Intensity extraction with interpolation and adaptation for base calling

Abstract

A computer-implemented method comprises: determining coefficients corresponding to a section of a flow cell; accessing an image depicting the section of the flow cell and intensity emissions from a target cluster of concatemers; and generating a base call for the target cluster of concatemers by applying the coefficients to the intensity emissions for the target cluster of concatemers.

Description

(19) *EP004679300A2* (11) EP 4 679 300 A2 (12) EUROPEAN PATENT APPLICATION (43) Date of publication: 14.01.2026 Bulletin 2026 / 03 (21) Application number: 25218859.4 (22) Date of filing: 14.07.2022 (51) International Patent Classification (IPC): G06F 18 / 2413 (2023.01) (52) Cooperative Patent Classification (CPC): G06V 20 / 698; G06F 18 / 23213; G06F 18 / 24137; G06V 10 / 763; G06V 10 / 778; G06V 10 / 82; G06V 2201 / 04 (84) Designated Contracting States: AL AT BE BG CH CY CZ DE DK EE ES FI FR GB GR HR HU IE IS IT LI LT LU LV MC MK MT NL NO PL PT RO RS SE SI SK SM TR (30) Priority: 19.07.2021 US 202163223408 P 26.10.2021 US 202117511483 (62) Document number(s) of the earlier application(s) in accordance with Art. 76 EPC: 22754607.4 / 4 374 343 (71) Applicant: ILLUMINA, INC. San Diego, CA 92122 (US) (72) Inventors: • KAGALWALLA, Abde Ali Hunaid San Diego, 92122 (US) • OJARD, Eric Jon San Diego, 92122 (US) • MEHIO, Rami San Diego, 92122 (US) • PARNABY, Gavin Derek San Diego, 92122 (US) • UDPA, Nitin San Diego, 92122 (US) • LU, Bo San Diego, 92122 (US) • VIECELI, John S. San Diego, 92122 (US) (74) Representative: Lowden, Samuel Robert James Marks & Clerk LLP 2nd Floor Wytham Court 11 West Way Oxford OX2 0JB (GB) Remarks: This application was filed on 26.11.2025 as a divisional application to the application mentioned under INID code 62. (54) INTENSITY EXTRACTION WITH INTERPOLATION AND ADAPTATION FOR BASE CALLING (57) A computer-implemented method comprises: determining coefficients corresponding to a section of a flow cell; accessing an image depicting the section of the flow cell and intensity emissions from a target cluster of concatemers; and generating a base call for the target cluster of concatemers by applying the coefficients to the intensity emissions for the target cluster of concatemers. EP 4 67 9 30 0 A 2 Processed by Luminess, 75001 PARIS (FR) Description PRIORITYAPPLICATIONS

[0001] This application claims the benefit of and priority to U.S. Provisional Patent Application No. 63 / 223,408, entitled "Specialist Signal Profilers for Base Calling," filed on July 19, 2021, (Atty. Docket No. ILLM 1041‑1 / IP‑2063-PRV).The priority applications are hereby incorporated by reference for all purposes.

[0002] This application also claims benefit of and priority to U.S. Nonprovisional Patent Application No. 17 / 511,483, entitled "Intensity Extraction with Crosstalk Attenuation Using Interpolation and Adaptation Calling," filed on October 26, 2021, (Atty. Docket No. ILLM 1053‑1 / IP‑2214-US). STATEMENT OF COMMON OWNERSHIP

[0003] Pursuant to 35 USC §102(b)(2)(C) and MPEP §2146.02(I), Applicant hereby states that this application, U.S. Provisional Patent ApplicationNo. 63 / 020,449, andU.S.Nonprovisional Patent ApplicationNo. 17 / 308,035, not later than the effective filing date of this application, were owned by or subject to an obligation of assignment to the same person (Illumina, Inc.), and that Illumina Software, Inc., the named applicant and assignee on this application, is a wholly owned subsidiary of Illumina, Inc. FIELD OF THE TECHNOLOGY DISCLOSED

[0004] The technologydisclosed relates toartificial intelligence typecomputersanddigital dataprocessingsystemsand corresponding data processing methods and products for emulation of intelligence (i.e., knowledge based systems, reasoningsystems,andknowledgeacquisitionsystems); and includingsystems for reasoningwithuncertainty (e.g., fuzzy logic systems), adaptive systems, machine learning systems, and artificial neural networks. In particular, the technology disclosed relates to using deep neural networks such as deep convolutional neural networks for analyzing data. INCORPORATIONS

[0005] The following are incorporated by reference for all purposes as if fully set forth herein: US Nonprovisional Patent Application No. 15 / 936,365, entitled "Detection Apparatus Having a Microfluorometer, a Fluidic System, and a Flow Cell Latch Clamp Module," filed on March 26, 2018; US Nonprovisional Patent Application No. 16 / 567,224, entitled "Flow Cells and Methods Related to Same," filed on September 11, 2019; US Nonprovisional Patent Application No. 16 / 439,635, entitled "Device for Luminescent Imaging," filed on June 12, 2019; US Nonprovisional Patent Application No. 15 / 594,413, entitled "Integrated Optoelectronic Read Head and Fluidic Cartridge Useful for Nucleic Acid Sequencing," filed on May 12, 2017; US Nonprovisional Patent Application No. 16 / 351,193, entitled "Illumination for Fluorescence Imaging Using Objective Lens," filed on March 12, 2019; US Nonprovisional Patent Application No. 12 / 638,770, entitled "Dynamic Autofocus Method and System for Assay Imager," filed on December 15, 2009; US Nonprovisional Patent Application No. 13 / 783,043, entitled "Kinetic Exclusion Amplification of Nucleic Acid Libraries," filed on March 1, 2013; US Nonprovisional Patent Application No. 13 / 006,206, entitled "Data Processing System and Methods," filed on January 13, 2011; USNonprovisionalPatentApplicationNo.14 / 530,299, entitled "ImageAnalysisUseful forPatternedObjects," filedon October 31, 2014; US Nonprovisional Patent Application No. 15 / 153,953, entitled "Methods and Systems for Analyzing Image Data," filed on December 3, 2014; USNonprovisional Patent Application No. 14 / 020,570, entitled "CentroidMarkers for Image Analysis of High Density Clusters In Complex Polynucleotide Sequencing," filed on September 6, 2013; USNonprovisionalPatentApplicationNo.14 / 530,299, entitled "ImageAnalysisUseful forPatternedObjects," filedon October 31, 2014; USNonprovisional Patent Application No. 12 / 565,341, entitled "Method and System for Determining the Accuracy of DNA Base Identifications," filed on September 23, 2009; US Nonprovisional Patent Application No. 12 / 295,337, entitled "Systems and Devices for Sequence by Synthesis 2 EP 4 679 300 A2 5 10 15 20 25 30 35 40 45 50 55 Analysis," filed on March 30, 2007; US Nonprovisional Patent Application No. 12 / 020,739, entitled "Image Data Efficient Genetic Sequencing Method and System," filed on January 28, 2008; US Nonprovisional Patent Application No. 13 / 833,619, entitled "Biosensors for Biological or Chemical Analysis and Systems and Methods for Same," filed on March 15, 2013, (Attorney Docket No. IP‑0626-US); US Nonprovisional Patent Application No. 15 / 175,489, entitled "Biosensors for Biological or Chemical Analysis and Methods of Manufacturing the Same," filed on June 7, 2016, (Attorney Docket No. IP‑0689-US); USNonprovisional PatentApplicationNo. 13 / 882,088, entitled "Microdevices andBiosensorCartridges forBiological or Chemical Analysis andSystems andMethods for theSame," filed onApril 26, 2013, (AttorneyDocket No. IP‑0462- US); US Nonprovisional Patent Application No. 13 / 624,200, entitled "Methods and Compositions for Nucleic Acid Sequencing," filed on September 21, 2012, (Attorney Docket No. IP‑0538-US); U.S. Provisional Patent Application No. 62 / 821,602, entitled "Training Data Generation for Artificial Intelligence- Based Sequencing," filed 21 March 2019 (Attorney Docket No. ILLM 1008‑1 / IP‑1693-PRV); U.S. Provisional Patent Application No. 62 / 821,618, entitled "Artificial Intelligence-Based Generation of Sequencing Metadata," filed 21 March 2019 (Attorney Docket No. ILLM 1008‑3 / IP‑1741-PRV); U.S. Provisional Patent Application No. 62 / 821,681, entitled "Artificial Intelligence-Based Base Calling," filed 21 March 2019 (Attorney Docket No. ILLM 1008‑4 / IP‑1744-PRV); U.S. Provisional Patent Application No. 62 / 821,724, entitled "Artificial Intelligence-Based Quality Scoring," filed 21 March 2019 (Attorney Docket No. ILLM 1008‑7 / IP‑1747-PRV); U.S. Provisional Patent Application No. 62 / 821,766, entitled "Artificial Intelligence-Based Sequencing," filed 21 March 2019 (Attorney Docket No. ILLM 1008‑9 / IP‑1752-PRV); NLApplicationNo. 2023310, entitled "TrainingDataGeneration for Artificial Intelligence-BasedSequencing," filed 14 June 2019 (Attorney Docket No. ILLM 1008‑11 / IP‑1693-NL); NLApplicationNo. 2023311, entitled "Artificial Intelligence-BasedGenerationofSequencingMetadata," filed14June 2019 (Attorney Docket No. ILLM 1008‑12 / IP‑1741-NL); NLApplicationNo. 2023312, entitled "Artificial Intelligence-BasedBaseCalling," filed 14 June 2019 (AttorneyDocket No. ILLM 1008‑13 / IP‑1744-NL); NL Application No. 2023314, entitled "Artificial Intelligence-Based Quality Scoring," filed 14 June 2019 (Attorney Docket No. ILLM 1008‑14 / IP‑1747-NL); NL Application No. 2023316, entitled "Artificial Intelligence-Based Sequencing," filed 14 June 2019 (Attorney Docket No. ILLM 1008‑15 / IP‑1752-NL); U.S. Nonprovisional Patent Application No. 16 / 825,987, entitled "Training Data Generation for Artificial Intelligence- Based Sequencing," filed 20 March 2020 (Attorney Docket No. ILLM 1008‑16 / IP‑1693-US); U.S. Nonprovisional Patent Application No. 16 / 825,991 entitled "Training Data Generation for Artificial Intelligence- Based Sequencing," filed 20 March 2020 (Attorney Docket No. ILLM 1008‑17 / IP‑1741-US); U.S. Nonprovisional Patent Application No. 16 / 826,126, entitled "Artificial Intelligence-Based Base Calling," filed 20 March 2020 (Attorney Docket No. ILLM 1008‑18 / IP‑1744-US); U.S. Nonprovisional Patent Application No. 16 / 826,134, entitled "Artificial Intelligence-Based Quality Scoring," filed 20 March 2020 (Attorney Docket No. ILLM 1008‑19 / IP‑1747-US); U.S. Nonprovisional Patent Application No. 16 / 826,168, entitled "Artificial Intelligence-Based Sequencing," filed 21 March 2020 (Attorney Docket No. ILLM 1008‑20 / IP‑1752-PRV); U.S. Provisional Patent Application No. 62 / 849,091, entitled," Systems and Devices for Characterization and Performance Analysis of Pixel-Based Sequencing," filed May 16, 2019 (Attorney Docket No. ILLM 1011‑1 / IP‑1750-PRV); U.S. Provisional Patent Application No. 62 / 849,132, entitled, "Base Calling Using Convolutions," filed May 16, 2019 (Attorney Docket No. ILLM 1011‑2 / IP‑1750-PR2); U.S. Provisional Patent Application No. 62 / 849,133, entitled, "Base Calling Using Compact Convolutions," filed May 16, 2019 (Attorney Docket No. ILLM 1011‑3 / IP‑1750-PR3); U.S. Provisional Patent Application No. 62 / 979,384, entitled, "Artificial Intelligence-Based Base Calling of Index Sequences," filed February 20, 2020 (Attorney Docket No. ILLM 1015‑1 / IP‑1857-PRV); U.S. Provisional Patent Application No. 62 / 979,414, entitled, "Artificial Intelligence-Based Many-To-Many Base Calling," filed February 20, 2020 (Attorney Docket No. ILLM 1016‑1 / IP‑1858-PRV); U.S. Provisional Patent ApplicationNo. 62 / 979,385, entitled, "KnowledgeDistillation-BasedCompression of Artificial Intelligence-Based Base Caller," filed February 20, 2020 (Attorney Docket No. ILLM 1017‑1 / IP‑1859-PRV); U.S.ProvisionalPatentApplicationNo.62 / 979,412, entitled, "Multi-CycleClusterBasedRealTimeAnalysisSystem," filed February 20, 2020 (Attorney Docket No. ILLM 1020‑1 / IP‑1866-PRV); U.S. Provisional Patent Application No. 62 / 979,411, entitled, "Data Compression for Artificial Intelligence-Based 3 EP 4 679 300 A2 5 10 15 20 25 30 35 40 45 50 55 Base Calling," filed February 20, 2020 (Attorney Docket No. ILLM 1029‑1 / IP‑1964-PRV); U.S. Nonprovisional Patent Application No. 63 / 020,449, entitled "Equalization-Based Image Processing and Spatial Crosstalk Attenuator," filed May 5, 2020 (Attorney Docket Number ILLM 1032‑1 / IP‑1991-PRV); U.S. Nonprovisional Patent Application No. 17 / 308,035, entitled "Equalization-Based Image Processing and Spatial Crosstalk Attenuator," filed May 4, 2021 (Attorney Docket Number ILLM 1032‑2 / IP‑1991-US); and U.S. Provisional Patent Application No. 62 / 979,399, entitled, "Squeezing Layer for Artificial Intelligence-Based Base Calling," filed February 20, 2020 (Attorney Docket No. ILLM 1030‑1 / IP‑1982-PRV). BACKGROUND

[0006] Thesubjectmatter discussed in this section shouldnot beassumed tobeprior artmerely asa result of itsmention in this section. Similarly, a problemmentioned in this section or associatedwith the subjectmatter providedasbackground should not be assumed to have been previously recognized in the prior art. The subject matter in this section merely represents different approaches, which in and of themselves can also correspond to implementations of the claimed technology.

[0007] The rapid improvement in computation capability has made deep Convolution Neural Networks (CNNs) a great success in recent years onmany computer vision tasks with significantly improved accuracy. During the inference phase, many applications demand low latency processing of one image with strict power consumption requirement, which reduces the efficiency of Graphics Processing Unit (GPU) and other general-purpose platform, bringing opportunities for specific acceleration hardware,e.g., FieldProgrammableGateArray (FPGA), by customizing thedigital circuit specific for the deep learning algorithm inference. However, deploying CNNs on portable and embedded systems is still challenging due to large data volume, intensive computation, varying algorithm structures, and frequent memory accesses.

[0008] As convolution contributes most operations in CNNs, the convolution acceleration scheme significantly affects the efficiency and performance of a hardware CNN accelerator. Convolution involves multiply and accumulate (MAC) operationswith four levelsof loops that slidealongkernel and featuremaps.Thefirst loop level computes theMACofpixels within a kernel window. The second loop level accumulates the sum of products of theMAC across different input feature maps. After finishing the first and second loop levels, a final output element in the output featuremap is obtained by adding the bias. The third loop level slides the kernel windowwithin an input featuremap. The fourth loop level generates different output feature maps.

[0009] FPGAs have gained increasing interest and popularity in particular to accelerate inference tasks, due to their (1) high degree of reconfigurability, (2) faster development time compared to Application Specific IntegratedCircuits (ASICs) to catch upwith the rapid evolving of CNNs, (3) good performance, and (4) superior energy efficiency compared toGPUs. The high performance and efficiency of an FPGA can be realized by synthesizing a circuit that is customized for a specific computation to directly process billions of operations with the customized memory systems. For instance, hundreds to thousands of digital signal processing (DSP) blocks on modern FPGAs support the core convolution operation, e.g., multiplication and addition, with high parallelism. Dedicated data buffers between external on-chip memory and on-chip processing engines (PEs) can be designed to realize the preferred dataflow by configuring tens of Mbyte on-chip block random access memories (BRAM) on the FPGA chip.

[0010] Efficient dataflow and hardware architecture of CNN acceleration are desired to minimize data communication while maximizing resource utilization to achieve high performance. An opportunity arises to design methodology and framework to accelerate the inference process of various CNN algorithms on acceleration hardware with high perfor- mance, efficiency, and flexibility. CNN algorithms and other machine learning algorithms can be applied to a variety of application areas, including calling bases (e.g., A, C, T, or G) of unknown nucleotides using a biological sequencing machine.

[0011] Various protocols in biological or chemical research involve performing a large number of controlled reactions on local support surfaces or within predefined reaction chambers. The desired reactions may then be observed or detected, andsubsequent analysismayhelp identify or reveal propertiesof chemicals involved in the reaction. For example, in some multiplex assays, anunknownanalyte havingan identifiable label (e.g., fluorescent label)maybeexposed to thousandsof knownprobes under controlled conditions. Each knownprobemaybedeposited into a correspondingwell of amicroplate. Observing any chemical reactions that occur between the known probes and the unknown analyte within the wells may help identify or reveal properties of the analyte. Other examples of such protocols include known DNA sequencing processes, such as sequencing-by-synthesis or cyclic-array sequencing. In cyclic-array sequencing, a dense array of DNA features (e.g., template nucleic acids) are sequenced through iterative cycles of enzymaticmanipulation. After each cycle, an image may be captured and subsequently analyzed with other images to determine a sequence of the DNA features.

[0012] Asamore specific example, one knownDNAsequencing systemusesapyrosequencingprocessand includes a chip havinga fusedfiber-optic faceplatewithmillionsofwells. A single capturebeadhaving clonally amplified sstDNA from a genome of interest is deposited into each well. After the capture beads are deposited into the wells, nucleotides are 4 EP 4 679 300 A2 5 10 15 20 25 30 35 40 45 50 55 sequentially added to thewells by flowing a solution containing a specific nucleotide along the faceplate. The environment within the wells is such that if a nucleotide flowing through a particular well complements the DNA strand on the corresponding capture bead, the nucleotide is added to the DNA strand. A colony of DNA strands is called a cluster. Incorporationof thenucleotide into thecluster initiatesaprocess that ultimately generatesachemiluminescent light signal. The system includes aCCDcamera that is positioned directly adjacent to the faceplate and is configured to detect the light signals from the DNA clusters in the wells. Subsequent analysis of the images taken throughout the pyrosequencing process can determine a sequence of the genome of interest.

[0013] However, the above pyrosequencing system, in addition to other systems, may have certain limitations. For example, the fiber-optic faceplate is acid-etched tomakemillions of small wells. Although thewellsmay be approximately spaced apart from each other, it is difficult to know a precise location of a well in relation to other adjacent wells. When the CCDcamera ispositioneddirectly adjacent to the faceplate, thewells arenot evenly distributedalong thepixelsof theCCD camera and, as such, the wells are not aligned in a known manner with the pixels. Spatial crosstalk is inter-well crosstalk between the adjacent wells and makes distinguishing true light signals from the well of interest from other unwanted light signals difficult in the subsequent analysis. Also, fluorescent emissions are substantially isotropic. As the density of the analytes increases, it becomes increasingly challenging tomanageor account for unwanted light emissions fromadjacent analytes (e.g., crosstalk). As a result, data recorded during the sequencing cycles must be carefully analyzed.

[0014] Base calling accuracy is crucial for high-throughput DNA sequencing and downstream analysis such as read mapping and genome assembly. Spatial crosstalk between adjacent clusters accounts for a large portion of sequencing errors. Accordingly, an opportunity arises to reduce DNA sequencing errors and improve base calling accuracy by correcting spatial crosstalk in the cluster intensity data. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] In the drawings, like reference characters generally refer to like parts throughout the different views. Also, the drawings are not necessarily to scale, with an emphasis instead generally being placed upon illustrating the principles of the technology disclosed. In the following description, various implementations of the technology disclosed are described with reference to the following drawings, in which. Fig. 1 illustrates a cross-section of a biosensor that can be used in various embodiments. Fig. 2 depicts one implementation of a flow cell that contains clusters in its tiles. Fig. 3 illustratesanexampleflowcellwith eight lanes, andalso illustratesazoom-inonone tile and its clustersand their surrounding background. Fig. 4 is a simplified block diagram of the system for analysis of sensor data from a sequencing system, such as base call sensor outputs. Fig. 5 is a simplified diagram showing aspects of the base calling operation, including functions of a runtime program executed by a host processor. Fig. 6 is a simplified diagram of a configuration of a configurable processor such as that of Fig. 4. Fig. 7 shows a system that generates and / or updates sharpening mask(s). Fig. 8A illustrates a plurality of sharpening masks used for corresponding sections of sequencing images generated for corresponding regionsof a flowcell,whereeach tile of the flowcell is divided in 3×3sub-tile regions,with eachsub- tile region assigned one or more corresponding sharpening masks. Fig. 8B illustrates a plurality of sharpening masks used for corresponding sections of sequencing images generated for corresponding regionsof a flowcell,whereeach tile of the flowcell is divided in 1×9sub-tile regions,with eachsub- tile region assigned one or more corresponding sharpening masks. Fig. 8C illustrates a plurality of sharpening masks used for corresponding sections of sequencing images generated for corresponding regions of a flow cell, where each tile of the flow cell is divided inmultiple periodically occurring sub- tile regions, with similar sub-regions occurring periodically in a tile are assigned one or more corresponding sharpening masks. Fig. 9A shows one implementation of base-wiseGaussian fits that contain at their centers base-wise intensity targets which are used as ground truth values for error calculation during training. Fig. 9B shows one implementation of an adaptive technique that can be used to train a base caller. Figs. 10A‑10K, in combination, illustrate various implementations of using trained sharpening masks, to attenuate spatial crosstalk from sensor pixels and to base call clusters using crosstalk-corrected sensor data. Fig. 11A illustrates a method of base calling, based on convolution of at least a section of a sequencing image and subsequent interpolation toassignoneormoreweighted featurevalues toacluster, andbasecalling theclusterbased on the assigned one or more weighted feature values. Fig. 11B illustrates comparison of performance results of the disclosed intensity extraction techniques using sharpening masks, with various other intensity extraction techniques associated with base calling. 5 EP 4 679 300 A2 5 10 15 20 25 30 35 40 45 50 55 Fig. 11C illustrates comparison of other performance results of the disclosed techniques using sharpening masks, with various other techniques of base calling. Fig. 12 illustrates a method of base calling, based on convolution of at least a section of a sequencing image and subsequent interpolation toassignoneormoreweighted featurevalues toacluster, andbasecalling theclusterbased on the assigned one or more weighted feature values, where coefficients of the sharpening masks are adaptively updated during the sequencing run. Fig. 13 illustrates adaptation of coefficients of sharpening masks used for intensity extraction. Fig. 14 illustrates comparison of performance results of the disclosed intensity extraction techniques using sharpen- ing masks and adaptation, with another intensity extraction techniques that does not use adaptation. Fig. 15 illustrates comparison of performance results of the disclosed intensity extraction techniques using sharpen- ing masks and adaptation, with another intensity extraction techniques that does not use adaptation. Fig. 16 is a computer system that can be used to implement the technology disclosed. DETAILED DESCRIPTION

[0016] The following description will typically be with reference to specific structural implementations andmethods. It is tobeunderstood that there isno intention to limit the technology to thespecifically disclosed implementationsandmethods but that the technology may be practiced using other features, elements, methods and implementations. Preferred implementations are described to illustrate the present technology, not to limit its scope, which is defined by the claims. Those of ordinary skill in the art will recognize a variety of equivalent variations on the description that follows.

[0017] As used herein, the terms "polynucleotide" or "nucleic acids" refer to deoxyribonucleic acid (DNA), but where appropriate the skilled artisan will recognize that the systems and devices herein can also be utilized with ribonucleic acid (RNA). The terms should be understood to include, as equivalents, analogs of either DNA or RNAmade from nucleotide analogs. The termsasusedherein also encompasses cDNA, that is complementary, or copy,DNAproduced fromanRNA template, for example by the action of reverse transcriptase.

[0018] The single stranded polynucleotide molecules sequenced by the systems and devices herein can have originated in single-stranded form, as DNA or RNA or have originated in double-stranded DNA (dsDNA) form (e.g., genomicDNA fragments, PCRandamplificationproducts and the like). Thus, a single strandedpolynucleotidemaybe the senseor antisense strandof apolynucleotide duplex.Methodsof preparation of single strandedpolynucleotidemolecules suitable for use in themethod of the disclosure using standard techniques arewell known in the art. The precise sequence of the primary polynucleotide molecules is generally not material to the disclosure, and may be known or unknown. The single stranded polynucleotide molecules can represent genomic DNAmolecules (e.g., human genomic DNA) including both intron and exon sequences (coding sequence), as well as non-coding regulatory sequences such as promoter and enhancer sequences.

[0019] In certain embodiments, the nucleic acid to be sequenced through use of the current disclosure is immobilized upon a substrate (e.g., a substrate within a flowcell or one or more beads upon a substrate such as a flowcell, etc.). The term "immobilized" as used herein is intended to encompass direct or indirect, covalent or non-covalent attachment, unless indicated otherwise, either explicitly or by context. In certain embodiments covalent attachment may be preferred, but generally all that is required is that the molecules (e.g., nucleic acids) remain immobilized or attached to the support under conditions in which it is intended to use the support, for example in applications requiring nucleic acid sequencing.

[0020] The term "solid support" (or "substrate" in certain usages) as used herein refers to any inert substrate ormatrix to which nucleic acids can be attached, such as for example glass surfaces, plastic surfaces, latex, dextran, polystyrene surfaces, polypropylene surfaces, polyacrylamidegels, gold surfaces, and siliconwafers. Inmanyembodiments, the solid support is a glass surface (e.g., the planar surface of a flowcell channel). In certain embodiments the solid support may comprisean inert substrateormatrixwhichhasbeen "functionalized," for exampleby theapplicationofa layer or coatingof an intermediate material comprising reactive groups which permit covalent attachment to molecules such as polynucleo- tides.Bywayof non-limitingexample such supports can includepolyacrylamidehydrogels supportedonan inert substrate such as glass. In such embodiments the molecules (polynucleotides) can be directly covalently attached to the intermediate material (e.g., the hydrogel) but the intermediate material can itself be non-covalently attached to the substrate or matrix (e.g., the glass substrate). Covalent attachment to a solid support is to be interpreted accordingly as encompassing this type of arrangement.

[0021] As indicated above, the present disclosure comprises novel systems and devices for sequencing nucleic acids. Aswill beapparent to thoseof skill in theart, referencesherein toaparticular nucleic acid sequencemay, dependingon the context, also refer to nucleic acidmoleculeswhich comprise suchnucleic acid sequence. Sequencing of a target fragment means that a readof the chronological order of bases is established. Thebases that are readdonot need tobecontiguous, although this is preferred, nor does every base on the entire fragment have to be sequenced during the sequencing. Sequencing can be carried out using any suitable sequencing technique, wherein nucleotides or oligonucleotides are added successively to a free 3’ hydroxyl group, resulting in synthesis of a polynucleotide chain in the 5’ to 3’ direction. The 6 EP 4 679 300 A2 5 10 15 20 25 30 35 40 45 50 55 nature of the nucleotide added is preferably determined after each nucleotide addition. Sequencing techniques using sequencing by ligation, wherein not every contiguous base is sequenced, and techniques such as massively parallel signature sequencing (MPSS) where bases are removed from, rather than added to, the strands on the surface are also amenable to use with the systems and devices of the disclosure.

[0022] In certain embodiments, the current disclosure discloses sequencing-by-synthesis (SBS). In SBS, four fluor- escently labeledmodifiednucleotidesareused to sequencedenseclusters of amplifiedDNA (possiblymillionsof clusters) present on the surfaceof a substrate (e.g., a flowcell). Variousadditional aspects regardingSBSproceduresandmethods, whichcanbeutilizedwith thesystemsanddevicesherein, aredisclosed in, for example,WO04018497,WO04018493and U.S. Pat. No. 7,057,026 (nucleotides), WO05024010 and WO06120433 (polymerases), WO05065814 (surface attach- ment techniques), and WO 9844151, WO06064199 and WO07010251, the contents of each of which are incorporated herein by reference in their entirety.

[0023] In particular uses of the systems / devices herein the flowcells containing the nucleic acid samples for sequencing are placed within the appropriate flowcell holder. The samples for sequencing can take the form of single molecules, amplified single molecules in the form of clusters, or beads comprising molecules of nucleic acid. The nucleic acids are prepared such that they comprise an oligonucleotide primer adjacent to an unknown target sequence. To initiate the first SBSsequencing cycle, oneormoredifferently labelednucleotides, andDNApolymerase, etc., are flowed into / through the flowcell by thefluid flowsubsystem(variousembodimentsofwhicharedescribedherein).Either asingle nucleotidecanbe added at a time, or the nucleotides used in the sequencing procedure can be specially designed to possess a reversible terminationproperty, thusallowingeachcycleof thesequencing reaction tooccur simultaneously in thepresenceofall four labelednucleotides (A,C,T,G).Where the four nucleotidesaremixed together, thepolymerase isable to select the correct base to incorporate and each sequence is extended by a single base. In such methods of using the systems, the natural competition between all four alternatives leads to higher accuracy than wherein only one nucleotide is present in the reaction mixture (where most of the sequences are therefore not exposed to the correct nucleotide). Sequences where a particular base is repeated one after another (e.g., homopolymers) are addressed like any other sequence and with high accuracy.

[0024] The fluid flow subsystem also flows the appropriate reagents to remove the blocked 3’ terminus (if appropriate) and the fluorophore from each incorporated base. The substrate can be exposed either to a second round of the four blocked nucleotides, or optionally to a second round with a different individual nucleotide. Such cycles are then repeated, and the sequenceof each cluster is readover themultiple chemistry cycles. The computer aspect of the current disclosure can optionally align the sequence data gathered from each singlemolecule, cluster or bead to determine the sequence of longer polymers, etc. Alternatively, the image processing and alignment can be performed on a separate computer.

[0025] The heating / cooling components of the system regulate the reaction conditions within the flowcell channels and reagent storage areas / containers (and optionally the camera, optics, and / or other components), while the fluid flow components allow the substrate surface to be exposed to suitable reagents for incorporation (e.g., the appropriate fluorescently labelednucleotides to be incorporated)while unincorporated reagents are rinsedaway.Anoptionalmovable stage upon which the flowcell is placed allows the flowcell to be brought into proper orientation for laser (or other light) excitation of the substrate and optionally moved in relation to a lens objective to allow reading of different areas of the substrate. Additionally, other components of the systemare also optionallymovable / adjustable (e.g., the camera, the lens objective, the heater / cooler, etc.). During laser excitation, the image / location of emitted fluorescence from the nucleic acidson thesubstrate is capturedby thecameracomponent, thereby, recording the identity, in thecomputer component, of the first base for each single molecule, cluster or bead.

[0026] Embodiments described herein may be used in various biological or chemical processes and systems for academic or commercial analysis. More specifically, embodiments described herein may be used in various processes and systemswhere it is desired to detect an event, property, quality, or characteristic that is indicative of a desired reaction. For example, embodiments described herein include cartridges, biosensors, and their components as well as bioassay systems that operate with cartridges and biosensors. In particular embodiments, the cartridges and biosensors include a flowcell andoneormore sensors, pixels, light detectors, or photodiodes that are coupled together in asubstantially unitary structure.

