; or 25 (xii) an amino acid sequence having at least 99.7% sequence identity to SEQ ID NO: 2, 3, or 5.

184. The fusion protein of claim 182 or 183, wherein said RT comprises: (i) an amino acid sequence having at least 50% sequence identity to SEQ ID NO: 35 or 41; (ii) an amino acid sequence having at least 70% sequence identity to SEQ ID NO: 1, 34, or 30 40; (iii) an amino acid sequence having at least 75% sequence identity to SEQ ID NO: 6, 8, 9, 36, 37, 837, or 846; (iv) an amino acid sequence having at least 80% sequence identity to SEQ ID NO: 4; (v) an amino acid sequence having at least 85% sequence identity to SEQ ID NO: 895 or 897; 35 (vi) an amino acid sequence having at least 90% sequence identity to SEQ ID NO: 18, 19, 20, 21, 22, 23, 889, 891, 892, 896, or 898; or 380 Atty Dkt No: L1034381430WO (00376)(vii) an amino acid sequence having at least 95% sequence identity to SEQ ID NO: 7, 38, 262, 881, 883, 887, 888, or 893.

185. The fusion protein of any one of claims 182-184, wherein said RT comprises: (i) an amino acid sequence having at least 60% sequence identity to SEQ ID NO: 35 or 41; 5 (ii) an amino acid sequence having at least 75% sequence identity to SEQ ID NO: 1, 34, or 40; (iii) an amino acid sequence having at least 80% sequence identity to SEQ ID NO: 6, 8, 9, 36, 37, 837, or 846; (iv) an amino acid sequence having at least 85% sequence identity to SEQ ID NO: 4; 10 (v) an amino acid sequence having at least 90% sequence identity to SEQ ID NO: 895 or 897; or (vi) an amino acid sequence having at least 95% sequence identity to SEQ ID NO: 18, 19, 20, 21, 22, 23, 889, 891, 892, 896, or 898.

186. The fusion protein of any one of claims 182-185, wherein said RT comprises: 15 (i) an amino acid sequence having at least 70% sequence identity to SEQ ID NO: 35 or 41; (ii) an amino acid sequence having at least 80% sequence identity to SEQ ID NO: 1, 34, or 40; (iii) an amino acid sequence having at least 85% sequence identity to SEQ ID NO: 6, 8, 9, 36, 37, 837, or 846; 20 (iv) an amino acid sequence having at least 90% sequence identity to SEQ ID NO: 4; or (v) an amino acid sequence having at least 95% sequence identity to SEQ ID NO: 895 or 897.

187. The fusion protein of any one of claims 182-186, wherein said RT comprises: (i) an amino acid sequence having at least 80% sequence identity to SEQ ID NO: 35 or 41; (ii) an amino acid sequence having at least 85% sequence identity to SEQ ID NO: 1, 34, or 25 40; (iii) an amino acid sequence having at least 90% sequence identity to SEQ ID NO: 6, 8, 9, 36, 37, 837, or 846; or (iv) an amino acid sequence having at least 95% sequence identity to SEQ ID NO:

4.

188. The fusion protein of any one of claims 182-187, wherein said RT comprises: 30 (i) an amino acid sequence having at least 85% sequence identity to SEQ ID NO: 35 or 41; (ii) an amino acid sequence having at least 90% sequence identity to SEQ ID NO: 1, 34, or 40; or (iii) an amino acid sequence having at least 95% sequence identity to SEQ ID NO: 6, 8, 9, 36, 37, 837, or 846. 35 189. The fusion protein of any one of claims 182-188, wherein said RT comprises: (i) an amino acid sequence having at least 90% sequence identity to SEQ ID NO: 35 or 41; or 381 Atty Dkt No: L1034381430WO (00376)(ii) an amino acid sequence having at least 95% sequence identity to SEQ ID NO: 1, 34, or 40.

190. The fusion protein of claim any one of claims 182-189, wherein said RT comprises an amino acid sequence having at least 95% sequence identity to SEQ ID NO: 35 or 41. 5 191. The fusion protein of any one of claims 182-190, wherein said RT comprises the amino acid sequence of any one of SEQ ID NO: 1-9, 18-41, 262, 837, 846, 881, 883, 885, 887, 888, 889, 891, 892, 893, 894, 895, 896, 897, and 898.

192. The fusion protein of any one of claims 182-191, wherein said RT lacks an RNase H domain. 10 193. The fusion protein of any one of claims 182-192, wherein said RT comprises: a) an N at a position corresponding to 200 of SEQ ID NO: 42; b) a P at a position corresponding to 330 of SEQ ID NO: 42; c) a K at a position corresponding to 306 of SEQ ID NO: 42; and d) an F at a position corresponding to 313 of SEQ ID NO:

42. 15 194. The fusion protein of claim 193, wherein said RT comprises: a) an amino acid sequence having at least 60% sequence identity to SEQ ID NO: 10, wherein said RT comprises at least one of: i) an N at a position corresponding to 198 of SEQ ID NO: 10; ii) a K at a position corresponding to 304 of SEQ ID NO: 10; 20 iii) an F at a position corresponding to 311 of SEQ ID NO: 10; and iv) a P at a position corresponding to 328 of SEQ ID NO: 10; b) an amino acid sequence having at least 99.5% sequence identity to SEQ ID NO: 11 or 12, wherein said RT comprises at least one of: i) an N at a position corresponding to 199 of SEQ ID NO: 11 or 12; 25 ii) a K at a position corresponding to 305 of SEQ ID NO: 11 or 12; iii) an F at a position corresponding to 312 of SEQ ID NO: 11 or 12; and iv) a P at a position corresponding to 329 of SEQ ID NO: 11 or 12; c) an amino acid sequence having at least 72% sequence identity to SEQ ID NO: 13, wherein said RT comprises at least one of: 30 i) a K at a position corresponding to 306 of SEQ ID NO: 13; ii) an F at a position corresponding to 313 of SEQ ID NO: 13; and iii) a P at a position corresponding to 330 of SEQ ID NO: 13; d) an amino acid sequence having at least 99.5% sequence identity to SEQ ID NO: 14, wherein said RT comprises at least one of: 35 i) an N at a position corresponding to 198 of SEQ ID NO: 14; ii) a K at a position corresponding to 304 of SEQ ID NO: 14; iii) an F at a position corresponding to 311 of SEQ ID NO: 14; and 382 Atty Dkt No: L1034381430WO (00376)iv) a P at a position corresponding to 328 of SEQ ID NO: 14; or e) an amino acid sequence having at least 87% sequence identity to SEQ ID NO: 15, 16 or 17, wherein said RT comprises at least one of: 5 i) an N at a position corresponding to 198 of SEQ ID NO: 15, 16 or 17; ii) a K at a position corresponding to 304 of SEQ ID NO: 15, 16 or 17; iii) an F at a position corresponding to 311 of SEQ ID NO: 15, 16 or 17; and iv) a P at a position corresponding to 328 of SEQ ID NO: 15, 16 or 17.

195. The fusion protein of claim 193 or 194, wherein said RT comprises: 10 a) an amino acid sequence having at least 70% sequence identity to SEQ ID NO: 10, wherein said RT comprises at least one of: i) an N at a position corresponding to 198 of SEQ ID NO: 10; ii) a K at a position corresponding to 304 of SEQ ID NO: 10; iii) an F at a position corresponding to 311 of SEQ ID NO: 10; and 15 iv) a P at a position corresponding to 328 of SEQ ID NO: 10; b) an amino acid sequence having at least 80% sequence identity to SEQ ID NO: 13, wherein said RT comprises at least one of: i) a K at a position corresponding to 306 of SEQ ID NO: 13; ii) an F at a position corresponding to 313 of SEQ ID NO: 13; and 20 iii) a P at a position corresponding to 330 of SEQ ID NO: 13; or c) an amino acid sequence having at least 90% sequence identity to SEQ ID NO: 15, 16 or 17, wherein said RT comprises at least one of: i) an N at a position corresponding to 198 of SEQ ID NO: 15, 16 or 17; 25 ii) a K at a position corresponding to 304 of SEQ ID NO: 15, 16 or 17; iii) an F at a position corresponding to 311 of SEQ ID NO: 15, 16 or 17; and iv) a P at a position corresponding to 328 of SEQ ID NO: 15, 16 or 17.

196. The fusion protein of any one of claims 193-195, wherein said RT comprises: a) an amino acid sequence having at least 75% sequence identity to SEQ ID NO: 10, wherein 30 said RT comprises at least one of: i) an N at a position corresponding to 198 of SEQ ID NO: 10; ii) a K at a position corresponding to 304 of SEQ ID NO: 10; iii) an F at a position corresponding to 311 of SEQ ID NO: 10; and iv) a P at a position corresponding to 328 of SEQ ID NO: 10; 35 b) an amino acid sequence having at least 85% sequence identity to SEQ ID NO: 13, wherein said RT comprises at least one of: i) a K at a position corresponding to 306 of SEQ ID NO: 13; 383 Atty Dkt No: L1034381430WO (00376)ii) an F at a position corresponding to 313 of SEQ ID NO: 13; and iii) a P at a position corresponding to 330 of SEQ ID NO: 13; or c) an amino acid sequence having at least 95% sequence identity to SEQ ID NO: 15, 16 or 17, 5 wherein said RT comprises at least one of: i) an N at a position corresponding to 198 of SEQ ID NO: 15, 16 or 17; ii) a K at a position corresponding to 304 of SEQ ID NO: 15, 16 or 17; iii) an F at a position corresponding to 311 of SEQ ID NO: 15, 16 or 17; and iv) a P at a position corresponding to 328 of SEQ ID NO: 15, 16 or 17. 10 197. The fusion protein of any one of claims 193-196, wherein said RT comprises: a) an amino acid sequence having at least 80% sequence identity to SEQ ID NO: 10, wherein said RT comprises at least one of: i) an N at a position corresponding to 198 of SEQ ID NO: 10; ii) a K at a position corresponding to 304 of SEQ ID NO: 10; 15 iii) an F at a position corresponding to 311 of SEQ ID NO: 10; and iv) a P at a position corresponding to 328 of SEQ ID NO: 10; or b) an amino acid sequence having at least 90% sequence identity to SEQ ID NO: 13, wherein said RT comprises at least one of: 20 i) a K at a position corresponding to 306 of SEQ ID NO: 13; ii) an F at a position corresponding to 313 of SEQ ID NO: 13; and iii) a P at a position corresponding to 330 of SEQ ID NO:

13.

