Machine learning model for recalibrating genotype detection from existing sequencing data files

Abstract

The present disclosure describes methods, non-transitory computer-readable media, and systems that may utilize a machine learning model to recalibrate genotype detection (e.g., variant detection) of existing sequencing data files. For example, the disclosed system may access one or more existing sequencing data files of a genomic sample, where the files include nucleotide read data and genotype detections at particular genomic coordinates. The disclosed system extracts sequencing metrics for nucleotide reads at particular genomic coordinates or particular genotype detection from the one or more existing sequencing data files. By processing the extracted sequencing metrics, the system further utilizes the detection recalibration machine learning model to generate a variant detection classification indicative of the accuracy of the particular genotype detection. In some cases, the system updates or recalibrates the genotype detection or a quality measurement sequencing metric for the genotype detection based on the variant detection classification.

Description

[0001] CROSS-REFERENCE TO RELATED APPLICATIONS

[0002] This application claims priority to and the benefit of U.S. Provisional Patent Application No. 63 / 499,845, filed on May 3, 2023, entitled “MACHINE LEARNING MODEL FOR RECALIBRATING GENOTYPECALLS FROM EXISTING SEQUENCING DATA FILES,” which is incorporated herein by reference in its entirety. Background Art

[0003] In recent years, biotechnology companies and research institutions have improved the hardware and software for sequencing nucleotides and determining variant detection of genomic samples. For example, some existing nucleotide base sequencing platforms determine the individual nucleotide bases in the sequence by using conventional Sanger sequencing or by using sequencing by synthesis (SBS) methods. When using SBS, existing platforms can monitor thousands to millions of nucleic acid polymers synthesized in parallel to predict nucleotide base detection based on larger base detection data sets. For example, cameras in many SBS platforms capture images of irradiated fluorescent labels incorporated into oligonucleotides for determining nucleotide base detection. After capturing such images, existing SBS platforms send base detection data (or image-based data) to a computing device to apply sequencing data analysis software that determines the nucleotide base sequence of nucleic acid polymers. Based on the differences between the aligned nucleotide reads and the reference genome, existing systems can further utilize variant detectors to identify variants of genomic samples, such as single nucleotide polymorphisms (SNPs), insertions or deletions (indels) and / or other structural variants and genotype detection.

[0004] Despite these recent advances in sequencing and variant calling, existing nucleotide base sequencing platforms and sequencing data analysis software (hereinafter collectively referred to as existing sequencing systems) typically determine or update models for determining variant calls (these models require considerable computing resources), or perform variant callers that inaccurately determine nucleotide base calls or corresponding variant calls. For example, some existing sequencing systems utilize overly complex models that inefficiently expend considerable computing resources (typically requiring considerable computer processing runtime) to accurately determine base calls or variant calls. For example, some existing sequencing systems utilize variant callers with deep learning architectures or some other neural network architectures that require a large amount of computing resources (e.g., computing time, processing power, and memory) to train and apply. For example, some existing sequencing systems utilize deep learning architectures that take many hours across multiple computing devices to generate genotype calls for a single sample sequence even after training.

[0005] In contrast to some deep learning architectures, some machine learning-based variant detectors have been developed, which accurately determine variant calls by processing various features of both nucleotide reads and reference genomes. However, some such machine learning-based variant detectors are limited to specific types of processors. For example, some existing machine learning-based variant detectors can only be executed on field programmable gate arrays (FPGAs) or similar processing systems. Due to such technical limitations, such existing machine learning-based variant detectors are generally not executed on remote servers running more mainstream processors (such as one or more of a central processing unit (CPU) or a graphics processing unit (GPU)).

[0006] However, as machine learning-based variant callers have been updated or newly introduced, some existing sequencing systems resequence or regenerate variant call files for existing sequencing data sets to take advantage of the improved accuracy of the newer variant callers. Although resequencing or regenerating variant call files using updated versions or newer machine learning-based variant callers generally improves variant call accuracy, such resequencing or regeneration methods can double or triple the computational resources required to determine accurate variant calls for a given genomic sample. For example, for a database of more than 100,000 genomic samples running on a previous version of the variant calling model, the computational runtime of a new version of the machine learning-based variant caller to determine variant calls based on read segment data can reach 2 million hours, 20 minutes per genomic sample.

[0007] Although computing time and other resources are required to perform machine learning-based variant detectors on previously detected genomic samples, some existing sequencing systems consume such computing resources because the accuracy of variant detection by such systems can have significant diagnostic or research consequences. In some cases, for example, existing sequencing systems apply variant detectors that inaccurately identify an excessive number of false-negative variant detections. To illustrate, existing sequencing systems sometimes determine that a genomic coordinate exhibits a homozygous reference genotype (and therefore does not include a variant) when, in fact, the genomic coordinate includes a variant. In fact, existing variant detectors achieve a certain degree of accuracy, but due to their limitations, there is still room for improvement in recovering false-negative variant detection. To illustrate the impact of such inaccuracies, variant detection that identifies a specific single nucleotide polymorphism (SNP) in the hemoglobin beta (HBB) gene can be of great significance. For example, when a variant detector identifies a SNP at rs344 on chromosome 11, the variant detector can either correctly identify the genetic cause of sickle cell anemia or miss the cause of the disease. As another example, a variant call that correctly or incorrectly identifies a deletion of one or more copies of the hemoglobin subunit alpha 1 (HbA1) gene or the hemoglobin subunit alpha 2 (HbA2) gene can result in correctly identifying the genetic cause of an inherited blood disorder or completely missing the gene deletion.