[0027] The followingdetaileddescriptionof certainembodimentswill bebetter understoodwhen read inconjunctionwith the appended drawings. To the extent that the figures illustrate diagrams of the functional blocks of various embodiments, the functional blocks are not necessarily indicative of the division between hardware circuitry. Thus, for example, one or more of the functional blocks (e.g., processors or memories) may be implemented in a single piece of hardware (e.g., a general purpose signal processor or random access memory, hard disk, or the like). Similarly, the programs may be standalone programs, may be incorporated as subroutines in an operating system, may be functions in an installed software package, and the like. It should be understood that the various embodiments are not limited to the arrangements and instrumentality shown in the drawings.

[0028] As used herein, an element or step recited in the singular and proceeded with the word "a" or "an" should be understood as not excluding plural of said elements or steps, unless such exclusion is explicitly stated. Furthermore, 7 EP 4 679 300 A2 5 10 15 20 25 30 35 40 45 50 55 references to "one embodiment" are not intended to be interpreted as excluding the existence of additional embodiments that also incorporate the recited features. Moreover, unless explicitly stated to the contrary, embodiments "comprising" or "having" or "including" an element or a plurality of elements having a particular property may include additional elements whether or not they have that property.

[0029] Asusedherein, a "desired reaction" includes a change in at least one of a chemical, electrical, physical, or optical property (or quality) of an analyte-of-interest. In particular embodiments, the desired reaction is a positive binding event (e.g., incorporation of a fluorescently labeled biomolecule with the analyte-of-interest). More generally, the desired reactionmay be a chemical transformation, chemical change, or chemical interaction. The desired reactionmay also be a change in electrical properties. For example, the desired reaction may be a change in ion concentration within a solution. Exemplary reactions include, but are not limited to, chemical reactions such as reduction, oxidation, addition, elimination, rearrangement, esterification, amidation, etherification, cyclization, or substitution; binding interactions in which a first chemical binds to a second chemical; dissociation reactions in which two or more chemicals detach from each other; fluorescence; luminescence; bioluminescence; chemiluminescence; and biological reactions, such as nucleic acid replication, nucleic acid amplification, nucleic acid hybridization, nucleic acid ligation, phosphorylation, enzymatic catalysis, receptor binding, or ligand binding. The desired reaction can also be an addition or elimination of a proton, for example, detectable as a change in pH of a surrounding solution or environment. An additional desired reaction can be detecting the flow of ions across a membrane (e.g., natural or synthetic bilayer membrane), for example as ions flow through a membrane the current is disrupted and the disruption can be detected.

[0030] In particular embodiments, the desired reaction includes the incorporation of a fluorescently-labeledmolecule to an analyte. The analyte may be an oligonucleotide and the fluorescently-labeled molecule may be a nucleotide. The desired reaction may be detected when an excitation light is directed toward the oligonucleotide having the labeled nucleotide, and the fluorophore emits a detectable fluorescent signal. In alternative embodiments, the detected fluor- escence is a result of chemiluminescence or bioluminescence. A desired reaction may also increase fluorescence (or Förster) resonance energy transfer (FRET), for example, by bringing a donor fluorophore in proximity to an acceptor fluorophore, decrease FRET by separating donor and acceptor fluorophores, increase fluorescence by separating a quencher from a fluorophore or decrease fluorescence by co-locating a quencher and fluorophore.

[0031] Asusedherein, a "reactioncomponent"or "reactant" includesanysubstance thatmaybeused toobtainadesired reaction. For example, reaction components include reagents, enzymes, samples, other biomolecules, and buffer solutions. The reaction components are typically delivered to a reaction site in a solution and / or immobilized at a reaction site. The reaction components may interact directly or indirectly with another substance, such as the analyte-of-interest.

[0032] As used herein, the term "reaction site" is a localized region where a desired reaction may occur. A reaction site may include support surfaces of a substratewhere a substancemay be immobilized thereon. For example, a reaction site may includeasubstantially planar surface inachannel of aflowcell thathasacolonyof nucleicacids thereon.Typically, but not always, the nucleic acids in the colony have the same sequence, being for example, clonal copies of a single stranded or double stranded template. However, in some embodiments a reaction site may contain only a single nucleic acid molecule, for example, in a single stranded or double stranded form. Furthermore, a plurality of reaction sites may be unevenly distributed along the support surfaceor arranged in apredeterminedmanner (e.g., side-by-side in amatrix, such as inmicroarrays).A reaction site canalso includea reactionchamber (orwell) that at least partially definesaspatial region or volume configured to compartmentalize the desired reaction.

[0033] This application uses the terms "reaction chamber" and "well" interchangeably. As used herein, the term "reaction chamber" or "well" includes a spatial region that is in fluid communication with a flow channel. The reaction chamber may be at least partially separated from the surrounding environment or other spatial regions. For example, a plurality of reaction chambersmaybeseparated fromeachother bysharedwalls. Asamore specificexample, the reaction chambermay include a cavity defined by interior surfaces of a well and have an opening or aperture so that the cavitymay be in fluid communicationwitha flowchannel. Biosensors includingsuch reaction chambersaredescribed in greater detail in international application no. PCT / US2011 / 057111, filed onOctober 20, 2011, which is incorporated herein by reference in its entirety.

[0034] In some embodiments, the reaction chambers are sized and shaped relative to solids (including semi-solids) so that the solids may be inserted, fully or partially, therein. For example, the reaction chamber may be sized and shaped to accommodate only one capture bead. The capture bead may have clonally amplified DNA or other substances thereon. Alternatively, the reaction chamber may be sized and shaped to receive an approximate number of beads or solid substrates.As another example, the reaction chambersmayalsobe filledwith aporousgel or substance that is configured to control diffusion or filter fluids that may flow into the reaction chamber.

[0035] In some embodiments, sensors (e.g., light detectors, photodiodes) are associated with corresponding pixel areas of a sample surface of a biosensor. As such, a pixel area is a geometrical construct that represents an area on the biosensor’s sample surface for one sensor (or pixel). A sensor that is associated with a pixel area detects light emissions gathered from the associated pixel area when a desired reaction has occurred at a reaction site or a reaction chamber overlying the associated pixel area. In a flat surface embodiment, the pixel areas can overlap. In some cases, a plurality of 8 EP 4 679 300 A2 5 10 15 20 25 30 35 40 45 50 55 sensorsmay be associatedwith a single reaction site or a single reaction chamber. In other cases, a single sensormay be associated with a group of reaction sites or a group of reaction chambers.

[0036] Asusedherein, a "biosensor" includesastructurehavingaplurality of reactionsitesand / or reactionchambers (or wells). A biosensor may include a solid-state imaging device (e.g., CCD or CMOS imager) and, optionally, a flow cell mounted thereto. The flow cell may include at least one flow channel that is in fluid communication with the reaction sites and / or the reactionchambers.Asonespecificexample, thebiosensor is configured to fluidically andelectrically couple toa bioassay system.Thebioassay systemmaydeliver reactants to the reaction sites and / or the reaction chambers according to a predetermined protocol (e.g., sequencing-by-synthesis) and perform a plurality of imaging events. For example, the bioassay system may direct solutions to flow along the reaction sites and / or the reaction chambers. At least one of the solutionsmay include four types of nucleotides having the same or different fluorescent labels. The nucleotides may bind to corresponding oligonucleotides located at the reaction sites and / or the reaction chambers. The bioassay systemmay then illuminate the reaction sites and / or the reaction chambers using an excitation light source (e.g., solid-state light sources, such as light-emitting diodes or LEDs). The excitation light may have a predetermined wavelength or wave- lengths, includinga rangeofwavelengths.Theexcitedfluorescent labelsprovideemissionsignals thatmaybecapturedby the sensors.

[0037] In alternative embodiments, the biosensormay include electrodes or other types of sensors configured to detect other identifiable properties. For example, the sensors may be configured to detect a change in ion concentration. In another example, the sensors may be configured to detect the ion current flow across a membrane.

[0038] As used herein, a "cluster" is a colony of similar or identical molecules or nucleotide sequences or DNA strands. For example, a cluster can be an amplified oligonucleotide or any other group of a polynucleotide or polypeptide with a sameor similar sequence. Inother embodiments, a cluster canbeanyelementor groupof elements that occupyaphysical area on a sample surface. In embodiments, clusters are immobilized to a reaction site and / or a reaction chamber during a base calling cycle.

[0039] As used herein, the term "immobilized," when used with respect to a biomolecule or biological or chemical substance, includes substantially attaching the biomolecule or biological or chemical substance at a molecular level to a surface. For example, a biomolecule or biological or chemical substancemay be immobilized to a surface of the substrate material using adsorption techniques including non-covalent interactions (e.g., electrostatic forces, van der Waals, and dehydration of hydrophobic interfaces) and covalent binding techniques where functional groups or linkers facilitate attaching thebiomolecules to thesurface. Immobilizingbiomoleculesorbiological or chemical substances toasurfaceof a substratematerial may be based upon the properties of the substrate surface, the liquidmedium carrying the biomolecule or biological or chemical substance, and the properties of the biomolecules or biological or chemical substances themselves. In some cases, a substrate surface may be functionalized (e.g., chemically or physically modified) to facilitate immobilizing the biomolecules (or biological or chemical substances) to the substrate surface. The substrate surface may be first modified to have functional groups bound to the surface. The functional groups may then bind to biomolecules or biological or chemical substances to immobilize them thereon. A substance can be immobilized to a surface via a gel, for example, as described in USPatent Publ. No. US 2011 / 0059865 A1, which is incorporated herein by reference.

[0040] In some embodiments, nucleic acids can be attached to a surface and amplified using bridge amplification. Useful bridge amplification methods are described, for example, in U.S. Patent No. 5,641,658; WO 2007 / 010251; U.S. Pat. No. 6,090,592; U.S. Patent Publ. No. 2002 / 0055100 A1; U.S. Patent No. 7,115,400; U.S. Patent Publ. No. 2004 / 0096853 A1; U.S. Patent Publ. No. 2004 / 0002090 A1; U.S. Patent Publ. No. 2007 / 0128624 A1; and U.S. Patent Publ. No. 2008 / 0009420 A1, each of which is incorporated herein in its entirety. Another useful method for amplifying nucleic acidsonasurface isRollingCircleAmplification (RCA), for example, usingmethodsset forth in further detail below. In some embodiments, the nucleic acids can be attached to a surface and amplified using one or more primer pairs. For example, one of the primers can be in solution and the other primer can be immobilized on the surface (e.g., 5’-attached). Byway of example, a nucleic acidmolecule can hybridize to one of the primers on the surface followed by extension of the immobilized primer to produce a first copy of the nucleic acid. The primer in solution then hybridizes to the first copy of the nucleicacidwhichcanbeextendedusing thefirst copyof thenucleicacidasa template.Optionally, after thefirst copyof the nucleic acid is produced, the original nucleic acid molecule can hybridize to a second immobilized primer on the surface and can be extended at the same time or after the primer in solution is extended. In any embodiment, repeated rounds of extension (e.g., amplification) using the immobilized primer and primer in solution provide multiple copies of the nucleic acid.

[0041] In particular embodiments, the assay protocols executed by the systems andmethods described herein include the use of natural nucleotides and also enzymes that are configured to interact with the natural nucleotides. Natural nucleotides include, for example, ribonucleotides (RNA) or deoxyribonucleotides (DNA).Natural nucleotides canbe in the mono‑, di‑, or tri-phosphate form and can have a base selected from adenine (A), thymine (T), uracil (U), guanine (G) or cytosine (C). It will be understood however that non-natural nucleotides, modified nucleotides or analogs of the aforementioned nucleotides can be used. Some examples of useful non-natural nucleotides are set forth below in regard 9 EP 4 679 300 A2 5 10 15 20 25 30 35 40 45 50 55 to reversible terminator-based sequencing by synthesis methods.

[0042] In embodiments that include reactionchambers, itemsor solid substances (includingsemisolid substances)may be disposed within the reaction chambers. When disposed, the item or solid may be physically held or immobilized within the reactionchamber throughan interferencefit, adhesion, or entrapment.Exemplary itemsor solids thatmaybedisposed within the reaction chambers includepolymerbeads, pellets, agarosegel, powders, quantumdots, or other solids thatmay becompressedand / or heldwithin the reaction chamber. In particular embodiments, a nucleic acid superstructure, suchas a DNA ball, can be disposed in or at a reaction chamber, for example, by attachment to an interior surface of the reaction chamber or by residence in a liquid within the reaction chamber. A DNA ball or other nucleic acid superstructure can be preformed and then disposed in or at the reaction chamber. Alternatively, a DNA ball can be synthesized in situ at the reaction chamber. A DNA ball can be synthesized by rolling circle amplification to produce a concatemer of a particular nucleicacid sequenceand theconcatemercanbe treatedwithconditions that forma relativelycompact ball.DNAballsand methods for their synthesis are described, for example in, U.S. Patent Publication Nos. 2008 / 0242560 A1 or 2008 / 0234136 A1, each of which is incorporated herein in its entirety. A substance that is held or disposed in a reaction chamber can be in a solid, liquid, or gaseous state.

[0043] As used herein, "base calling" identifies a nucleotide base in a nucleic acid sequence. Base calling refers to the process of determining a base call (A, C, G, T) for every cluster at a specific cycle. As an example, base calling can be performed utilizing four-channel, two-channel or one-channel methods and systems described in the incorporated materials of U.S. Patent Application Publication No. 2013 / 0079232. In particular embodiments, a base calling cycle is referred to as a "sampling event." In one dye and two-channel sequencing protocol, a sampling event comprises two illumination stages in time sequence, such that a pixel signal is generated at each stage. The first illumination stage induces illumination from a given cluster indicating nucleotide bases A and T in a AT pixel signal, and the second illumination stage induces illumination from a given cluster indicating nucleotide bases C and T in a CT pixel signal.

[0044] The technology disclosed, e.g., the disclosed base callers can be implemented on processors like Central Processing Units (CPUs), Graphics Processing Units (GPUs), Field Programmable Gate Arrays (FPGAs), Coarse- Grained Reconfigurable Architectures (CGRAs), Application-Specific Integrated Circuits (ASICs), Application Specific Instruction-set Processor (ASIP), and Digital Signal Processors (DSPs). Biosensor

[0045] Fig. 1 illustrates a cross-section of a biosensor 100 that can be used in various embodiments. Biosensor 100 has pixel areas 106’, 108’, 110’, 112’, and 114’ that can each hold more than one cluster during a base calling cycle (e.g., 2 clusters per pixel area). As shown, the biosensor 100 may include a flow cell 102 that is mounted onto a sampling device 104. In the illustrated embodiment, the flow cell 102 is affixed directly to the sampling device 104. However, in alternative embodiments, the flow cell 102 may be removably coupled to the sampling device 104. The sampling device 104 has a sample surface 134 thatmay be functionalized (e.g., chemically or physicallymodified in a suitablemanner for conducting the desired reactions). For example, the sample surface 134 may be functionalized and may include a plurality of pixel areas106’, 108’, 110’, 112’, and114’ that caneachholdmore thanonecluster duringabasecalling cycle (e.g., eachhaving a corresponding cluster pair 106A, 106B; 108A, 108B; 110A, 110B; 112A, 112B; and 114A, 114B immobilized thereto). Each pixel area is associated with a corresponding sensor (or pixel or photodiode) 106, 108, 110, 112, and 114, such that light received by the pixel area is captured by the corresponding sensor. A pixel area 106’ can be also associated with a corresponding reaction site 106" on the sample surface 134 that holds a cluster pair, such that light emitted from the reaction site 106" is received by the pixel area 106’ and captured by the corresponding sensor 106. As a result of this sensing structure, in the case in which two or more clusters are present in a pixel area of a particular sensor during a base calling cycle (e.g., each having a corresponding cluster pair), the pixel signal in that base calling cycle carries information based on all of the two or more clusters. As a result, signal processing as described herein is used to distinguish each cluster, where there are more clusters than pixel signals in a given sampling event of a particular base calling cycle.

[0046] In the illustratedembodiment, theflowcell 102 includessidewalls 138, 125, andaflowcover136 that is supported by the sidewalls 138, 125. The sidewalls 138, 125 are coupled to the sample surface 134 and extend between the flow cover 136 and the sidewalls 138, 125. In some embodiments, the sidewalls 138, 125 are formed from a curable adhesive layer that bonds the flow cover 136 to the sampling device 104.

[0047] Thesidewalls138,125aresizedandshapedso thataflowchannel 144existsbetween theflowcover136and the sampling device 104. The flowcover 136may includeamaterial that is transparent to excitation light 101propagating from anexterior of thebiosensor 100 into theflowchannel 144. Inanexample, theexcitation light 101approaches theflowcover 136 at a non-orthogonal angle.

[0048] Alsoshown, theflowcover136may include inlet andoutlet ports142, 146 that areconfigured tofluidically engage other ports (not shown). For example, the other portsmaybe from the cartridge or theworkstation. The flowchannel 144 is sized and shaped to direct a fluid along the sample surface 134. A height H1 and other dimensions of the flow channel 144 maybe configured tomaintain a substantially even flowof a fluid along the sample surface134. Thedimensions of the flow 10 EP 4 679 300 A2 5 10 15 20 25 30 35 40 45 50 55 channel 144 may also be configured to control bubble formation.

[0049] Bywayof example, the flowcover 136 (or the flowcell 102)maycomprisea transparentmaterial, suchasglassor plastic. The flow cover 136 may constitute a substantially rectangular block having a planar exterior surface and a planar inner surface that defines the flow channel 144. The blockmay bemounted onto the sidewalls 138, 125. Alternatively, the flow cell 102may be etched to define the flow cover 136 and the sidewalls 138, 125. For example, a recessmay be etched into the transparentmaterial.When theetchedmaterial ismounted to thesamplingdevice104, the recessmaybecome the flow channel 144.

[0050] The sampling device 104 may be similar to, for example, an integrated circuit comprising a plurality of stacked substrate layers 120‑126. The substrate layers 120‑126may include a base substrate 120, a solid-state imager 122 (e.g., CMOS imagesensor), a filter or light-management layer 124, andapassivation layer 126. It shouldbenoted that theabove is only illustrative and that other embodiments may include fewer or additional layers. Moreover, each of the substrate layers 120‑126may include aplurality of sub-layers. The sampling device 104maybemanufactured using processes that are similar to those used inmanufacturing integrated circuits, such asCMOS image sensors andCCDs. For example, the substrate layers 120‑126 or portions thereof may be grown, deposited, etched, and the like to form the sampling device 104.

[0051] The passivation layer 126 is configured to shield the filter layer 124 from the fluidic environment of the flow channel 144. In somecases, thepassivation layer 126 is also configured toprovideasolid surface (i.e., the samplesurface 134) that permits biomolecules or other analytes-of-interest to be immobilized thereon. For example, each of the reaction sitesmay includeacluster of biomolecules that are immobilized to the sample surface134.Thus, thepassivation layer 126 maybe formed fromamaterial thatpermits the reactionsites tobe immobilized thereto. Thepassivation layer126mayalso comprise amaterial that is at least transparent to a desired fluorescent light. By way of example, the passivation layer 126 may include silicon nitride (Si2N4) and / or silica (SiO2). However, other suitable material(s) may be used. In the illustrated embodiment, the passivation layer 126maybe substantially planar.However, in alternative embodiments, the passivation layer 126 may include recesses, such as pits, wells, grooves, and the like. In the illustrated embodiment, the passivation layer 126 has a thickness that is about 150‑200 nm and, more particularly, about 170 nm.

[0052] The filter layer 124 may include various features that affect the transmission of light. In some embodiments, the filter layer 124 canperformmultiple functions. For instance, the filter layer 124maybeconfigured to (a) filter unwanted light signals, such as light signals from an excitation light source; (b) direct emission signals from the reaction sites toward corresponding sensors 106, 108, 110, 112, and 114 that are configured to detect the emission signals from the reaction sites; or (c) block or prevent detection of unwanted emission signals from adjacent reaction sites. As such, the filter layer 124mayalso be referred to as a light-management layer. In the illustrated embodiment, the filter layer 124 has a thickness that is about 1‑5 µmand, more particularly, about 2‑4 µm. In alternative embodiments, the filter layer 124 may include an array of microlenses or other optical components. Each of the microlenses may be configured to direct emission signals from an associated reaction site to a sensor.

[0053] In some embodiments, the solid-state imager 122 and the base substrate 120 may be provided together as a previously constructed solid-state imagingdevice (e.g., CMOSchip). For example, the base substrate 120maybeawafer of silicon and the solid-state imager 122 may be mounted thereon. The solid-state imager 122 includes a layer of semiconductor material (e.g., silicon) and the sensors 106, 108, 110, 112, and 114. In the illustrated embodiment, the sensors are photodiodes configured to detect light. In other embodiments, the sensors comprise light detectors. The solid- state imager 122 may be manufactured as a single chip through a CMOS-based fabrication processes.

[0054] The solid-state imager 122may include a dense array of sensors 106, 108, 110, 112, and 114 that are configured to detect activity indicative of a desired reaction from within or along the flow channel 144. In some embodiments, each sensor has a pixel area (or detection area) that is about 1‑2 square micrometer (µm2). The array can include 500,000 sensors, 5million sensors, 10millionsensors, or even120million sensors.Thesensors106, 108, 110, 112, and114canbe configured to detect a predetermined wavelength of light that is indicative of the desired reactions.

[0055] In some embodiments, the sampling device 104 includes a microcircuit arrangement, such as the microcircuit arrangement described in U.S. Patent No. 7,595,882, which is incorporated herein by reference in the entirety. More specifically, thesamplingdevice104maycomprisean integratedcircuit havingaplanararrayof thesensors106, 108, 110, 112, and 114. Circuitry formed within the sampling device 104 may be configured for at least one of signal amplification, digitization, storage, and processing. The circuitry may collect and analyze the detected fluorescent light and generate pixel signals (or detection signals) for communicating detection data to a signal processor. The circuitry may also perform additional analog and / or digital signal processing in the sampling device 104. Sampling device 104 may include conductive vias 130 that perform signal routing (e.g., transmit the pixel signals to the signal processor). The pixel signals may also be transmitted through electrical contacts 132 of the sampling device 104.

[0056] The sampling device 104 is discussed in further details with respect to U.S. Nonprovisional Patent Application No. 16 / 874,599, titled "SystemsandDevices forCharacterizationandPerformanceAnalysis ofPixel-BasedSequencing," filed May 14, 2020, which is incorporated by reference as if fully set forth herein. The sampling device 104 is not limited to the above constructions or uses as described above. In alternative embodiments, the sampling device 104may take other 11 EP 4 679 300 A2 5 10 15 20 25 30 35 40 45 50 55 forms.Forexample, the samplingdevice104maycompriseaCCDdevice, suchasaCCDcamera, that is coupled toaflow cell or is moved to interface with a flow cell having reaction sites therein.

[0057] Fig. 2depictsone implementationof a flowcell 200 that containsclusters in its tiles. Theflowcell 200corresponds to the flow cell 102 of Fig. 1, e.g., without the flow cover 136. Furthermore, the depiction of the flow cell 200 is symbolic in nature, and the flow cell 200 symbolically depicts various lanes and tiles therewithin, without illustrating various other components therewithin. Fig. 2 illustrates a top view of the flow cell 200.

[0058] In an embodiment, the flow cell 200 is divided or partitioned in a plurality of lanes, such as lanes 202a, 202b, ..., 202P, i.e., P number of lanes. In the example of Fig. 2, the flow cell 200 is illustrated to include 8 lanes, i.e., P = 8 in this example, although the number of lanes within a flow cell is implementation specific.

[0059] In anembodiment, individual lanes 202are further partitioned into non-overlapping regions called "tiles" 212. For example, Fig. 2 illustratesamagnified viewof a section 208of anexample lane. Thesection 208 is illustrated to comprise a plurality of tiles 212.

[0060] In an example, each lane 202 comprises one or more columns of tiles. For example, in Fig. 2, each lane 202 comprises two corresponding columns of tiles 212, as illustratedwithin themagnified section 208. A number of tiles within each column of tiles within each lane is implementation specific, and in one example, there can be 50 tiles, 60 tiles, 100 tiles, or another appropriate number of tiles in each column of tiles within each lane.

[0061] Each tile comprisesacorrespondingplurality of clusters.During the sequencingprocedure, the clusters and their surrounding background on the tiles are imaged. For example, Fig. 2 illustrates example clusters 216 within an example tile.

[0062] Fig. 3 illustrates an example Illumina GA-IIx™ flow cell with eight lanes, and also illustrates a zoom-in on one tile and its clusters and their surrounding background. For example, there are a hundred tiles per lane in Illumina Genome Analyzer II and sixty-eight tiles per lane in Illumina HiSeq2000. A tile 212 holds hundreds of thousands to millions of clusters. In Fig. 3, an image generated from a tile with clusters shown as bright spots is shown at 308 (e.g., 308 is a magnified imageviewof a tile), withanexample cluster 304 labelled.A cluster 304comprisesapproximately one thousand identical copies of a template molecule, though clusters vary in size and shape. The clusters are grown from the template molecule, prior to the sequencing run, by bridge amplification of the input library. The purpose of the amplification and cluster growth is to increase the intensity of the emitted signal since the imaging device cannot reliably sense a single fluorophore. However, the physical distance of the DNA fragments within a cluster 304 is small, so the imaging device perceives the cluster of fragments as a single spot 304.

[0063] The clusters and the tiles are discussed in further details with respect to U.S. Nonprovisional Patent Application No. 16 / 825,987, titled "Training Data Generation for Artificial Intelligence-Based Sequencing," filed 20 March 2020.

[0064] Fig. 4 is a simplified block diagram of the system for analysis of sensor data from a sequencing system, such as base call sensor outputs (e.g., see Fig. 1). In the example of Fig. 4, the system includes a sequencing machine 400 and a configurable processor 450. The configurable processor 450 can execute a neural network-based base caller and / or a non-neural network-based base caller (which will be discussed herein in further detail) in coordination with a runtime program executed by a host processor, such as a central processing unit (CPU) 402. The sequencing machine 400 comprises base call sensors and flowcell 401 (e.g., discussedwith respect to Figs. 1‑3). The flowcell can comprise one or more tiles in which clusters of genetic material are exposed to a sequence of analyte flows used to cause reactions in the clusters to identify the bases in the genetic material, as discussed with respect to Figs. 1‑3. The sensors sense the reactions for each cycle of the sequence in each tile of the flow cell to provide tile data. Examples of this technology are described in more detail below. Genetic sequencing is a data intensive operation, which translates base call sensor data into sequences of base calls for each cluster of genetic material sensed in during a base call operation.

[0065] The system in this example includes the CPU 402which executes a runtime program to coordinate the base call operations, memory 403 to store sequences of arrays of tile data, base call reads produced by the base calling operation, and other information used in the base call operations. Also, in this illustration the system includesmemory 404 to store a configuration file (or files), such as FPGA bit files, and model parameters for the neural network used to configure and reconfigure the configurable processor 450 and execute the neural network. The sequencing machine 400 can include a program for configuring a configurable processor and in some embodiments a reconfigurable processor to execute the neural network.

[0066] The sequencing machine 400 is coupled by a bus 405 to the configurable processor 450. The bus 405 can be implemented using a high throughput technology, such as in one example bus technology compatible with the PCIe standards (Peripheral Component Interconnect Express) currently maintained and developed by the PCI-SIG (PCI Special InterestGroup). Also, in this example, amemory460 is coupled to the configurable processor 450by bus461. The memory 460 can be on-boardmemory, disposed on a circuit board with the configurable processor 450. Thememory 460 is used for high-speed access by the configurable processor 450 of working data used in the base call operation. The bus 461 can also be implemented using a high throughput technology, such as bus technology compatible with the PCIe standards. The memory 460 can store genomics data, for example, variant call format (VCF) files.

[0067] Configurable processors, including Field ProgrammableGate Arrays (FPGAs), CoarseGrainedReconfigurable 12 EP 4 679 300 A2 5 10 15 20 25 30 35 40 45 50 55 Arrays (CGRAs), andother configurable and reconfigurable devices, canbe configured to implement a variety of functions more efficiently or faster than might be achieved using a general-purpose processor executing a computer program. Configuration of configurable processors involves compiling a functional description to produce a configuration file, referred to sometimes as a bitstream or bit file, and distributing the configuration file to the configurable elements on the processor.

[0068] The configuration file defines the logic functions to be executed by the configurable processor, by configuring the circuit to set data flow patterns, use of distributed memory and other on-chip memory resources, lookup table contents, operations of configurable logic blocks and configurable execution units like multiply-and-accumulate units, configurable interconnects and other elements of the configurable array. A configurable processor is reconfigurable if the configuration filemaybechanged in the field, by changing the loadedconfiguration file. For example, the configuration filemaybestored in volatile SRAM elements, in non-volatile read-write memory elements, and in combinations of the same, distributed among the array of configurable elements on the configurable or reconfigurable processor. A variety of commercially available configurableprocessorsare suitable for use inabasecallingoperationasdescribedherein. In someexamples, a host CPU can be implemented on the same integrated circuit as the configurable processor.

[0069] Embodiments described herein implement the multi-cycle neural network using a configurable processor 450. The configuration file for a configurable processor can be implemented by specifying the logic functions to be executed using a high-level description language (HDL) or a register transfer level (RTL) language specification. The specification can be compiled using the resources designed for the selected configurable processor to generate the configuration file. The same or similar specification can be compiled for the purposes of generating a design for an application-specific integrated circuit which may not be a configurable processor.

[0070] Alternatives for the configurable processor, in all embodiments described herein, therefore include a configured processor comprising an application specific ASIC or special purpose integrated circuit or set of integrated circuits, or a system-on-a-chip SOC device, configured to execute a neural network based base call operation as described herein.

[0071] In general, configurable processors and configured processors described herein, as configured to execute runs of a neural network, are referred to herein asneural networkprocessors. In another example, configurable processors and configured processors described herein, as configured to execute runs of a non-neural network based base caller, are referred to herein as non-neural network processors. In general, the configurable processors and configured processors can be used to implement one or both a neural network based base caller and a non-neural network based base caller, as will be discussed herein later.

[0072] The configurable processor 450 is configured in this example by a configuration file loaded using a program executed by the CPU 402, or by other sources, which configures the array of configurable elements on the configurable processor 454 to execute the base call function. In this example, the configuration includes data flow logic 451 which is coupled to thebuses405and461andexecutes functions for distributingdataandcontrol parameters among theelements used in the base call operation.

[0073] Also, the configurable processor 450 is configured with base call execution logic 452 to execute a multi-cycle neural network. The logic 452 comprises a plurality of multi-cycle execution clusters (e.g., 453) which, in this example, includesmulti-cycle cluster 1 throughmulti-cycle cluster X. The number of multi-cycle clusters can be selected according to a trade-off involving the desired throughput of the operation, and the available resources on the configurable processor.

[0074] The multi-cycle clusters are coupled to the data flow logic 451 by data flow paths 454 implemented using configurable interconnect andmemory resourceson theconfigurableprocessor.Also, themulti-cycle clusters are coupled to the data flow logic 451 by control paths 455 implemented using configurable interconnect and memory resources for example on the configurable processor, which provide control signals indicating available clusters, readiness to provide input units for execution of a run of the neural network to the available clusters, readiness to provide trained parameters for the neural network, readiness to provide output patches of base call classification data, and other control data used for execution of the neural network.