198. The fusion protein of any one of claims 193-197, wherein said RT comprises: a) an amino acid sequence having at least 85% sequence identity to SEQ ID NO: 10, wherein 25 said RT comprises at least one of: i) an N at a position corresponding to 198 of SEQ ID NO: 10; ii) a K at a position corresponding to 304 of SEQ ID NO: 10; iii) an F at a position corresponding to 311 of SEQ ID NO: 10; and iv) a P at a position corresponding to 328 of SEQ ID NO: 10; 30 or b) an amino acid sequence having at least 95% sequence identity to SEQ ID NO: 13, wherein said RT comprises at least one of: i) a K at a position corresponding to 306 of SEQ ID NO: 13; ii) an F at a position corresponding to 313 of SEQ ID NO: 13; and 35 iii) a P at a position corresponding to 330 of SEQ ID NO:

13. 384 Atty Dkt No: L1034381430WO (00376)199. The fusion protein of any one of claims 193-198, wherein said RT comprises an amino acid sequence having at least 90% sequence identity to SEQ ID NO: 10, wherein said RT comprises at least one of: i) an N at a position corresponding to 198 of SEQ ID NO: 10; 5 ii) a K at a position corresponding to 304 of SEQ ID NO: 10; iii) an F at a position corresponding to 311 of SEQ ID NO: 10; and iv) a P at a position corresponding to 328 of SEQ ID NO:

10.

200. The fusion protein of any one of claims 193-199, wherein said RT comprises an amino acid sequence having at least 95% sequence identity to SEQ ID NO: 10, wherein said RT 10 comprises at least one of: i) an N at a position corresponding to 198 of SEQ ID NO: 10; ii) a K at a position corresponding to 304 of SEQ ID NO: 10; iii) an F at a position corresponding to 311 of SEQ ID NO: 10; and iv) a P at a position corresponding to 328 of SEQ ID NO:

10. 15 201. The fusion protein of any one of claims 193-200, wherein said RT comprises the amino acid sequence of any one of SEQ ID NOs: 10-17.

202. The fusion protein of any one of claims 182-201, wherein said at least one heterologous polypeptide comprises a DNA-binding polypeptide or a polymerase editor (PE)- enhancing polypeptide. 20 203. The fusion protein of any one of claims 182-201, wherein said at least one heterologous polypeptide comprises a DNA-binding polypeptide and a PE-enhancing polypeptide.

204. The fusion protein of claim 202 or 203, wherein said RT is operably fused to the N- terminus of said DNA-binding polypeptide or to the N-terminus of said PE-enhancing polypeptide.

205. The fusion protein of claim 202 or 203, wherein said RT is operably fused to the C- 25 terminus of said DNA-binding polypeptide or to the C-terminus of said PE-enhancing polypeptide.

206. The fusion protein of claim 203, wherein said fusion protein comprises from amino terminus to carboxy terminus: said RT, said PE-enhancing polypeptide, and said DNA-binding polypeptide.

207. The fusion protein of claim 203, wherein said fusion protein comprises from amino 30 terminus to carboxy terminus: said RT, said DNA-binding polypeptide, and said PE-enhancing polypeptide.

208. The fusion protein of claim 203, wherein said PE comprises from amino terminus to carboxy terminus: said DNA-binding polypeptide, said RT, and said PE-enhancing polypeptide.

209. The fusion protein of claim 203, wherein said PE comprises from amino terminus to 35 carboxy terminus: said DNA-binding polypeptide, said PE-enhancing polypeptide, and said RT. 385 Atty Dkt No: L1034381430WO (00376)210. The fusion protein of claim 203, wherein said fusion protein comprises from amino terminus to carboxy terminus: said PE-enhancing polypeptide, said RT, and said DNA-binding polypeptide.

211. The fusion protein of claim 203, wherein said fusion protein comprises from amino 5 terminus to carboxy terminus: said PE-enhancing polypeptide, said DNA-binding polypeptide, and said RT.

212. The fusion protein of claim 202 or 203, wherein said fusion protein comprises one or more nuclear localization signal (NLS).

213. The fusion protein of claim 212, wherein said one or more NLS is operably fused at 10 the N-terminus, C-terminus, or both the N-terminus and C-terminus of said RT, said DNA-binding polypeptide, or said PE-enhancing polypeptide.

214. The fusion protein of claim 213, wherein said one or more NLS is selected from the group consisting of SEQ ID NOs: 425-430.

215. The fusion protein of claim 202 or 203, wherein said fusion protein further comprises 15 one or more peptide linker.

216. The fusion protein of claim 215, wherein said one or more peptide linker comprises at least one NLS.

217. The fusion protein of claim 216, wherein said one or more peptide linker comprises two NLSs. 20 218. The fusion protein of any one of claims 215-217, wherein said one or more peptide linker is operably fused at the N-terminus, C-terminus, or both the N-terminus and C-terminus of said RT, said DNA-binding polypeptide, or said PE-enhancing polypeptide.

219. The fusion protein of any one of claims 215-218, wherein said one or more peptide linker has a formula of –[(SGGS)x-NLS]m-(SGGS)y-, wherein x or y is 0, 1, 2, 3, or 4, and m is 1, 2, 3, 25 or 4.

220. The fusion protein of any one of claims 215-218, wherein said one or more peptide linker has a formula of –[(SGGS)x-NLS]m-(SGGS)y-, wherein x or y is 1, and m is 1, 2, 3, or 4.

221. The fusion protein of any one of claims 215-218, wherein said one or more peptide linker has a formula of –[(SGGS)x-NLS]m-(SGGS)y-, wherein x is 1, y is 1, and m is 1, 2, 3, or 4. 30 222. The fusion protein of any one of claims 215-218, wherein said one or more peptide linker has a formula of –[(SGGS)x-NLS]m-(SGGS)y-, wherein x is 1, y is 1, and m is 1.

223. The fusion protein of any one of claims 215-218, wherein said one or more peptide linker has a formula of –[(SGGS)x-NLS]m-(SGGS)y-, wherein x is 1, y is 1, and m is 2.

224. The fusion protein of any one of claims 215-218, wherein said one or more peptide 35 linker has a formula of –[(SGGS)x-NLS]m-(SGGS)y-, wherein x is 1, y is 1, and m is 3.

225. The fusion protein of any one of claims 215-218, wherein said one or more peptide linker has a formula of –[(SGGS)x-NLS]m-(SGGS)y-, wherein x is 1, y is 1, and m is 4. 386 Atty Dkt No: L1034381430WO (00376)226. The fusion protein of any one of claims 215-218, wherein said one or more peptide linker has a formula of –(SGGS)x-NLSm-(SGGS)y-NLSn-(SGGS)z-, wherein each of x, y, or z is 0, 1, 2, 3, or 4; and wherein each of m or n is 0 or 1.

227. The fusion protein of any one of claims 215-218, wherein said one or more peptide 5 linker has a formula of –(SGGS)x-NLSm-(SGGS)y-NLSn-(SGGS)z-, wherein each of x or z is 0, 1, 2, 3, or 4, and y is 0; and wherein one of m or n is 0, and the other is 1.

228. The fusion protein of any one of claims 215-218, wherein said one or more peptide linker has a formula of –(SGGS)x-NLSm-(SGGS)y-NLSn-(SGGS)z-, wherein each of x, y, or z is 0, 1, 2, 3, or 4; and wherein each of m or n is 1, and y is not 0. 10 229. The fusion protein of any one of claims 215-218, wherein said one or more peptide linker has a length of 42 amino acids.

230. The fusion protein of any one of claims 215-218, wherein said one or more peptide linker has a length of more than or equal to 13 amino acids.

231. The fusion protein of any one of claims 215-218, wherein said one or more peptide 15 linker comprises one or more copies of amino acid sequence SGGS.

232. The fusion protein of claim 215, wherein said one or more peptide linker has the sequence of SEQ ID NO: 431-436, and 935-937.

233. The fusion protein of any one of claims 182-232, wherein said DNA-binding polypeptide is an RNA-guided nuclease (RGN) polypeptide. 20 234. The fusion protein of claim 233, wherein said RT is operably fused at an internal location of said RGN polypeptide.

235. The fusion protein of claim 234, wherein said RT is operably fused within a linker domain 2, a wedge domain, a RuvC domain, an HNH domain, a Rec-2 domain, or a PAM-interacting domain of said RGN polypeptide, or wherein said RT is operably fused between a linker domain 2, a 25 wedge domain, a RuvC domain, an HNH domain, a Rec-2 domain, or a PAM-interacting domain of said RGN polypeptide and another domain N-terminal or C-terminal to said linker domain 2, said wedge domain, said RuvC domain, said HNH domain, said Rec-2 domain, or said PAM-interacting domain.

236. The fusion protein of claim 235, wherein said RuvC domain is a RuvCIII domain. 30 237. The fusion protein of claim 236, wherein said RT is operably fused within a linker domain 2, a wedge domain, or a RuvCIII domain of said RGN polypeptide.

238. The fusion protein of claim 233, wherein said RT is operably fused within said RGN polypeptide immediately after an amino acid at a position selected from the group consisting of: a) an amino acid position corresponding to position 678 of SEQ ID NO: 388; 35 b) an amino acid position corresponding to position 736 of SEQ ID NO: 388; c) an amino acid position corresponding to position 922 of SEQ ID NO: 388; 387 Atty Dkt No: L1034381430WO (00376)d) an amino acid position corresponding to position 642 of SEQ ID NO: 387, 389, 392, 393, 394, or 395; e) an amino acid position corresponding to position 772 of SEQ ID NO: 387, 389, 392, 393, 394, or 395; 5 f) an amino acid position corresponding to position 739 of SEQ ID NO: 391; g) an amino acid position corresponding to position 744 of SEQ ID NO: 391; h) an amino acid position corresponding to position 680 of SEQ ID NO: 390; i) an amino acid position corresponding to position 785 of SEQ ID NO: 390; and j) an amino acid position corresponding to position 910 of SEQ ID NO:

390. 10 239. The fusion protein of any one of claims 233-238, wherein said RGN polypeptide is capable of binding a target sequence in a target polynucleotide in an RNA-guided sequence specific manner when bound to a guide RNA (gRNA), wherein said target sequence comprises a target strand and a non-target strand, and wherein said gRNA is capable of hybridizing to the target strand of the target sequence. 15 240. The fusion protein of claim 239, wherein said RGN polypeptide recognizes a protospacer adjacent motif (PAM) that is 3′ of said target sequence.

241. The fusion protein of claim 240, wherein: a) said RGN polypeptide comprising an amino acid sequence having at least 90% sequence identity to SEQ ID NO: 388 recognizes a PAM having a consensus nucleotide sequence set 20 forth as NNRYA; b) said RGN polypeptide comprising an amino acid sequence having at least 90% sequence identity to SEQ ID NO: 389 recognizes a PAM having a consensus nucleotide sequence set forth as NNNNCC; c) said RGN polypeptide comprising an amino acid sequence having at least 90% 25 sequence identity to SEQ ID NO: 391 recognizes a PAM having a consensus nucleotide sequence set forth as NNGRR; or d) said RGN polypeptide comprising an amino acid sequence having at least 90% sequence identity to SEQ ID NO: 390 recognizes a PAM having a consensus nucleotide sequence set forth as NNGG. 30 242. The fusion protein of any one of claims 239-241, wherein said RGN polypeptide is capable of cleaving said target polynucleotide upon binding.