[0075] The configurable processor is configured to execute runs of a multi-cycle neural network using trained parameters to produce classification data for sensing cycles of the base flow operation. A run of the neural network is executed to produce classification data for a subject sensing cycle of the base call operation. A run of the neural network operates on a sequence including a number N of arrays of tile data from respective sensing cycles of N sensing cycles, where theNsensingcyclesprovidesensordata fordifferent basecall operations foronebasepositionperoperation in time sequence in theexamplesdescribedherein.Optionally, someof theNsensingcycles canbeout of sequence if theneeded according to a particular neural network model being executed. The number N can be any number greater than one. In someexamples described herein, sensing cycles of theN sensing cycles represent a set of sensing cycles for at least one sensing cycle preceding the subject sensing cycle and at least one sensing cycle following the subject cycle in time sequence. Examples are described herein in which the number N is an integer equal to or greater than five.

[0076] Thedata flow logic 451 is configured tomove tile data andat least some trainedparameters of themodel from the memory460 to the configurable processor for runsof the neural network, using input units for a given run including tile data for spatially alignedpatchesof theNarrays. The input units canbemovedbydirectmemoryaccessoperations inoneDMA 13 EP 4 679 300 A2 5 10 15 20 25 30 35 40 45 50 55 operation, or in smaller units moved during available time slots in coordination with the execution of the neural network deployed.

[0077] Tile data for a sensing cycle as described herein can comprise an array of sensor data having one or more features. For example, the sensor data can comprise two imageswhichareanalyzed to identify oneof four basesat a base position in a genetic sequence of DNA, RNA, or other genetic material. The tile data can also include metadata about the imagesand thesensors.For example, in embodimentsof thebasecallingoperation, the tile data cancomprise information about alignment of the images with the clusters such as distance from center information indicating the distance of each pixel in the array of sensor data from the center of a cluster of genetic material on the tile.

[0078] During execution of the multi-cycle neural network as described below, tile data can also include data produced during execution of the multi-cycle neural network, referred to as intermediate data, which can be reused rather than recomputed during a run of the multi-cycle neural network. For example, during execution of the multi-cycle neural network, thedataflow logic canwrite intermediatedata to thememory460 inplaceof thesensordata foragivenpatchofan array of tile data. Embodiments like this are described in more detail below.

[0079] As illustrated, a system is described for analysis of base call sensor output, comprising memory (e.g., 460) accessible by the runtime program storing tile data including sensor data for a tile from sensing cycles of a base calling operation.Also, the system includesaneural network processor, suchas configurable processor 450havingaccess to the memory. The neural network processor is configured to execute runs of a neural network using trained parameters to produce classification data for sensing cycles. As described herein, a run of the neural network is operating ona sequence of N arrays of tile data from respective sensing cycles of N sensing cycles, including a subject cycle, to produce the classification data for the subject cycle. The data flow logic 451 is provided to move tile data and the trained parameters from thememory to theneural networkprocessor for runs of theneural network using input units includingdata for spatially aligned patches of the N arrays from respective sensing cycles of N sensing cycles.

[0080] Also, a system is described in which the neural network processor has access to the memory, and includes a plurality of execution clusters, the execution logic clusters in the plurality of execution clusters configured to execute a neural network. The data flow logic has access to the memory and to execution clusters in the plurality of execution clusters, to provide input units of tile data to available execution clusters in the plurality of execution clusters, the input units including a number N of spatially aligned patches of arrays of tile data from respective sensing cycles, including a subject sensingcycle, and to cause theexecutionclusters toapply theNspatially alignedpatches to theneural network toproduce output patches of classification data for the spatially aligned patch of the subject sensing cycle, where N is greater than 1.

[0081] Fig. 5 is a simplified diagram showing aspects of the base calling operation, including functions of a runtime program executed by a host processor. In this diagram, the output of image sensors from a flow cell (such as those illustrated inFigs. 1‑2)areprovidedon lines500 to imageprocessing threads501,whichcanperformprocesseson images such as resampling, alignment and arrangement in an array of sensor data for the individual tiles, and can be used by processes which calculate a tile cluster mask for each tile in the flow cell, which identifies pixels in the array of sensor data that correspond to clusters of genetic material on the corresponding tile of the flow cell. To compute a cluster mask, one example algorithm is based on a process to detect clusters which are unreliable in the early sequencing cycles using a metric derived from the softmax output, and then the data from those wells / clusters is discarded, and no output data is produced for those clusters. For example, a process can identify clusters with high reliability during the first N1 (e.g., 25) base-calls, and reject theothers.Rejectedclustersmight bepolyclonal or veryweak intensity orobscuredbyfiducials. This procedure canbeperformedon thehostCPU. In alternative implementations, this informationwouldpotentially beused to identify the necessary clusters of interest to be passed back to the CPU, thereby limiting the storage required for intermediate data.

[0082] The outputs of the image processing threads 501 are provided on lines 502 to a dispatch logic 510 in the CPU which routes thearraysof tiledata toadatacache504onahigh-speedbus503,oronhigh-speedbus505 tohardware520, such as the configurable processor of Fig. 4, according to the state of the base calling operation. The hardware 520 can be multi-cluster neural network processor to execute a neural network based base caller, or can be hardware to execute a non-neural based base caller, as will be discussed herein later.

[0083] Thehardware520 returnsclassificationdata (e.g., output by theneural networkbasecaller and / or thenon-neural network base caller) to the dispatch logic 510, which passes the information to the data cache 504, or on lines 511 to threads502 thatperformbasecall andquality scorecomputationsusing theclassificationdata,andcanarrange thedata in standard formats for base call reads. The outputs of the threads 502 that perform base calling and quality score computations are provided on lines 512 to threads 503 that aggregate the base call reads, perform other operations such as data compression, and write the resulting base call outputs to specified destinations for utilization by the customers.

[0084] In someembodiments, the host can include threads (not shown) that perform final processing of the output of the hardware 520 in support of the neural network. For example, the hardware 520 can provide outputs of classification data fromafinal layer of themulti-cluster neural network. Thehost processor canexecute anoutput activation function, suchas a softmax function, over the classification data to configure the data for use by the base call and quality score threads 502. 14 EP 4 679 300 A2 5 10 15 20 25 30 35 40 45 50 55 Also, the host processor can execute input operations (not shown), such as resampling, batch normalization or other adjustments of the tile data prior to input to the hardware 520.

[0085] Fig. 6 is a simplified diagram of a configuration of a configurable processor such as that of Fig. 4. In Fig. 6, the configurable processor comprises in FPGAwith a plurality of high speed PCIe interfaces. The FPGA is configured with a wrapper 600 which comprises the data flow logic described with reference to Fig. 1. The wrapper 600 manages the interface and coordination with a runtime program in the CPU across the CPU communication link 609 and manages communicationwith the on-boardDRAM602 (e.g.,memory460) viaDRAMcommunication link 610. Thedata flow logic in the wrapper 600 provides patch data retrieved by traversing the arrays of tile data on the on-board DRAM 602 for the number N cycles to a cluster 601 and retrieves process data 615 from the cluster 601 for delivery back to the on-board DRAM602. The wrapper 600 alsomanages transfer of data between the on-board DRAM602 and host memory, for both the input arraysof tile data, and for theoutput patchesof classificationdata.Thewrapper transferspatchdataon line613 to the allocated cluster 601. The wrapper provides trained parameters, such asweights and biases on line 612 to the cluster 601 retrieved from the on-boardDRAM602. Thewrapper provides configuration and control data on line 611 to the cluster 601 provided from, or generated in response to, the runtime programon the host via theCPUcommunication link 609. The cluster can also provide status signals on line 616 to the wrapper 600, which are used in cooperation with control signals from the host tomanage traversal of the arrays of tile data to provide spatially aligned patch data, and to execute themulti- cycle neural network for base calling and / or operations for non-neural network based base calling, over the patch data using the resources of the cluster 601.

[0086] Asmentioned above, there can bemultiple clusters on a single configurable processormanaged by thewrapper 600 configured for executing on corresponding ones of multiple patches of the tile data. Each cluster can be configured to provide classification data for base calls in a subject sensing cycle using the tile data of multiple sensing cycles described herein.

[0087] In examples of the system, model data, including kernel data like filter weights and biases can be sent from the host CPU to the configurable processor, so that the model can be updated as a function of cycle number. A base calling operation can comprise, for a representative example, on the order of hundreds of sensing cycles. Base calling operation can include paired end reads in some embodiments. For example, the model trained parameters may be updated once every 20 cycles (or other number of cycles), or according to update patterns implemented for particular systems. In some embodiments including paired end reads in which a sequence for a given string in a genetic cluster on a tile includes a first part extending from a first end down (or up) the string, and a second part extending from a second end up (or down) the string, the trained parameters can be updated on the transition from the first part to the second part.

[0088] In some examples, image data for multiple cycles of sensing data for a tile can be sent from the CPU to the wrapper600.Thewrapper600canoptionallydosomepre-processingand transformationof thesensingdataandwrite the information to the on-board DRAM 602. The input tile data for each sensing cycle can include arrays of sensor data including on the order of 4000 x 3000 pixels per sensing cycle per tile ormore, with two features representing colors of two images of the tile, and one or two bytes per feature per pixel. For an embodiment in which the number N is three sensing cycles to be used in each run of the multi-cycle neural network, the array of tile data for each run of the multi-cycle neural network can consume on the order of hundreds of megabytes per tile. In some embodiments of the system, the tile data also includes an array of DFC data, stored once per tile, or other type of metadata about the sensor data and the tiles.

[0089] In operation, when a multi-cycle cluster is available, the wrapper allocates a patch to the cluster. The wrapper fetches a next patch of tile data in the traversal of the tile and sends it to the allocated cluster alongwith appropriate control and configuration information. The cluster can be configuredwith enoughmemory on the configurable processor to hold a patch of data including patches frommultiple cycles in some systems, that is beingworked on in place, and a patch of data that is to be worked on when the current patch of processing is finished using a ping-pong buffer technique or raster scanning technique in various embodiments.

[0090] When an allocated cluster completes its run of the neural network for the current patch and produces an output patch, it will signal the wrapper. The wrapper will read the output patch from the allocated cluster, or alternatively the allocatedclusterwill push thedataout to thewrapper. Then thewrapperwill assembleoutput patches for theprocessed tile in theDRAM602.When the processing of the entire tile has been completed, and the output patches of data transferred to the DRAM, the wrapper sends the processed output array for the tile back to the host / CPU in a specified format. In some embodiments, the on-board DRAM 602 is managed by memory management logic in the wrapper 600. The runtime program can control the sequencing operations to complete analysis of all the arrays of tile data for all the cycles in the run in a continuous flow to provide real time analysis. Sharpening Mask Generation

[0091] Fig. 7 shows a system700 that generates and / or updates sharpeningmask(s) 706, by training a base caller 704. System 700 comprises a trainer 714 that trains the base caller 704 using least square estimation, for example. As used herein, a "sharpeningmask" maximizes the signal-to-noise ratio of a signal that is disturbed by noise. A sharpeningmask 15 EP 4 679 300 A2 5 10 15 20 25 30 35 40 45 50 55 can be a value or function that is applied to data tomodify the data in a desiredway. For example, the data can bemodified to increase its accuracy, relevance, or applicability with regard to a particular situation. The sharpening mask can be applied to the data by any of a variety of mathematical manipulations including, but not limited to addition, subtraction, division, multiplication, or a combination thereof. The sharpening mask can be a mathematical formula, logic function, computer implemented algorithm, or the like. The data can be image data, electrical data, or a combination thereof. In one implementation, the sharpening mask is an equalizer (e.g., a spatial equalizer). The equalizer can be trained (e.g., using least square estimation, adaptive equalization algorithm) to improve and / or maximize the signal-to-noise ratio of cluster intensity data in sequencing images. In some implementations, the equalizer includes coefficients that are learned from the training. In one implementation of a convolution operation, the training produces equalizer coefficients that are configured tomix / combine intensity values of pixels that depict intensity emissions from a target cluster being base called and intensityemissions fromoneormoreadjacent clusters inamanner thatmaximizes thesignal-to-noise ratio.Thesignal maximized in the signal-to-noise ratio is the intensity emissions from the target cluster, and the noise minimized in the signal-to-noise ratio is the intensity emissions from the adjacent clusters, i.e., spatial crosstalk, plus some random noise (e.g., to account for background intensity emissions). The equalizer coefficients are used as weights and the mixing / - combining includes executing element-wise multiplication between the equalizer coefficients and the intensity values of the pixels to calculate a weighted sum of the intensity values of the pixels, i.e., a convolution operation. Furthermore, in cases the image data spans across multiple color channels, a set of equalizer coefficients is generated for each color channel (e.g., one channel, three channels, four channels, etc.).

[0092] Sequencing images 702 are generated during sequencing runs carried out by a sequencing instrument, such as a sequencing instrument that includes the biosensor 100 discussed with respect to Fig. 1. Examples of such sequencing instruments include Illumina’s iSeq, HiSeqX, HiSeq 3000, HiSeq 4000, HiSeq 2500, NovaSeq 6000, NextSeq 550, NextSeq1000,NextSeq2000,NextSeqDx,MiSeq,andMiSeqDx. Inone implementation, the Illuminasequencersemploy cyclic reversible termination (CRT) chemistry for base calling. The process relies on growing nascent strands comple- mentary to template strandswith fluorescently-labeled nucleotides, while tracking the emitted signal of each newly added nucleotide. The fluorescently-labeled nucleotides have a 3’ removable block that anchors a fluorophore signal of the nucleotide type.

[0093] Sequencing occurs in repetitive cycles, each comprising three steps: (a) extension of a nascent strand by adding the fluorescently-labeled nucleotide; (b) excitation of the fluorophore using one or more lasers of an optical system of the sequencing instrument and imaging through different filters of the optical system, yielding the sequencing images; and (c) cleavage of the fluorophore and removal of the 3’ block in preparation for the next sequencing cycle. Incorporation and imaging cycles are repeated up to a designated number of sequencing cycles, defining the read length. Using this approach, each cycle interrogates a new position along the template strands.

[0094] The tremendous power of the Illumina sequencers stems from their ability to simultaneously execute and sense millions or even billions of analytes (e.g., clusters) undergoing CRT reactions. A cluster comprises approximately one thousand identical copies of a template strand, though clusters vary in size and shape. The clusters are grown from the template strand, prior to the sequencing run, by bridge amplification or exclusion amplification of the input library. The purpose of the amplification and cluster growth is to increase the intensity of the emitted signal since the imaging device cannot reliably sense fluorophore signal of a single strand. However, the physical distance of the strandswithin a cluster is small, so the imaging device perceives the cluster of strands as a single spot.

[0095] Sequencing occurs in a flow cell - a small glass slide that holds the input strands (e.g., seeFig. 2). The flow cell is connected to the optical system, which comprises microscopic imaging, excitation lasers, and fluorescence filters. The flow cell comprises multiple chambers called lanes. The lanes are physically separated from each other andmay contain different tagged sequencing libraries, distinguishable without sample cross contamination. In some implementations, the flow cell comprises a patterned surface. A "patterned surface" refers to an arrangement of different regions in or on an exposed layer of a solid support. For example, one ormore of the regions can be featureswhere one ormore amplification primers are present. The features can be separated by interstitial regions where amplification primers are not present. In some implementations, the pattern can be an x-y format of features that are in rows and columns. In some implementa- tions, the pattern can be a repeating arrangement of features and / or interstitial regions. In some implementations, the pattern can be a random arrangement of features and / or interstitial regions. Exemplary patterned surfaces that can be used in themethods and compositions set forth herein are described inUSPat.No. 8,778,849,USPat.No. 9,079,148,US Pat. No. 8,778,848, and US Pub. No. 2014 / 0243224, each of which is incorporated herein by reference.

[0096] In some implementations, the flow cell comprises an array of wells or depressions in a surface. This may be fabricated as is generally known in the art using a variety of techniques, including, but not limited to, photolithography, stamping techniques, molding techniques and microetching techniques. As will be appreciated by those in the art, the technique used will depend on the composition and shape of the array substrate.

[0097] The features in a patterned surface can be wells in an array of wells (e.g., microwells or nanowells) on glass, silicon, plastic or other suitable solid supports with patterned, covalently-linked gel such as poly(N‑(5-azidoacetamidyl- pentyl)acrylamide-co-acrylamide) (PAZAM, see, for example, US Pub. No. 2013 / 184796, WO 2016 / 066586, and WO 16 EP 4 679 300 A2 5 10 15 20 25 30 35 40 45 50 55 2015‑002813, each of which is incorporated herein by reference in its entirety). The process creates gel pads used for sequencing that can be stable over sequencing runs with a large number of cycles. The covalent linking of the polymer to the wells is helpful for maintaining the gel in the structured features throughout the lifetime of the structured substrate during a variety of uses. However, in many implementations, the gel need not be covalently linked to the wells. For example, in some conditions silane free acrylamide (SFA, see, for example, USPat. No. 8,563,477, which is incorporated herein by reference in its entirety) which is not covalently attached to any part of the structured substrate, can be used as the gel material.

[0098] In particular implementations, a structured substrate can be made by patterning a solid support material with wells (e.g. microwells or nanowells), coating the patterned support with a gel material (e.g. PAZAM, SFA or chemically modified variants thereof, such as the azidolyzed version of SFA (azido-SFA)) and polishing the gel coated support, for example via chemical ormechanical polishing, thereby retaining gel in the wells but removing or inactivating substantially all of the gel from the interstitial regions on the surface of the structured substrate between the wells. Primer nucleic acids canbeattached togelmaterial.Asolutionof targetnucleicacids (e.g.a fragmentedhumangenome)can thenbecontacted with the polished substrate such that individual target nucleic acids will seed individual wells via interactions with primers attached to the gel material; however, the target nucleic acids will not occupy the interstitial regions due to absence or inactivity of the gelmaterial. Amplification of the target nucleic acidswill be confined to thewells since absenceor inactivity of gel in the interstitial regions prevents outwardmigration of the growing nucleic acid colony. The process is manufactur- able, being scalable and utilizing conventional micro‑ or nano-fabrication methods.

[0099] The imaging device of the sequencing instrument (e.g., a solid-state imager such as a charge-coupled device (CCD) or a complementary metal-oxide-semiconductor (CMOS) sensor) takes snapshots at multiple locations along the lanes in a series of non-overlapping regions called tiles. For example, there can be sixty four or ninety six tiles per lane. A tile holds hundreds of thousands to millions of clusters.

[0100] The output of the sequencing runs is the sequencing images, each depicting intensity emissions of the clusters and their surrounding background. The sequencing images depict intensity emissions generated as a result of nucleotide incorporation in the sequences during the sequencing. The intensity emissions are fromassociated analytes / clusters and their surrounding background.

[0101] Sequencing images 702 are sourced from a plurality of sequencing instruments, sequencing runs, cycles, flow cells, tiles, wells, and clusters. In one implementation, the sequencing images are processed by the base caller 704 on an imaging-channel basis. Sequencing runs produce m image(s) per sequencing cycle that correspond to m imaging channels. Inone implementation, each imagingchannel (also referred toascolor channel) corresponds tooneofaplurality of filter wavelength bands. In another implementation, each imaging channel corresponds to one of a plurality of imaging events at a sequencing cycle. In yet another implementation, each imaging channel corresponds to a combination of illuminationwithaspecific laser and imaging throughaspecificoptical filter. In different implementationssuchas4‑, 2‑, and 1-channel chemistries, m is 4 or 2. In other implementations, m is 1, 3, or greater than 4.

[0102] In another implementation, the input data is basedonpHchanges inducedby the releaseof hydrogen ionsduring molecule extension. The pH changes are detected and converted to a voltage change that is proportional to the number of bases incorporated (e.g., in the case of Ion Torrent). In yet another implementation, the input data is constructed from nanopore sensing that uses biosensors to measure the disruption in current as an analyte passes through a nanopore or near its aperture while determining the identity of the base. For example, the Oxford Nanopore Technologies (ONT) sequencing is based on the following concept: pass a single strand of DNA (or RNA) through amembrane via a nanopore and apply a voltage difference across the membrane. The nucleotides present in the pore will affect the pore’s electrical resistance, so current measurements over time can indicate the sequence of DNA bases passing through the pore. This electrical current signal (the ’squiggle’ due to its appearancewhen plotted) is the rawdata gathered by anONTsequencer. These measurements are stored as 16-bit integer data acquisition (DAC) values, taken at 4kHz frequency (for example). With a DNA strand velocity of ~450 base pairs per second, this gives approximately nine raw observations per base on average. This signal is then processed to identify breaks in the open pore signal corresponding to individual reads. These stretches of raw signal are base called - the process of converting DAC values into a sequence of DNA bases. In some implementations, the input data comprises normalized or scaled DAC values. Additional information about non-image based sequenced data can be found in U.S. Provisional Patent Application No. 62 / 849,132, entitled, "Base Calling Using Convolutions," filed May 16, 2019, U.S. Provisional Patent Application No. 62 / 849,133, entitled, "Base Calling Using CompactConvolutions," filedMay16,2019,andU.S.NonprovisionalPatentApplicationNo.16 / 826,168,entitled "Artificial Intelligence-Based Sequencing," filed 21 March 2020. Spatially Varying Sharpening Masks

[0103] A particular sharpening mask / mask / convolution kernel can be configured to / trained to improve and / or improve and / or maximize the signal-to-noise ratio of a particular category / type / configuration / characteristic / class / bin of data. Similarly, respective sharpeningmasks can be configured to improve and / or improve and / ormaximize the signal-to-noise 17 EP 4 679 300 A2 5 10 15 20 25 30 35 40 45 50 55 ratio of respective instances / categories / types / configurations / characteristics / classes / bins of dataWedisclose a variety of sharpening masks. For example, a "surface-specific specialist sharpening mask" is configured to / trained to improve and / or maximize the signal-to-noise ratio of sequencing data of clusters located on a particular surface or a particular surface-type / category / class (e.g., top surfaces or bottom surfaces or surfaces 1 to N of a flow cell). Similarly, a "lane- specific specialist sharpening mask" is configured to / trained to improve and / or maximize the signal-to-noise ratio of sequencing data of clusters located on a particular lane or a particular lane-type / category / class (e.g., central lanes or peripheral lanes or lanes 1 to N of a flow cell). Also, a "tile-specific specialist sharpening mask" is configured to / trained to improve and / or maximize the signal-to-noise ratio of sequencing data of clusters located on a particular tile or a particular tile-type / category / class (e.g., central tiles or peripheral tiles or tiles 1 to N of a flow cell). Also, a "sub-tile-specific specialist sharpening mask" is configured to / trained to improve and / or maximize the signal-to-noise ratio of sequencing data of clusters locatedonaparticular sub-tile or a particular sub-tile-type / category / class (e.g., central sub-tiles or peripheral sub- tiles or sub-tiles 1 to N of a flow cell). In some implementations, a single sharpening mask can comprise a plurality of specialist coefficient sets, such that each specialist coefficient set is configured to / trained to improve and / or maximize the signal-to-noise ratio of a particular category / type / configuration / characteristic / class / bin of data. In some implementations, thesingle sharpeningmaskcancompriseavariety of specialist coefficient sets. For example, a "surface-specific specialist coefficient set" is configured to / trained to improve and / ormaximize the signal-to-noise ratio of sequencing data of clusters located on a particular surface or a particular surface-type / category / class (e.g., top surfaces or bottom surfaces or surfaces 1 toNof a flow cell). Similarly, a "lane-specific specialist coefficient set" is configured to / trained to improve and / or maximize the signal-to-noise ratio of sequencing data of clusters located on a particular lane or a particular lane- type / category / class (e.g., central lanes or peripheral lanes or lanes 1 to N of a flow cell). Also, a "tile-specific specialist coefficient set" is configured to / trained to improve and / ormaximize the signal-to-noise ratio of sequencing data of clusters located on a particular tile or a particular tile-type / category / class (e.g., central tiles or peripheral tiles or tiles 1 toN of a flow cell). Also, a "sub-tile-specific specialist coefficient set" is configured to / trained to improve and / or maximize the signal-to- noise ratio of sequencing data of clusters located on a particular sub-tile or a particular sub-tile-type / category / class (e.g., central sub-tiles or peripheral sub-tiles or sub-tiles 1 to N of a flow cell). The disclosed specialist sharpening masks are applicable to clusters located on both patterned and unpatterned surfaces of a flow cell. With unpatterned surfaces, the clusters are randomly distributedon the flowcell. The randomlydistributed clusters anddata therefor (e.g., images) canbe binned spatially, temporally, signal-wise, or by any combination thereof. Accordingly, the specialist sharpeningmasks can beconfiguredand trained for different configurationsof thedifferently binned randomlydistributedclusters.Withpatterned surfaces, the clusters are located on patterned wells with fixed locations. The patterned wells and the constituent clusters can be binned spatially, temporally, signal-wise, or by any combination thereof. Accordingly, the specialist sharpening masks canbe configured and trained for different configurations of the differently binned patterned clusters. Thedisclosed specialist sharpeningmasks are configuration-specific sharpeningmasks that are trained to improve and / ormaximize the signal-to-noise ratio of imagedata generated for different configurations of a sequencing run. These configurations canbe spatial configurations relating to different regions on a flow cell, temporal configurations relating to different sequencin- g / imaging cycles of the sequencing run, signal distribution configurations relating to different distributions / patterns of signal profiles observed / encoded in the imaged data, or a combination thereof. Other examples of configurations covered by this disclosure include segmenting sequencing data and training corresponding specialist sharpening masks by imaging type, color channel type, laser type, optics type, lens type, optical filter type, illumination type, library type, sample type, indexing type (first index readv / ssecond index read), read type (forward readv / s reverse read), physicalpropertiesof the sample, noise type (e.g., bubble), and reagent type.

[0104] Fig. 8A illustrates a plurality of sharpeningmasks 820used for corresponding sections of the sequencing images generated for corresponding regions of a flow cell, where each tile of the flow cell is divided in 3×3 sub-tile regions, with each sub-tile region assigned one or more corresponding sharpening masks.

[0105] For example, in Fig. 8A, two example tiles 812 and 814 of a flow-cell are illustrated (see Fig. 2 for further discussion of tiles and flow-cell), where the flow-cell generates the sequencing images 702 of Fig. 7. Tile 812 is divided in 3×3 sub-tile regions 812a, 812b, ..., 812i, as illustrated. Similarly, tile 814 is divided in 3×3 sub-tile regions 814a, 814b, ..., 814i, as illustrated. Similarly, other tiles of the flow cell may also be divided in corresponding 3×3 sub-tile regions. Merely asanexample, if a tile has9000×9000pixels in thecorresponding image, the image isdivided in sub-tile regions, such that each sub-tile region has 3000×3000 pixels.

[0106] Each sub-tile comprises a plurality of clusters. For example, each 3000×3000-pixel sub-tile region of the image comprises images of the corresponding plurality of clusters.

[0107] Each sub-tile region of a tile is assigned one or more corresponding sharpening masks. For example, in the example of Fig. 8A, two color channels 802A, 802B are assumed merely as an example, although there may be any different number of color channels. For example, sharpening masks 820Ax correspond to color channel 802A, and sharpeningmasks 820Bx correspond to color channel 802B, where the "A" in sharpeningmasks 820Ax implies that these masksare for processing images for color channel 802A, and the "B" in sharpeningmasks820Bx implies that thesemasks are for processing images for color channel 802B. 18 EP 4 679 300 A2 5 10 15 20 25 30 35 40 45 50 55

[0108] Furthermore, the indices "x" inmasks 820Ax and 820Bx are associated with corresponding sub-tiles 812x, 814x for which the masks are to be used. For example, mask 820Aa is used for sections of the sequencing images 702 generated fromsub-tile 812a of the tile 812 andalso for the sub-tile 814a of the tile 814;mask 820Ba is used for sections of the sequencing images 702 generated from sub-tile 812a of the tile 812 and also for the sub-tile 814a of the tile 814; mask 820Ab is used for sections of the sequencing images 702 generated from sub-tile 812b of the tile 812 and also for the sub- tile 814b of the tile 814, and so on.

[0109] Thus, in summary, for example,mask 820Aa is used for sections of the sequencing images 702 that corresponds to color channel 802A and for sub-tile regions 812a and 814a; mask 820Ba is used for sections of the sequencing images 702 that corresponds to color channel 802Band for sub-tile regions 812aand814a;mask 820Ab is used for sections of the sequencing images 702 that corresponds to color channel 802A and for sub-tile regions 812b and 814b; mask 820Bb is used for sections of the sequencing images 702 that corresponds to color channel 802B and for sub-tile regions 812b and 814b; and so on.

[0110] Note that a same sharpeningmask is used for corresponding sub-tile regions of multiples tiles. For example, the sharpeningmasks802Aaand802Baareused for top-left sub-tile ofmultiple or all tilesof theflowcell, thesharpeningmask 802Ae and 802Be are used for the central sub-tile of multiple or all tiles of the flow cell, and so on.

[0111] Thus, in the example of Fig. 8A where each tile is divided in 3×3 sub-tile regions and 2 color channels are assumed, there are 9*2 or 18 sharpening masks. In general, if each tile is divided in N number of sub-tile regions and M color channels are assumed, then there are M*N number of sharpening masks.

[0112] In an example, the k×k (such as 3×3) subdivision of a tile may be used for scenarios where a point and shoot image capturing system is used to capture the sequencing image. For example, in a point and shoot image capturing system, a center of the tile may be captured slightly different from an edge of the tile, e.g., due to distortion effects, due to different focusing on different sections of the tile, and / or the like. Accordingly, an edge of the tile can have a different sharpening mask than a center of the tile, as illustrated in Fig. 8A. Furthermore, due to factors like tilting in the optical system relative to the flow cell, images fromdifferent edges of the tile can also be slightly different (i.e., each edgemay not be similarly represented in the image). Accordingly, in the example of Fig. 8A, each of the 9 sub-tiles can have different associated sharpening masks.

[0113] Fig. 8B illustrates a plurality of sharpeningmasks 840used for corresponding sections of the sequencing images generated for corresponding regions of a flow cell, where each tile of the flow cell is divided in 1×9 sub-tile regions, with each sub-tile region assigned one or more corresponding sharpening masks.

[0114] For example, in Fig. 8B, two example tiles 832 and 834 of a flow-cell are illustrated (see Fig. 2 for further discussion of tiles and flow-cell), where the flow-cell generates the sequencing images 702 of Fig. 7. Tile 832 is divided in 1×9 sub-tile regions 832a, 832b, ..., 832i, as illustrated. Similarly, tile 834 is divided in 1×9 sub-tile regions 834a, 834b, ..., 834i, as illustrated. Similarly, other tiles of the flow cell may also be divided in corresponding 1×9 sub-tile regions.

[0115] Merely as an example, if a tile has 9000×9000 pixels in the corresponding image, the image is divided in sub-tile regions, such that each sub-tile region has 9000× 1000 pixels. Each 9000×1000-pixel sub-tile region of the image comprises images of corresponding plurality of clusters.

[0116] Each sub-tile region of a tile is assigned one ormore corresponding sharpeningmasks. In the example of Fig. 8B (and similar to the example of Fig. 8A), two color channels 804A, 804Bare assumedmerely as anexample, although there maybeanydifferent number of color channels. For example, sharpeningmasks840Ax correspond to color channel 804A, and sharpening masks 840Bx correspond to color channel 804B, where the "A" in the sharpening masks 840Ax implies that these masks are for processing images for color channel 804A, and the "B" in the sharpening masks 840Bx implies that these masks are for processing images for color channel 804B.

[0117] Furthermore, the indices "x" inmasks 840Ax and 840Bx are associated with corresponding sub-tiles 832x, 834x forwhich themasksare to beused. For example,mask 840Aa is used for section of the sequencing images702generated from sub-tile 832a of the tile 832 and also for the sub-tile 834a of the tile 834; mask 840Ba is used for section of the sequencing images 702 generated from sub-tile 832a of the tile 832 and also for the sub-tile 834a of the tile 834. Similarly, masks 840Ab and 840Bb are used for section of the sequencing images 702 generated from sub-tile 832b of the tile 832 and also from sub-tile 834b of the tile 834, and so on.

[0118] Thus,mask840Aa isused for sectionsof thesequencing images702 that corresponds tocolor channel 804Aand for sub-tile regions 832a and 834a; mask 840Ba is used for sections of the sequencing images 702 that corresponds to color channel 804Band for sub-tile regions832aand834a;mask840Ab isused for sectionsof thesequencing images702 that corresponds to color channel 804A and for sub-tile regions 832b and 834b; mask 840Bb is used for sections of the sequencing images 702 that corresponds to color channel 804B and for sub-tile regions 832b and 834b; and so on.

[0119] Thus, in the example of Fig. 8B where each tile is divided in 1×9 sub-tile regions and 2 color channels are assumed, there are 9*2 or 18 sharpening masks. In general, if each tile is divided in N number of sub-tile regions and M color channels are assumed, then there are M*N number of sharpening masks.

[0120] In an example, the 1×k (such as 1×9) subdivision of a tile may be used for scenarios where a line scan image capturing system is used to capture the sequencing image. For example, in a line scan image capturing system, various 19 EP 4 679 300 A2 5 10 15 20 25 30 35 40 45 50 55 vertical sub-regions of the image may be captured differently. Accordingly, the image is divided in different vertical sub- regions, as illustrated in Fig. 8B, with each sub-region assigned its own corresponding sharpening mask.

[0121] Fig. 8C illustrates a plurality of sharpeningmasks860used for corresponding sections of the sequencing images generated for corresponding regions of a flowcell, where each tile of the flowcell is divided inmultiple sub-tile regions,with similar sub-regions occurring periodically in a tile are assigned one or more corresponding sharpening masks.

[0122] For example, in Fig. 8C, twoexample tiles 852 and854of a flow-cell are illustrated,where the flow-cell generates the sequencing images 702 of Fig. 7. Tile 852 is divided in 3×3 sub-tile regions, wherein a corner region of each sub-tile is illustrated using grey shadings. The shaded regions in various sub-tiles of the tiles 852 and 858 are labelled as shaded regions 855a, and the non-shaded regions in various sub-tiles of the tiles 852 and 858 are labelled as non-shaded regions 855b.

[0123] Although in the example of Fig. 8C the shaded regions 855a occur with a specific periodicity (e.g., top-left corner of each sub-tile), this is merely an example, and the shaded regions 855a can occur with any other type of periodicity as well. For example, two horizontal lines of pixel of a tile can be included in a shaded region 855a, followed by a non-shaded region855b including fivehorizontal linesof pixel, and this patternmay repeat. Thus, in this example, the two linesof pixels of the shaded regions 855a and the five lines of pixels of the non-shaded regions 855b are interleaved and occur in a repeating pattern. Any other pattern of shaded regions 855a and non-shaded regions 855bmay also be possible. Merely as an example, intersection of every other (fourth row) and (fifth and sixth columns) of pixels can be included in the shaded region 855a, and this pattern of shaded region can be repeated throughout the image.

[0124] In an example, the use of repeating patterns of shadedandnon-shaded regions illustrated in Fig. 8C canbeused for scenarios where CMOS (complementary metal oxide semiconductor) image capturing sensors are used for capturing the sequencing images. For example, some sequencing platforms use flowcells that have embedded CMOS sensors. Sequencing chemistry is performed directly on top of the CMOS sensor, and then imaged with the assistance of LED exciting the fluorescent molecules on the sensor. In an example (e.g., due to design and cost requirements to satisfy both imaging and chemistry), the CMOS sensor read-out circuitry is embedded into the sensor itself as repeating rows and columns of "dark pixels," where such periodic patches of dark pixels are symbolically represented as the shaded region 855a in Fig. 8C. This design pattern creates a unique intensity extraction challenge that necessitates use of different extraction kernels at certain periodicity, as discussed with respect to Fig. 8C. Use of CMOS sensor embedded within the flow cell may be found in PCT Publication No. WO 2020 / 236945, which is incorporated by reference as if fully set forth herein.

[0125] Each shaded region 855a of a tile is assigned one or more corresponding sharpening masks. In the example of Fig. 8C (and similar to the example of Fig. 8A), two color channels 806A, 806B are assumed merely as an example, although theremaybeanydifferent number of color channels. For example, sharpeningmasks860Ax correspond to color channel 806A, and sharpening masks 860Bx correspond to color channel 806B, where the "A" in the sharpening masks 840Bx implies that these masks are for processing images for color channel 806A, and the "B" in the sharpening masks 860Bx implies that these masks are for processing images for color channel 806B.

[0126] Furthermore, the indices "x" inmasks 860Ax and 860Bx are associatedwith corresponding shaded / non-shaded regions 855x for which the masks are to be used. For example, masks 860Aa and 860Ba are used for section of the sequencing images 702 generated from the shaded regions 855a of various tiles. Similarly, masks 860Ab and 860Bb are used for section of the sequencing images 702 generated from the non-shaded regions 855b of various tiles.

[0127] Thus,mask860Aa isused for sectionsof thesequencing images702 that corresponds tocolor channel 806Aand for shaded regions855a;mask860Ba isused for sectionsof thesequencing images702 that corresponds to color channel 806B and for shaded regions 855a; mask 860Ab is used for sections of the sequencing images 702 that corresponds to color channel 806Aand for non-shaded regions 855b; andmask860Bb is used for sections of the sequencing images 702 that corresponds to color channel 806B and for non-shaded regions 855b.

[0128] Thus, in theexampleof Fig. 8Cwhereeach tile is divided in shadedandnon-shaded regionsand2color channels are assumed, there are 2*2 or 4 sharpening masks. Training

[0129] Referring again to Fig. 7, the base caller 704 generates one or more sharpening masks 706 (e.g., such as the sharpening masks discussed with respect to Figs. 8A‑8C), which are used to sharpen the sequencing images 702 (the sharpening operations are discussed in further detail with respect to Figs. 10A‑10K and 11). The sharpening operations involve intensity extraction from the sequencing image to generate corresponding feature map, and subsequent interpolation operation to assign weighted feature values of various clusters, based on sub-pixel location of the clusters, as discussed in further detail herein later. The clusters, with the corresponding assignedweighted feature values, are then base called.

[0130] In one implementation, the number of sharpening masks 706 generated by the base caller 704 may be implementation specific, as discussed with respect to Figs. 8A‑8C. For example, each color channel may have 20 EP 4 679 300 A2 5 10 15 20 25 30 35 40 45 50 55 corresponding sharpeningmask 706. In another example, a tile of the flow cell fromwhich the sequencing images 702 are generated may be divided in two or more sections, with a dedicated sharpening mask for individual section of the tile, as discussed in further detail with respect to Figs. 8A‑8C.

[0131] Aswill be discussed in further detail (e.g., in Fig. 10F herein later), the sharpeningmasks 706 act as convolution kernels, andasharpeningmask is convolvedwithacorrespondingsectionof the image.Merely asanexample, referring to Fig. 8A, the sharpening mask 820Aa is convolved with a section of the sequencing image 702 generated by the sub-tile 812a for the color channel 802A. In one implementation of the training, the coefficients of each sharpeningmasks 706 are determined using least squares estimation on the corresponding subset of data from the corresponding sections of the images. Thus, again referring to Figs. 7 and 8A, for example, data for color channel 802A and from the sub-tile 812a are used to generate and / or train the sharpening mask 820a.

[0132] As illustrated in Fig. 7, the input to the base caller 704 is the raw sensory pixels of the sequencing images from various tile of the flow cell. Each sharpening mask 706 has a plurality of coefficients that are learned from the training. In one implementation, the number of coefficients in a sharpeningmask corresponds to the number of sensor pixels that are used for base calling a cluster. In an example, a sharpeningmask is a squarematrix having k×k coefficients, where k is an appropriate positive integer, such as 3, 5, 7, 9, or the like. Thus, each sharpening mask 706 has k2 coefficients.

[0133] The training produces sharpeningmask coefficients that are configured tomix / combine intensity values of pixels that depict intensity emissions fromacluster being base called and intensity emissions fromoneormore adjacent clusters in a manner that maximizes a signal-to-noise ratio. The signal maximized in the signal-to-noise ratio is the intensity emissions from a target cluster, and the noise minimized in the signal-to-noise ratio in the intensity emissions from the adjacent clusters, i.e., spatial crosstalk, plus some random noise (e.g., to account for background intensity emissions). The sharpening mask coefficients are used as weights and the mixing / combining includes executing element-wise multiplication between the sharpeningmask coefficients and the intensity values of the pixels, to calculate aweighted sum of the intensity values of the pixels (e.g., which are features in a feature map, see Figs. 10E and 10F).

[0134] During training, the base caller 704 learns to improve and / or maximize the signal-to-noise ratio by least squares estimation, according to one implementation.Using the least squares estimation, the base caller 704 is trained to estimate shared sharpening mask coefficients from the pixel intensities around a subject well and a desired output. Least squares estimation is well suited for this purpose because it outputs coefficients that minimize squared error and take into account the effects of noise amplification.

[0135] The desired output is an impulse at thewell (i.e., cluster) location (the point source) when the intensity channel is ON and the background level when the intensity channels is OFF. In some implementations, ground truth 712 are used to generate the desired output. In an example, the ground truth 712 comprises ground truth base calls. Additionally or alternatively, in someexamples, theground truth comprisesacenter of a cloud (or anaverage) for eachbase, as illustrated in Fig. 9A and as will be discussed herein in further detail.

[0136] In some implementations, the ground truth 712 are modified to account for per-well DC offset, amplification coefficient, degree of polyclonality, and gain offset parameters that are included in the least squares estimate. In one implementation, during the training, aDCoffset, i.e.,afixedoffset is calculatedaspart of the least squaresestimate.During inference, the DC offset is added as a bias to each sharpening mask calculation.

[0137] In one implementation, the desired output is estimated using Illumina’s Real-time Analysis (RTA) base caller. Details about the RTA can be found in USPatent ApplicationNo. 13 / 006,206, which is incorporated by reference as if fully set forth herein. The base calling errors get averaged out acrossmany training examples. In another implementation, the ground truth 712 are sourced using aligned genomic data,which has better quality because aligned genomic data canuse reference genome and truth informationwhich incorporate the knowledge gained frommultiple sequencing platforms and sequencing runs to average out the noise.

[0138] The ground truth 712 are base-specific intensity values (or feature values, discussed herein later) that reliably represent intensity profiles of bases A, C, G, and T, respectively. A base caller like the RTA base calls clusters by processing the sequencing images 702 and producing, for each base call, color-wise intensity values / outputs. The color- wise intensity values can be considered base-wise intensity values because, depending on the type of chemistry (e.g., 2- color chemistry or 4-color chemistry), the colors map to each of the bases A, C, G, and T. The base with the closest matching intensity profile is called.

[0139] Fig. 9A shows one implementation of base-wise Gaussian fits that contain at their centers base-wise intensity targetswhichareusedasground truth values for error calculationduring training.Base-wise intensity outputs producedby the base caller for amultiplicity of base calls in the training data (e.g., tens, hundreds, thousands, or millions of base calls) are used to produce a base-wise intensity distribution. Fig. 9A shows a chart with four Gaussian clouds that are a probabilistic distribution of the base-wise intensity outputs of the bases A, C, G, and T, respectively. Intensity values at the centers of the four Gaussian clouds are used as the ground truth intensity targets (or feature value targets) of the ground truth 712 for the bases A, C, G, and T, respectively, and referred to herein as the targets (e.g., intensity or feature value targets).

[0140] Consider that, during the training, input image data that is fed to the base caller 704 is annotatedwith base "A" as 21 EP 4 679 300 A2 5 10 15 20 25 30 35 40 45 50 55 theground truthbasecall. Theground truth712also includesbase-specific intensity values that reliably represent intensity profilesof basesA,C,G, andT, respectively. Thus, for example, theground truth712also includes, for baseA, coordinates of an average intensity or average feature value for baseA (i.e., a center of the green cloud in Fig. 9A), as illustrated in Fig. 9A (feature values have been discussed herein later). Then, the target / desired output of the base caller 704 is the intensity value or feature value at the center of the green cloud in Fig. 9A, i.e., the intensity target for base A. Similarly, for base "C," ground truth comprises the intensity value or feature value at the center of the blue cloud in Fig. 9A, i.e., the intensity target (or the feature value target) for base C having coordinates (Cx,Cy). Similarly, for base "T," ground truth comprises the intensity value or feature value at the center of the red cloud in Fig. 9A, i.e., the intensity target (or the feature value target) for baseT having coordinates (Tx,Ty). Also, for base "G," ground truth comprises the intensity value or feature value at the center of the brown cloud in Fig. 9A, i.e., the intensity target (or the feature value target) for base G having coordinates (Gx,Gy).

[0141] Accordingly, targets or desired outputs during the training of the base caller 704 are the average intensities (or average feature values) for the respective basesA, C,G, and Tafter averaging in the training data. In one implementation, the trainer 714 uses the least squares estimation to fit the coefficients of the sharpeningmasks 706, tominimize the output error to these targets.

[0142] Inone implementation, during the training, thebasecaller 704applies thecoefficients inagivensharpeningmask to pixels of a sequencing image labelledwith a given base. This includes element-wisemultiplying the coefficientswith the intensity values of the pixels and generating a weighted sum of the intensity values of a feature map, with the coefficients serving / acting / used as theweights. The featuremap includes various features having corresponding feature values.Note that a center of a cluster may not align with a center of a pixel of the sequencing images 702. To account for such misalignment, in the feature map generated from the sequencing images 702 (where the feature map is generated by convolvingasharpeningmaskwithacorrespondingsectionof the image), aweighted feature valueassigned toacluster is generated by bilinear interpolation, e.g., where neighboring features are interpolated to generate the weighted feature value corresponding to a cluster, as will be discussed herein in further detail in turn. The interpolated feature value corresponding to the cluster then becomes the predicted output of the base caller 704 for that cluster. Then, based on a cost / error function (e.g., sumof squarederrors (SSE)), anerror (e.g., the least squareerror, the leastmeanssquarederror) is calculated between the interpolatedweighted feature value and the intensity target determined for the given base of the cluster (e.g., from the center of the corresponding intensity Gaussian fit as the average intensity observed for the given base). The cost function, such as theSSE, is a differentiable function used to estimate sharpeningmask coefficients using an adaptive approach, andwe can therefore evaluate the derivatives of the error with respect to the coefficients, and these derivatives are then used to update the coefficients with values that minimize the error. This process is repeated until the updated coefficients do not reduce the error anymore. In other implementations, batch least squares approach is used to train the base caller 704.

[0143] For example, assume that the center of the green cloud in Fig. 9A, i.e., the intensity target for base A is (Ax,Ay), which is the target or desired output (e.g., a target feature value) for base A base calls. Assume that during a sequencing run, a cluster 904 has a weighted feature value represented at coordinate (Ix,Iy). In an embodiment, the base caller 704 updates coefficients in a given sharpening mask, such that the intensity of cluster 904 is transposed to the coordinates (Ax,Ay) from the coordinates (Ix,Iy). Thus, the training aims to minimize or reduce the distance between the coordinates (Ax,Ay) and (Ix,Iy).

[0144] In an example, the base-wise intensity distributions / Gaussian clouds shown in Fig. 9A can be generated on a well-by-well basis and corrected for noise by addition of a DC offset, amplification coefficient, and / or phasing parameter. Thisway, depending upon thewell location of a particularwell, the correspondingbase-wiseGaussian clouds canbeused to generate target intensity values for that particular well (or a cluster corresponding to the well).

[0145] In one implementation, a bias term is added to the dot product that produces the output of the base caller 704. During training, the bias parameter can be estimated using a similar approach used to learn the coefficients of the sharpening masks, i.e., least squares or least mean squares (LMS). In some implementations, the value for the bias parameter is a constant value equal to one, i.e., a value that does not varywith the input pixel intensities. There is one bias per set of coefficients. Thebias is learnedduring the training and thereafter fixed for useduring inference. The learnedbias represents a DC offset that is used in every calculation during the inference, along with the learned coefficients of each sharpeningmask. The bias accounts for random noise caused by different cluster sizes, different background intensities, varying stimulation responses, varying focus, varying sensor sensitivities, and varying lens aberrations.

[0146] In yet other decision-directed implementations, the outputs of the base caller 704 are presumed to be correct for the training purposes.

[0147] The trainer 714 can train the base caller 704 and generate the trained coefficients of the sharpening masks 706 using a plurality of training techniques. Examples of the training techniques include least squares estimation, ordinary least squares, least-mean squares, and recursive least-squares. The least squares technique adjusts the parameters of a function to best fit a data set so that the sum of the squared residuals is minimized. In other implementations, other estimation algorithms and adaptive algorithms can be used to train the base caller 704. 22 EP 4 679 300 A2 5 10 15 20 25 30 35 40 45 50 55

[0148] The base caller 704 can be trained in an offline mode or online mode of adaptation. According to one implementation, the trained coefficients of the base caller 704 are generated and / or updated using the following batch least squares logic:

[0149] In the equation above, the sharpeningmask coefficients are beta hat (β̂). For example, if a sharpeningmask 706 has a dimension of k×k, then the beta hat (β̂) is a vector having a dimension of (k×k). Thus, for a 3×3 dimensional sharpening mask, the beta hat (β̂) is a vector of size 9.

[0150] X is amatrix with pixel values of sizem×(k×k), i.e.,mrowsand (k×k) column,wherem is anappropriate positive integer.Each rowof thematrixXcorresponds toonecluster, andeachcolumn is thevalueof imagepixelsafter adjusting for subpixel interpolation.

[0151] y is a vector of sizem that corresponds to a centroid location of each cluster. For example, y is a target output for every training example, i.e., each value is the intensity center of an ON / OFF cloud depending upon the training example truth. Beta hat is then the set of coefficients that minimize the sum of the squared residuals.

[0152] In an example, the base caller 704 can also be trained in an online mode to adapt the coefficients of the sharpening masks 706, e.g., to track changes in the temperature (e.g., optical distortion), focus, chemistry, machine- specific variation, etc., while the sequencing machine is running and the sequencing run is cyclically progressing. In the online mode, the trained coefficients of the sharpening masks 706 are updated using adaptive techniques. The online modeuses the least-meansquaresas the trainingalgorithm,which is a formof stochastic gradient descent. Further details about online adaptation of the coefficients of the sharpening masks 706 have been discussed herein later, e.g., with respect to Figs. 12 and 13.

[0153] The least-mean squares technique uses the gradient of the squared error with respect to each coefficient, to move the coefficients in a direction that minimizes the cost function which is the expected value of the squared error. This has a very low computational cost-only a multiply and accumulate operation per coefficient is executed. No long-term storage is needed, except for the coefficients. The least-mean squares technique is well suited to for processing huge amountsofdata (e.g., processingdata frombillionsof clusters inparallel).Extensionsof the least-meansquares technique include normalized least-mean-square and frequency-domain least-mean-square, which can also be used herein. In some implementations, the least-mean squares technique can be applied in a decision-directed fashion in which we assume thatour decisionsarecorrect, i.e.,ourerror rate is very lowandsmallmuvalueswill filter outanydisturbedupdates due to incorrect base calls.

[0154] Fig. 9B shows one implementation of an adaptive technique that can be used to train the base caller 104, e.g., using an offline or onlinemode. Here, the logic is y = x.h + d, where x is the input pixel intensities, h is the sharpeningmask coefficients, d is theDCoffset. In one implementation, xandhare rowandcolumnvectors respectively,with length81. This vector model is equivalent to a dot product of 9 x 9 matrices representing input pixels and coefficients. The cost is the expected value of error squared. The gradient update moves each coefficient in a direction that reduces the expected value of error squared. This leads to the following update: Formost systems the expectation function E {x(n)e*(n)}must be approximated. This can donewith the following unbiased estimator: Where N indicates the number of samples that estimate. The simplest case is N = 1. For that simple case the update algorithm follows as: 23 EP 4 679 300 A2 5 10 15 20 25 30 35 40 45 50 55 Indeed, this constitutes the update algorithm for the LMS filter.

[0155] Inequationsabove,h isavectorof sharpeningmaskcoefficients, x isavectorof input intensities, ande is theerror for the calculation that was performed using the values in x, i.e., only 1 error term per output.

[0156] Applying thisupdategeneratesanewestimateof thecoefficients thatmoves them inadirection that (onaverage) reduces the mean squared error (MSE). In some implementations, Mu is a small constant used to change the adaptation rate / convergencespeed.ADC termupdate canbecalculated in asimilarway.Again termupdatealso canbecalculated in a similar way.

[0157] In some implementations, since linear interpolation is applied on the coefficient sets, the updates are applied slightly differently in the following manner:

[0158] In the equation above, h(q, n) is weight q at cycle n, lambda_q is the linear interpolationweight for a particular set of coefficients and can include four updates per output due to linear interpolation in two dimensions.

[0159] The recursive least-squares technique extends the least squares technique to a recursive algorithm. Spatial Crosstalk Attenuator

[0160] Figs. 10A‑10K, in combination, illustrate various implementations of using the trained sharpening masks 706 of Figs. 7‑8C, to attenuate spatial crosstalk from sensor pixels and to base call clusters using crosstalk-corrected sensor data.Specifically, Fig. 10A illustratesasection1000of thesequencing image702 fromasub-tile of a tile (e.g.,sub-tile 812a of tile 812, see Fig. 8A), in which various cluster centers are offset with respect to centers of corresponding pixels.

[0161] Although a sub-tile is likely to generate a large number of pixels of the sequencing image 706, the section 1000 of Fig. 10A corresponding to a sub-tile includes merely a few pixels, for purposes of simplicity.

[0162] Fig. 10A further illustrates centers of a plurality of clusterswithin the sub-tile,where the centers of the clusters are superimposed on the section 1000 of the sequencing image 706. Also assume that the section 1000 displayed in Fig. 10 is for a specific color channel. Consider an optical system of a sequencer that uses two different imaging channels: a red channel and a green channel (although the sequencermay generate any different number of color channels, such as 1, 3, 4, or higher). Then, at each sequencing cycle, the optical system produces a red image with red channel intensities and a green imagewithgreenchannel intensities,which together formasingle sequencing image (likeRGBchannelsof a typical color image). In an example, the pixels depicted in Fig. 10 are for a specific color channel.

[0163] InFig. 10A, someof theclusters,whosecentersare illustratedusingblackdots, are labelled.Forexample, I theX- Y coordinate plane, cluster 1011 has a center disposed at location (x1,y1); cluster 1012 has a center disposed at location (x2,y2); cluster 1013 has a center disposed at location (x3,y3); cluster 1014 has a center disposed at location (x4,y4); and cluster 1015 has a center disposed at location (x5,y5).

[0164] In an example, locations (e.g., coordinates) of clusters on a tile are identified using fiducial markers. A solid support upon which a biological specimen is imaged can include such fiducial markers, to facilitate determination of the orientation of the specimen or the image thereof in relation to probes that are attached to the solid support. Exemplary fiducials include, butarenot limited tobeads (withorwithout fluorescentmoietiesormoieties suchasnucleicacids towhich labeled probes can be bound), fluorescent molecules attached at known or determinable features, or structures that combinemorphological shapes with fluorescent moieties. Exemplary fiducials are set forth in U.S. Patent Publication No. 2002 / 0150909,which is incorporated herein by reference. Thus, in anexample, fiducialmarkers areused to determine the locations of the clusters with respect to the section 1000 of the sequencing image 706, and the coordinates of the clusters illustrated in Fig. 10A.

[0165] Note that thecenterof aclustermaynot coincidewithacenterof a correspondingpixel. Forexample, thecenterof the cluster 1011 is within, but off-centered, with respect to a pixel 1001; the center of the cluster 1012 is within, but off- centered,with respect to a pixel 1002; the center of the cluster 1013 iswithin, but off-centered, with respect to a pixel 1003; the center of the cluster 1014 is within, but off-centered, with respect to a pixel 1004; and the center of the cluster 1015 is within, but off-centered, with respect to a pixel 1005.

[0166] Fig. 10Bvisualizesoneexampleof cluster-to-pixel signals 1033. Inone implementation, thesensorpixelsare ina pixel plane. The spatial crosstalk is causedby periodical distribution 1037 of clusters in a sample plane (e.g., a flowcell). In one implementation, the clusters are periodically distributed on the flow cell in a diamond shape and immobilized onwells of theflowcell. Inanother implementation, theclustersareperiodically distributedon theflowcell inahexagonal shapeand immobilized on wells of the flow cell. Signal cones 1035 from the cluster are optically coupled to local grids of the sensor pixels through at least one lens (e.g., one or more lenses of overhead or adjacent CCD cameras).

[0167] In addition to the diamond shape and hexagonal shape, the clusters can be arranged in other regular shapes such as a square, a rhombus, a triangle, and so on. In yet other implementations, the clusters are arranged on the sample 24 EP 4 679 300 A2 5 10 15 20 25 30 35 40 45 50 55 plane in a random, non-periodic arrangement.One skilled in the art will appreciate that the clusters can bearranged on the sample plane in any arrangement, as needed by a particular sequencing implementation.

[0168] Fig. 10C visualizes one example of cluster-to-pixel signal overlap. The signal cones 1035 (see Fig. 10B) overlap and impinge on the sensor pixels, creating spatial crosstalk 1037.

[0169] Fig. 10D visualizes one example of cluster signal pattern. In one implementation, the cluster signal pattern follows an attenuation pattern 1039 in which the cluster signal is strongest at a cluster center and attenuates as it propagates away from the cluster center.

[0170] Fig. 10E illustrates a convolution operation 1030Aa, where a sharpening mask 820Aa is convolved with a corresponding section of the sequencing image, to generate a corresponding feature map. In the example of Fig. 10E, a k×k (wherek=3 in thisexample, althoughkcanbeanotherappropriatepositive integer) sharpeningmask820Aa (seeFig. 8A) is convolved with the section 1000 of the sequencing image 702 from sub-tile 812a of tile 812 (see Fig. 10A depicting the section 1000), and for color channel 802A. Similar to Fig. 10A, cluster centers in black dots are superimposed on the section 1000 of the sequencing image 702.

[0171] Feature map 1042Aa is generated as a result of the convolution operation. Note that the feature map 1042Aa is specific to the sub-tile 812aof the tile 812and is specific for the color channel 802A.Again, cluster centers in black dots are superimposed on the feature map 1042Aa.

[0172] The section 1000 has dimensions w×h, where w (width) and h (height) can be as high as 100,000 or evenmore, e.g., depending ona sizeof the sub-tile 812a. Thus,wandhare basedon the sectioning of the tile into different sub-tiles. In one implementation, due to the convolution 1030Aa, a dimensionality of the feature map 1042Aa can be different from (e.g., less than) a dimensionality of the section 1000. In another implementation, the dimensionality can be preserved by, for example, appropriately padding the section 1000 prior to the convolution 1030Aa, or by appropriately padding the feature map 1042A after the convolution operation.

[0173] The featuremap 1042Aa comprises a plurality of features, where each feature corresponds to a respective pixel in the section 1000 of the sequencing image 702. Merely as an example, feature 1051 of the feature map 1042Aa corresponds to the pixel 1001 of the section 1000. For example, during the convolution 1030Aa, the sharpening mask 820Aa is moved across the section 1000, andmultiplication and summation operations are performed at each position of the sharpeningmask820Aa. The feature 1051 is generated due to themultiplication and summation operation,e.g.,when the sharpeningmask 820Aa is convolvedwith a patch of the section 1000 centering the pixel 1001 - thus, the feature 1051 corresponds to the pixel 1001. Similarly, other features of the feature map 1042Aa correspond to respective pixels of the section 1000 (i.e., on-to-one positional mapping between pixels of the section 1000 and features of the feature map 1042Aa).

[0174] In the example of Fig. 10E, the locations of the clusters are also superimposed on the features of the featuremap 1042Aa.Forexample, as illustrated inFig. 10A, thecluster centersof oneormoreclusterswereoffcenteredwith respect to the center of the corresponding pixels. Similarly, in Fig. 10E, the cluster centers of one or more clusters are also off centered with respect to the center of the corresponding features.

[0175] Fig. 10F illustrates a plurality of convolution operations, where each of a plurality of sharpening masks is convolved with a corresponding section of a plurality of sections of the sequencing images 702, to generate a corresponding one of a plurality of feature maps. For example, referring to Figs. 8A and 10F, the sharpening mask 820Aa is convolvedwith the section 1000of the sequencing image702 corresponding to the sub-tile 812aand for the color channel 802A, to generate corresponding feature map 1042Aa, where this convolution operation is discussed in further detail with respect to Fig. 10E. Similarly, the sharpening mask 820Ab is convolved with a respective section of the sequencing image 702 corresponding to the sub-tile 812b and for the color channel 802A, to generate corresponding featuremap1042Ab.Similarly, thesharpeningmask820Ai is convolvedwitha respective sectionof the sequencing image 702 corresponding to the sub-tile 812i and for the color channel 802A, to generate corresponding feature map 1042Ai. Generally speaking, the sharpening mask 820Ax is convolved with a respective section of the sequencing image 702 corresponding to the sub-tile 812x and for the color channel 802A, to generate corresponding featuremap 1042Ax, where x = a, ..., i. The convolution operations 1030Ax (where x = a, ..., i) on the left side of Fig. 10F are for the example color channel 802A.

[0176] The convolution operations 1030By (where y = a, ..., i) on the right side of Fig. 10F are for the example color channel 802B. For example, the sharpeningmask 820Ba is convolved with a respective section of the sequencing image 702 corresponding to the sub-tile 812a and for the color channel 802B, to generate corresponding feature map 1042Ba. Similarly, the sharpeningmask 820Bb is convolved with a respective section of the sequencing image 702 corresponding to the sub-tile 812b and for the color channel 802B, to generate corresponding featuremap 1042Bb, and so on. Generally speaking, the sharpeningmask 820Bx is convolvedwith a respective section of the sequencing image 702 corresponding to the sub-tile 812y and for the color channel 802B, to generate corresponding feature map 1042By, where y = a, ..., i.

[0177] As also discussed earlier, the two color channels 802A and 802B are merely examples, and the sequencer can include any different number of color channels, such as one color channel, or three or another higher number of color channels. 25 EP 4 679 300 A2 5 10 15 20 25 30 35 40 45 50 55

[0178] Fig. 10G illustrates the featuremap1042Aa of Fig. 10E in further detail, where someof the features and center of the clusters are labelled. For example, cluster 1011 has a center at location (x1,y1) and within the feature 1051, cluster 1012hasacenterat location (x2,y2)andwithin the feature1052,andsoon (alsoseeFig. 10A for cluster center coordinates in the section 1000 of the sequencing image).

[0179] Fig. 10H illustrates the feature map 1042Aa of Figs. 10E and 10G, wherein a portion 1029 of the feature map 1042Aa including a target cluster 1011 is illustrated in further detail in a zoomed-in view. For example, the view of the portion 1029 of the feature map 1042Aa is amplified or zoomed in, and the center of the cluster 1011 at location (x1,y1) is superimposed on the portion 1029 of the feature map 1042Aa.