243. The fusion protein of claim 242, wherein said RGN polypeptide is capable of generating a double-stranded break.

244. The fusion protein of claim 242, wherein said RGN polypeptide is capable of 35 generating a single-stranded break.

245. The fusion protein of any one of claims 233-241, wherein said RGN polypeptide comprises an HNH domain with at least one mutation that reduces or eliminates its nuclease activity. 388 Atty Dkt No: L1034381430WO (00376)246. The fusion protein of any one of claims 233-241, wherein said RGN polypeptide comprises an HNH domain with at least two mutations that reduces or eliminates its nuclease activity.

247. The fusion protein of any one of claims 233-241, wherein said RGN polypeptide does not comprise an HNH domain. 5 248. The fusion protein of claim 247, wherein said HNH domain of said RGN polypeptide has been replaced with said RT.

249. The fusion protein of any one of claims 233-241, wherein said RGN polypeptide is nuclease inactive.

250. The fusion protein of any one of claims 233-241, wherein said RGN polypeptide 10 comprises an RGN nickase.

251. The fusion protein of claim 250, wherein said RGN nickase comprises an amino acid sequence having at least 90% sequence identity to any one of SEQ ID NO: 411-420.

252. The fusion protein of claim 251, wherein said RGN nickase comprises an amino acid sequence having at least 95% sequence identity to any one of SEQ ID NO: 411-420. 15 253. The fusion protein of claim 251 or 252, wherein said RGN nickase comprises the amino acid sequence of any one of SEQ ID NO: 411-420.

254. The fusion protein of any one of claims 233-253, wherein said RGN polypeptide comprises an amino acid sequence having at least 90% sequence identity to any one of SEQ ID NO: 387-420. 20 255. The fusion protein of claim 254, wherein said RGN polypeptide comprises an amino acid sequence having at least 95% sequence identity to any one of SEQ ID NO: 387-420.

256. The fusion protein of claim 254 or 255, wherein said RGN polypeptide comprises the amino acid sequence of any one of SEQ ID NO: 387-420.

257. The fusion protein of any one of claims 202-256, wherein said PE-enhancing 25 polypeptide is a single-stranded RNA (ssRNA) binding protein.

258. The fusion protein of claim 257, wherein said ssRNA binding protein comprises an amino acid sequence having at least 90% sequence identity to any one of SEQ ID NO: 335, 336, 337, 338, 339, 340, 341, 342, 343, 344, 482, and 483.

259. The fusion protein of claim 258, wherein said ssRNA binding protein comprises an 30 amino acid sequence having at least 95% sequence identity to any one of SEQ ID NO: 335, 336, 337, 338, 339, 340, 341, 342, 343, 344, 482, and 483.

260. The fusion protein of claim 258 or 259, wherein said ssRNA binding protein comprises the amino acid sequence of any one of SEQ ID NO: 335, 336, 337, 338, 339, 340, 341, 342, 343, 344, 482, and 483. 35 261. The fusion protein of any one of claims 202-256, wherein said PE-enhancing polypeptide is a single-stranded DNA (ssDNA) binding protein. 389 Atty Dkt No: L1034381430WO (00376)262. The fusion protein of claim 261, wherein said ssDNA binding protein comprises an amino acid sequence having at least 90% sequence identity to any one of SEQ ID NO: 359, 360, 361, 362, 363, 364, 365, and 371.

263. The fusion protein of claim 262, wherein said ssDNA binding protein comprises an 5 amino acid sequence having at least 95% sequence identity to any one of SEQ ID NO: 359, 360, 361, 362, 363, 364, 365, and 371.

264. The fusion protein of claim 262 or 263, wherein said ssDNA binding protein comprises the amino acid sequence of any one of SEQ ID NO: 359, 360, 361, 362, 363, 364, 365, and 371. 10 265. A fusion protein comprising a reverse transcriptase (RT) and a DNA-binding polypeptide, wherein the RT comprises an amino acid sequence having at least 40% sequence identity to SEQ ID NO: 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30, 31, 32, 33, 34, 35, 36, 37, 38, 40, 41, 262, 837, 846, 881, 883, 885, 887, 888, 889, 891, 892, 893, 894, 895, 896, 897, or 898, and wherein the DNA-binding polypeptide has at least 90% 15 identity to any one of SEQ ID NOs: 387-420, and 484-489.

266. The fusion protein of claim 265, wherein the RT comprises: (i) an amino acid sequence having at least 40% sequence identity to SEQ ID NO: 35 or 41; (ii) an amino acid sequence having at least 60% sequence identity to SEQ ID NO: 1, 34, or 40; 20 (iii) an amino acid sequence having at least 70% sequence identity to SEQ ID NO: 6, 8, 9, 36, 37, 837, or 846; (iv) an amino acid sequence having at least 75% sequence identity to SEQ ID NO: 4; (v) an amino acid sequence having at least 80% sequence identity to SEQ ID NO: 895 or 897; (vi) an amino acid sequence having at least 83% sequence identity to SEQ ID NO: 18, 19, 20, 25 21, 22, 23, 892, or 896; (vii) an amino acid sequence having at least 85% sequence identity to SEQ ID NO: 891; (viii) an amino acid sequence having at least 87% sequence identity to SEQ ID NO: 889 or 898; (ix) an amino acid sequence having at least 90% sequence identity to SEQ ID NO: 7, 38, 262, 30 881, 883, or 893; (x) an amino acid sequence having at least 92% sequence identity to SEQ ID NO: 887 or 888; (xi) an amino acid sequence having at least 95% sequence identity to SEQ ID NO: 24, 25, 26, 27, 28, 29, 30, 31, 32, 33, 885, or 894; or (xii) an amino acid sequence having at least 99.7% sequence identity to SEQ ID NO: 2, 3, or 35 5.

267. A fusion protein comprising a reverse transcriptase (RT) and a PE-enhancing polypeptide, wherein the RT comprises an amino acid sequence having at least 40% sequence identity 390 Atty Dkt No: L1034381430WO (00376)to SEQ ID NO: 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30, 31, 32, 33, 34, 35, 36, 37, 38, 40, 41, 262, 837, 846, 881, 883, 885, 887, 888, 889, 891, 892, 893, 894, 895, 896, 897, or 898, and wherein the PE-enhancing polypeptide has at least 90% sequence identity to any one of SEQ ID NOs: 335-344, 359-365, 371, 482, and 483. 5 268. The fusion protein of claim 267, wherein the RT comprises: (i) an amino acid sequence having at least 40% sequence identity to SEQ ID NO: 35 or 41; (ii) an amino acid sequence having at least 60% sequence identity to SEQ ID NO: 1, 34, or 40; (iii) an amino acid sequence having at least 70% sequence identity to SEQ ID NO: 6, 8, 9, 36, 10 37, 837, or 846; (iv) an amino acid sequence having at least 75% sequence identity to SEQ ID NO: 4; (v) an amino acid sequence having at least 80% sequence identity to SEQ ID NO: 895 or 897; (vi) an amino acid sequence having at least 83% sequence identity to SEQ ID NO: 18, 19, 20, 21, 22, 23, 892, or 896; 15 (vii) an amino acid sequence having at least 85% sequence identity to SEQ ID NO: 891; (viii) an amino acid sequence having at least 87% sequence identity to SEQ ID NO: 889 or 898; (ix) an amino acid sequence having at least 90% sequence identity to SEQ ID NO: 7, 38, 262, 881, 883, or 893; 20 (x) an amino acid sequence having at least 92% sequence identity to SEQ ID NO: 887 or 888; (xi) an amino acid sequence having at least 95% sequence identity to SEQ ID NO: 24, 25, 26, 27, 28, 29, 30, 31, 32, 33, 885, or 894; or (xii) an amino acid sequence having at least 99.7% sequence identity to SEQ ID NO: 2, 3, or 5. 25 269. A fusion protein comprising a reverse transcriptase (RT), a DNA-binding polypeptide, and a PE-enhancing polypeptide, wherein the RT comprises an amino acid sequence having at least 40% sequence identity to SEQ ID NO: 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30, 31, 32, 33, 34, 35, 36, 37, 38, 40, 41, 262, 837, 846, 881, 883, 885, 887, 888, 889, 891, 892, 893, 894, 895, 896, 897, or 898, wherein the DNA- 30 binding polypeptide has at least 90% identity to any one of SEQ ID NOs: 387-420, and 484-489, and wherein the PE-enhancing polypeptide has at least 90% sequence identity to any one of SEQ ID NOs: 335-344, 359-365, 371, 482, and 483.

270. The fusion protein of claim 269, wherein the RT comprises: (i) an amino acid sequence having at least 40% sequence identity to SEQ ID NO: 35 or 41; 35 (ii) an amino acid sequence having at least 60% sequence identity to SEQ ID NO: 1, 34, or 40; 391 Atty Dkt No: L1034381430WO (00376)(iii) an amino acid sequence having at least 70% sequence identity to SEQ ID NO: 6, 8, 9, 36, 37, 837, or 846; (iv) an amino acid sequence having at least 75% sequence identity to SEQ ID NO: 4; (v) an amino acid sequence having at least 80% sequence identity to SEQ ID NO: 895 or 897; 5 (vi) an amino acid sequence having at least 83% sequence identity to SEQ ID NO: 18, 19, 20, 21, 22, 23, 892, or 896; (vii) an amino acid sequence having at least 85% sequence identity to SEQ ID NO: 891; (viii) an amino acid sequence having at least 87% sequence identity to SEQ ID NO: 889 or 898; 10 (ix) an amino acid sequence having at least 90% sequence identity to SEQ ID NO: 7, 38, 262, 881, 883, or 893; (x) an amino acid sequence having at least 92% sequence identity to SEQ ID NO: 887 or 888; (xi) an amino acid sequence having at least 95% sequence identity to SEQ ID NO: 24, 25, 26, 27, 28, 29, 30, 31, 32, 33, 885, or 894; or 15 (xii) an amino acid sequence having at least 99.7% sequence identity to SEQ ID NO: 2, 3, or 5.

271. The fusion protein of any one of claims 182-270, wherein said fusion protein comprises an amino acid sequence having at least 90% identical to any one of SEQ ID NOs: 808-812, and 899-916. 20 272. The fusion protein of claim 271, wherein said fusion protein comprises an amino acid sequence having at least 95% identical to any one of SEQ ID NOs: 808-812, and 899-916.

273. The fusion protein of claim 271 or 272, wherein said fusion protein comprises the amino acid sequence of any one of SEQ ID NOs: 808-812, and 899-916.