[0180] As discussed, the cluster 1011 is within the feature 1051 (labelled as 1051e in Fig. 10H), but off centered with respect to a center of the feature 1051e. Eight neighboring features 1051a, ..., 1051d, 1051f, ..., 1051i, which surround the feature 1051e, are also labelled.

[0181] Centers of each feature is represented using black squares in Fig. 10Handsomesubsequent figures. A center of the feature1051ahascoordinates (xa,ya), a centerof the feature1051bhascoordinates (xb,yb), andsoon,andacenter of the feature 1051i has coordinates (xi,yi), as illustrated in Fig. 10H.

[0182] As discussedwith respect to Fig. 10E, each feature 1051(a,e) of Fig. 10Hhas a corresponding feature value that is generated by the convolution 1030Aa. Referring to Fig. 10H, in an example, the cluster 1011 is assigned a weighted feature value, where the weighted feature value is assigned based on an appropriate interpolation technique. For example, if thecenter of thecluster 1011coincideswith thecenterof the feature1051e, then the featurevalueof the feature 1051e can be assigned to the cluster 1011. However, as the center of the cluster 1011 does not coincide with the center of the feature 1051e in the example of Fig. 10H, theweighted feature value to be assigned to the cluster 1011 is influencedby not only the feature 1051e, but also one or more features that are neighboring the feature 1051e.

[0183] Inanembodiment, anappropriate interpolation technique isused toassignaweighted featurevalue to thecluster 1011, e.g., based on (i) feature value of the feature 1051e within which the center of the cluster 1011 resides, (ii) feature values of one or more neighboring features that are within a threshold distance from the center of the cluster 1011, (iii) center-to-center distance between a cluster center and a feature center, (iv) center-to-center distance between a cluster center and a pixel center, and (v) center-to-center distance associated with a cluster.

[0184] Note that Fig. 10H is in the feature map domain ‑ i.e., illustrates the feature map 1042A, with the cluster 1011 superimposed on the feature map. Coordinates of the centers of the features and the center of the cluster 1011 are also illustrated. As the name implies, center-to-center distance between a cluster center and a feature center refers to the distance between a center of a cluster and a center of a feature, and is also referred to as center-to-center distance between cluster and feature. For example, center-to-center distanced1 between the cluster 1011and the feature 1051e is the distance between the coordinates (x1,y1) and (xe,ye), determined, for example, as:

[0185] Similarly, center-to-center distance between the cluster 1011 and any other feature may also be determined.

[0186] On the other hand, a center-to-center distance between a cluster center and a pixel center, also referred to as center-to-center distance between cluster and pixel, refers to a distance between a center of a cluster and a center of a pixel. For example, referring to Fig. 10A, illustrated is the section 1000 of the sequencing image 702. Similar to Fig. 10H, coordinates of center of various pixels can be determined, and accordingly, center-to-center distance between the cluster 1011 and various pixels can also be determined.

[0187] For example, Fig. 10I illustrates the convolution operation 1030Aa of Fig. 10E, and further illustrates a center-to- center distance d2 between the cluster 1011 and the pixel 1011, as well as a center-to-center distance d1 between the cluster 1011 and the feature 1051e. Note that as discussedwith respect to Fig. 10E, the feature 1051e corresponds to the pixel 1011. For example, during the convolution 1030Aa, the sharpening mask 820Aa is moved across the section 1000, andmultiplication and summation operations are performed at each position of the sharpening mask 820Aa. The feature 1051e is generated due to the multiplication and summation operation, e.g., when the sharpening mask 820Aa is convolvedwith a patch of the section 1000 centering the pixel 1001 - thus, the feature 1051 corresponds to the pixel 1001. Thus, the position of the cluster 1011 relative to the center of the pixel 1001 is same as the position of the cluster 1011 relative to the center of the feature 1051e. That is, the distances d1 and d2 are the same.

[0188] For at least some of the interpolation operations discussed herein later, either of (i) the center-to-center distance between cluster andpixel, or (ii) the center-to-center distancebetween cluster and featuremaybeused. For example, one implementation may use the center-to-center distance between cluster and pixel, while another implementation may use the center-to-center distance between cluster and feature - these two center-to-center distances are numerically the same.

[0189] Some of the interpolation examples discussed herein later discusses the center-to-center distance between cluster and feature. However, as will be readily appreciated by those skilled in the art, the center-to-center distance 26 EP 4 679 300 A2 5 10 15 20 25 30 35 40 45 50 55 between cluster and pixel may also be used instead.

[0190] For the purposes of this disclosure and unlessmentioned otherwise, a center-to-center distance associatedwith a cluster implies a center-to-center distance between the cluster and a corresponding pixel, or a center-to-center distance between the cluster and a corresponding feature.

[0191] In anexample, a subpixel position of a cluster comprises aposition of a center of the cluster relative to aboundary of a pixel or a center of the pixel withinwhich the cluster is located. For example, if the pixel 1001 of Fig. 10I is divided into a grid of 3×3 subpixels, then the cluster 1011 is likely to be included within a top-right subpixel of the pixel 1001.

[0192] In an example, a sub-feature position of a cluster comprises a position of a center of the cluster relative to a boundary of a feature or a center of the feature within which the cluster is located. For example, if the feature 1051e of Fig. 10I isdivided intoagridof 3x3sub‑ features, then thecluster 1011 is likely tobe includedwithina top-right sub-featureof the pixel 1001. Interpolation for Determining Weighted Feature Value of a Target cluster

[0193] As discussed with respect to Fig. 10H herein above, any appropriate interpolation technique may be used to assign theweighted feature value to the cluster 1011, e.g., based on (i) feature value of the feature 1051ewithin which the center of the cluster 1011 resides, and (ii) feature values of one or more neighboring features that are within a threshold distance from thecenter of the cluster 1011.Somesuch interpolation techniquesarediscussedherein below.Note that the list of interpolation techniquesdiscussed below is not exclusive, and another appropriate interpolation technique known to those skilled in the art may also be used. A. Nearest Neighbor Interpolation

[0194] In this interpolation technique, a feature nearest to the cluster 1011 is determined, and the feature value of the nearest feature is assigned to the cluster 1011. As illustrated in Fig. 10H, the center of the feature 1051e at location (xe,ye) is closest to the center (x1,y1) of the cluster 1011. Accordingly, the cluster 1011 is assigned the feature value of the feature 1051e.

[0195] Thus, this technique involves determining center-to-center distances, where for example, a center-to-center distance between the center of the cluster 1011 (i.e., coordinate (x1,y1)) and centers of neighboring features are determined (although center-to-center distance between cluster and pixels can also be used). The feature corresponding to the nearest center-to-center distance is selected as being the nearest neighbor, and the feature value of the nearest feature is assigned to the cluster. Note that the interpolation is also based on subpixel or sub-feature location of the cluster. B. Average of Nearest Neighbor Interpolation

[0196] Another example interpolation technique involves averaging feature values of n number of nearest neighboring pixels,wheren is anappropriate integer, suchas1, 4, 9, or the like. For example, assumingn=4, then theweighted feature value assigned to the cluster 1011 is an average of feature values of nearest four neighboring features, which are features 1051b, 1051c, 1051e, and 1051f in the example of Fig. 10H. Thus, this technique involves determining center-to-center distances between the center of the cluster 1011 (i.e., coordinate (x1,y1)) and centers of neighboring features (although center-to-center distances between the cluster and neighboring pixels can also be used). Four nearest features are selected, and their intensities are averaged, to determine the weighted feature value to be assigned to the cluster 1011. Thus, the interpolation is alsobasedonsubpixel or sub-feature locationof the cluster.Note that n=4 ismerely anexample, andncanbeanyotherappropriate value, aswouldbe readily appreciatedby thoseskilled in theart basedon the teachings of this disclosure. C. Bilinear Interpolation

[0197] In an embodiment, bilinear interpolation may be used to determine weighted feature value to be assigned to the cluster 1011, based on feature values of adjacent features.

[0198] Bilinear interpolation is an extension of linear interpolation for interpolating functions of two variables (e.g., x and y) on a rectilinear 2D grid. Bilinear interpolation is performed using linear interpolation first in one direction, and then again in the other direction. Although each step is linear in the sampled values and in the position, the interpolation as awhole is not linear but rather quadratic in the sample location. Bilinear interpolation is one of the basic resampling techniques in computer vision and image processing, where it is also called bilinear filtering or bilinear texture mapping.

[0199] Fig. 10J illustrate an example scheme depicting bilinear interpolation. In Fig. 10J, four features 1051b, 1051e, 1051c, and 1051fare four nearest features to a center of the cluster 1011 (see Fig. 10H for further detail), and the features values of the features 1051b, 1051e, 1051c, and 1051f are to be bilinearly interpolated to generate a weighted feature 27 EP 4 679 300 A2 5 10 15 20 25 30 35 40 45 50 55 value for the cluster 1011.

[0200] Assume that the coordinateof the center of the feature1051b is (x1,y2); thecoordinate of the center of the feature 1051e is (x1,y1); the coordinate of the center of the feature 1051c is (x2,y2); the coordinate of the center of the feature 1051f is (x2,y1); and the coordinate of the center of the cluster 1011 is (x,y), as illustrated in Fig. 10J. Note that such labellingof thecoordinates is contrary to the labellingofFig. 10H.Thecoordinatesof thecentersare labelled in thismanner in Fig. 10J for purposes of simplicity.

[0201] Assume that the features 1051b, 1051e, 1051c, and1051f are labelled asQ12,Q11,Q22, andQ21, respectively, based on the above discussed coordinates. The feature values of the features 1051b, 1051e, 1051c, and 1051f are accordingly labelled as f(Q12), f(Q11), f(Q22), and f(Q21), respectively, which are known. For example, during the convolution operation discussed with respect to Fig. 10E, the feature values f(Q12), f(Q11), f(Q22), and f(Q21) are determined.

[0202] Bilinear interpolationaims to interpolate the feature values f(Q12), f(Q11), f(Q22), and f(Q21) to the cluster center at (x,y), to assign a weighted feature value to the cluster 1011.

[0203] Initially, linear interpolation in the x-direction is performed for coordinates (x,y1) and (x,y2), as follows:

[0204] Then, linear interpolation in the y-direction is performed for coordinate (x,y), as follows:

[0205] Thus, f(x,y) provides the weighted feature at coordinate (x,y) using bilear interpolation, which is the center of the cluster 1011. Thus, f(x,y) is the weighted feature assigned to the cluster 1011. D. Bicubic Interpolation

[0206] In mathematics, bicubic interpolation is an extension of cubic interpolation for interpolating data points on a two- dimensional regular grid. The interpolated surface is smoother than corresponding surfaces obtained by bilinear interpolation or nearest-neighbor interpolation. Bicubic interpolation can be accomplished using either Lagrange poly- nomials, cubic splines, or cubic convolution algorithm. In an example, bicubic interpolation is sometimes chosen over bilinear or nearest-neighbor interpolation in image resampling, when processing speed is not an issue.

[0207] In contrast to the above discussed bilinear interpolation that takes four neighboring features into account when determining theweighted feature value for the cluster 1011, bicubic interpolation considers 16 feature values (such as in a grid of 4×4 features surrounding the center of the cluster 1011). For example, center-to-center distance between the cluster center and feature centers (or pixel centers, as discussed herein previously) are considered, to select a 4×4 grid of features that arenearest to thecluster center. Then, the feature valuesof the4×4gridof featuresareused todetermine the weighted feature value of the cluster 1011, e.g., in accordance with bicubic interpolation. E. Interpolation Based on Weighted Area Coverage

[0208] Another interpolation technique assigns weighted feature values to the cluster 1011, based on an area of coveragearound thecentral cluster, as illustrated inFig.10K.Forexample, as illustrated inFig. 10K,anareaof coverageA is drawnaround the cluster 1011, such that a center of the cluster 1011 and a center of the area of coverageA coincides. In an example, the area of coverage A has a square shape. In an example, the area of coverage A has a size that is equal to, merely as anexample, a sizeof a feature. Assume, for example, that the areaof coverageAcoversWb%of feature 1051b, 28 EP 4 679 300 A2 5 10 15 20 25 30 35 40 45 50 55 Wc%of feature 1051c,Wf%of feature 1051f, andWe%of feature 1051e. Then, theweighted feature value assigned to the cluster 1011 would be:

[0209] Note that Fig. 10K assumes that the area of coverage A has a size that is equal to a size of a feature. In another example, theareaofcoverageAmayhaveasize that isequal to, for example, twiceor thriceasizeofa feature, ormayeven be a non-integer multiple of a feature (e.g., 1.5 times a size of a feature, for example). In such an example, the weighted feature valueof cluster 1011 canbebasedon feature valuesofmore than four features, aswould be readily appreciatedby those skilled in the art based on the teachings of this disclosure. F. Other Example Interpolation Techniques

[0210] Some examples of interpolation techniques are discussed herein above. In an embodiment, any other appro- priate interpolation techniquemay also be used. For example, Lanczos resampling or Lanczos interpolationmay be used for interpolation, to determine theweighted feature value to be assigned to the cluster 1011. Lanczos filtering and Lanczos resampling are twoapplications of amathematical formula,which canbeused to smoothly interpolate the value of a digital signal between its samples. For example, the technique maps each sample of the given signal to a translated and scaled copy of a Lanczos kernel, which is a sinc functionwindowed by the central lobe of a second, longer, sinc function. The sum of these translated and scaled kernels is then evaluated at the desired points. The filter is named after its inventor, Cornelius Lanczos.

[0211] Another example type of interpolation technique uses Hanning window, which can be used for interpolation to determine the weighted feature value to be assigned to the cluster 1011. In signal processing and statistics, a window function is a mathematical function that is zero-valued outside of some chosen interval, normally symmetric around the middle of the interval, usually near amaximum in themiddle, and usually tapering away from themiddle. Hanningwindow, also known as raised cosine because of zero-phase version, is an example of a window function. Unlike the Hamming window, the end points of the Hanning window just touch zero. In an embodiment, another appropriate window function may also be used for interpolation. Base Calling

[0212] Subsequent to the interpolation discussed herein above, theweighted feature value(s) of a cluster is fed as input to the base caller 704, to produce a base call for that cluster. The base caller 704 can be a non-neural network-based base caller or a neural network-based base caller, examples of both are described in applications incorporated herein by reference such as U.S. Patent Application No. 62 / 821,766 and U.S. Patent Application No. 16 / 826,168.

[0213] As discussed, the assignment of the weighted feature value to a clustermaximizes or increases a signal to noise ratio, and reduces spatial cross talk betweenadjacent clusters. For example, due to the convolution (seeFig. 10E) and the interpolation, spatial cross talk between adjacent clusters is reduced or eliminated. For example, the coefficients of the sharpeningmasks820are tuned inamanner thatmaximizesor increase thesignal-to-noise ratio. Thesignalmaximizedor increased in the signal-to-noise ratio is the intensity emissions froma target cluster, and the noiseminimized or reduced in the signal-to-noise ratio is the intensity emissions from the adjacent cluster, i.e., spatial crosstalk, plus some randomnoise (e.g., to account for background intensity emissions).

[0214] Onceaweighted feature value is assigned toacluster, a basecall ismadeby thebase caller for the cluster, based on the weighted feature value assigned to the cluster. Thus, for a sequencing run comprising a plurality of sequencing cycles, sequencing images 702 are generated for each sequencing cycle. The sequencing images 702, for a given sequencing cycle, includes images for a plurality of clusters and for one or more color channels.

[0215] For example, as discussed, for a specific sequencing cycle, a first weighted feature value can be assigned to a specific cluster for a first color channel, and a second weighted feature value can be assigned to the specific cluster for a second color channel (e.g., assuming that there are two color channels, although there may be one, three, or any other higher number of color channels). In such an example, the base call for the specific cluster and for the specific sequencing cycle can be based on the first weighted feature and the second weighted feature. Further details of base calling are described in applications incorporated herein by reference such as U.S. Patent Application No. 62 / 821,766 and U.S. Patent Application No. 16 / 826,168. 29 EP 4 679 300 A2 5 10 15 20 25 30 35 40 45 50 55 Base Calling Method Using Convolution and Interpolation, and Performance Results

[0216] Fig. 11A illustrates a method 1100 of base calling, based on convolution of at least a section of a sequencing imageandsubsequent interpolation toassignoneormoreweighted feature values toacluster, andbasecalling the cluster based on the assigned one or more weighted feature values.

[0217] At 1104 of the method 1100, for a specific sequencing cycle of a sequencing run, sequencing images (e.g., sequencing images 702 of Fig. 7) output by the flow cell (e.g., flow cell discussed with respect to Fig. 1) during the corresponding sequencing cycle is accessed by a base caller, such as the base caller 704 of Fig. 7.

[0218] At 1108, the sequencing image is sectioned in a plurality of sections, based on color channels and / or spatial portions of the flow cell, where each section of the sequencing image includes, for a corresponding color channel, a plurality of clusters.

[0219] Forexample, inFig. 8A,each tile of theflowcell is divided in3×3spatial portions, and thus, thesequencing image generated from a tile for a specific color channel is sectioned in a corresponding 3×3 section. Furthermore, in Fig. 8A, without limiting the scope of this disclosure andmerely as an example, two color channels are assumed. Accordingly, for a specific tile, the sequencing image is sectioned in first 3×3 section for a first color channel and second 3×3 section for a second color channel.

[0220] Similarly, in the example of Fig. 8B, each tile of the flow cell is divided in 1×9 portions, and thus, the sequencing image generated from a tile for a specific color channel is sectioned in a corresponding first 1×9 section for a first color channel and second 1×9 section for a second color channel (i.e., assuming two color channels).

[0221] Other example sectioning of the sequencing images can also be envisioned by those skilled in the art based on the teachings of this disclosure, e.g., for different example portioning of a tile and a different number of color channels.

[0222] The method 1100 then proceeds to 1112, where each section of the sequencing image is convolved with a corresponding sharpening mask, to generate a corresponding feature map for a corresponding the section, such that a plurality of feature maps is generated for the plurality of sections. For example, as discussed with respect to Figs. 8A and 8B,each sectionof the sequencing imagehasacorresponding sharpeningmask.As illustrated inFig. 10F, each sectionof the sequencing image is convolved with the corresponding sharpening mask, to generate a corresponding feature map. Fig. 10E illustrates a convolution operation for a specific section of the sequencing image.

[0223] Note that each section of the sequencing imagehasacorrespondingplurality of clusters. For example, assumea first section and a second section of the sequencing image are generated for a first color channel and a second color channel, respectively, and are generated from a same first sub-tile portion of a tile - accordingly, both the first section and the second sectionwill have the samefirst plurality of clusters. In another example, assume that a third sectionanda fourth section of the sequencing image are generated for the first color channel and the second color channel, respectively, and are generated from a same second sub-tile portion of a tile. Accordingly, both the third section and the fourth section will have the same second plurality of clusters that are different from the first plurality of clusters.

[0224] The method 1100 then proceeds to 1116, where for each cluster within each features map, a weighted feature value is assigned to the cluster, based on an appropriate interpolation technique, such that each cluster has one or more corresponding weighted feature values for one or more color channels. For example, assuming a two color channel example, each cluster is assigned two weighted feature values corresponding to the two color channels. Some example interpolation techniques are discussed herein previously, although any other interpolation techniques not discussed herein may also be used.

[0225] The method 1100 then proceeds to 1120, where the base caller calls the base of each cluster, based on the corresponding one or more weighted feature values for the corresponding cluster. For example, the weighted feature valuesof a cluster are fedas input to thebasecaller 704, toproduceabasecall for that cluster. Thebasecaller 704canbea non-neural network-based base caller or a neural network-based base caller, examples of both are described in applications incorporatedhereinby referencesuchasU.S.PatentApplicationNo. 62 / 821,766andU.S.PatentApplication No. 16 / 826,168.

[0226] The method 1100 then proceeds to 1124, where the method 1100 proceeds to a next sequencing cycle of the sequencing run, and the method 1100 loops back to 1104. This iteration of the method 1100 continues, until all the sequencing cycles of the sequencing run is complete.

[0227] Fig. 11B illustrates comparison of performance results of the disclosed intensity extraction techniques using sharpeningmasks, with various other intensity extraction techniques associatedwith base calling. TheXaxis of the plot of Fig. 11B represents the sequencing cycles, and the Yaxis of the plot represents error rates for base calling. For example, the red line in theplot is for basecallingwithout useof sharpeningmask for intensity extraction; and thegreen line in theplot is for base calling with sharpening mask using equalizer techniques, as disclosed in co-pending U.S. Patent Application No. 17 / 308,035, entitled "Equalization-Based Image Processing and Spatial Crosstalk Attenuator," which is incorporated by reference for all purposes as if fully set forth herein. The blue line in the plot is for base calling with sharpening mask using techniques discussed herein with respect to Figs. 7‑11A. As seen, the blue line in the plot (for base calling with sharpeningmaskusing techniquesdiscussed)hassubstantially lowererror rate than the red line in theplot (for basecalling 30 EP 4 679 300 A2 5 10 15 20 25 30 35 40 45 50 55 without use of sharpening mask for intensity extraction).

[0228] Fig. 11B also depicts a table illustrating average error rates for base calling and average pass filter percentage. The pass filter percentage represents a fraction of clusters that have good quality base calls (e.g., base calls having confidence levels above a threshold percentage), and are base called. So, a higher pass filter percentage improves throughput. As seen, base calling with sharpening mask using techniques discussed herein (represented in the third column of the table) has a lower error rate and a better pass filter percentage than the scenario using no sharpeningmask (represented in the first columnof the table). Furthermore, base callingwith sharpeningmask using techniques discussed herein (represented in the third column of the table) has slightly lower error rate and slightly higher pass filter percentage, relative to the scenario that uses sharpening mask using equalizer techniques, as disclosed in co-pending U.S. Patent Application No. 17 / 308,035, entitled "Equalization-Based Image Processing and Spatial Crosstalk Attenuator," also referred to herein as "scenario that uses sharpening mask using equalizer techniques". Note that the base calling with sharpening mask using techniques discussed herein uses lower number of sharpening mask and has faster execution time, compared to the scenario that uses sharpening mask using equalizer techniques, as will be discussed herein with respect to Fig. 11C.

[0229] Fig. 11C illustrates another comparison of performance result of the disclosed techniques using sharpening masks,with variousother techniquesof basecalling.Specifically, thespeedof basecalling (or basecallingexecution time) for various scenarios is compared in Fig. 11C.

[0230] Two plots are illustrated, plot 1100c 1 and 1100c2. The plot 1100c 1 is generated using sequencing data from a new sequencing platform under development, and the plot 1100c2 is generated using sequencing data from Illumina NextSeq1000 / NextSeq2000 sequencers. Furthermore, for plot 1100c 1, the number of wells or cluster per pixel is 0.3 and the kernel (or sharpening mask) size used in 7×7. For plot 1100c2, the number of wells or cluster per pixel is 0.1 and the kernel (or sharpening mask) size used in 9×9. Thus, the plot 1100c1 has a higher cluster density compared to the plot 1100c2.

[0231] Asseen in theplot 1100c2, basecallingwith sharpeningmaskusing techniquesdiscussedherein (represented in green) is 12.5% faster than a scenario that uses sharpening mask using equalizer techniques. The improvement in performance is evenmore prominent in the plot 1100c1 that has a higher cluster density. For example, in the plot 1100c 1, base calling with sharpening mask using techniques discussed herein (represented in green) is 49.8% faster than a scenario that uses sharpening mask using equalizer techniques. Regular Cache Access

[0232] The scenario that uses sharpening mask using equalizer techniques (as disclosed in co-pending U.S. Patent Application No. 17 / 308,035, entitled "Equalization-Based Image Processing and Spatial Crosstalk Attenuator") uses different sharpeningmask fordifferent clusters, e.g., dependingonasub-pixel locationof thecluster relative toacenterof a pixel. Thus, for example, threeadjacent clustersona tile of theflowcell canarguablyuse threedifferent sharpeningmasks.

[0233] In contrast, for the intensity extraction techniques disclosed in this disclosure (e.g., with respect to Figs. 7‑11A), clustersonanentire sub-tile regionofa tile use thesamesharpeningmask.Forexample, referring toFig. 8A,all clusters on the sub-tile 812a uses the same sharpening mask 820Aa for the color channel 802A. Thus, in an example, when processing clusters on the sub-tile 812a for the color channel 802A, the corresponding sharpeningmask 820Aa is loaded in the cache, and the same sharpening mask 820Aa is repeatedly accessed from the cache during the convolution operation1030AaofFig. 10F. Inanotherexample, once thesharpeningmask820Aa is loaded inaprocessingunit from the cache, the same sharpening mask 820Aa is used for entirety of the convolution operation 1030Aa. This improves cache access pattern, which is relatively more regular (i.e., regular cache access pattern) and results in less or no cache miss.

[0234] In contrast, asdiscussed, for the scenario that uses sharpeningmaskusingequalizer techniques (asdisclosed in co-pending U.S. Patent Application No. 17 / 308,035, entitled "Equalization-Based Image Processing and Spatial Cross- talk Attenuator"), different adjacent clusters on a tile of the flow cell can use corresponding different sharpening masks, which results in relatively irregular cache access pattern and higher number of cache miss. Accordingly, the intensity extraction techniques disclosed in this disclosure (e.g., with respect to Figs. 7‑11A) is relatively faster than the equalizer- based intensity extraction technique disclosed in co-pending U.S. Patent Application No. 17 / 308,035, as also reflected in Fig. 11C. On-line Adaptation of the Coefficients of the Sharpening Masks

[0235] Note that eachsharpeningmaskused for theconvolutionof a correspondingsectionof thesequencing image isa k×k matrix, where k is an appropriate positive integer, such as three, five, seven, nine, or higher. Assuming there are "m" number of color channels (where m is a positive integer, such as one, two, or higher), for each sub-tile of a tile, there are m×k×k coefficients. Assuming that a tile is subdivided in "n" number of portions (e.g., see Figs. 8A and 8B), there are n×m×k×k number of coefficients that are to be updated during a training process. Because of the relatively low values of 31 EP 4 679 300 A2 5 10 15 20 25 30 35 40 45 50 55 n, m, and k, the number of coefficients to be updated is not significantly high. Merely as an example, if two color channels are assumed, a sharpening mask is assumed to have a dimension of 3×3, and each tile is divided in 3×3 or 9 sub-tiles, then total number of coefficients of all the sharpening masks is 2×9×3×3 = 162.

[0236] In addition to theoffline trainingdiscussedhereinpreviously, in anembodiment, thecoefficientsof thesharpening masks are also updated adaptively during the sequencing run. For example, in the above discussed example, there are merely 162 number of coefficients of all the sharpeningmasks, and it is relatively easy to adapt the 162 coefficients online, e.g., when the sequencing run is in progress (although note that the number 162 is merely an example). In contrast, the sharpeningmaskusing equalizer techniques (as disclosed in co-pendingU.S. Patent ApplicationNo. 17 / 308,035, entitled "Equalization-Based ImageProcessingandSpatialCrosstalkAttenuator")mayhaveahighernumberof parametersof the sharpening masks (such as 4050 in an example).

[0237] Fig. 12 illustrates amethod1200of base calling, basedonconvolution of at least a section of a sequencing image andsubsequent interpolation toassignoneormoreweighted feature values toacluster, andbasecalling thecluster based on the assigned one ormoreweighted feature values, where coefficients of the sharpeningmasks are adaptively updated during the sequencing run.

[0238] In an example, the online adaptation of the coefficients of the sharpeningmasks enables the coefficients to track changes in operating parameters of the sequencing run, such as changes in temperature, focus (e.g., optical distortion), chemistry, machine-specific variation, etc., while the sequencing machine is running and the sequencing run is cyclically progressing. For example, temperature (e.g., optical distortion), focus, chemistry, and / or machine-specific variation may at least partly invalidate the offline training of the sharpening mask coefficients. The online adaptation of the coefficients, e.g., when the sequencing run is cyclically progressing, can bring the coefficients back on track, to adapt to any change on any parameter(s) affecting the sequencing run.

[0239] The method 1200 and the method 1100 share various common operations, which are labelled using the same labels in the two figures. For example, blocks 1104, 1108, 1112, 1116, 1120, and 1124 in both figures are the same and labelled the same, and operations for these blocks are not discussed again with respect to Fig. 12.

[0240] After completeoperationsdiscussedwith respect toblocks1104 to1120 (whicharediscussedwith respect toFig. 11A), the method 1200 of Fig. 12 proceeds to 1204, where it is determined whether coefficients of the sharpening masks are to be updated / trained using data of the current sequencing cycle. For example, the coefficients of the sharpening masksmay not be updated at every sequencing cycle of the sequencing run. Rather, in an example, the coefficients of the sharpening masks may be updated during one or more selected sequencing cycles (but not necessarily all) of the sequencing run (although in another example, the coefficients may be updated during each sequencing cycle).

[0241] For example, the sequencing cycle(s) during which the coefficients are to be updated may be implementation specific, and may be a user configurable parameter. For example, as will be seen herein later in Fig. 14, results are presented for a scenario in which the sharpening mask coefficients are updated during sequencing cycles 10 and 30.

[0242] If "No" at 1204 (i.e., the coefficients are not to be updated during the current sequencing run), the method 1200 proceeds to 1124 and then loops back to 1104, as discussed with respect to the method 1100 of Fig. 11A.

[0243] If "Yes" at 1204 (i.e., the coefficients are to be updated during the current sequencing run), the method 1200 proceeds to 1208, where coefficients of the sharpening masks are updated or adapted using data from a current sequencing cycle C. In an example, the updated coefficients of the sharpening masks are applied for intensity extraction during sequencing cycles (C+2) and subsequent sequencing cycles. The adaptation or updating process is discussed hereinpreviously in further detail,with respect toequation1andFigs. 9Aand9B.Then, themethodproceeds toblock1124, and then loops back to block 1104.

[0244] In anexampleandalthoughnot illustrated inFig. 12, theupdatingor adaptingof the coefficients of the sharpening masks using data from sequencing cycle C occurs at least in part on next iteration of at least some of the operations of blocks 1104 to 1102. That is, while the base caller is processing data from sequencing cycle (C+1), the base caller in parallelmay also perform the updating of the coefficients using data fromsequencing cycleC. Accordingly, in an example, the updated coefficientsmaynot be applied to the imagesof the sequencing cycle (C+1) andmaybeapplied to the images of the sequencing cycle (C+2).

[0245] Note that to base call a current sequencing cycle C, intensity of sequencing cycle (C+1) has to be extracted first. For example, intensity of sequencing cycle (C+1) is used to correct pre-phasing / phasing of sequencing cycle C. Further detail about phasing and pre-phasing are discussed in co-pending U.S. Provisional Patent application No. 63 / 228,954, entitled "BaseCallingUsingMultiple BaseCallerModels," which is incorporated by reference for all purposes as if fully set forth herein.

[0246] Fig. 13 illustrates adaptation of coefficients of sharpening masks used for intensity extraction. For example, at 1304, the base caller receives sequencing images from the flow cell for sequencing cycle (C+1) and extracts the intensity using the techniques disclosed herein (e.g., using convolution, followed by interpolation). Note that it is assumed that intensity extraction for earlier cycles, such as sequencing cycle C, has already been completedwhen the operations 1304 are executed for the sequencing cycle (C+ 1).