274. A polymerase editor (PE) comprising: 25 a) a reverse transcriptase (RT), or a polynucleotide encoding said RT; and b) a DNA-binding polypeptide, or a polynucleotide encoding said DNA-binding polypeptide, wherein said RT comprises an amino acid sequence having at least 40% sequence identity to SEQ ID NO: 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30, 31, 32, 33, 34, 35, 36, 37, 38, 40, 41, 262, 837, 846, 881, 883, 885, 887, 888, 889, 891, 30 892, 893, 894, 895, 896, 897, or 898.

275. The polymerase editor (PE) of claim 274, wherein said RT comprises: (i) an amino acid sequence having at least 40% sequence identity to SEQ ID NO: 35 or 41; (ii) an amino acid sequence having at least 60% sequence identity to SEQ ID NO: 1, 34, or 40; 35 (iii) an amino acid sequence having at least 70% sequence identity to SEQ ID NO: 6, 8, 9, 36, 37, 837, or 846; (iv) an amino acid sequence having at least 75% sequence identity to SEQ ID NO: 4; 392 Atty Dkt No: L1034381430WO (00376)(v) an amino acid sequence having at least 80% sequence identity to SEQ ID NO: 895 or 897; (vi) an amino acid sequence having at least 83% sequence identity to SEQ ID NO: 18, 19, 20, 21, 22, 23, 892, or 896; (vii) an amino acid sequence having at least 85% sequence identity to SEQ ID NO: 891; 5 (viii) an amino acid sequence having at least 87% sequence identity to SEQ ID NO: 889 or 898; (ix) an amino acid sequence having at least 90% sequence identity to SEQ ID NO: 7, 38, 262, 881, 883, or 893; (x) an amino acid sequence having at least 92% sequence identity to SEQ ID NO: 887 or 888; 10 (xi) an amino acid sequence having at least 95% sequence identity to SEQ ID NO: 24, 25, 26, 27, 28, 29, 30, 31, 32, 33, 885, or 894; or (xii) an amino acid sequence having at least 99.7% sequence identity to SEQ ID NO: 2, 3, or 5.

276. The PE of claim 274 or 275, wherein said RT comprises: 15 (i) an amino acid sequence having at least 50% sequence identity to SEQ ID NO: 35 or 41; (ii) an amino acid sequence having at least 70% sequence identity to SEQ ID NO: 1, 34, or 40; (iii) an amino acid sequence having at least 75% sequence identity to SEQ ID NO: 6, 8, 9, 36, 37, 837, or 846; 20 (iv) an amino acid sequence having at least 80% sequence identity to SEQ ID NO: 4; (v) an amino acid sequence having at least 85% sequence identity to SEQ ID NO: 895 or 897; (vi) an amino acid sequence having at least 90% sequence identity to SEQ ID NO: 18, 19, 20, 21, 22, 23, 889, 891, 892, 896, or 898; or (vii) an amino acid sequence having at least 95% sequence identity to SEQ ID NO: 7, 38, 262, 25 881, 883, 887, 888, or 893.

277. The PE of any one of claims 274-276, wherein said RT comprises: (i) an amino acid sequence having at least 60% sequence identity to SEQ ID NO: 35 or 41; (ii) an amino acid sequence having at least 75% sequence identity to SEQ ID NO: 1, 34, or 40; 30 (iii) an amino acid sequence having at least 80% sequence identity to SEQ ID NO: 6, 8, 9, 36, 37, 837, or 846; (iv) an amino acid sequence having at least 85% sequence identity to SEQ ID NO: 4; (v) an amino acid sequence having at least 90% sequence identity to SEQ ID NO: 895 or 897; or 35 (vi) an amino acid sequence having at least 95% sequence identity to SEQ ID NO: 18, 19, 20, 21, 22, 23, 889, 891, 892, 896, or 898.

278. The PE of any one of claims 274-277, wherein said RT comprises: 393 Atty Dkt No: L1034381430WO (00376)(i) an amino acid sequence having at least 70% sequence identity to SEQ ID NO: 35 or 41; (ii) an amino acid sequence having at least 80% sequence identity to SEQ ID NO: 1, 34, or 40; (iii) an amino acid sequence having at least 85% sequence identity to SEQ ID NO: 6, 8, 9, 36, 5 37, 837, or 846; (iv) an amino acid sequence having at least 90% sequence identity to SEQ ID NO: 4; or (v) an amino acid sequence having at least 95% sequence identity to SEQ ID NO: 895 or 897.

279. The PE of any one of claims 274-278, wherein said RT comprises: (i) an amino acid sequence having at least 80% sequence identity to SEQ ID NO: 35 or 41; 10 (ii) an amino acid sequence having at least 85% sequence identity to SEQ ID NO: 1, 34, or 40; (iii) an amino acid sequence having at least 90% sequence identity to SEQ ID NO: 6, 8, 9, 36, 37, 837, or 846; or (iv) an amino acid sequence having at least 95% sequence identity to SEQ ID NO:

4. 15 280. The PE of any one of claims 274-279, wherein said RT comprises: (i) an amino acid sequence having at least 85% sequence identity to SEQ ID NO: 35 or 41; (ii) an amino acid sequence having at least 90% sequence identity to SEQ ID NO: 1, 34, or 40; or (iii) an amino acid sequence having at least 95% sequence identity to SEQ ID NO: 6, 8, 9, 36, 20 37, 837, or 846.

281. The PE of any one of claims 274-280, wherein said RT comprises: (i) an amino acid sequence having at least 90% sequence identity to SEQ ID NO: 35 or 41; or (ii) an amino acid sequence having at least 95% sequence identity to SEQ ID NO: 1, 34, or 40. 25 282. The PE of any one of claims 274-281, wherein said RT comprises an amino acid sequence having at least 95% sequence identity to SEQ ID NO: 35 or 41.

283. The PE of any one of claims 274-282, wherein said RT comprises the amino acid sequence of any one of SEQ ID NO: 1-9, 18-41, 262, 837, 846, 881, 883, 885, 887, 888, 889, 891, 892, 893, 894, 895, 896, 897, and 898. 30 284. The PE of any one of claims 274-283, wherein said RT lacks an RNase H domain.

285. The PE of any one of claims 274-284, wherein said RT comprises: a) an N at a position corresponding to 200 of SEQ ID NO: 42; b) a P at a position corresponding to 330 of SEQ ID NO: 42; c) a K at a position corresponding to 306 of SEQ ID NO: 42; and 35 d) an F at a position corresponding to 313 of SEQ ID NO:

42.

286. The PE of any one of claims 274-285, wherein said RT comprises: 394 Atty Dkt No: L1034381430WO (00376)a) an amino acid sequence having at least 60% sequence identity to SEQ ID NO: 10, wherein said RT comprises at least one of: i) an N at a position corresponding to 198 of SEQ ID NO: 10; ii) a K at a position corresponding to 304 of SEQ ID NO: 10; 5 iii) an F at a position corresponding to 311 of SEQ ID NO: 10; and iv) a P at a position corresponding to 328 of SEQ ID NO: 10; b) an amino acid sequence having at least 99.5% sequence identity to SEQ ID NO: 11 or 12, wherein said RT comprises at least one of: i) an N at a position corresponding to 199 of SEQ ID NO: 11 or 12; 10 ii) a K at a position corresponding to 305 of SEQ ID NO: 11 or 12; iii) an F at a position corresponding to 312 of SEQ ID NO: 11 or 12; and iv) a P at a position corresponding to 329 of SEQ ID NO: 11 or 12; c) an amino acid sequence having at least 72% sequence identity to SEQ ID NO: 13, wherein said RT comprises at least one of: 15 i) a K at a position corresponding to 306 of SEQ ID NO: 13; ii) an F at a position corresponding to 313 of SEQ ID NO: 13; and iii) a P at a position corresponding to 330 of SEQ ID NO: 13; d) an amino acid sequence having at least 99.5% sequence identity to SEQ ID NO: 14, wherein said RT comprises at least one of: 20 i) an N at a position corresponding to 198 of SEQ ID NO: 14; ii) a K at a position corresponding to 304 of SEQ ID NO: 14; iii) an F at a position corresponding to 311 of SEQ ID NO: 14; and iv) a P at a position corresponding to 328 of SEQ ID NO: 14; or 25 e) an amino acid sequence having at least 87% sequence identity to SEQ ID NO: 15, 16 or 17, wherein said RT comprises at least one of: i) an N at a position corresponding to 198 of SEQ ID NO: 15, 16 or 17; ii) a K at a position corresponding to 304 of SEQ ID NO: 15, 16 or 17; iii) an F at a position corresponding to 311 of SEQ ID NO: 15, 16 or 17; and 30 iv) a P at a position corresponding to 328 of SEQ ID NO: 15, 16 or 17.

287. The PE of claim 286, wherein said RT comprises: a) an amino acid sequence having at least 70% sequence identity to SEQ ID NO: 10, wherein said RT comprises at least one of: i) an N at a position corresponding to 198 of SEQ ID NO: 10; 35 ii) a K at a position corresponding to 304 of SEQ ID NO: 10; iii) an F at a position corresponding to 311 of SEQ ID NO: 10; and iv) a P at a position corresponding to 328 of SEQ ID NO: 10; 395 Atty Dkt No: L1034381430WO (00376)b) an amino acid sequence having at least 80% sequence identity to SEQ ID NO: 13, wherein said RT comprises at least one of: i) a K at a position corresponding to 306 of SEQ ID NO: 13; ii) an F at a position corresponding to 313 of SEQ ID NO: 13; and 5 iii) a P at a position corresponding to 330 of SEQ ID NO: 13; or c) an amino acid sequence having at least 90% sequence identity to SEQ ID NO: 15, 16 or 17, wherein said RT comprises at least one of: i) an N at a position corresponding to 198 of SEQ ID NO: 15, 16 or 17; 10 ii) a K at a position corresponding to 304 of SEQ ID NO: 15, 16 or 17; iii) an F at a position corresponding to 311 of SEQ ID NO: 15, 16 or 17; and iv) a P at a position corresponding to 328 of SEQ ID NO: 15, 16 or 17.

288. The PE of claim 286 or 287, wherein said RT comprises: a) an amino acid sequence having at least 75% sequence identity to SEQ ID NO: 10, wherein 15 said RT comprises at least one of: i) an N at a position corresponding to 198 of SEQ ID NO: 10; ii) a K at a position corresponding to 304 of SEQ ID NO: 10; iii) an F at a position corresponding to 311 of SEQ ID NO: 10; and iv) a P at a position corresponding to 328 of SEQ ID NO: 10; 20 b) an amino acid sequence having at least 85% sequence identity to SEQ ID NO: 13, wherein said RT comprises at least one of: i) a K at a position corresponding to 306 of SEQ ID NO: 13; ii) an F at a position corresponding to 313 of SEQ ID NO: 13; and iii) a P at a position corresponding to 330 of SEQ ID NO: 13; 25 or c) an amino acid sequence having at least 95% sequence identity to SEQ ID NO: 15, 16 or 17, wherein said RT comprises at least one of: i) an N at a position corresponding to 198 of SEQ ID NO: 15, 16 or 17; ii) a K at a position corresponding to 304 of SEQ ID NO: 15, 16 or 17; 30 iii) an F at a position corresponding to 311 of SEQ ID NO: 15, 16 or 17; and iv) a P at a position corresponding to 328 of SEQ ID NO: 15, 16 or 17.

289. The PE of any one of claims 286-288, wherein said RT comprises: a) an amino acid sequence having at least 80% sequence identity to SEQ ID NO: 10, wherein said RT comprises at least one of: 35 i) an N at a position corresponding to 198 of SEQ ID NO: 10; ii) a K at a position corresponding to 304 of SEQ ID NO: 10; iii) an F at a position corresponding to 311 of SEQ ID NO: 10; and 396 Atty Dkt No: L1034381430WO (00376)iv) a P at a position corresponding to 328 of SEQ ID NO: 10; or b) an amino acid sequence having at least 90% sequence identity to SEQ ID NO: 13, wherein said RT comprises at least one of: 5 i) a K at a position corresponding to 306 of SEQ ID NO: 13; ii) an F at a position corresponding to 313 of SEQ ID NO: 13; and iii) a P at a position corresponding to 330 of SEQ ID NO:

13.

290. The PE of any one of claims 286-289, wherein said RT comprises: a) an amino acid sequence having at least 85% sequence identity to SEQ ID NO: 10, wherein 10 said RT comprises at least one of: i) an N at a position corresponding to 198 of SEQ ID NO: 10; ii) a K at a position corresponding to 304 of SEQ ID NO: 10; iii) an F at a position corresponding to 311 of SEQ ID NO: 10; and iv) a P at a position corresponding to 328 of SEQ ID NO: 10; 15 or b) an amino acid sequence having at least 95% sequence identity to SEQ ID NO: 13, wherein said RT comprises at least one of: i) a K at a position corresponding to 306 of SEQ ID NO: 13; ii) an F at a position corresponding to 313 of SEQ ID NO: 13; and 20 iii) a P at a position corresponding to 330 of SEQ ID NO:

13.

291. The PE of any one of claims 286-290, wherein said RT comprises an amino acid sequence having at least 90% sequence identity to SEQ ID NO: 10, wherein said RT comprises at least one of: i) an N at a position corresponding to 198 of SEQ ID NO: 10; 25 ii) a K at a position corresponding to 304 of SEQ ID NO: 10; iii) an F at a position corresponding to 311 of SEQ ID NO: 10; and iv) a P at a position corresponding to 328 of SEQ ID NO:

10.

292. The PE of any one of claims 286-291, wherein said RT comprises an amino acid sequence having at least 95% sequence identity to SEQ ID NO: 10, wherein said RT comprises at 30 least one of: i) an N at a position corresponding to 198 of SEQ ID NO: 10; ii) a K at a position corresponding to 304 of SEQ ID NO: 10; iii) an F at a position corresponding to 311 of SEQ ID NO: 10; and iv) a P at a position corresponding to 328 of SEQ ID NO:

10. 35 293. The PE of any one of claims 286-292, wherein said RT comprises the amino acid sequence of any one of SEQ ID NOs: 10-17. 397 Atty Dkt No: L1034381430WO (00376)294. The PE of any one of claims 286-293, wherein at least one of said polynucleotides is codon optimized for expression in a eukaryotic cell.

295. The PE of claim 294, wherein said eukaryotic cell is a mammalian cell.

296. The PE of any one of claims 286-295, wherein at least one of said polynucleotides is 5 an RNA polynucleotide.

297. The PE of claim 296, wherein said RNA polynucleotide is an mRNA.

298. The PE of claim 296, wherein said RNA polynucleotide is a circRNA.

299. The PE of any one of claims 286-295, wherein at least one of said polynucleotides is comprised within a viral vector. 10 300. The PE of claim 299, wherein said viral vector is an adeno-associated viral (AAV) vector.

301. The PE of any one of claims 286-300, wherein said PE further comprises a polymerase editor (PE)-enhancing polypeptide, or a polynucleotide encoding said PE-enhancing polypeptide. 15 302. The PE of claim 301, wherein said polynucleotide encoding said RT, said polynucleotide encoding said DNA-binding polypeptide, and said polynucleotide encoding said PE- enhancing polypeptide are translated as three separate polypeptides.

303. The PE of claim 301 or 302, wherein said polynucleotide encoding said RT, said polynucleotide encoding said DNA-binding polypeptide, and said polynucleotide encoding said PE- 20 enhancing polypeptide are comprised in at least two nucleic acid molecules.

304. The PE of any one of claims 301-303, wherein said polynucleotide encoding said RT, said polynucleotide encoding said DNA-binding polypeptide, and said polynucleotide encoding said PE-enhancing polypeptide are comprised in three nucleic acid molecules.

305. The PE of claim 301, wherein said polynucleotide encoding said RT, said25 polynucleotide encoding said DNA-binding polypeptide, and said polynucleotide encoding said PE- enhancing polypeptide are comprised in a single nucleic acid molecule.

306. The PE of claim 305, wherein: (a) said polynucleotide encoding said RT and said polynucleotide encoding said DNA- binding polypeptide are operably linked, wherein a fusion protein comprising said RT and said DNA- 30 binding polypeptide is encoded; (b) said polynucleotide encoding said RT and said polynucleotide encoding said PE- enhancing polypeptide are operably linked, wherein a fusion protein comprising said RT and said PE- enhancing polypeptide is encoded; (c) said polynucleotide encoding said DNA-binding polypeptide and said polynucleotide 35 encoding said PE-enhancing polypeptide are operably linked, wherein a fusion protein comprising said DNA-binding polypeptide and said PE-enhancing polypeptide is encoded; or 398 Atty Dkt No: L1034381430WO (00376)(d) said polynucleotide encoding said RT, said polynucleotide encoding said DNA-binding polypeptide, and said polynucleotide encoding said PE-enhancing polypeptide are operably linked, wherein a fusion protein comprising said RT, said DNA-binding polypeptide, and said PE-enhancing polypeptide is encoded. 5 307. The PE of claim 306, wherein said RT of (a) is operably fused to the N-terminus of said DNA-binding polypeptide, or wherein said RT of (b) is operably fused to the N-terminus of said PE-enhancing polypeptide.

308. The PE of claim 306, wherein said RT of (a) is operably fused to the C-terminus of said DNA-binding polypeptide, or wherein said RT of (b) is operably fused to the C-terminus of said 10 PE-enhancing polypeptide.

309. The PE of claim 306, wherein said DNA-binding polypeptide of (c) is operably fused to the N-terminus of said PE-enhancing polypeptide, or wherein said DNA-binding polypeptide of (c) is operably fused to the C-terminus of said PE-enhancing polypeptide.

310. The PE of claim 306, wherein said PE of (d) comprises from amino terminus to 15 carboxy terminus: said RT, said DNA-binding polypeptide, and said PE-enhancing polypeptide.

311. The PE of claim 306, wherein said PE of (d) comprises from amino terminus to carboxy terminus: said RT, said PE-enhancing polypeptide, and said DNA-binding polypeptide.

312. The PE of claim 306, wherein said PE of (d) comprises from amino terminus to carboxy terminus: said PE-enhancing polypeptide, said RT, and said DNA-binding polypeptide. 20 313. The PE of claim 306, wherein said PE of (d) comprises from amino terminus to carboxy terminus: said DNA-binding polypeptide, said RT, and said PE-enhancing polypeptide.

314. The PE of claim 306, wherein said PE of (d) comprises from amino terminus to carboxy terminus: said DNA-binding polypeptide, said PE-enhancing polypeptide, and said RT.

315. The PE of claim 306, wherein said PE of (d) comprises from amino terminus to 25 carboxy terminus: said PE-enhancing polypeptide, said DNA-binding polypeptide, and said RT.

316. The PE of any one of claims 301-315, wherein said PE comprises one or more nuclear localization signal (NLS).

317. The PE of claim 316, wherein said one or more NLS is operably fused at the N- terminus, C-terminus, or both the N-terminus and C-terminus of said RT, said DNA-binding 30 polypeptide, or said PE-enhancing polypeptide.

318. The PE of claim 316 or 317, wherein said one or more NLS is selected from the group consisting of SEQ ID NOs: 425-430.

319. The PE of any one of claims 301-318, wherein said fusion protein further comprises one or more peptide linker. 35 320. The PE of claim 319, wherein said one or more peptide linker comprises at least one NLS.

321. The PE of claim 320, wherein said one or more peptide linker comprises two NLSs. 399 Atty Dkt No: L1034381430WO (00376)322. The PE of any one of claims 319-321, wherein said one or more peptide linker is operably fused at the N-terminus, C-terminus, or both the N-terminus and C-terminus of said RT, said DNA-binding polypeptide, or said PE-enhancing polypeptide.

323. The PE of any one of claims 319-322, wherein said one or more peptide linker has a 5 formula of –[(SGGS)x-NLS]m-(SGGS)y-, wherein x or y is 0, 1, 2, 3, or 4, and m is 1, 2, 3, or 4.

324. The PE of any one of claims 319-322, wherein said one or more peptide linker has a formula of –[(SGGS)x-NLS]m-(SGGS)y-, wherein x or y is 1, and m is 1, 2, 3, or 4.

325. The PE of any one of claims 319-322, wherein said one or more peptide linker has a formula of –[(SGGS)x-NLS]m-(SGGS)y-, wherein x is 1, y is 1, and m is 1, 2, 3, or 4. 10 326. The PE of any one of claims 319-322, wherein said one or more peptide linker has a formula of –[(SGGS)x-NLS]m-(SGGS)y-, wherein x is 1, y is 1, and m is 1.

327. The PE of any one of claims 319-322, wherein said one or more peptide linker has a formula of –[(SGGS)x-NLS]m-(SGGS)y-, wherein x is 1, y is 1, and m is 2.

328. The PE of any one of claims 319-322, wherein said one or more peptide linker has a 15 formula of –[(SGGS)x-NLS]m-(SGGS)y-, wherein x is 1, y is 1, and m is 3.

329. The PE of any one of claims 319-322, wherein said one or more peptide linker has a formula of –[(SGGS)x-NLS]m-(SGGS)y-, wherein x is 1, y is 1, and m is 4.

330. The PE of any one of claims 319-322, wherein said one or more peptide linker has a formula of –(SGGS)x-NLSm-(SGGS)y-NLSn-(SGGS)z-, wherein each of x, y, or z is 0, 1, 2, 3, or 4; 20 and wherein each of m or n is 0 or 1.

331. The PE of any one of claims 319-322, wherein said one or more peptide linker has a formula of –(SGGS)x-NLSm-(SGGS)y-NLSn-(SGGS)z-, wherein each of x or z is 0, 1, 2, 3, or 4, and y is 0; and wherein one of m or n is 0, and the other is 1.