[0247] At 1308, the base caller corrects phasing error of cycle (C+1). At 1312, the base caller corrects pre-phasing error 32 EP 4 679 300 A2 5 10 15 20 25 30 35 40 45 50 55 of sequencing cycle C, e.g., using extracted (and phasing-corrected) intensity of sequencing cycle (C+1). At 1316, the base caller calls the bases of various clusters for the sequencing cycle C. At 1320, the base caller adapts or updates coefficients of sharpeningmasks, using data from sequencing cycle C. Finally, the updated coefficients of the sharpening masks are used for sequencing cycle (C+2) onwards. The actual adaptation or updating process is discussed herein previously, with respect to equation1 and Figs. 9A and 9B.

[0248] Fig. 14 illustrates comparison of performance results of the disclosed intensity extraction techniques using sharpeningmasks and adaptation, with another intensity extraction techniques that does not use adaptation. A plot and a Table in Fig. 14 were generated based on sequencing data from the NextSeq 1000 / NextSeq 2000 sequencer. The X axis of the plot of Fig. 14 represents the sequencing cycles, and theYaxis of the plot represents error rates for base calling. For example, the red dotted line in the plot is for base calling without use of adaptation for the sharpening mask for intensity extraction; and the blue line in the plot is for base calling with adaptation of the sharpening mask as disclosed in this disclosure (see Fig. 12). The Table in Fig. 14 compares the error rate and the pass filter percentage for the two scenarios. As seen in the Table, the average error rate improves by about 9.4%, when adaptation is used for the sharpeningmask. In the example of Fig. 14, adaptation is performed on sequencing cycles 10 and 30 of non-index reads. The discontinuity in the graphat and after sequencing cycle 150 is due to index reads occurring during those sequencing cycles. Further detail about index reads may be found in U.S. Provisional Patent Application No. 62 / 979,384, entitled, "Artificial Intelligence- Based Base Calling of Index Sequences," filed February 20, 2020, which is incorporated herein by reference.

[0249] Fig. 15 illustrates comparison of performance results of the disclosed intensity extraction techniques using sharpeningmasks and adaptation, with another intensity extraction techniques that does not use adaptation. The plot and the Table in Fig. 15 were generated based on sequencing data from a new sequencing platform under development by Illumina, Inc. (SanDiego,Calif.). TheXaxis of theplot of Fig. 15 represents the sequencingcycles, and theYaxis of theplot represents error rates for base calling. For example, the red line in the plot is for base calling with use of adaptation for the sharpeningmask for intensity extraction, as disclosed in this disclosure (e.g., see Fig. 12); and the blue line in the plot is for base calling without adaptation of the sharpening mask. The Table in Fig. 15 compares the error rate and the pass filter percentage for the two intensity extraction techniques.Asseen in theTable, theaverageerror rate improvesbyabout 23%, whenadaptation is used for the sharpeningmask, alongwith some improvements in thepass filter percentageaswell. The discontinuity in the graph at and after sequencing cycle 150 is due to index reads occurring during those sequencing cycles. Further detail about index reads may be found in U.S. Provisional Patent Application No. 62 / 979,384, entitled, "Artificial Intelligence-Based Base Calling of Index Sequences," filed February 20, 2020, which is incorporated herein by reference.

[0250] In this application, the terms "cluster", "well", "sample", and "fluorescent sample" are interchangeably used because a well contains a corresponding cluster / sample / fluorescent sample. As defined herein, "sample" and its derivatives, is used in its broadest sense and includes any specimen, culture and the like that is suspected of including a target. In some implementations, the sample comprisesDNA,RNA,PNA, LNA, chimeric or hybrid formsof nucleic acids. The sample can include any biological, clinical, surgical, agricultural, atmospheric or aquatic-based specimen containing one or more nucleic acids. The term also includes any isolated nucleic acid sample such a genomic DNA, fresh-frozen or formalin-fixed paraffin-embedded nucleic acid specimen. It is also envisioned that the sample can be from a single individual, a collection of nucleic acid samples from genetically related members, nucleic acid samples from genetically unrelated members, nucleic acid samples (matched) from a single individual such as a tumor sample and normal tissue sample, or sample froma single source that contains twodistinct formsof geneticmaterial such asmaternal and fetal DNA obtained fromamaternal subject, or thepresenceof contaminatingbacterial DNA ina sample that contains plant or animal DNA. In some implementations, the source of nucleic acidmaterial can include nucleic acids obtained fromanewborn, for example as typically used for newborn screening.

[0251] The nucleic acid sample can include highmolecular weight material such as genomic DNA (gDNA). The sample can include lowmolecular weightmaterial such as nucleic acidmolecules obtained fromFFPE or archived DNA samples. In another implementation, low molecular weight material includes enzymatically or mechanically fragmented DNA. The sample can include cell-free circulating DNA. In some implementations, the sample can include nucleic acid molecules obtained from biopsies, tumors, scrapings, swabs, blood, mucus, urine, plasma, semen, hair, laser capture micro- dissections, surgical resections, and other clinical or laboratory obtained samples. In some implementations, the sample can be an epidemiological, agricultural, forensic or pathogenic sample. In some implementations, the sample can include nucleic acid molecules obtained from an animal such as a human or mammalian source. In another implementation, the sample can include nucleic acid molecules obtained from a non-mammalian source such as a plant, bacteria, virus or fungus. In some implementations, the source of the nucleic acid molecules may be an archived or extinct sample or species.

[0252] Further, the methods and compositions disclosed herein may be useful to amplify a nucleic acid sample having low-quality nucleic acid molecules, such as degraded and / or fragmented genomic DNA from a forensic sample. In one implementation, forensic samples can include nucleic acids obtained from a crime scene, nucleic acids obtained from a missing persons DNA database, nucleic acids obtained from a laboratory associated with a forensic investigation or 33 EP 4 679 300 A2 5 10 15 20 25 30 35 40 45 50 55 include forensic samplesobtainedby lawenforcement agencies, oneormoremilitary servicesor any suchpersonnel. The nucleic acid samplemay be a purified sample or a crude DNA containing lysate, for example derived from a buccal swab, paper, fabric or other substrate that may be impregnated with saliva, blood, or other bodily fluids. As such, in some implementations, the nucleic acid samplemay comprise lowamounts of, or fragmented portions ofDNA, suchas genomic DNA. In some implementations, target sequences can be present in one or more bodily fluids including but not limited to, blood, sputum, plasma, semen, urine and serum. In some implementations, target sequences can be obtained from hair, skin, tissue samples, autopsy or remains of a victim. In some implementations, nucleic acids including one or more target sequences can be obtained from a deceased animal or human. In some implementations, target sequences can include nucleic acids obtained from non-human DNA such a microbial, plant or entomological DNA. In some implementations, target sequences or amplified target sequences are directed to purposes of human identification. In some implementa- tions, the disclosure relates generally tomethods for identifying characteristics of a forensic sample. In some implementa- tions, the disclosure relates generally to human identificationmethods using one ormore target specific primers disclosed herein or one or more target specific primers designed using the primer design criteria outlined herein. In one implementation, a forensic or human identification sample containing at least one target sequence can be amplified using any one or more of the target-specific primers disclosed herein or using the primer criteria outlined herein.

[0253] As used herein, the term "adjacent" when used with respect to two reaction sites means no other reaction site is located between the two reaction sites. The term "adjacent" may have a similar meaning when used with respect to adjacent detection paths and adjacent light detectors (e.g., adjacent light detectors have no other light detector there- between). In some cases, a reaction sitemay not be adjacent to another reaction site, but may still bewithin an immediate vicinity of the other reaction site. A first reaction site may be in the immediate vicinity of a second reaction site when fluorescent emission signals from the first reaction site are detected by the light detector associated with the second reaction site. More specifically, a first reaction sitemay be in the immediate vicinity of a second reaction site when the light detector associated with the second reaction site detects, for example crosstalk from the first reaction site. Adjacent reaction sites can be contiguous such that they abut each other or the adjacent sites can be non-contiguous having an intervening space between. Upsampled Implementations

[0254] In one implementation, an image can be upsampled, for example, by using one ormore interpolation techniques or transpose convolution techniques, to generate an upsampled image. In some implementations, the image can have a pixel resolution, and the upsampled image can have a subpixel resolution. In one implementation, a convolution kernel / sharpening mask / mask can be upsampled, for example, by using the one or more interpolation techniques or the transpose convolution techniques, to generate an upsampled convolution kernel / sharpening mask / mask. In some implementations, the convolution kernel / sharpening mask / mask can have a pixel resolution, and the upsampled con- volution kernel / sharpeningmask / mask can have a subpixel resolution. Then, the upsampled convolution kernel / sharpen- ing mask / mask is applied to the upsampled image to generate upsampled features. In some implementations, features canhave a pixel resolution, and the upsampled features canhave a subpixel resolution. The upsampled features can then be analyzed on a pixel-by-pixel correspondence to base call target clusters. In other implementations, the upsampled features can then be analyzed on a cluster-by-cluster correspondence to base call target clusters. Technical Improvements and Terminology

[0255] All literatureandsimilarmaterial cited in this application, including, but not limited to, patents, patent applications, articles, books, treatises, and web pages, regardless of the format of such literature and similar materials, are expressly incorporated by reference in their entirety. In the event that one ormore of the incorporated literature and similarmaterials differs fromor contradicts this application, including but not limited to defined terms, term usage, described techniques, or the like, this application controls. Additional information about the terminology can be found inU.S. Nonprovisional Patent Application No. 16 / 826,168, entitled "Artificial Intelligence-Based Sequencing," filed 21March 2020 and U.S. Provisional Patent Application No. 62 / 821,766, entitled "Artificial Intelligence-Based Sequencing," filed 21 March 2019.

[0256] The technology disclosed uses neural networks to improve the quality and quantity of nucleic acid sequence information that can be obtained from a nucleic acid sample such as a nucleic acid template or its complement, for instance, a DNA or RNA polynucleotide or other nucleic acid sample. Accordingly, certain implementations of the technology disclosed provide higher throughput polynucleotide sequencing, for instance, higher rates of collection of DNAorRNAsequencedata, greater efficiency in sequencedata collection, and / or lower costsof obtainingsuch sequence data, relative to previously available methodologies.

[0257] The technology disclosed uses neural networks to identify the center of a solid-phase nucleic acid cluster and to analyze optical signals that are generated during sequencing of such clusters, to discriminate unambiguously between adjacent, abutting or overlapping clusters in order to assign a sequencing signal to a single, discrete source cluster. These 34 EP 4 679 300 A2 5 10 15 20 25 30 35 40 45 50 55 and related implementations thus permit retrieval ofmeaningful information, such as sequence data, from regions of high- density cluster arrays where useful information could not previously be obtained from such regions due to confounding effects of overlapping or very closely spacedadjacent clusters, including theeffects of overlapping signals (e.g.,asused in nucleic acid sequencing) emanating therefrom.

[0258] Asdescribed in greater detail below, in certain implementations there is provided a composition that comprises a solid support having immobilized thereto one or a plurality of nucleic acid clusters as provided herein. Each cluster comprisesaplurality of immobilizednucleic acidsof the samesequenceandhasan identifiable center havingadetectable center label as provided herein, by which the identifiable center is distinguishable from immobilized nucleic acids in a surrounding region in the cluster. Also described herein are methods for making and using such clusters that have identifiable centers.

[0259] The presently disclosed implementations will find uses in numerous situations where advantages are obtained from the ability to identify, determine, annotate, record or otherwise assign the position of a substantially central location within acluster, suchashigh-throughput nucleic acid sequencing, development of imageanalysis algorithms for assigning optical or other signals todiscrete sourceclusters, andotherapplicationswhere recognitionof thecenter of an immobilized nucleic acid cluster is desirable and beneficial.

[0260] In certain implementations, the present invention contemplates methods that relate to high-throughput nucleic acid analysis such as nucleic acid sequence determination (e.g., "sequencing"). Exemplary high-throughput nucleic acid analyses include without limitation de novo sequencing, re-sequencing, whole genome sequencing, gene expression analysis, gene expressionmonitoring, epigenetic analysis, genomemethylation analysis, allele specific primer extension (APSE), genetic diversity profiling, whole genomepolymorphismdiscovery and analysis, single nucleotide polymorphism analysis, hybridization based sequence determination methods, and the like. One skilled in the art will appreciate that a variety of different nucleic acids can be analyzed using the methods and compositions of the present invention.

[0261] Although the implementations of the present invention are described in relation to nucleic acid sequencing, they areapplicable in anyfieldwhere imagedataacquiredat different timepoints, spatial locationsor other temporal or physical perspectives isanalyzed.Forexample, themethodsandsystemsdescribedhereinareuseful in the fieldsofmolecular and cell biology where image data from microarrays, biological specimens, cells, organisms and the like is acquired and at different time points or perspectives and analyzed. Images can be obtained using any number of techniques known in the art including, but not limited to, fluorescencemicroscopy, lightmicroscopy, confocalmicroscopy, optical imaging,magnetic resonance imaging, tomographyscanningor the like.Asanotherexample, themethodsandsystemsdescribedherein can be applied where image data obtained by surveillance, aerial or satellite imaging technologies and the like is acquired at different time points or perspectives and analyzed. Themethods and systems are particularly useful for analyzing images obtained for a field of view inwhich theanalytes being viewed remain in the same locations relative to eachother in the field of view. The analytes may however have characteristics that differ in separate images, for example, the analytes may appear different in separate images of the field of view. For example, the analytes may appear different with regard to the color of a given analyte detected in different images, a change in the intensity of signal detected for a given analyte in different images, or even the appearance of a signal for a given analyte in one image and disappearance of the signal for the analyte in another image.

[0262] As used herein, the term "analyte" is intended tomean a point or area in a pattern that can be distinguished from other points or areas according to relative location. An individual analyte can include one ormoremolecules of a particular type. For example, an analyte can include a single target nucleic acidmolecule having a particular sequence or an analyte can include several nucleic acid molecules having the same sequence (and / or complementary sequence, thereof). Different molecules that are at different analytes of a pattern can be differentiated from each other according to the locations of the analytes in the pattern. Example analytes include without limitation, wells in a substrate, beads (or other particles) in or on a substrate, projections from a substrate, ridges on a substrate, pads of gel material on a substrate, or channels in a substrate.

[0263] Anyof avariety of target analytes that are tobedetected, characterized, or identifiedcanbeused inanapparatus, system or method set forth herein. Exemplary analytes include, but are not limited to, nucleic acids (e.g., DNA, RNA or analogs thereof), proteins, polysaccharides, cells, antibodies, epitopes, receptors, ligands, enzymes (e.g., kinases, phosphatases or polymerases), small molecule drug candidates, cells, viruses, organisms, or the like.

[0264] The terms "analyte," "nucleic acid," "nucleic acid molecule," and "polynucleotide" are used interchangeably herein. In various implementations, nucleic acids may be used as templates as provided herein (e.g., a nucleic acid template, or anucleic acid complement that is complementary toanucleic acidnucleic acid template) for particular typesof nucleicacidanalysis, includingbutnot limited tonucleicacidamplification, nucleicacidexpressionanalysis, and / or nucleic acid sequence determination or suitable combinations thereof. Nucleic acids in certain implementations include, for instance, linear polymers of deoxyribonucleotides in 3’‑5’ phosphodiester or other linkages, such as deoxyribonucleic acids (DNA), for example, single‑ and double-stranded DNA, genomic DNA, copy DNA or complementary DNA (cDNA), recombinant DNA, or any form of synthetic or modified DNA. In other implementations, nucleic acids include for instance, linear polymers of ribonucleotides in 3’‑5’ phosphodiester or other linkages such as ribonucleic acids (RNA), for example, 35 EP 4 679 300 A2 5 10 15 20 25 30 35 40 45 50 55 single‑ and double-stranded RNA, messenger (mRNA), copy RNA or complementary RNA (cRNA), alternatively spliced mRNA, ribosomalRNA, small nucleolar RNA (snoRNA),microRNAs (miRNA), small interferingRNAs (sRNA), piwi RNAs (piRNA), or any form of synthetic or modified RNA. Nucleic acids used in the compositions and methods of the present inventionmay vary in length andmay be intact or full-lengthmolecules or fragments or smaller parts of larger nucleic acid molecules. In particular implementations, a nucleic acidmay have one ormore detectable labels, as described elsewhere herein.

[0265] The terms "analyte," "cluster," "nucleic acid cluster," "nucleic acid colony," and "DNA cluster" are used inter- changeably and refer to a plurality of copies of a nucleic acid template and / or complements thereof attached to a solid support. Typically and in certain preferred implementations, the nucleic acid cluster comprises a plurality of copies of template nucleic acid and / or complements thereof, attached via their 5’ termini to the solid support. The copies of nucleic acid strands making up the nucleic acid clusters may be in a single or double stranded form. Copies of a nucleic acid template that are present in a cluster can have nucleotides at corresponding positions that differ from each other, for example, due to presence of a label moiety. The corresponding positions can also contain analog structures having different chemical structure but similar Watson-Crick base-pairing properties, such as is the case for uracil and thymine.

[0266] Coloniesof nucleic acids canalsobe referred toas "nucleic acid clusters".Nucleic acid colonies canoptionally be created by cluster amplification or bridge amplification techniques as set forth in further detail elsewhere herein. Multiple repeats of a target sequencecanbepresent in a single nucleic acidmolecule, suchasa concatamer createdusinga rolling circle amplification procedure.

[0267] The nucleic acid clusters of the invention can have different shapes, sizes and densities depending on the conditions used. For example, clusters can have a shape that is substantially round, multi-sided, donut-shaped or ring- shaped. The diameter of a nucleic acid cluster can be designed to be from about 0.2 µm to about 6 µm, about 0.3 µm to about 4µm, about 0.4µm to about 3µm, about 0.5µm to about 2µm, about 0.75µm to about 1.5 µm, or any intervening diameter. In a particular implementation, the diameter of a nucleic acid cluster is about 0.5µm, about 1µm, about 1.5µm, about 2µm, about 2.5µm, about 3µm, about 4µm, about 5µm, or about 6µm.Thediameter of a nucleic acid clustermay be influenced by a number of parameters, including, but not limited to the number of amplification cycles performed in producing the cluster, the length of the nucleic acid template or the density of primers attached to the surface upon which clusters are formed. The density of nucleic acid clusters can be designed to typically be in the range of 0.1 / mm2, 1 / mm2, 10 / mm2, 100 / mm2, 1,000 / mm2, 10,000 / mm2 to 100,000 / mm2. The present invention further contemplates, in part, higher density nucleic acid clusters, for example, 100,000 / mm2 to 1,000,000 / mm2 and 1,000,000 / mm2 to 10,000,000 / mm2.

[0268] Asusedherein, an "analyte" is anareaof interestwithin a specimenor field of view.Whenused in connectionwith microarray devices or other molecular analytical devices, an analyte refers to the area occupied by similar or identical molecules. For example, an analyte can be an amplified oligonucleotide or any other group of a polynucleotide or polypeptide with a same or similar sequence. In other implementations, an analyte can be any element or group of elements that occupy a physical area on a specimen. For example, an analyte could be a parcel of land, a body of water or the like. When an analyte is imaged, each analyte will have some area. Thus, in many implementations, an analyte is not merely one pixel.

[0269] The distances between analytes can be described in any number of ways. In some implementations, the distances between analytes can be described from the center of one analyte to the center of another analyte. In other implementations, the distances can be described from the edge of one analyte to the edge of another analyte, or between the outer-most identifiable points of each analyte. The edge of an analyte can be described as the theoretical or actual physical boundary on a chip, or somepoint inside the boundary of the analyte. In other implementations, the distances can be described in relation to a fixed point on the specimen or in the image of the specimen.

[0270] Generally several implementations will be described herein with respect to a method of analysis. It will be understood that systems are also provided for carrying out the methods in an automated or semi-automated way. Accordingly, this disclosure provides neural network-based template generation and base calling systems, wherein the systems can include a processor; a storage device; and a program for image analysis, the program including instructions for carrying out oneormore of themethods set forth herein. Accordingly, themethods set forth herein can be carried out on a computer, for example, having components set forth herein or otherwise known in the art.

[0271] Themethods and systems set forth herein are useful for analyzing any of a variety of objects. Particularly useful objects are solid supports or solid-phase surfaces with attached analytes. The methods and systems set forth herein provide advantages when used with objects having a repeating pattern of analytes in an xy plane. An example is a microarray having an attached collection of cells, viruses, nucleic acids, proteins, antibodies, carbohydrates, small molecules (such as drug candidates), biologically active molecules or other analytes of interest.

[0272] An increasing number of applications have been developed for arrays with analytes having biological molecules such as nucleic acids and polypeptides. Such microarrays typically include deoxyribonucleic acid (DNA) or ribonucleic acid (RNA) probes. These are specific for nucleotide sequences present in humans and other organisms. In certain applications, for example, individual DNAorRNAprobes can be attached at individual analytes of an array. A test sample, such as from a known person or organism, can be exposed to the array, such that target nucleic acids (e.g., gene 36 EP 4 679 300 A2 5 10 15 20 25 30 35 40 45 50 55 fragments, mRNA, or amplicons thereof) hybridize to complementary probes at respective analytes in the array. The probescanbe labeled ina target specificprocess (e.g.,due to labelspresenton the targetnucleicacidsordue toenzymatic labeling of the probes or targets that are present in hybridized form at the analytes). The array can then be examined by scanning specific frequencies of light over the analytes to identify which target nucleic acids are present in the sample.

[0273] Biological microarrays may be used for genetic sequencing and similar applications. In general, genetic sequencing comprises determining the order of nucleotides in a length of target nucleic acid, such as a fragment of DNAorRNA.Relatively short sequences are typically sequenced at each analyte, and the resulting sequence information may be used in various bioinformaticsmethods to logically fit the sequence fragments together so as to reliably determine the sequence of much more extensive lengths of genetic material from which the fragments were derived. Automated, computer-based algorithms for characteristic fragments have been developed, and have been used more recently in genome mapping, identification of genes and their function, and so forth. Microarrays are particularly useful for characterizing genomic content because a large number of variants are present and this supplants the alternative of performing many experiments on individual probes and targets. The microarray is an ideal format for performing such investigations in a practical manner.

[0274] Any of a variety of analyte arrays (also referred to as "microarrays") known in the art can be used in a method or systemset forth herein. A typical array contains analytes, each having an individual probe or a population of probes. In the latter case, the population of probes at each analyte is typically homogenous having a single species of probe. For example, in the caseof a nucleic acid array, eachanalyte canhavemultiple nucleic acidmolecules eachhavinga common sequence. However, in some implementations the populations at each analyte of an array can be heterogeneous. Similarly, protein arrays can have analytes with a single protein or a population of proteins typically, but not always, having the sameamino acid sequence. The probes can be attached to the surface of an array for example, via covalent linkage of the probes to the surface or via non-covalent interaction(s) of the probes with the surface. In some implementations, probes, such as nucleic acid molecules, can be attached to a surface via a gel layer as described, for example, in U.S. patent applicationSer. No. 13 / 784,368 andUSPat. App. Pub. No. 2011 / 0059865A1, each of which is incorporated herein by reference.

[0275] Example arrays include, without limitation, a BeadChip Array available from Illumina, Inc. (San Diego, Calif.) or others such as those where probes are attached to beads that are present on a surface (e.g., beads in wells on a surface) such as those described in U.S. Pat. No. 6,266,459; 6,355,431; 6,770,441; 6,859,570; or 7,622,294; or PCT Publication No. WO 00 / 63437, each of which is incorporated herein by reference. Further examples of commercially available microarrays that can beused include, for example, anAffymetrix®GeneChip®microarray or othermicroarray synthesized in accordance with techniques sometimes referred to as VLSIPS™ (Very Large Scale Immobilized Polymer Synthesis) technologies. A spotted microarray can also be used in a method or system according to some implementations of the present disclosure. Anexample spottedmicroarray is aCodeLink™Array available fromAmershamBiosciences. Another microarray that is useful is one that is manufactured using inkjet printing methods such as SurePrint™ Technology available from Agilent Technologies.

[0276] Other useful arrays include those that are used in nucleic acid sequencing applications. For example, arrays having amplicons of genomic fragments (often referred to as clusters) are particularly useful such as those described in Bentley et al., Nature 456:53‑59 (2008), WO 04 / 018497; WO 91 / 06678; WO 07 / 123744; U.S. Pat. No. 7,329,492; 7,211,414; 7,315,019; 7,405,281, or 7,057,026; orUSPat. App.Pub.No. 2008 / 0108082A1, each ofwhich is incorporated herein by reference. Another type of array that is useful for nucleic acid sequencing is an array of particles produced from an emulsion PCR technique. Examples are described in Dressman et al., Proc. Natl. Acad. Sci. USA 100:8817‑8822 (2003), WO 05 / 010145, US Pat. App. Pub. No. 2005 / 0130173 or US Pat. App. Pub. No. 2005 / 0064460, each of which is incorporated herein by reference in its entirety.

[0277] Arrays used for nucleic acid sequencing often have random spatial patterns of nucleic acid analytes. For example,HiSeqorMiSeqsequencingplatformsavailable from Illumina Inc. (SanDiego,Calif.) utilize flowcells uponwhich nucleic acid arrays are formedby randomseeding followedbybridgeamplification.However, patternedarrays canalsobe used for nucleic acid sequencing or other analytical applications. Example patterned arrays, methods for their manu- facture and methods for their use are set forth in U.S. Ser. No. 13 / 787,396; U.S. Ser. No. 13 / 783,043; U.S. Ser. No. 13 / 784,368; US Pat. App. Pub. No. 2013 / 0116153 A1; and US Pat. App. Pub. No. 2012 / 0316086 A1, each of which is incorporated herein by reference. The analytes of such patterned arrays can be used to capture a single nucleic acid template molecule to seed subsequent formation of a homogenous colony, for example, via bridge amplification. Such patterned arrays are particularly useful for nucleic acid sequencing applications.

[0278] The size of an analyte on an array (or other object used in a method or system herein) can be selected to suit a particular application. For example, in some implementations, an analyte of an array can have a size that accommodates only a single nucleic acid molecule. A surface having a plurality of analytes in this size range is useful for constructing an array of molecules for detection at single molecule resolution. Analytes in this size range are also useful for use in arrays havinganalytes that each contain a colonyof nucleic acidmolecules. Thus, the analytes of anarray caneachhaveanarea that is no larger than about 1 mm2, no larger than about 500 µm2, no larger than about 100 µm2, no larger than about 10 37 EP 4 679 300 A2 5 10 15 20 25 30 35 40 45 50 55 µm2, no larger than about 1 µm2, no larger than about 500 nm2, or no larger than about 100 nm2, no larger than about 10 nm2, no larger than about 5 nm2, or no larger than about 1 nm2. Alternatively or additionally, the analytes of an arraywill be no smaller than about 1 mm2, no smaller than about 500 µm2, no smaller than about 100 µm2, no smaller than about 10 µm2, no smaller than about 1µm2, no smaller than about 500 nm2, no smaller than about 100 nm2, no smaller than about 10 nm2, no smaller than about 5 nm2, or no smaller than about 1 nm2. Indeed, an analyte can have a size that is in a range between an upper and lower limit selected from those exemplified above. Although several size ranges for analytes of a surface have been exemplified with respect to nucleic acids and on the scale of nucleic acids, it will be understood that analytes in thesesize rangescanbeused for applications that donot includenucleic acids. It will be further understood that the size of the analytes need not necessarily be confined to a scale used for nucleic acid applications.

[0279] For implementations that include an object having a plurality of analytes, such as an array of analytes, the analytes can be discrete, being separated with spaces between each other. An array useful in the invention can have analytes that are separated by edge to edge distance of at most 100 µm, 50 µm, 10 µm, 5 µm, 1 µm, 0.5 µm, or less. Alternatively or additionally, anarray canhaveanalytes that are separatedbyanedge toedgedistanceof at least 0.5µm,1 µm, 5µm, 10µm, 50 µm, 100 µm, or more. These ranges can apply to the average edge to edge spacing for analytes as well as to the minimum or maximum spacing.

[0280] In some implementations theanalytesof anarrayneednotbediscreteand insteadneighboringanalytescanabut eachother.Whether or not the analytes are discrete, the size of the analytes and / or pitch of the analytes can vary such that arrays can have a desired density. For example, the average analyte pitch in a regular pattern can be at most 100 µm, 50 µm,10µm,5µm,1µm,0.5µm,or less.Alternatively or additionally, theaverageanalytepitch ina regular pattern canbeat least 0.5µm,1µm,5µm,10µm,50µm,100µm,ormore. These ranges canapply to themaximumorminimumpitch for a regular pattern as well. For example, the maximum analyte pitch for a regular pattern can be at most 100 µm, 50 µm, 10 µm, 5µm, 1µm, 0.5µm, or less; and / or theminimumanalyte pitch in a regular pattern can be at least 0.5µm, 1µm, 5µm, 10 µm, 50 µm, 100 µm, or more.

[0281] The density of analytes in an array can also be understood in terms of the number of analytes present per unit area. For example, the average density of analytes for an array can be at least about 1x103 analytes / mm2, 1x104 analytes / mm2, 1x105 analytes / mm2, 1x106 analytes / mm2, 1x107 analytes / mm2, 1x108 analytes / mm2, or 1x109 analy- tes / mm2, or higher. Alternatively or additionally the average density of analytes for an array can be at most about 1x109 analytes / mm2, 1x108 analytes / mm2, 1x107 analytes / mm2, 1x106 analytes / mm2, 1x105 analytes / mm2, 1x104 analy- tes / mm2, or 1x103 analytes / mm2, or less.

[0282] The above ranges can apply to all or part of a regular pattern including, for example, all or part of an array of analytes.

[0283] The analytes in a pattern can have any of a variety of shapes. For example, when observed in a two dimensional plane, such as on the surface of an array, the analytes can appear rounded, circular, oval, rectangular, square, symmetric, asymmetric, triangular, polygonal, or the like. The analytes can be arranged in a regular repeating pattern including, for example, a hexagonal or rectilinear pattern. A pattern can be selected to achieve a desired level of packing. For example, roundanalytesareoptimallypacked inahexagonal arrangement.Of courseotherpackingarrangements canalsobeused for round analytes and vice versa.

[0284] A pattern can be characterized in terms of the number of analytes that are present in a subset that forms the smallest geometric unit of the pattern. The subset can include, for example, at least about 2, 3, 4, 5, 6, 10 ormore analytes. Depending upon the size and density of the analytes the geometric unit can occupy an area of less than 1mm2, 500µm2, 100 µm2, 50 µm2, 10µm2, 1 µm2, 500 nm2, 100 nm2, 50 nm2, 10 nm2, or less. Alternatively or additionally, the geometric unit can occupy an area of greater than 10 nm2, 50 nm2, 100 nm2, 500 nm2, 1µm2, 10µm2, 50µm2, 100µm2, 500µm2, 1 mm2, or more. Characteristics of the analytes in a geometric unit, such as shape, size, pitch and the like, can be selected from those set forth herein more generally with regard to analytes in an array or pattern.

[0285] An array having a regular pattern of analytes can be ordered with respect to the relative locations of the analytes but randomwith respect tooneormoreother characteristic ofeachanalyte.Forexample, in thecaseofanucleicacidarray, the nuclei acid analytes can be orderedwith respect to their relative locations but randomwith respect to one’s knowledge of the sequence for the nucleic acid species present at any particular analyte. As a more specific example, nucleic acid arrays formed by seeding a repeating pattern of analytes with template nucleic acids and amplifying the template at each analyte to form copies of the template at the analyte (e.g., via cluster amplification or bridge amplification) will have a regular pattern of nucleic acid analytes but will be randomwith regard to the distribution of sequences of the nucleic acids across the array. Thus, detection of the presence of nucleic acid material generally on the array can yield a repeating pattern of analytes, whereas sequence specific detection can yield non-repeating distribution of signals across the array.