332. The PE of any one of claims 319-322, wherein said one or more peptide linker has a 25 formula of –(SGGS)x-NLSm-(SGGS)y-NLSn-(SGGS)z-, wherein each of x, y, or z is 0, 1, 2, 3, or 4; and wherein each of m or n is 1, and y is not 0.

333. The PE of any one of claims 319-322, wherein said one or more peptide linker has a length of 42 amino acids.

334. The PE of claim 319-322, wherein said one or more peptide linker has a length of 30 more than or equal to 13 amino acids.

335. The PE of claim 319-322, wherein said one or more peptide linker comprises one or more copies of amino acid sequence SGGS.

336. The PE of claim 319, wherein said one or more peptide linker has the sequence of SEQ ID NO: 431-436, and 935-937. 35 337. The PE of any one of claims 274-336, wherein said DNA-binding polypeptide is an RNA-guided nuclease (RGN) polypeptide. 400 Atty Dkt No: L1034381430WO (00376)338. The PE of claim 337, wherein said RT is operably fused at an internal location of said RGN polypeptide.

339. The PE of claim 338, wherein said RT is operably fused within a linker domain 2, a wedge domain, a RuvC domain, an HNH domain, a Rec-2 domain, or a PAM-interacting domain of 5 said RGN polypeptide, or wherein said RT is operably fused between a linker domain 2, a wedge domain, a RuvC domain, an HNH domain, a Rec-2 domain, or a PAM-interacting domain of said RGN polypeptide and another domain N-terminal or C-terminal to said linker domain 2, said wedge domain, said RuvC domain, said HNH domain, said Rec-2 domain, or said PAM-interacting domain.

340. The PE of claim 339, wherein said RuvC domain is a RuvCIII domain. 10 341. The PE of claim 340, wherein said RT is operably fused within a linker domain 2, a wedge domain, or a RuvCIII domain of said RGN polypeptide.

342. The PE of claim 338, wherein said RT is operably fused within said RGN polypeptide immediately after an amino acid at a position selected from the group consisting of: a) an amino acid position corresponding to position 678 of SEQ ID NO: 388; 15 b) an amino acid position corresponding to position 736 of SEQ ID NO: 388; c) an amino acid position corresponding to position 922 of SEQ ID NO: 388; d) an amino acid position corresponding to position 642 of SEQ ID NO: 387, 389, 392, 393, 394, or 395; e) an amino acid position corresponding to position 772 of SEQ ID NO: 387, 389, 392, 20 393, 394, or 395; f) an amino acid position corresponding to position 739 of SEQ ID NO: 391; g) an amino acid position corresponding to position 744 of SEQ ID NO: 391; h) an amino acid position corresponding to position 680 of SEQ ID NO: 390; i) an amino acid position corresponding to position 785 of SEQ ID NO: 390; and 25 j) an amino acid position corresponding to position 910 of SEQ ID NO:

390.

343. The PE of any one of claims 337-342, wherein said RGN polypeptide is capable of binding a target sequence in a target polynucleotide in an RNA-guided sequence specific manner when bound to a guide RNA (gRNA), wherein said target sequence comprises a target strand and a non-target strand, and wherein said gRNA is capable of hybridizing to the target strand of the target 30 sequence.

344. The PE of claim 343, wherein said RGN polypeptide recognizes a protospacer adjacent motif (PAM) that is 3′ of said target sequence.

345. The PE of claim 344, wherein: a) said RGN polypeptide comprising an amino acid sequence having at least 90% 35 sequence identity to SEQ ID NO: 388 recognizes a PAM having a consensus nucleotide sequence set forth as NNRYA; 401 Atty Dkt No: L1034381430WO (00376)b) said RGN polypeptide comprising an amino acid sequence having at least 90% sequence identity to SEQ ID NO: 389 recognizes a PAM having a consensus nucleotide sequence set forth as NNNNCC; c) said RGN polypeptide comprising an amino acid sequence having at least 90% 5 sequence identity to SEQ ID NO: 391 recognizes a PAM having a consensus nucleotide sequence set forth as NNGRR; or d) said RGN polypeptide comprising an amino acid sequence having at least 90% sequence identity to SEQ ID NO: 390 recognizes a PAM having a consensus nucleotide sequence set forth as NNGG. 10 346. The PE of any one of claims 343-345, wherein said RGN polypeptide is capable of cleaving said target polynucleotide upon binding.

347. The PE of claim 346, wherein said RGN polypeptide is capable of generating a double-stranded break.

348. The PE of claim 346, wherein said RGN polypeptide is capable of generating a 15 single-stranded break.

349. The PE of any one of claims 337-345, wherein said RGN polypeptide comprises an HNH domain with at least one mutation that reduces or eliminates its nuclease activity.

350. The PE of any one of claims 337-345, wherein said RGN polypeptide comprises an HNH domain with at least two mutations that reduces or eliminates its nuclease activity. 20 351. The PE of any one of claims 337-345, wherein said RGN polypeptide does not comprise an HNH domain.

352. The PE of claim 351, wherein said HNH domain of said RGN polypeptide has been replaced with said RT.

353. The PE of any one of claims 337-345, wherein said RGN polypeptide is nuclease 25 inactive.

354. The PE of any one of claims 337-345, wherein said RGN polypeptide comprises an RGN nickase.

355. The PE of claim 354, wherein said RGN nickase comprises an amino acid sequence having at least 90% sequence identity to any one of SEQ ID NO: 411-420. 30 356. The PE of claim 355, wherein said RGN nickase comprises an amino acid sequence having at least 95% sequence identity to any one of SEQ ID NO: 411-420.

357. The PE of claim 355 or 356, wherein said RGN nickase comprises the amino acid sequence of any one of SEQ ID NO: 411-420.

358. The PE of any one of claims 337-357, wherein said RGN polypeptide comprises an 35 amino acid sequence having at least 90% sequence identity to any one of SEQ ID NO: 387-420.

359. The PE of claim 358, wherein said RGN polypeptide comprises an amino acid sequence having at least 95% sequence identity to any one of SEQ ID NO: 387-420. 402 Atty Dkt No: L1034381430WO (00376)360. The PE of claim 358 or 359, wherein said RGN polypeptide comprises the amino acid sequence of any one of SEQ ID NO: 387-420.

361. The PE of any one of claims 301-360, wherein said PE-enhancing polypeptide is a single-stranded RNA (ssRNA) binding protein. 5 362. The PE of claim 361, wherein said ssRNA binding protein comprises an amino acid sequence having at least 90% sequence identity to any one of SEQ ID NO: 335, 336, 337, 338, 339, 340, 341, 342, 343, 344, 482, and 483.

363. The PE of claim 362, wherein said ssRNA binding protein comprises an amino acid sequence having at least 95% sequence identity to any one of SEQ ID NO: 335, 336, 337, 338, 339, 10 340, 341, 342, 343, 344, 482, and 483.

364. The PE of claim 362 or 363, wherein said ssRNA binding protein comprises the amino acid sequence of any one of SEQ ID NO: 335, 336, 337, 338, 339, 340, 341, 342, 343, 344, 482, and 483.

365. The PE of any one of claims 301-360, wherein said PE-enhancing polypeptide is a 15 single-stranded DNA (ssDNA) binding protein.

366. The PE of claim 365, wherein said ssDNA binding protein comprises an amino acid sequence having at least 90% sequence identity to any one of SEQ ID NO: 359, 360, 361, 362, 363, 364, 365, and 371.

367. The PE of claim 366, wherein said ssDNA binding protein comprises an amino acid 20 sequence having at least 95% sequence identity to any one of SEQ ID NO: 359, 360, 361, 362, 363, 364, 365, and 371.

368. The PE of claim 366 or 367, wherein said ssDNA binding protein comprises the amino acid sequence of any one of SEQ ID NO: 359, 360, 361, 362, 363, 364, 365, and 371.

369. A polymerase editor (PE) comprising a reverse transcriptase (RT) and a DNA- 25 binding polypeptide, wherein the RT comprises an amino acid sequence having at least 40% sequence identity to SEQ ID NO: 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30, 31, 32, 33, 34, 35, 36, 37, 38, 40, 41, 262, 837, 846, 881, 883, 885, 887, 888, 889, 891, 892, 893, 894, 895, 896, 897, or 898, wherein the DNA-binding polypeptide has at least 90% identity to any one of SEQ ID NOs: 387-420, and 484-489. 30 370. The PE of claim 369, wherein the RT comprises: (i) an amino acid sequence having at least 40% sequence identity to SEQ ID NO: 35 or 41; (ii) an amino acid sequence having at least 60% sequence identity to SEQ ID NO: 1, 34, or 40; (iii) an amino acid sequence having at least 70% sequence identity to SEQ ID NO: 6, 8, 9, 36, 35 37, 837, or 846; (iv) an amino acid sequence having at least 75% sequence identity to SEQ ID NO: 4; (v) an amino acid sequence having at least 80% sequence identity to SEQ ID NO: 895 or 897; 403 Atty Dkt No: L1034381430WO (00376)(vi) an amino acid sequence having at least 83% sequence identity to SEQ ID NO: 18, 19, 20, 21, 22, 23, 892, or 896; (vii) an amino acid sequence having at least 85% sequence identity to SEQ ID NO: 891; (viii) an amino acid sequence having at least 87% sequence identity to SEQ ID NO: 889 or 5 898; (ix) an amino acid sequence having at least 90% sequence identity to SEQ ID NO: 7, 38, 262, 881, 883, or 893; (x) an amino acid sequence having at least 92% sequence identity to SEQ ID NO: 887 or 888; (xi) an amino acid sequence having at least 95% sequence identity to SEQ ID NO: 24, 25, 26, 10 27, 28, 29, 30, 31, 32, 33, 885, or 894; or (xii) an amino acid sequence having at least 99.7% sequence identity to SEQ ID NO: 2, 3, or 5.

371. A polymerase editor (PE) comprising a reverse transcriptase (RT) and a PE- enhancing polypeptide, wherein the RT comprises an amino acid sequence having at least 40% 15 sequence identity to SEQ ID NO: 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30, 31, 32, 33, 34, 35, 36, 37, 38, 40, 41, 262, 837, 846, 881, 883, 885, 887, 888, 889, 891, 892, 893, 894, 895, 896, 897, or 898, wherein the PE-enhancing polypeptide has at least 90% sequence identity to any one of SEQ ID NOs: 335-344, 359-365, 371, 482, and 483.

372. The PE of claim 371, wherein the RT comprises: 20 (i) an amino acid sequence having at least 40% sequence identity to SEQ ID NO: 35 or 41; (ii) an amino acid sequence having at least 60% sequence identity to SEQ ID NO: 1, 34, or 40; (iii) an amino acid sequence having at least 70% sequence identity to SEQ ID NO: 6, 8, 9, 36, 37, 837, or 846; 25 (iv) an amino acid sequence having at least 75% sequence identity to SEQ ID NO: 4; (v) an amino acid sequence having at least 80% sequence identity to SEQ ID NO: 895 or 897; (vi) an amino acid sequence having at least 83% sequence identity to SEQ ID NO: 18, 19, 20, 21, 22, 23, 892, or 896; (vii) an amino acid sequence having at least 85% sequence identity to SEQ ID NO: 891; 30 (viii) an amino acid sequence having at least 87% sequence identity to SEQ ID NO: 889 or 898; (ix) an amino acid sequence having at least 90% sequence identity to SEQ ID NO: 7, 38, 262, 881, 883, or 893; (x) an amino acid sequence having at least 92% sequence identity to SEQ ID NO: 887 or 888; 35 (xi) an amino acid sequence having at least 95% sequence identity to SEQ ID NO: 24, 25, 26, 27, 28, 29, 30, 31, 32, 33, 885, or 894; or 404 Atty Dkt No: L1034381430WO (00376)(xii) an amino acid sequence having at least 99.7% sequence identity to SEQ ID NO: 2, 3, or 5.

373. A polymerase editor (PE) comprising a reverse transcriptase (RT), a DNA-binding polypeptide, and a PE-enhancing polypeptide, wherein the RT comprises an amino acid sequence 5 having at least 40% sequence identity to SEQ ID NO: 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30, 31, 32, 33, 34, 35, 36, 37, 38, 40, 41, 262, 837, 846, 881, 883, 885, 887, 888, 889, 891, 892, 893, 894, 895, 896, 897, or 898, wherein the DNA- binding polypeptide has at least 90% identity to any one of SEQ ID NOs: 387-420, and 484-489, and wherein the PE-enhancing polypeptide has at least 90% sequence identity to any one of SEQ ID NOs: 10 335-344, 359-365, 371, 482, and 483.

374. The PE of claim 373, wherein the RT comprises: (i) an amino acid sequence having at least 40% sequence identity to SEQ ID NO: 35 or 41; (ii) an amino acid sequence having at least 60% sequence identity to SEQ ID NO: 1, 34, or 40; 15 (iii) an amino acid sequence having at least 70% sequence identity to SEQ ID NO: 6, 8, 9, 36, 37, 837, or 846; (iv) an amino acid sequence having at least 75% sequence identity to SEQ ID NO: 4; (v) an amino acid sequence having at least 80% sequence identity to SEQ ID NO: 895 or 897; (vi) an amino acid sequence having at least 83% sequence identity to SEQ ID NO: 18, 19, 20, 20 21, 22, 23, 892, or 896; (vii) an amino acid sequence having at least 85% sequence identity to SEQ ID NO: 891; (viii) an amino acid sequence having at least 87% sequence identity to SEQ ID NO: 889 or 898; (ix) an amino acid sequence having at least 90% sequence identity to SEQ ID NO: 7, 38, 262, 25 881, 883, or 893; (x) an amino acid sequence having at least 92% sequence identity to SEQ ID NO: 887 or 888; (xi) an amino acid sequence having at least 95% sequence identity to SEQ ID NO: 24, 25, 26, 27, 28, 29, 30, 31, 32, 33, 885, or 894; or (xii) an amino acid sequence having at least 99.7% sequence identity to SEQ ID NO: 2, 3, or 30 5.

375. The PE of any one of claims 274-374, wherein said fusion protein comprises an amino acid sequence having at least 90% identical to any one of SEQ ID NOs: 808-812, and 899-916.

376. The PE of claim 375, wherein said fusion protein comprises an amino acid sequence having at least 95% identical to any one of SEQ ID NOs: 808-812, and 899-916. 35 377. The PE protein of claim 375 or 376, wherein said fusion protein comprises the amino acid sequence of any one of SEQ ID NOs: 808-812, and 899-916. 405 Atty Dkt No: L1034381430WO (00376)378. A ribonucleoprotein (RNP) complex comprising the PE of any one of claims 337- 368, and 375-377 and a PEgRNA bound to the DNA-binding polypeptide, wherein said PEgRNA comprises a primer binding site (PBS) and a DNA synthesis template.

379. The RNP complex of claim 378, wherein the PEgRNA comprises a spacer that 5 hybridizes to a eukaryotic target sequence.

380. The RNP complex of claim 379, wherein the eukaryotic target sequence comprises a mammalian target sequence.

381. A PE system for editing one or more target sequence in a target polynucleotide, said system comprising: 10 a) one or more PEgRNAs, or one or more polynucleotides encoding the one or more PEgRNAs, wherein the one or more PEgRNAs comprises an extension arm, wherein the extension arm comprises a primer binding site (PBS) and a DNA synthesis template sequence; and b) a PE of any one of claims 337-368, and 375-377; wherein said one or more PEgRNAs are capable of binding to said DNA-binding polypeptide 15 of said PE.

382. The PE system of claim 381, wherein each of the one or more PEgRNAs is capable of hybridizing to the target strand of said one or more target sequence and forming a complex with the DNA-binding polypeptide to direct said RGN polypeptide to bind to said one or more target sequence.

383. The PE system of claim 381 or 382, wherein the spacer hybridizes to a eukaryotic 20 target sequence.

384. The PE system of claim 383, wherein the eukaryotic target sequence comprises a mammalian target sequence.

385. The PE system of any one of claims 381-384, wherein said extension arm is at the 3' end of said PEgRNA. 25 386. The PE system of any one of claims 381-385, wherein said DNA synthesis template sequence is 19, 22, 23, 24, 25, 26, 29, 30, 32, 34, 37, 38, 40, 42, or 46 nucleotides in length.

387. The PE system of any one of claims 381-386, wherein said DNA synthesis template sequence comprises an RT template (RTT) sequence.

388. The PE system of any one of claims 381-387, wherein said primer binding site is 9, 30 11, 12, 13, or 15 nucleotides in length.

389. The PE system of any one of claims 381-388, wherein the PEgRNA comprises a CRISPR RNA comprising a CRISPR RNA (crRNA) repeat comprising a nucleotide sequence of any one of SEQ ID NOs: 444, 445, and 446, or that differs from any one of SEQ ID NOs: 444, 445, and 446 by 1 to 5 nucleotides, wherein said RGN polypeptide comprises an amino acid sequence having at 35 least 90% sequence identity to the amino acid sequence of SEQ ID NO: 387 or 389.

390. The PE system of claim 389, wherein the PEgRNA comprises a CRISPR RNA comprising a CRISPR RNA (crRNA) repeat comprising the nucleotide sequence of any one of SEQ 406 Atty Dkt No: L1034381430WO (00376)ID NOs: 444, 445, and 446, wherein said RGN polypeptide comprises the amino acid sequence of SEQ ID NO: 387 or 389.

391. The PE system of claim 389 or 390, wherein the PEgRNA comprises a tracrRNA comprising a nucleotide sequence having at least 90% sequence identity to any one of SEQ ID NOs: 5 447, 448, 449, and 450.

392. The PE system of claim 391, wherein the PEgRNA comprises a tracrRNA comprising a nucleotide sequence having at least 95% sequence identity to any one of SEQ ID NOs: 447, 448, 449, and 450.

393. The PE system of claim 391 or 392, wherein the PEgRNA comprises a tracrRNA 10 comprising the nucleotide sequence of any one of SEQ ID NOs: 447, 448, 449, and 450.

394. The PE system of any one of claims 381-388, wherein the PEgRNA comprises a CRISPR RNA comprising a CRISPR RNA (crRNA) repeat comprising a nucleotide sequence of any one of SEQ ID NO: 455, 456, and 457, or that differs from any one of SEQ ID NO: 455, 456, and 457 by 1 to 5 nucleotides, wherein said RGN polypeptide comprises an amino acid sequence having at 15 least 90% sequence identity to the amino acid sequence of SEQ ID NO:

388.

395. The PE system of claim 394, wherein the PEgRNA comprises a CRISPR RNA comprising a CRISPR RNA (crRNA) repeat comprising the nucleotide sequence of any one of SEQ ID NOs: 455, 456, and 457, wherein said RGN polypeptide comprises the amino acid sequence of SEQ ID NO:

388. 20 396. The PE system of claim 394 or 395, wherein the PEgRNA comprises a tracrRNA comprising a nucleotide sequence having at least 90% sequence identity to any one of SEQ ID NOs: 458, 459, 460, 461, and 462.

397. The PE system of claim 396, wherein the PEgRNA comprises a tracrRNA comprising a nucleotide sequence having at least 95% sequence identity to any one of SEQ ID NOs: 458, 459, 25 460, 461, and 462.

398. The PE system of claim 396 or 397, wherein the PEgRNA comprises a tracrRNA comprising the nucleotide sequence of any one of SEQ ID NOs: 458, 459, 460, 461, and 462.

399. The PE system of any one of claims 381-388, wherein the PEgRNA comprises a CRISPR RNA comprising a CRISPR RNA (crRNA) repeat comprising a nucleotide sequence of SEQ 30 ID NO: 468, or that differs from SEQ ID NO: 468 by 1 to 5 nucleotides, wherein said RGN polypeptide comprises an amino acid sequence having at least 90% sequence identity to the amino acid sequence of SEQ ID NO:

391.

400. The PE system of claim 399, wherein the PEgRNA comprises a CRISPR RNA comprising a CRISPR RNA (crRNA) repeat comprising the nucleotide sequence of SEQ ID NO: 468, 35 wherein said RGN polypeptide comprises the amino acid sequence of SEQ ID NO:

391.

401. The PE system of claim 399 or 400, wherein the PEgRNA comprises a tracrRNA comprising a nucleotide sequence having at least 90% sequence identity to SEQ ID NO:

469. 407 Atty Dkt No: L1034381430WO (00376)402. The PE system of claim 401, wherein the PEgRNA comprises a tracrRNA comprising a nucleotide sequence having at least 95% sequence identity to SEQ ID NO:

469.

403. The PE system of claim 401 or 402, wherein the PEgRNA comprises a tracrRNA comprising the nucleotide sequence of SEQ ID NO:

469. 5 404. The PE system of any one of claims 381-388, wherein the PEgRNA comprises a CRISPR RNA comprising a CRISPR RNA (crRNA) repeat comprising a nucleotide sequence of SEQ ID NO: 471 or 472, or that differs from SEQ ID NO: 471 or 472 by 1 to 5 nucleotides, wherein said RGN polypeptide comprises an amino acid sequence having at least 90% sequence identity to the amino acid sequence of SEQ ID NO:

390. 10 405. The PE system of claim 404, wherein the PEgRNA comprises a CRISPR RNA comprising a CRISPR RNA (crRNA) repeat comprising the nucleotide sequence of SEQ ID NO: 471 or 472, wherein said RGN polypeptide comprises the amino acid sequence of SEQ ID NO:

390.

406. The PE system of claim 404 or 405, wherein the PEgRNA comprises a tracrRNA comprising a nucleotide sequence having at least 90% sequence identity to SEQ ID NO: 473 or 474. 15 407. The PE system of claim 406, wherein the PEgRNA comprises a tracrRNA comprising a nucleotide sequence having at least 95% sequence identity to SEQ ID NO: 473 or 474.