[0286] It will be understood that the description herein of patterns, order, randomness and the like pertain not only to analytes on objects, such as analytes on arrays, but also to analytes in images. As such, patterns, order, randomness and the like can be present in any of a variety of formats that are used to store, manipulate or communicate image data including, but not limited to, a computer readable medium or computer component such as a graphical user interface or other output device. 38 EP 4 679 300 A2 5 10 15 20 25 30 35 40 45 50 55

[0287] As used herein, the term "image" is intended to mean a representation of all or part of an object. The representation can be an optically detected reproduction. For example, an image can be obtained from fluorescent, luminescent, scatter, or absorption signals. The part of the object that is present in an image can be the surface or other xy plane of the object. Typically, an image is a 2 dimensional representation, but in some cases information in the image can be derived from 3 or more dimensions. An image need not include optically detected signals. Non-optical signals can be present instead.An imagecanbeprovided ina computer readable format ormediumsuchasoneormoreof those set forth elsewhere herein.

[0288] As used herein, "image" refers to a reproduction or representation of at least a portion of a specimen or other object. In some implementations, the reproduction is an optical reproduction, for example, produced by a camera or other optical detector. The reproduction can be a non-optical reproduction, for example, a representation of electrical signals obtained fromanarray of nanopore analytes or a representation of electrical signals obtained froman ion-sensitiveCMOS detector. In particular implementations non-optical reproductions can be excluded from a method or apparatus set forth herein. An imagecanhavea resolution capable of distinguishinganalytes of a specimen that arepresent at anyof a variety of spacings including, for example, those that are separated by less than 100 µm, 50 µm, 10 µm, 5 µm, 1 µmor 0.5 µm .

[0289] Asused herein, "acquiring", "acquisition" and like terms refer to any part of the process of obtaining an image file. In some implementations, data acquisition can include generating an image of a specimen, looking for a signal in a specimen, instructing a detection device to look for or generate an image of a signal, giving instructions for further analysis or transformation of an image file, and any number of transformations or manipulations of an image file.

[0290] As used herein, the term "template" refers to a representation of the location or relation between signals or analytes. Thus, in some implementations, a template is a physical grid with a representation of signals corresponding to analytes in a specimen. In some implementations, a template can bea chart, table, text file or other computer file indicative of locations corresponding to analytes. In implementations presented herein, a template is generated in order to track the location of analytes of a specimen across a set of images of the specimen captured at different reference points. For example, a template could be a set of x,y coordinates or a set of values that describe the direction and / or distance of one analyte with respect to another analyte.

[0291] As used herein, the term "specimen" can refer to an object or area of an object of which an image is captured. For example, in implementations where images are taken of the surface of the earth, a parcel of land can be a specimen. In other implementations where the analysis of biological molecules is performed in a flow cell, the flow cell may be divided into any number of subdivisions, each of which may be a specimen. For example, a flow cell may be divided into various flow channels or lanes, and each lane can be further divided into 2, 3, 4, 5, 6, 7, 8, 9, 10, 20, 30, 40, 50, 60 70, 80, 90, 100, 110,120, 140, 160, 180, 200, 400, 600, 800, 1000ormoreseparate regions that are imaged.Oneexampleofa flowcell has 8 lanes, with each lane divided into 120 specimens or tiles. In another implementation, a specimen may be made up of a plurality of tiles or evenan entire flowcell. Thus, the image of each specimen can represent a region of a larger surface that is imaged.

[0292] It will be appreciated that references to ranges and sequential number lists described herein include not only the enumerated number but all real numbers between the enumerated numbers.

[0293] As used herein, a "reference point" refers to any temporal or physical distinction between images. In a preferred implementation, a reference point is a time point. In a more preferred implementation, a reference point is a time point or cycle during a sequencing reaction. However, the term "reference point" can include other aspects that distinguish or separate images, such as angle, rotational, temporal, or other aspects that can distinguish or separate images.

[0294] As used herein, a "subset of images" refers to a group of imageswithin a set. For example, a subsetmay contain 1, 2, 3, 4, 6, 8, 10, 12, 14, 16, 18, 20, 30, 40, 50, 60 or any number of images selected from a set of images. In particular implementations, a subset may contain nomore than 1, 2, 3, 4, 6, 8, 10, 12, 14, 16, 18, 20, 30, 40, 50, 60 or any number of images selected from a set of images. In a preferred implementation, images are obtained from one or more sequencing cycles with four images correlated to each cycle. Thus, for example, a subset could be a group of 16 images obtained through four cycles.

[0295] A base refers to a nucleotide base or nucleotide, A (adenine), C (cytosine), T (thymine), or G (guanine). This application uses "base(s)" and "nucleotide(s)" interchangeably.

[0296] The term "chromosome" refers to the heredity-bearing gene carrier of a living cell, which is derived from chromatin strands comprising DNA and protein components (especially histones). The conventional internationally recognized individual human genome chromosome numbering system is employed herein.

[0297] The term "site" refers to a unique position (e.g., chromosome ID, chromosome position and orientation) on a reference genome. In some implementations, a site may be a residue, a sequence tag, or a segment’s position on a sequence. The term "locus" may be used to refer to the specific location of a nucleic acid sequence or polymorphism on a reference chromosome.

[0298] The term "sample" herein refers to a sample, typically derived from a biological fluid, cell, tissue, organ, or organism containing a nucleic acid or amixture of nucleic acids containing at least one nucleic acid sequence that is to be sequenced and / or phased. Such samples include, but are not limited to sputum / oral fluid, amniotic fluid, blood, a blood 39 EP 4 679 300 A2 5 10 15 20 25 30 35 40 45 50 55 fraction, fine needle biopsy samples (e.g., surgical biopsy, fine needle biopsy, etc.), urine, peritoneal fluid, pleural fluid, tissue explant, organ culture and any other tissue or cell preparation, or fraction or derivative thereof or isolated therefrom. Although the sample is often taken from a human subject (e.g., patient), samples can be taken from any organism having chromosomes, including, but not limited to dogs, cats, horses, goats, sheep, cattle, pigs, etc. The sample may be used directly as obtained from the biological source or following a pretreatment to modify the character of the sample. For example, such pretreatment may include preparing plasma from blood, diluting viscous fluids and so forth. Methods of pretreatment may also involve, but are not limited to, filtration, precipitation, dilution, distillation, mixing, centrifugation, freezing, lyophilization, concentration, amplification, nucleic acid fragmentation, inactivation of interfering components, the addition of reagents, lysing, etc.

[0299] The term "sequence" includes or represents a strand of nucleotides coupled to each other. The nucleotidesmay be based onDNAor RNA. It should be understood that one sequencemay includemultiple sub-sequences. For example, a single sequence (e.g., of a PCR amplicon) may have 350 nucleotides. The sample read may include multiple sub- sequences within these 350 nucleotides. For instance, the sample read may include first and second flanking sub- sequenceshaving, for example, 20‑50nucleotides. Thefirst andsecond flanking sub-sequencesmaybe locatedoneither side of a repetitive segment having a corresponding sub-sequence (e.g., 40‑100 nucleotides). Each of the flanking sub- sequencesmay include (or include portions of) a primer sub-sequence (e.g., 10‑30 nucleotides). For ease of reading, the term "sub-sequence" will be referred to as "sequence," but it is understood that two sequences are not necessarily separate from each other on a common strand. To differentiate the various sequences described herein, the sequences may be given different labels (e.g., target sequence, primer sequence, flanking sequence, reference sequence, and the like). Other terms, such as "allele,"may be given different labels to differentiate between like objects. The application uses "read(s)" and "sequence read(s)" interchangeably.

[0300] The term "paired-end sequencing" refers to sequencing methods that sequence both ends of a target fragment. Paired-end sequencing may facilitate detection of genomic rearrangements and repetitive segments, as well as gene fusions and novel transcripts. Methodology for paired-end sequencing are described in PCT publication WO07010252, PCTapplicationSerialNo.PCTGB2007 / 003798andUSpatent applicationpublicationUS2009 / 0088327, eachofwhich is incorporated by reference herein. In one example, a series of operations may be performed as follows; (a) generate clusters of nucleic acids; (b) linearize the nucleic acids; (c) hybridize a first sequencing primer and carry out repeated cyclesofextension, scanninganddeblocking, asset forthabove; (d) "invert" the target nucleicacidson theflowcell surface by synthesizing a complimentary copy; (e) linearize the resynthesized strand; and (f) hybridize a second sequencing primer and carry out repeated cycles of extension, scanning and deblocking, as set forth above. The inversion operation can be carried out be delivering reagents as set forth above for a single cycle of bridge amplification.

[0301] The term "reference genome" or "reference sequence" refers to any particular known genome sequence, whether partial or complete, of any organism which may be used to reference identified sequences from a subject. For example, a referencegenomeused for humansubjectsaswell asmanyother organisms is foundat theNationalCenter for Biotechnology Information at ncbi.nlm.nih.gov. A "genome" refers to the complete genetic information of an organism or virus, expressed in nucleic acid sequences. A genome includes both the genes and the noncoding sequences of theDNA. The reference sequencemaybe larger than the reads that are aligned to it. For example, itmay be at least about 100 times larger, or at least about 1000 times larger, or at least about 10,000 times larger, or at least about 105 times larger, or at least about 106 times larger, or at least about 107 times larger. In one example, the reference genome sequence is that of a full length human genome. In another example, the reference genome sequence is limited to a specific human chromosome such as chromosome 13. In some implementations, a reference chromosome is a chromosome sequence from human genome version hg19. Such sequences may be referred to as chromosome reference sequences, although the term reference genome is intended to cover such sequences. Other examples of reference sequences include genomes of other species, as well as chromosomes, sub-chromosomal regions (such as strands), etc., of any species. In various implementations, the reference genome is a consensus sequence or other combination derived frommultiple individuals. However, in certain applications, the reference sequence may be taken from a particular individual. In other implementa- tions, the "genome" also covers so-called "graph genomes", which use a particular storage format and representation of the genome sequence. In one implementation, graph genomes store data in a linear file. In another implementation, the graph genomes refer to a representation where alternative sequences (e.g., different copies of a chromosome with small differences) are stored as different paths in a graph. Additional information regarding graph genome implementations can be found in https: / / www.biorxiv.org / content / biorxiv / early / 2018 / 03 / 20 / 194530.full.pdf, the content of which is hereby incorporated herein by reference in its entirety.

[0302] The term "read" refer to a collection of sequence data that describes a fragment of a nucleotide sample or reference. The term "read" may refer to a sample read and / or a reference read. Typically, though not necessarily, a read represents a short sequence of contiguous base pairs in the sample or reference. The read may be represented symbolically by the base pair sequence (in ATCG) of the sample or reference fragment. It may be stored in a memory deviceandprocessedasappropriate todeterminewhether the readmatchesa referencesequenceormeetsother criteria. A read may be obtained directly from a sequencing apparatus or indirectly from stored sequence information concerning 40 EP 4 679 300 A2 5 10 15 20 25 30 35 40 45 50 55 the sample. In some cases, a read is a DNA sequence of sufficient length (e.g., at least about 25 bp) that can be used to identify a larger sequenceor region, e.g., that canbealignedandspecificallyassigned toachromosomeorgenomic region or gene.

[0303] Next-generation sequencing methods include, for example, sequencing by synthesis technology (Illumina), pyrosequencing (454), ion semiconductor technology (Ion Torrent sequencing), single-molecule real-time sequencing (PacificBiosciences) and sequencing by ligation (SOLiD sequencing). Depending on the sequencingmethods, the length of each readmay vary from about 30 bp to more than 10,000 bp. For example, the DNA sequencingmethod using SOLiD sequencer generates nucleic acid reads of about 50 bp. For another example, Ion Torrent Sequencing generates nucleic acid readsof up to400bpand454pyrosequencinggeneratesnucleicacid readsof about 700bp.For yet another example, single-molecule real-time sequencing methods may generate reads of 10,000 bp to 15,000 bp. Therefore, in certain implementations, the nucleic acid sequence reads have a length of 30‑100 bp, 50‑200 bp, or 50‑400 bp.

[0304] The terms "sample read", "sample sequence" or "sample fragment" refer to sequence data for a genomic sequenceof interest fromasample. For example, the sample readcomprises sequencedata fromaPCRampliconhaving a forward and reverse primer sequence. The sequence data can be obtained fromany select sequencemethodology. The sample read can be, for example, from a sequencing-by-synthesis (SBS) reaction, a sequencing-by-ligation reaction, or any other suitable sequencing methodology for which it is desired to determine the length and / or identity of a repetitive element.Thesample readcanbeaconsensus (e.g., averagedorweighted) sequencederived frommultiple sample reads. In certain implementations, providing a reference sequence comprises identifying a locus-of-interest based upon the primer sequence of the PCR amplicon.

[0305] The term "raw fragment" refers to sequence data for a portion of a genomic sequence of interest that at least partially overlaps a designated position or secondary position of interest within a sample read or sample fragment. Non- limiting examples of raw fragments include a duplex stitched fragment, a simplex stitched fragment, a duplex un-stitched fragment and a simplex un-stitched fragment. The term "raw" is used to indicate that the raw fragment includes sequence data having some relation to the sequence data in a sample read, regardless of whether the raw fragment exhibits a supporting variant that corresponds to and authenticates or confirms a potential variant in a sample read. The term "raw fragment" does not indicate that the fragment necessarily includes a supporting variant that validates a variant call in a sample read. For example, when a sample read is determined by a variant call application to exhibit a first variant, the variant call application may determine that one or more raw fragments lack a corresponding type of "supporting" variant that may otherwise be expected to occur given the variant in the sample read.

[0306] The terms "mapping," "aligned," "alignment," or "aligning" refer to the process of comparing a read or tag to a reference sequence and thereby determining whether the reference sequence contains the read sequence. If the reference sequence contains the read, the readmaybemapped to the reference sequenceor, in certain implementations, to a particular location in the reference sequence. In some cases, alignment simply tells whether or not a read is amember of aparticular referencesequence (i.e.,whether the read ispresent orabsent in the referencesequence). Forexample, the alignment of a read to the reference sequence for human chromosome 13 will tell whether the read is present in the reference sequence for chromosome 13. A tool that provides this information may be called a set membership tester. In some cases, an alignment additionally indicates a location in the reference sequence where the read or tag maps to. For example, if the reference sequence is the whole human genome sequence, an alignment may indicate that a read is present on chromosome 13, andmay further indicate that the read is on a particular strand and / or site of chromosome 13.

[0307] The term "indel" refers to the insertion and / or the deletion of bases in the DNA of an organism. A micro-indel represents an indel that results in a net changeof 1 to 50nucleotides. In coding regions of the genome, unless the length of an indel is a multiple of 3, it will produce a frameshift mutation. Indels can be contrasted with point mutations. An indel inserts and deletes nucleotides from a sequence, while a point mutation is a form of substitution that replaces one of the nucleotides without changing the overall number in the DNA. Indels can also be contrasted with a TandemBaseMutation (TBM), which may be defined as substitution at adjacent nucleotides (primarily substitutions at two adjacent nucleotides, but substitutions at three adjacent nucleotides have been observed.

[0308] The term "variant" refers to a nucleic acid sequence that is different froma nucleic acid reference. Typical nucleic acid sequence variant includes without limitation single nucleotide polymorphism (SNP), short deletion and insertion polymorphisms (Indel), copy number variation (CNV), microsatellite markers or short tandem repeats and structural variation. Somatic variant calling is the effort to identify variants present at low frequency in the DNA sample. Somatic variant calling is of interest in the context of cancer treatment.Cancer is causedbyanaccumulation ofmutations inDNA.A DNAsample froma tumor is generally heterogeneous, including somenormal cells, some cells at an early stage of cancer progression (with fewermutations), and some late-stage cells (withmoremutations). Becauseof this heterogeneity, when sequencing a tumor (e.g., from an FFPE sample), somatic mutations will often appear at a low frequency. For example, a SNVmight be seen in only 10%of the reads covering a given base. A variant that is to be classified as somatic or germline by the variant classifier is also referred to herein as the "variant under test."

[0309] The term "noise" refers to a mistaken variant call resulting from one or more errors in the sequencing process and / or in the variant call application. 41 EP 4 679 300 A2 5 10 15 20 25 30 35 40 45 50 55

[0310] The term "variant frequency" represents the relative frequency of an allele (variant of a gene) at a particular locus in a population, expressed as a fraction or percentage. For example, the fraction or percentage may be the fraction of all chromosomes in the population that carry that allele. Byway of example, sample variant frequency represents the relative frequency of an allele / variant at a particular locus / position along a genomic sequence of interest over a "population" corresponding to thenumber of readsand / or samplesobtained for thegenomic sequenceof interest froman individual. As another example, a baseline variant frequency represents the relative frequency of an allele / variant at a particular locus / position along one or more baseline genomic sequences where the "population" corresponding to the number of reads and / or samples obtained for the one or more baseline genomic sequences from a population of normal individuals.

[0311] The term "variant allele frequency (VAF)" refers to the percentage of sequenced reads observed matching the variant divided by the overall coverage at the target position. VAF is a measure of the proportion of sequenced reads carrying the variant.

[0312] The terms "position", "designated position", and "locus" refer to a location or coordinate of one or more nucleotides within a sequence of nucleotides. The terms "position", "designated position", and "locus" also refer to a location or coordinate of one or more base pairs in a sequence of nucleotides.

[0313] The term "haplotype" refers to a combination of alleles at adjacent sites on a chromosome that are inherited together. Ahaplotypemaybeone locus, several loci, or anentire chromosomedependingon thenumber of recombination events that have occurred between a given set of loci, if any occurred.

[0314] The term "threshold" herein refers to a numeric or non-numeric value that is used as a cutoff to characterize a sample, a nucleic acid, or portion thereof (e.g., a read). A threshold may be varied based upon empirical analysis. The threshold may be compared to a measured or calculated value to determine whether the source giving rise to such value suggests should be classified in a particular manner. Threshold values can be identified empirically or analytically. The choice of a threshold is dependent on the level of confidence that the user wishes to have to make the classification. The threshold may be chosen for a particular purpose (e.g., to balance sensitivity and selectivity). As used herein, the term "threshold" indicates a point at which a course of analysis may be changed and / or a point at which an action may be triggered.A threshold is not required to beapredeterminednumber. Instead, the thresholdmaybe, for instance, a function that is based on a plurality of factors. The threshold may be adaptive to the circumstances. Moreover, a threshold may indicate an upper limit, a lower limit, or a range between limits.

[0315] In some implementations, ametric or score that is based on sequencing datamay be compared to the threshold. As used herein, the terms "metric" or "score"may include values or results thatwere determined from the sequencing data or may include functions that are based on the values or results that were determined from the sequencing data. Like a threshold, themetric or scoremaybeadaptive to the circumstances. For instance, themetric or scoremaybeanormalized value. As an example of a score ormetric, one ormore implementationsmay use count scoreswhen analyzing the data. A count score may be based on number of sample reads. The sample reads may have undergone one or more filtering stages such that the sample reads have at least one common characteristic or quality. For example, each of the sample reads that are used to determine acount scoremayhavebeenalignedwith a reference sequenceormaybeassigned asa potential allele. The number of sample reads having a common characteristic may be counted to determine a read count. Count scoresmaybebasedon the readcount. In some implementations, thecount scoremaybeavalue that isequal to the readcount. In other implementations, the count scoremaybebasedon the readcount andother information. For example, a count score may be based on the read count for a particular allele of a genetic locus and a total number of reads for the genetic locus. In some implementations, the count scoremaybebasedon the read count andpreviously-obtaineddata for the genetic locus. In some implementations, the count scoresmay be normalized scores between predetermined values. The count score may also be a function of read counts from other loci of a sample or a function of read counts from other samples thatwere concurrently runwith the sample-of-interest. For instance, the count scoremaybea function of the read count of aparticular alleleand the readcountsof other loci in thesampleand / or the readcounts fromother samples.Asone example, the read counts from other loci and / or the read counts from other samples may be used to normalize the count score for the particular allele.

[0316] The terms "coverage" or "fragment coverage" refer to a count or other measure of a number of sample reads for the same fragment of a sequence. A read countmay represent a count of the number of reads that cover a corresponding fragment. Alternatively, the coveragemaybedeterminedbymultiplying the readcount by adesignated factor that is based on historical knowledge, knowledge of the sample, knowledge of the locus, etc.

[0317] The term "read depth" (conventionally a number followed by "×") refers to the number of sequenced reads with overlappingalignment at the target position.This is oftenexpressedasanaverageorpercentageexceedingacutoffovera set of intervals (suchasexons, genes, or panels). For example, a clinical reportmight say that a panel average coverage is 1,105 × with 98% of targeted bases covered >100×.

[0318] The terms "base call quality score" or "Q score" refer to a PHRED-scaled probability ranging from 0‑50 inversely proportional to the probability that a single sequencedbase is correct. For example, aTbase call withQof 20 is considered likely correct with a probability of 99.99%. Any base call with Q<20 should be considered low quality, and any variant identifiedwhereasubstantial proportionof sequenced readssupporting thevariant areof lowquality shouldbeconsidered 42 EP 4 679 300 A2 5 10 15 20 25 30 35 40 45 50 55 potentially false positive.

[0319] The terms "variant reads" or "variant read number" refer to the number of sequenced reads supporting the presence of the variant.

[0320] Regarding "strandedness" (or DNA strandedness), the genetic message in DNA can be represented as a string of the letters A,G,C, andT. For example, 5’ - AGGACA - 3’. Often, the sequence is written in the direction shownhere, i.e., with the 5’ end to the left and the 3’ end to the right. DNAmay sometimes occur as single-strandedmolecule (as in certain viruses), but normallywe findDNAasadouble-stranded unit. It has a double helical structurewith twoantiparallel strands. In this case, the word "antiparallel" means that the two strands run in parallel, but have opposite polarity. The double- strandedDNA is held together by pairing betweenbasesand thepairing is always such that adenine (A) pairswith thymine (T) and cytosine (C) pairswith guanine (G). This pairing is referred to as complementarity, and one strand of DNA is said to be thecomplementof theother. Thedouble-strandedDNAmay thusbe representedas twostrings, like this: 5’ -AGGACA- 3’ and 3’ - TCCTGT - 5’. Note that the two strands have opposite polarity. Accordingly, the strandedness of the two DNA strands can be referred to as the reference strand and its complement, forward and reverse strands, top and bottom strands, sense and antisense strands, or Watson and Crick strands.

[0321] The readsalignment (alsocalled readsmapping) is theprocessof figuringoutwhere in thegenomeasequence is from. Once the alignment is performed, the "mapping quality" or the "mapping quality score (MAPQ)" of a given read quantifies the probability that its position on the genome is correct. The mapping quality is encoded in the phred scale whereP is the probability that the alignment is not correct. The probability is calculated as:P= 10(-MAQ / 10), whereMAPQ is themappingquality. Forexample, amappingquality of 40=10 to thepowerof ‑4,meaning that there isa0.01%chance that the read was aligned incorrectly. The mapping quality is therefore associated with several alignment factors, such as the basequality of the read, the complexity of the reference genome, and the paired-end information.Regarding the first, if the base quality of the read is low, it means that the observed sequence might be wrong and thus its alignment is wrong. Regarding the second, themappability refers to the complexity of the genome. Repeated regions aremore difficult tomap and reads falling in these regions usually get lowmapping quality. In this context, theMAPQ reflects the fact that the reads are not uniquely aligned and that their real origin cannot be determined. Regarding the third, in case of paired-end sequencing data, concordant pairs are more likely to be well aligned. The higher is the mapping quality, the better is the alignment. A read aligned with a goodmapping quality usually means that the read sequence was good and was aligned with few mismatches in a high mappability region. The MAPQ value can be used as a quality control of the alignment results. The proportion of reads aligned with an MAPQ higher than 20 is usually for downstream analysis.

[0322] As used herein, a "signal" refers to a detectable event such as an emission, preferably light emission, for example, in an image. Thus, in preferred implementations, a signal can represent any detectable light emission that is captured in an image (i.e., a "spot"). Thus, as used herein, "signal" can refer to both an actual emission from an analyte of the specimen, and can refer to a spurious emission that does not correlate to an actual analyte. Thus, a signal could arise from noise and could be later discarded as not representative of an actual analyte of a specimen.

[0323] As used herein, the term "clump" refers to a group of signals. In particular implementations, the signals are derived fromdifferent analytes. In apreferred implementation, a signal clump is agroupof signals that cluster together. In a more preferred implementation, a signal clump represents a physical region covered by one amplified oligonucleotide. Each signal clump should be ideally observed as several signals (one per template cycle, and possiblymore due to cross- talk). Accordingly, duplicate signals are detected where two (or more) signals are included in a template from the same clump of signals.

[0324] Asusedherein, termssuchas "minimum," "maximum," "minimize," "maximize" andgrammatical variants thereof can include values that are not the absolute maxima or minima. In some implementations, the values include near maximum and near minimum values. In other implementations, the values can include local maximum and / or local minimum values. In some implementations, the values include only absolute maximum or minimum values.

[0325] As used herein, "cross-talk" refers to the detection of signals in one image that are also detected in a separate image. In a preferred implementation, cross-talk can occur when an emitted signal is detected in two separate detection channels. For example,where an emitted signal occurs in one color, the emission spectrumof that signalmayoverlapwith anotheremittedsignal inanother color. Inapreferred implementation, fluorescentmoleculesused to indicate thepresence of nucleotide bases A, C, G and Tare detected in separate channels. However, because the emission spectra of A and C overlap, some of the C color signal may be detected during detection using the A color channel. Accordingly, cross-talk between the A and C signals allows signals from one color image to appear in the other color image. In some implementations,GandTcross-talk. In some implementations, theamount of cross-talk betweenchannels is asymmetric. It will be appreciated that the amount of cross-talk between channels can be controlled by, among other things, the selection of signal molecules having an appropriate emission spectrum as well as selection of the size and wavelength range of the detection channel.

[0326] Asusedherein, "register," "registering," "registration" and like terms refer toanyprocess to correlate signals inan image or data set from a first time point or perspective with signals in an image or data set from another time point or perspective. For example, registration can be used to align signals from a set of images to form a template. In another 43 EP 4 679 300 A2 5 10 15 20 25 30 35 40 45 50 55 example, registration can be used to align signals fromother images to a template. One signalmay be directly or indirectly registered to another signal. For example, a signal from image "S" may be registered to image "G" directly. As another example, a signal from image "N"maybedirectly registered to image "G,"oralternatively, thesignal from image "N"maybe registered to image "S," which has previously been registered to image "G." Thus, the signal from image "N" is indirectly registered to image "G."

[0327] As used herein, the term "fiducial" is intended tomean a distinguishable point of reference in or on an object. The point of reference can be, for example, amark, second object, shape, edge, area, irregularity, channel, pit, post or the like. Thepoint of reference canbepresent in an imageof the object or in another data set derived fromdetecting theobject. The point of referencecanbespecifiedbyanxand / or y coordinate in aplaneof theobject. Alternatively or additionally, thepoint of reference can be specified by a z coordinate that is orthogonal to the xy plane, for example, being defined by the relative locations of the object and a detector. One or more coordinates for a point of reference can be specified relative to one or more other analytes of an object or of an image or other data set derived from the object.

[0328] As used herein, the term "optical signal" is intended to include, for example, fluorescent, luminescent, scatter, or absorption signals. Optical signals can be detected in the ultraviolet (UV) range (about 200 to 390 nm), visible (VIS) range (about 391 to 770 nm), infrared (IR) range (about 0.771 to 25 microns), or other range of the electromagnetic spectrum. Optical signals can be detected in a way that excludes all or part of one or more of these ranges.

[0329] As used herein, the term "signal level" is intended to mean an amount or quantity of detected energy or coded information that hasadesired or predefined characteristic. For example, an optical signal canbequantified byoneormore of intensity, wavelength, energy, frequency, power, luminance or the like. Other signals can be quantified according to characteristics suchasvoltage, current, electric field strength,magnetic field strength, frequency, power, temperature, etc. Absence of signal is understood to be a signal level of zero or a signal level that is not meaningfully distinguished from noise.

[0330] As used herein, the term "simulate" is intended tomean creating a representation or model of a physical thing or action thatpredicts characteristicsof the thingoraction.The representationormodel can inmanycasesbedistinguishable from the thingor action.Forexample, the representationormodel canbedistinguishable froma thingwith respect tooneor more characteristic such as color, intensity of signals detected from all or part of the thing, size, or shape. In particular implementations, the representation ormodel canbe idealized, exaggerated,muted, or incompletewhen compared to the thing or action. Thus, in some implementations, a representation of model can be distinguishable from the thing or action that it represents, for example, with respect to at least one of the characteristics set forth above. The representation or model can be provided in a computer readable format ormedium such as one ormore of those set forth elsewhere herein.

[0331] As used herein, the term "specific signal" is intended to mean detected energy or coded information that is selectively observed over other energy or information such as background energy or information. For example, a specific signal can be an optical signal detected at a particular intensity, wavelength or color; an electrical signal detected at a particular frequency, power or field strength; or other signals known in the art pertaining to spectroscopy and analytical detection.

[0332] As used herein, the term "swath" is intended to mean a rectangular portion of an object. The swath can be an elongated strip that is scanned by relativemovement between the object and a detector in a direction that is parallel to the longest dimension of the strip. Generally, the width of the rectangular portion or strip will be constant along its full length. Multiple swaths of an object can be parallel to each other. Multiple swaths of an object can be adjacent to each other, overlapping with each other, abutting each other, or separated from each other by an interstitial area.

[0333] As used herein, the term "variance" is intended to mean a difference between that which is expected and that which is observed or a difference between two or more observations. For example, variance can be the discrepancy between an expected value and a measured value. Variance can be represented using statistical functions such as standard deviation, the square of standard deviation, coefficient of variation or the like.

[0334] As used herein, the term "xy coordinates" is intended to mean information that specifies location, size, shape, and / or orientation in an xy plane. The information can be, for example, numerical coordinates in a Cartesian system. The coordinates can be provided relative to one or both of the x and y axes or can be provided relative to another location in the xy plane. For example, coordinates of a analyte of an object can specify the location of the analyte relative to location of a fiducial or other analyte of the object.

[0335] Asusedherein, the term "xy plane" is intended tomeana2dimensional areadefinedby straight line axes x and y. When used in reference to a detector and an object observed by the detector, the area can be further specified as being orthogonal to the direction of observation between the detector and object being detected.

[0336] As used herein, the term "z coordinate" is intended tomean information that specifies the location of a point, line or area along an axes that is orthogonal to an xy plane. In particular implementations, the z axis is orthogonal to an area of anobject that isobservedbyadetector. Forexample, thedirectionof focus for anoptical systemmaybespecifiedalong the z axis.

[0337] In some implementations, acquired signal data is transformed using an affine transformation. In some such implementations, template generation makes use of the fact that the affine transforms between color channels are 44 EP 4 679 300 A2 5 10 15 20 25 30 35 40 45 50 55 consistent between runs. Because of this consistency, a set of default offsets can be used when determining the coordinates of the analytes in a specimen. For example, a default offsets file can contain the relative transformation (shift, scale, skew) for the different channels relative to one channel, such as the A channel. In other implementations, however, the offsets between color channels drift during a run and / or between runs, making offset-driven template generation difficult. In such implementations, the methods and systems provided herein can utilize offset-less template generation, which is described further below.