408. The PE system of claim 406 or 407, wherein the PEgRNA comprises a tracrRNA comprising the nucleotide sequence of SEQ ID NO: 473 or 474.

409. The PE system of any one of claims 381-408, wherein said PE system further 20 comprises a nicking guide RNA or a polynucleotide comprising a nucleotide sequence encoding a nicking guide RNA.

410. The PE system of any one of claims 381-409, wherein said PE system further comprises a dominant negative MLH1 or a polynucleotide comprising a nucleotide sequence encoding a dominant negative MLH1. 25 411. The PE system of any one of claims 381-410, wherein said one or more polynucleotides encoding said one or more PEgRNAs and said polynucleotides encoding said RT and RGN polypeptide are on a single vector.

412. The PE system of any one of claims 381-411, wherein said one or more polynucleotides encoding said one or more PEgRNAs and said polynucleotides encoding said RT and 30 RGN polypeptide are on separate vectors.

413. The PE system of any one of claims 381-410, said polynucleotide encoding said RT and said polynucleotide encoding said RGN polypeptide are on separate vectors.

414. The PE system of any one of claims 381-410, wherein said polynucleotide encoding said one or more PEgRNAs, said polynucleotide encoding said RT, and said polynucleotide encoding 35 said RGN polypeptide are all on separate vectors. 408 Atty Dkt No: L1034381430WO (00376)415. The PE system of any one of claims 381-410, wherein said polynucleotides encoding said RT and DNA-binding polypeptide is within one nucleic acid molecule, and wherein said nucleic acid molecule is an RNA polynucleotide.

416. The PE system of claim 415, wherein said RNA polynucleotide is an mRNA. 5 417. The PE system of claim 415, wherein said RNA polynucleotide is a circRNA.

418. A cell comprising the PE of any one of claims 337-377, the RNP complex of any one of claims 378-380, or the PE system of any one of claims 381-417.

419. The cell of claim 418, wherein the cell is a prokaryotic cell.

420. The cell of claim 418, wherein the cell is a eukaryotic cell. 10 421. The cell of claim 420, wherein the eukaryotic cell is a mammalian cell.

422. The cell of claim 421, wherein the mammalian cell is a human cell.

423. The cell of claim 422, wherein the human cell is an immune cell.

424. The cell of claim 422, wherein the human cell is a stem cell.

425. The cell of claim 424, wherein the stem cell is an induced pluripotent stem cell. 15 426. The cell of claim 420, wherein the eukaryotic cell is an insect or avian cell.

427. The cell of claim 420, wherein the eukaryotic cell is a fungal cell.

428. The cell of claim 420, wherein the eukaryotic cell is a plant cell.

429. A plant or plant part comprising the plant cell of claim 428.

430. A pharmaceutical composition comprising the one or more polynucleotides of any 20 one of claims 1-20 and 41-137, the RT of any one of claims 21-40, the one or more vectors of any one of claims 138-167, the PE of any one of claims 274-377, the RNP complex of any one of claims 378- 380, the cell of any one of claims 168, 170-175, 418, and 420-425, or the PE system of any one of claims 381-417, and a pharmaceutically acceptable carrier.

431. A method for editing a target polynucleotide comprising a target sequence, said 25 method comprising delivering a PE system according to any one of claims 381-417 to said target sequence or a cell comprising the target sequence, wherein said method generates an edited target polynucleotide, and wherein components of said PE system are delivered simultaneously or sequentially to said target sequence or to said cell.

432. The method of claim 431, wherein said edited target polynucleotide comprises 30 insertion of heterologous DNA into the target polynucleotide.

433. The method of claim 431, wherein said edited target polynucleotide comprises deletion of at least one nucleotide from the target polynucleotide.

434. The method of claim 431, wherein said edited target polynucleotide comprises mutation of at least one nucleotide in the target polynucleotide. 35 435. A method for editing one or more target sequence in a target polynucleotide, said method comprising: a) assembling a ribonucleoprotein (RNP) complex by combining: 409 Atty Dkt No: L1034381430WO (00376)i) a PEgRNA comprising an extension arm, wherein said extension arm comprises a primer binding site (PBS) and a DNA synthesis template; and ii) a PE of any one of claims 337-368, and 375-377; under conditions suitable for formation of the RNP complex; and 5 b) contacting said target polynucleotide or a cell comprising said target polynucleotide with the assembled RNP complex; thereby editing said one or more target sequence.

436. The method of any one of claims 431-435, wherein said method is performed in vitro, in vivo, or ex vivo. 10 437. The method of any one of claims 431-436, wherein said target polynucleotide is within a cell.

438. The method of claim 437, wherein the cell is a eukaryotic cell.

439. The method of claim 438, wherein the eukaryotic cell is a mammalian cell.

440. A cell produced according to the method of claim 438, wherein said target 15 polynucleotide has been edited at said target sequence.

441. The cell of claim 440, wherein the cell is a prokaryotic cell.

442. The cell of claim 440, wherein the cell is a eukaryotic cell.

443. The cell of claim 442, wherein the eukaryotic cell is a mammalian cell.

444. The cell of claim 443, wherein the mammalian cell is a human cell. 20 445. The cell of claim 444, wherein the human cell is an immune cell.

446. The cell of claim 444, wherein the human cell is a stem cell.

447. The cell of claim 446, wherein the stem cell is an induced pluripotent stem cell.

448. The cell of claim 442, wherein the eukaryotic cell is an insect or avian cell.

449. The cell of claim 442, wherein the eukaryotic cell is a fungal cell. 25 450. The cell of claim 442, wherein the eukaryotic cell is a plant cell.

451. A plant or plant part comprising the plant cell of claim 450.

452. A pharmaceutical composition comprising the cell of any one of claims 440, and 442- 447 and a pharmaceutically acceptable carrier.

453. A method for treating a subject having or at risk of developing a disease, disorder, or 30 condition, the method comprising: administering to the subject the one or more polynucleotides of any one of claims 41-137, the one or more vectors of any one of claims 138-167, the PE of any one of claims 274-368, and 375-377, the RNP complex of any one of claims 378-380, the cell of any one of claims 168, 170-175, 418, 420- 425, 440, and 442-447, the PE system of any one of claims 381-417, or the pharmaceutical 35 composition of claim 430 or 452.

454. The method of claim 453, wherein said disease, disorder, or condition is associated with a mutation and said treating comprises correcting said mutation. 410 Atty Dkt No: L1034381430WO (00376)455. Use of the one or more polynucleotides of any one of claims 41-137, the one or more vectors of any one of claims 138-167, the PE of any one of claims 274-368, and 375-377, the RNP complex of any one of claims 378-380, the cell of any one of claims 168, 170-175, 418, 420-425, 440, and 442-447, the PE system of any one of claims 381-417, or the pharmaceutical composition of 5 claim 430 or 452 for the treatment of a disease, disorder, or condition in a subject having or at risk of developing said disease, disorder, or condition.

456. The use of claim 455, wherein said disease, disorder, or condition is associated with a mutation and said treating comprises correcting said mutation.

457. Use of the one or more polynucleotides of any one of claims 41-137, the one or more 10 vectors of any one of claims 138-167, the PE of any one of claims 274-368, and 375-377, the RNP complex of any one of claims 378-380, the cell of any one of claims 168, 170-175, 418, 420-425, 440, and 442-447, the PE system of any one of claims 381-417, or the pharmaceutical composition of claim 430 or 452 for the manufacture of a medicament useful for treating a disease, disorder, or condition. 15 458. The use of claim 457, wherein said disease, disorder, or condition is associated with a mutation and an effective amount of said medicament corrects said mutation.

459. Use of the PE system of one of claims 381-417 for editing a target polynucleotide comprising a target sequence, wherein said PE system is delivered to said target sequence or a cell comprising the target sequence, wherein an edited target polynucleotide is generated, and wherein 20 components of said PE system are delivered simultaneously or sequentially to said target sequence or said cell.

460. The use of claim 459, wherein said edited target polynucleotide comprises insertion of heterologous DNA into the target polynucleotide.

461. The use of claim 459, wherein said edited target polynucleotide comprises deletion of 25 at least one nucleotide from the target polynucleotide.

462. The use of claim 459, wherein said edited target polynucleotide comprises mutation of at least one nucleotide in the target polynucleotide.

463. Use of the PE according to any one of claims 337-368, and 375-377 for editing one or more target sequences in a target polynucleotide, wherein a ribonucleoprotein (RNP) complex is 30 assembled by combining: i) a PEgRNA comprising an extension arm, wherein said extension arm comprises a primer binding site (PBS) and a DNA synthesis template; and ii) said PE; under conditions suitable for formation of the RNP complex; and 35 wherein said target polynucleotide or a cell comprising said target polynucleotide are contacted with the assembled RNP complex; and wherein said one or more target sequence are edited with said PE. 411 Atty Dkt No: L1034381430WO (00376)464. A PE system of any one of claims 381-417 for editing a target polynucleotide comprising a target sequence.

465. The PE system of claim 464, wherein said target polynucleotide is within a cell.

466. The PE system of claim 464 or 465, wherein said editing comprises insertion of 5 heterologous DNA into the target polynucleotide.

467. The PE system of claim 464 or 465, wherein said editing comprises deletion of at least one nucleotide from the target polynucleotide.

468. The PE system of claim 464 or 465, wherein said editing comprises mutation of at least one nucleotide in the target polynucleotide. 10 469. A ribonucleoprotein (RNP) complex comprising: i) a PEgRNA comprising an extension arm, wherein said extension arm comprises a primer binding site (PBS) and a DNA synthesis template; and ii) the PE of any one of claims 337-368, and 375-377; for editing a target polynucleotide comprising a target sequence. 15 470. The RNP complex of claim 469, wherein said target polynucleotide is within a cell.

471. The RNP complex of claim 470, wherein the cell is a eukaryotic cell.

472. The RNP complex of claim 471, wherein the eukaryotic cell is a mammalian cell.

473. The one or more polynucleotides of any one of claims 41-137, the one or more vectors of any one of claims 138-167, the PE of any one of claims 274-368, and 375-377, the RNP 20 complex of any one of claims 378-380, the cell of any one of claims 168, 170-175, 418, 420-425, 440, and 442-447, the PE system of any one of claims 381-417, or the pharmaceutical composition of claim 430 or 452 for treating a disease, disorder, or condition.

474. The one or more polynucleotides, the one or more vectors, the PE, the RNP complex, the cell, the PE system, or the pharmaceutical composition of claim 473, wherein said disease, 25 disorder, or condition is associated with a mutation and an effective amount of the one or more polynucleotides, the one or more vectors, the PE, the RNP complex, the cell, the PE system, or the pharmaceutical composition corrects said mutation. 412 Atty Dkt No: L1034381430WO (00376)

Images