[0338] In someaspectsof theabove implementations, thesystemcancompriseaflowcell. In someaspects, theflowcell comprises lanes, or other configurations, of tiles, wherein at least some of the tiles comprise one or more arrays of analytes. In someaspects, theanalytes compriseaplurality ofmolecules suchasnucleic acids. In certain aspects, the flow cell is configured todelivera labelednucleotidebase toanarrayofnucleicacids, therebyextendingaprimerhybridized toa nucleic acid within a analyte so as to produce a signal corresponding to a analyte comprising the nucleic acid. In preferred implementations, the nucleic acids within a analyte are identical or substantially identical to each other.

[0339] In some of the systems for image analysis described herein, each image in the set of images includes color signals, wherein a different color corresponds to a different nucleotide base. In some aspects, each image of the set of images comprises signals having a single color selected fromat least four different colors. In someaspects, each image in the set of images comprises signals having a single color selected from four different colors. In some of the systems described herein, nucleic acids can be sequenced by providing four different labeled nucleotide bases to the array of molecules so as to produce four different images, each image comprising signals having a single color, wherein the signal color is different for eachof the four different images, therebyproducingacycle of four color images that corresponds to the four possiblenucleotidespresent at aparticular position in thenucleic acid. In certainaspects, thesystemcomprisesaflow cell that is configured to deliver additional labeled nucleotide bases to the array ofmolecules, thereby producing a plurality of cycles of color images.

[0340] In preferred implementations, the methods provided herein can include determining whether a processor is actively acquiring data or whether the processor is in a low activity state. Acquiring and storing large numbers of high- quality images typically requires massive amounts of storage capacity. Additionally, once acquired and stored, the analysis of image data can become resource intensive and can interfere with processing capacity of other functions, such as ongoing acquisition and storage of additional image data. Accordingly, as used herein, the term low activity state refers to the processing capacity of a processor at a given time. In some implementations, a low activity state occurs when a processor is not acquiring and / or storing data. In some implementations, a low activity state occurs when some data acquisition and / or storage is taking place, but additional processing capacity remains such that image analysis can occur at the same time without interfering with other functions.

[0341] As used herein, "identifying a conflict" refers to identifying a situation where multiple processes compete for resources. In somesuch implementations, oneprocess is givenpriority over another process. In some implementations, a conflict may relate to the need to give priority for allocation of time, processing capacity, storage capacity or any other resource for which priority is given. Thus, in some implementations, where processing time or capacity is to be distributed between twoprocessessuchaseither analyzingadata set andacquiringand / or storing thedata set, a conflict between the two processes exists and can be resolved by giving priority to one of the processes.

[0342] Alsoprovidedherein are systems for performing imageanalysis. Thesystemscan includeaprocessor; a storage capacity; and a program for image analysis, the program comprising instructions for processing a first data set for storage and the second data set for analysis, wherein the processing comprises acquiring and / or storing the first data set on the storage device and analyzing the second data set when the processor is not acquiring the first data set. In certain aspects, the program includes instructions for identifying at least one instanceof a conflict betweenacquiring and / or storing the first data set and analyzing the second data set; and resolving the conflict in favor of acquiring and / or storing image data such that acquiring and / or storing the first data set is given priority. In certain aspects, the first data set comprises image files obtained from an optical imaging device. In certain aspects, the system further comprises an optical imaging device. In some aspects, the optical imaging device comprises a light source and a detection device.

[0343] As used herein, the term "program" refers to instructions or commands to perform a task or process. The term "program" can be used interchangeablywith the termmodule. In certain implementations, a programcanbea compilation of various instructions executed under the same set of commands. In other implementations, a program can refer to a discrete batch or file.

[0344] Set forth below are some of the surprising effects of utilizing the methods and systems for performing image analysis set forthherein. In somesequencing implementations, an importantmeasureofasequencingsystem’sutility is its overall efficiency. For example, the amount ofmappable data produced per day and the total cost of installing and running the instrumentare important aspectsof aneconomical sequencingsolution.To reduce the time togeneratemappabledata and to increase the efficiency of the system, real-time base calling can be enabled on an instrument computer and can run in parallel with sequencing chemistry and imaging. This allowsmuch of the data processing and analysis to be completed before the sequencing chemistry finishes. Additionally, it can reduce the storage required for intermediate data and limit the amount of data that needs to travel across the network. 45 EP 4 679 300 A2 5 10 15 20 25 30 35 40 45 50 55

[0345] While sequence output has increased, the data per run transferred from the systems provided herein to the network and to secondary analysis processing hardware has substantially decreased. By transforming data on the instrument computer (acquiring computer), network loads are dramatically reduced. Without these on-instrument, off- network data reduction techniques, the image output of a fleet of DNA sequencing instruments would cripple most networks.

[0346] Thewidespreadadoption of the high-throughputDNAsequencing instruments hasbeendriven in part by easeof use, support for a range of applications, and suitability for virtually any lab environment. The highly efficient algorithms presented herein allow significant analysis functionality to be added to a simple workstation that can control sequencing instruments. This reduction in the requirements for computational hardwarehasseveral practical benefits thatwill become even more important as sequencing output levels continue to increase. For example, by performing image analysis and base calling on a simple tower, heat production, laboratory footprint, and power consumption are kept to a minimum. In contrast, other commercial sequencing technologies have recently ramped up their computing infrastructure for primary analysis, with up to five times more processing power, leading to commensurate increases in heat output and power consumption. Thus, in some implementations, the computational efficiency of the methods and systems provided herein enables customers to increase their sequencing throughput while keeping server hardware expenses to a minimum.

[0347] Accordingly, in some implementations, the methods and / or systems presented herein act as a state machine, keeping track of the individual state of each specimen, andwhen it detects that a specimen is ready to advance to the next state, it does the appropriate processing and advances the specimen to that state. A more detailed example of how the state machine monitors a file system to determine when a specimen is ready to advance to the next state according to a preferred implementation described below.

[0348] In preferred implementations, themethods and systems provided herein aremulti-threaded and canwork with a configurable number of threads. Thus, for example in the context of nucleic acid sequencing, the methods and systems provided herein are capable of working in the background during a live sequencing run for real-time analysis, or it can be run using a pre-existing set of image data for offline analysis. In certain preferred implementations, the methods and systems handle multi-threading by giving each thread its own subset of specimen for which it is responsible. This minimizes the possibility of thread contention.

[0349] Amethod of the present disclosure can include a step of obtaining a target image of an object using a detection apparatus, wherein the image includes a repeating pattern of analytes on the object. Detection apparatus that are capable of high resolution imaging of surfaces are particularly useful. In particular implementations, the detection apparatus will have sufficient resolution to distinguish analytes at the densities, pitches, and / or analyte sizes set forth herein. Particularly useful are detectionapparatus capableof obtaining imagesor imagedata fromsurfaces.Exampledetectors are those that are configured to maintain an object and detector in a static relationship while obtaining an area image. Scanning apparatus can also be used. For example, an apparatus that obtains sequential area images (e.g., so called ’step and shoot’ detectors) can be used. Also useful are devices that continually scan a point or line over the surface of an object to accumulate data to construct an image of the surface. Point scanning detectors can be configured to scan a point (i.e., a small detection area) over the surface of an object via a raster motion in the x-y plane of the surface. Line scanning detectors can be configured to scan a line along the y dimension of the surface of an object, the longest dimension of the line occurringalong the xdimension. Itwill beunderstood that thedetectiondevice, object or both canbemoved toachieve scanning detection. Detection apparatus that are particularly useful, for example in nucleic acid sequencing applications, are described in US Pat App. Pub. Nos. 2012 / 0270305 A1; 2013 / 0023422 A1; and 2013 / 0260372 A1; and U.S. Pat. Nos. 5,528,050; 5,719,391; 8,158,926 and 8,241,573, each of which is incorporated herein by reference.

[0350] The implementations disclosed herein may be implemented as a method, apparatus, system or article of manufacture using programming or engineering techniques to produce software, firmware, hardware, or any combination thereof. The term "article of manufacture" as used herein refers to code or logic implemented in hardware or computer readablemedia suchasoptical storagedevices, andvolatile or non-volatilememorydevices.Suchhardwaremay include, but is not limited to, field programmable gate arrays (FPGAs), coarse grained reconfigurable architectures (CGRAs), application-specific integrated circuits (ASICs), complex programmable logic devices (CPLDs), programmable logic arrays (PLAs), microprocessors, or other similar processing devices. In particular implementations, information or algorithms set forth herein are present in non-transient storage media.

[0351] In particular implementations, a computer implemented method set forth herein can occur in real time while multiple images of an object are being obtained. Such real time analysis is particularly useful for nucleic acid sequencing applicationswherein an array of nucleic acids is subjected to repeated cycles of fluidic and detection steps. Analysis of the sequencing data can often be computationally intensive such that it can be beneficial to perform the methods set forth herein in real time or in the background while other data acquisition or analysis algorithms are in process. Example real time analysis methods that can be used with the present methods are those used for the MiSeq and HiSeq sequencing devices commercially available from Illumina, Inc. (San Diego, Calif.) and / or described in US Pat. App. Pub. No. 2012 / 0020537 A1, which is incorporated herein by reference.

[0352] An example data analysis system, formed by one or more programmed computers, with programming being 46 EP 4 679 300 A2 5 10 15 20 25 30 35 40 45 50 55 stored on one or more machine readable media with code executed to carry out one or more steps of methods described herein. In one implementation, for example, the system includes an interface designed to permit networking of the system to one or more detection systems (e.g., optical imaging systems) that are configured to acquire data from target objects. The interface may receive and condition data, where appropriate. In particular implementations the detection system will output digital image data, for example, image data that is representative of individual picture elements or pixels that, together, forman imageofanarrayorotherobject.Aprocessorprocesses the receiveddetectiondata inaccordancewitha oneormore routinesdefinedbyprocessing code. Theprocessing codemaybe stored in various types ofmemory circuitry.

[0353] In accordancewith the presently contemplated implementations, the processing code executed on the detection data includes a data analysis routine designed to analyze the detection data to determine the locations and metadata of individual analytes visible or encoded in thedata, aswell as locationsatwhichnoanalyte is detected (i.e.,where there isno analyte, or where no meaningful signal was detected from an existing analyte). In particular implementations, analyte locations in an array will typically appear brighter than non-analyte locations due to the presence of fluorescing dyes attached to the imaged analytes. It will be understood that the analytes need not appear brighter than their surrounding area, for example, when a target for the probe at the analyte is not present in an array being detected. The color at which individual analytes appear may be a function of the dye employed as well as of the wavelength of the light used by the imaging system for imaging purposes. Analytes to which targets are not bound or that are otherwise devoid of a particular label can be identified according to other characteristics, such as their expected location in the microarray.

[0354] Once thedataanalysis routinehas located individual analytes in thedata, a valueassignmentmaybecarriedout. In general, the value assignment will assign a digital value to each analyte based upon characteristics of the data representedbydetector components (e.g., pixels) at thecorresponding location. That is, for examplewhen imagingdata is processed, the value assignment routine may be designed to recognize that a specific color or wavelength of light was detected at a specific location, as indicated by a group or cluster of pixels at the location. In a typical DNA imaging application, for example, the four common nucleotides will be represented by four separate and distinguishable colors. Each color, then, may be assigned a value corresponding to that nucleotide.

[0355] As used herein, the terms "module," "system," or "system controller" may include a hardware and / or software system and circuitry that operates to perform one ormore functions. For example, amodule, system, or system controller may include a computer processor, controller, or other logic-based device that performs operations based on instructions stored on a tangible and non-transitory computer readable storagemedium, such as a computer memory. Alternatively, a module, system, or systemcontrollermay include ahard-wired device that performs operations based on hard-wired logic and circuitry. The module, system, or system controller shown in the attached figures may represent the hardware and circuitry that operates based on software or hardwired instructions, the software that directs hardware to perform the operations, or a combination thereof. Themodule, system, or systemcontroller can include or represent hardware circuits or circuitry that include and / or are connected with one or more processors, such as one or computer microprocessors.

[0356] As used herein, the terms "software" and "firmware" are interchangeable, and include any computer program stored in memory for execution by a computer, including RAM memory, ROM memory, EPROM memory, EEPROM memory, and non-volatile RAM (NVRAM)memory. The abovememory types are examples only, and are thus not limiting as to the types of memory usable for storage of a computer program.

[0357] In the molecular biology field, one of the processes for nucleic acid sequencing in use is sequencing-by- synthesis. The technique can be applied to massively parallel sequencing projects. For example, by using an automated platform, it is possible to carry out hundreds of thousands of sequencing reactions simultaneously. Thus, one of the implementations of the present invention relates to instruments and methods for acquiring, storing, and analyzing image data generated during nucleic acid sequencing.

[0358] Enormous gains in the amount of data that can be acquired and stored make streamlined image analysis methodsevenmorebeneficial. For example, the imageanalysismethodsdescribed herein permit both designers andend users tomakeefficient use of existing computer hardware. Accordingly, presented herein aremethods and systemswhich reduce the computational burden of processing data in the face of rapidly increasing data output. For example, in the field ofDNAsequencing, yieldshave scaled15-fold over the courseof a recent year, and cannow reachhundredsof gigabases in a single run of a DNA sequencing device. If computational infrastructure requirements grew proportionately, large genome-scale experiments would remain out of reach to most researchers. Thus, the generation of more raw sequence data will increase the need for secondary analysis and data storage, making optimization of data transport and storage extremely valuable. Some implementations of themethods and systemspresented herein can reduce the time, hardware, networking, and laboratory infrastructure requirements needed to produce usable sequence data.

[0359] Thepresent disclosure describes variousmethodsand systems for carrying out themethods.Examples of some of themethodsaredescribedasa series of steps.However, it should beunderstood that implementations arenot limited to the particular steps and / or order of steps described herein. Steps may be omitted, steps may be modified, and / or other stepsmay be added.Moreover, steps described hereinmay be combined, stepsmay be performed simultaneously, steps may be performed concurrently, stepsmay be split intomultiple sub-steps, stepsmay be performed in a different order, or steps (or a series of steps)maybe re-performed in an iterative fashion. In addition, althoughdifferentmethods are set forth 47 EP 4 679 300 A2 5 10 15 20 25 30 35 40 45 50 55 herein, it should be understood that the different methods (or steps of the different methods) may be combined in other implementations.

[0360] In some implementations, a processing unit, processor, module, or computing system that is "configured to" perform a task or operation may be understood as being particularly structured to perform the task or operation (e.g., havingoneormoreprogramsor instructionsstored thereonorused in conjunction therewith tailoredor intended toperform the task or operation, and / or having an arrangement of processing circuitry tailored or intended to perform the task or operation). For the purposes of clarity and the avoidance of doubt, a general purpose computer (which may become "configured to"perform the taskoroperation if appropriatelyprogrammed) isnot "configured to"performa taskoroperation unless or until specifically programmed or structurally modified to perform the task or operation.

[0361] Moreover, the operations of the methods described herein can be sufficiently complex such that the operations cannot be mentally performed by an average human being or a person of ordinary skill in the art within a commercially reasonable time period. For example, the methods may rely on relatively complex computations such that such a person cannot complete the methods within a commercially reasonable time.

[0362] Throughout this application various publications, patents or patent applications have been referenced. The disclosures of these publications in their entireties are hereby incorporated by reference in this application in order tomore fully describe the state of the art to which this invention pertains.

[0363] The term "comprising" is intended herein to be open-ended, including not only the recited elements, but further encompassing any additional elements.

[0364] As used herein, the term "each," when used in reference to a collection of items, is intended to identify an individual item in the collection but does not necessarily refer to every item in the collection. Exceptions canoccur if explicit disclosure or context clearly dictates otherwise.

[0365] Although the invention has been described with reference to the examples provided above, it should be understood that various modifications can be made without departing from the invention.

[0366] The modules in this application can be implemented in hardware or software, and need not be divided up in precisely thesameblocksasshown in thefigures.Somecanalsobe implementedondifferent processorsor computers, or spread among a number of different processors or computers. In addition, it will be appreciated that some of themodules can be combined, operated in parallel or in a different sequence than that shown in the figures without affecting the functions achieved. Also as used herein, the term "module" can include "sub-modules", which themselves can be considered herein to constitute modules. The blocks in the figures designated as modules can also be thought of as flowchart steps in a method.

[0367] Asusedherein, the "identification" of an itemof informationdoesnot necessarily require thedirect specificationof that itemof information. Information can be "identified" in a field by simply referring to the actual information through oneor more layers of indirection, or by identifying one or more items of different information which are together sufficient to determine the actual item of information. In addition, the term "specify" is used herein to mean the same as "identify."

[0368] Asusedherein, a given signal, event or value is "in dependenceupon" apredecessor signal, event or value of the predecessor signal, event or value influenced by the given signal, event or value. If there is an intervening processing element, step or time period, the given signal, event or value can still be "in dependence upon" the predecessor signal, event or value. If the intervening processing element or step combines more than one signal, event or value, the signal outputof theprocessingelementor step is considered "independenceupon"eachof thesignal, eventor value inputs. If the givensignal, eventor value is thesameas thepredecessor signal, event or value, this ismerely adegenerate case inwhich the given signal, event or value is still considered to be "in dependence upon" or "dependent on" or "based on" the predecessor signal, event or value. "Responsiveness" of a given signal, event or value uponanother signal, event or value is defined similarly.

[0369] Asusedherein, "concurrently" or "in parallel" doesnot require exact simultaneity. It is sufficient if theevaluation of one of the individuals begins before the evaluation of another of the individuals completes. Computer System

[0370] Fig. 16 is a computer system 1600 that can be used to implement the technology disclosed. Computer system 1600 includes at least one central processing unit (CPU) 1672 that communicateswith a number of peripheral devices via bus subsystem 1655. These peripheral devices can include a storage subsystem 1610 including, for example, memory devices and a file storage subsystem 1636, user interface input devices 1638, user interface output devices 1676, and a network interface subsystem 1674. The input and output devices allow user interaction with computer system 1600. Network interface subsystem 1674 provides an interface to outside networks, including an interface to corresponding interface devices in other computer systems.

[0371] In one implementation, the base caller 704 is communicably linked to the storage subsystem 1610 and the user interface input devices 1638.

[0372] User interface input devices 1638 can include a keyboard; pointing devices such as a mouse, trackball, 48 EP 4 679 300 A2 5 10 15 20 25 30 35 40 45 50 55 touchpad, or graphics tablet; a scanner; a touch screen incorporated into the display; audio input devices such as voice recognition systems and microphones; and other types of input devices. In general, use of the term "input device" is intended to include all possible types of devices and ways to input information into computer system 1600.

[0373] User interface output devices 1676 can include a display subsystem, a printer, a fax machine, or non-visual displayssuchasaudiooutputdevices.Thedisplaysubsystemcan includeanLEDdisplay, acathode ray tube (CRT),aflat- panel device such as a liquid crystal display (LCD), a projection device, or some other mechanism for creating a visible image. The display subsystem can also provide a non-visual display such as audio output devices. In general, use of the term "output device" is intended to include all possible types of devices and ways to output information from computer system 1600 to the user or to another machine or computer system.

[0374] Storage subsystem 1610 stores programming and data constructs that provide the functionality of some or all of the modules and methods described herein. These software modules are generally executed by processors 1678.

[0375] Processors 1678 can be graphics processing units (GPUs), field-programmable gate arrays (FPGAs), applica- tion-specific integrated circuits (ASICs), and / or coarse-grained reconfigurable architectures (CGRAs). Processors 1678 can be hosted by a deep learning cloud platform such asGoogleCloudPlatform™, Xilinx™, andCirrascale™. Examples of processors 1678 include Google’s Tensor Processing Unit (TPU)™, rackmount solutions like GX4 Rackmount Series™, GX16Rackmount Series™,NVIDIADGX‑1™,Microsoft’ StratixVFPGA™,Graphcore’s IntelligentProcessorUnit (IPU)™, Qualcomm’s Zeroth Platform™ with Snapdragon processors™, NVIDIA’s Volta™, NVIDIA’s DRIVE PX™, NVIDIA’s JET- SON TX1 / TX2 MODULE™, Intel’s Nirvana™, Movidius VPU™, Fujitsu DPI™, ARM’s DynamicIQ™, IBM TrueNorth™, Lambda GPU Server with Testa V100s™, and others.

[0376] Memory subsystem 1622 used in the storage subsystem 1610 can include a number of memories including a main random access memory (RAM) 1632 for storage of instructions and data during program execution and a read only memory (ROM) 1634 in which fixed instructions are stored. A file storage subsystem 1636 can provide persistent storage for programand data files, and can include a hard disk drive, a floppy disk drive alongwith associated removablemedia, a CD-ROM drive, an optical drive, or removable media cartridges. The modules implementing the functionality of certain implementations can be stored by file storage subsystem 1636 in the storage subsystem 1610, or in other machines accessible by the processor.

[0377] Bus subsystem 1655 provides a mechanism for letting the various components and subsystems of computer system1600 communicatewith each other as intended. Although bus subsystem1655 is shown schematically as a single bus, alternative implementations of the bus subsystem can use multiple busses.

[0378] Computer system 1600 itself can be of varying types including a personal computer, a portable computer, a workstation, a computer terminal, a network computer, a television, amainframe, a server farm, awidely-distributed set of loosely networked computers, or any other data processing system or user device. Due to the ever-changing nature of computers and networks, the description of computer system 1600 depicted in Fig. 16 is intended only as a specific example for purposes of illustrating the preferred implementations of the present invention. Many other configurations of computer system 1600 are possible having more or less components than the computer system depicted in Fig. 16. Clauses

[0379] The technology disclosed attenuates spatial crosstalk from sensor pixels using sharpening mask-based image processing techniques. The technology disclosed canbe practiced as a system,method, or article ofmanufacture.One or more featuresofan implementationcanbecombinedwith thebase implementation. Implementations that arenotmutually exclusive are taught to be combinable. One or more features of an implementation can be combined with other implementations. This disclosure periodically reminds the user of these options. Omission from some implementations of recitations that repeat these options should not be taken as limiting the combinations taught in the preceding sections - these recitations are hereby incorporated forward by reference into each of the following implementations.

[0380] In one implementation, the technology disclosed proposes a computer-implemented method of attenuating spatial crosstalk from sensor pixels.

[0381] The technology disclosed can be practiced as a system,method, or article ofmanufacture.One ormore features of an implementation canbe combinedwith the base implementation. Implementations that are notmutually exclusive are taught to be combinable. One or more features of an implementation can be combined with other implementations. This disclosure periodically reminds the user of these options. Omission from some implementations of recitations that repeat these options should not be taken as limiting the combinations taught in the preceding sections - these recitations are hereby incorporated forward by reference into each of the following implementations.

[0382] One ormore implementations and clauses of the technology disclosed or elements thereof can be implemented in the form of a computer product, including a non-transitory computer readable storage medium with computer usable program code for performing the method steps indicated. Furthermore, one or more implementations and clauses of the technology disclosed or elements thereof can be implemented in the formof an apparatus including amemory andat least one processor that is coupled to the memory and operative to perform exemplary method steps. Yet further, in another 49 EP 4 679 300 A2 5 10 15 20 25 30 35 40 45 50 55 aspect, one ormore implementations and clauses of the technology disclosed or elements thereof can be implemented in the form of means for carrying out one or more of themethod steps described herein; the means can include (i) hardware module(s), (ii) software module(s) executing on one or more hardware processors, or (iii) a combination of hardware and softwaremodules; any of (i)‑(iii) implement the specific techniques set forth herein, and the softwaremodules are stored in a computer readable storage medium (or multiple such media).

[0383] The clauses described in this section can be combined as features. In the interest of conciseness, the combinations of features are not individually enumerated and are not repeated with each base set of features. The reader will understand how features identified in the clauses described in this section can readily be combinedwith sets of base features identified as implementations in other sections of this application. These clauses are not meant to be mutually exclusive, exhaustive, or restrictive; and the technology disclosed is not limited to these clauses but rather encompasses all possible combinations, modifications, and variations within the scope of the claimed technology and its equivalents.

[0384] Other implementations of the clauses described in this section can include a non-transitory computer readable storagemediumstoring instructions executable by a processor to performany of the clauses described in this section. Yet another implementation of the clauses described in this section can include a system including memory and one or more processors operable to execute instructions, stored in thememory, to perform any of the clauses described in this section.

[0385] We disclose the following clauses: 1. A computer-implemented method of base calling, the method including: accessing a section of an image output by a biosensor, the section of the image including a plurality of pixels depicting intensity emission values from a plurality of clusters within the biosensor and from locations within the biosensor that are adjacent to the plurality of clusters, wherein the plurality of clusters includes a target cluster; convolving the section of the image with a convolution kernel, to generate a featuremap comprising a plurality of features having a corresponding plurality of feature values; assigningaweighted feature value to the target cluster, theweighted feature valuebasedononeormore features values of the plurality of feature values of the feature map; and processing the weighted feature value assigned to the target cluster, to base call the target cluster. 2. The method of clause 1, wherein the section of the image is a first section that is generated from a first portion of a flow cell of the biosensor, wherein the convolution kernel is a first convolution kernel, the plurality of clusters is a first plurality of clusters, theplurality of pixels is a first plurality of pixels, the featuremap is afirst featuremap, theplurality of feature values is a first plurality of feature values, the target cluster is a first target cluster, theweighted feature value is a first weighted feature value, and wherein the method further comprises: accessing a second section of the image output by a second portion of the flow cell of the biosensor, the second section of the image including a second plurality of pixels depicting intensity emission values from a second plurality of clusters within the biosensor and from locations within the biosensor that are adjacent to the second plurality of clusters, wherein the second plurality of clusters includes a second target cluster; convolving the second section of the image with a second convolution kernel that is different from the first convolution kernel, to generate a second feature map comprising a second plurality of features having a corresponding second plurality of feature values; assigning a secondweighted feature value to the second target cluster, the secondweighted feature value based on one or more features values of the second plurality of feature values of the second feature map; and processing the second weighted feature value assigned to the second target cluster, to base call the second target cluster. 3. The method of clause 2, wherein: a tile of theflowcell of thebiosensor isdivided ink×kportions,wherek isapositive integer, andwherein thefirst portion and the second portion are two portions of the k×k portions of the tile. 4. The method of clause 3, wherein k is one of three, five, or nine. 5. The method of any of clauses 1‑4, further comprising: capturing the image within the biosensor using a point and shoot image capturing system. 6. The method of clause 2, wherein: a tileof theflowcell of thebiosensor isdivided in1×kportions,wherek isapositive integer, andwherein thefirst portion 50 EP 4 679 300 A2 5 10 15 20 25 30 35 40 45 50 55 and the second portion are two portions of the 1×k portions of the tile. 7. The method of any of clauses 1‑6, further comprising: capturing the image within the biosensor using a line scan image capturing system. 8. The method of any of clauses 2‑7, wherein: a tile of the flowcell of the biosensor is divided in a plurality of portions, the plurality portions comprising a first type of portions and a second type of portions, the second type of portions interleavedwithin the first type of portions in a periodic manner; the first portion is one of the first type of portions; and the second portion is one of the second type of portions. 9. The method of any of clauses 1‑8, further comprising: capturing the image within the biosensor using one or more CMOS (complementary metal oxide semiconductor) sensors. 10. The method of any of clauses 2‑9, wherein: a tile of the flow cell of the biosensor is divided in a plurality of portions that includes the first portion, the second portion, and a third portion; the first section of the image generated from the first portion of the tile of the flow cell is convolved with the first convolution kernel; the second section of the image generated from the second portion of the tile of the flow cell is convolvedwith the second convolution kernel; and a third section of the image generated from the third portion of the tile of the flow cell is convolved with a third convolution kernel that is different from each of the first and second convolution kernels. 11. Themethodof any of clauses1‑9,wherein the section of the image is a first section that is generated for a first color channel from a first portion of a flow cell, wherein the convolution kernel is a first convolution kernel, the plurality of pixels is a first plurality of pixels, the featuremap is a first featuremap, the plurality of feature values is a first plurality of feature values, theweighted feature value is a firstweighted feature value, andwherein themethod further comprises: accessing a second section of the image that is generated for a second color channel from the first portion of the flowcell, the second section of the image in...

Claims

1. A computer-implemented method comprising: determining coefficients corresponding to a section of a flow cell; accessing an image depicting the section of the flow cell and intensity emissions from a target cluster of concatemers; and generating a base call for the target cluster of concatemers by applying the coefficients to the intensity emissions for the target cluster of concatemers.

2. The computer-implemented method of claim 1, wherein: determining the coefficients comprises determining the coefficients based on one or more specialist coefficients increasing a signal-to-noise ratio for the intensity emissions based on a set of intensity values from images depicting concatemers; and generating the base call for the target cluster of concatemers comprises applying the one or more specialist coefficients from the coefficients to intensity values for the intensity emissions from the target cluster of concatemers.

3. The computer-implemented method of claim 1, further comprising: determining that a location of the target cluster of concatemers within the section of the flow cell is off-centered with a pixel of the image; and generating the base call for the target cluster of concatemers by applying one or more specialist coefficients from the coefficients to intensity values for the intensity emissions from the target cluster of concatemers and accounting for the off-centered location of the target cluster of concatemers.

4. The computer-implemented method of claim 3, wherein the location of the target cluster of concatemers comprises a center of the target cluster of concatemers.

5. The computer-implemented method of claim 1, further comprising: determining weights based on respective locations of the target cluster of concatemers and adjacent clusters of concatemers on the section of the flow cell; and applying one or more specialist coefficients, adjusted according to the respective location of the target cluster of concatemers, from the coefficients to intensity values from the target cluster of concatemers.

6. The computer-implemented method of claim 1, wherein the target cluster of concatemers comprises concatemers created using a rolling circle amplification procedure.

7. The computer-implemented method of claim 1, wherein: the section of the flow cell comprises a lane, a tile, or a sub-tile of the flow cell; and the coefficients comprise lane-specific specialist coefficients, tile-specific specialist coefficients, or sub-tile-specific specialist coefficients.

8. The computer-implemented method of claim 1, further comprising determining the coefficients for an imaging channel of a set of imaging channels.

9. The computer-implemented method of claim 1, wherein: determining the coefficients comprises determining the coefficients based on a set of intensity values from images, for a single sequencing cycle, depicting clusters of concatemers on the section of the flow cell; and generating the base call for the target cluster of concatemers comprises applying a one or more specialist coefficients, for the single sequencing cycle, from the coefficients to intensity values for the intensity emissions from the target cluster of concatemers.

10. The computer-implemented method of claim 1, wherein: determining the coefficients comprises determining the coefficients based on a set of intensity values from images, for a set of sequencing cycles, depicting clusters of concatemers on the section of the flow cell; and generating the base call for the target cluster of concatemers comprises applying a one or more specialist coefficients, for the set of sequencing cycles, from the coefficients to intensity values for the intensity emissions from the target cluster of concatemers.

11. The computer-implemented method of claim 1, further comprising: configuring the coefficients for at least one of an unpatterned flow cell configuration or a patterned flow cell configuration.

12. The computer-implemented method of claim 1, further comprising: generating a feature map by applying the coefficients to the section of the image; and generating the base call for the target cluster of concatemers based on the feature map.

13. The computer-implemented method of claim 12, further comprising: applying one or more interpolation operations to the feature map to generate the base call for the target cluster of concatemers.

14. A non-transitory computer readable storage medium storing computer readable instructions configured to cause system to perform a method according to any one of claims 1-13.

15. A system including one or more processors coupled to memory loaded with computer instructions that, when executed on the one or more processors, implement actions comprising a method according to any one of claims 1-13.

Images