[0008] As a contributing factor to the above-mentioned inaccuracies, many existing sequencing systems utilize only limited data sets in determining nucleotide base calls. For example, existing sequencing systems often rely only on information directly extracted from the nucleotide reads of the sample sequence, such as read depth, mismatch counts, sequence alignment scores, and mapping quality, to determine nucleotide base calls. Although sequence information from nucleotide reads can provide valuable insights for determining nucleotide base calls, existing sequencing systems that rely only on these data may perform poorly in accurately determining nucleotide base calls (including variant calls). In fact, some existing sequencing systems that rely on raw sequence data incorrectly determine SNPs, insertions, deletions, or other variants in genomic sample sequences compared to more complex models. In fact, existing sequencing systems often identify false-negative variants or false-positive variants in real challenges of the U.S. Food and Drug Administration (FDA). Summary of the invention

[0009] The present disclosure describes the method, non-transient computer-readable medium and system embodiments that can utilize machine learning models to recalibrate the genotype detection (e.g., variant detection) or variant quality metric of existing sequencing data files. As described below, the disclosed system can access one or more existing sequencing data files of a genomic sample, wherein such existing files include nucleotide read data and genotype detection at specific genomic coordinates. The disclosed system extracts sequencing metrics for nucleotide reads or specific genotype detection at specific genomic coordinates from such existing sequencing data files. By processing the extracted sequencing metrics, the system further utilizes detection to recalibrate the machine learning model to generate variant detection classification indicating the accuracy of specific genotype detection. Based on the variant detection classification, in some cases, the system updates or recalibrates the specific genotype detection or the quality measurement sequencing metric corresponding to the specific genotype detection. After recalibrating the specific genotype detection and other genotype detections of the genomic sample, the disclosed system can output the updated or recalibrated sequencing data file of the genomic sample, such as the updated variant detection file.

[0010] By extracting sequencing metrics for genotype calls from existing sequencing data files, and utilizing the call recalibration machine learning model to generate variant call classifications for updated previously generated genotype calls or corresponding metrics, the disclosed system can improve accuracy, efficiency, and speed relative to existing sequencing systems. Notably, the disclosed system can also avoid the computational expense of re-running the entire machine learning-based variant calling model on the sequencing data of a genomic sample to determine an updated genotype call or an updated quality measurement sequencing metric for the genomic sample, as some existing sequencing systems must do. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] The detailed description refers to the accompanying drawings which are briefly described below.

[0012] Figure 1 A block diagram of a sequencing system including a call recalibration system according to one or more embodiments is illustrated.

[0013] Figure 2A An overview of (i) processing base call data of a genomic sample by an original call generation model to produce an original sequencing data file and (ii) reprocessing the base call data by an updated call generation model through a call recalibration machine learning model of the genomic sample to generate an updated sequencing data file according to one or more embodiments is illustrated.

[0014] Figure 2BA call recalibration system according to one or more embodiments is illustrated to analyze information from a raw sequencing data file using a call recalibration machine learning model to generate a summary of a recalibrated sequencing data file.

[0015] Figure 3 A call recalibration system according to one or more embodiments is illustrated, which receives an existing sequencing data file, extracts sequencing metrics therefrom, generates a variant call classification based on the extracted sequencing metrics, and generates a recalibrated sequencing data file (e.g., an updated variant call file) based on the variant call classification.

[0016] FIG. 4A to FIG. 4C A call recalibration system is illustrated that identifies or extracts sequencing metrics from existing sequencing data files or external sources and generates variant call classifications according to one or more embodiments.

[0017] FIG. 5A to FIG. 5C A call recalibration system according to one or more embodiments is illustrated that generates variant call classifications (e.g., genotype probabilities), utilizes a call recalibration machine learning model to generate corresponding recalibrated genotype calls or recalibrated sequencing metrics, and generates a recalibrated genotype call data file including updated genotype calls based on such classifications.

[0018] Figure 6 An example process for training a detection recalibration machine learning model for a detection recalibration system according to one or more embodiments is illustrated.

[0019] Figure 7 Tables describing a computational node and runtime according to one or more embodiments are illustrated for reprocessing base call data for a genomic sample using an updated call generation machine learning model as compared to recalibrating genotype calls for the genomic sample using a call recalibration machine learning model.

[0020] FIG. 8A to FIG. 8B Illustrated is a graph of false positives and false negatives (for SNPs or indels) comparing the results of reprocessing sequencing data using an existing call generation model with the results of recalibrating existing genotype calls using a call recalibration machine learning model according to one or more embodiments.

[0021] Fig. 9 A flow chart illustrating a series of actions for generating a recalibrated sequencing data file according to one or more embodiments.

[0022] Fig.10A block diagram of an example computing device for implementing one or more embodiments of the present disclosure is illustrated. DETAILED DESCRIPTION

[0023] The present disclosure describes an embodiment of a detection recalibration system, which utilizes a detection recalibration machine learning model to recalibrate a genotype detection (e.g., variant detection) or a corresponding sequencing metric for a sample nucleotide sequence. In order to recalibrate such genotype detection or a corresponding metric, the detection recalibration system accesses one or more existing sequencing data files of a genomic sample. Such sequencing data files may include, for example, genotype detection data files such as variant detection format (VCF) files and / or alignment data files such as binary alignment maps (BAM) files or reference-oriented compressed alignment maps (CRAM) files). By processing the sequencing metrics extracted from the existing sequencing data files via the detection recalibration machine learning model, the detection recalibration system can generate a variant detection classification or prediction for confirmation, recalibration, or modification of the genotype detection previously generated by the detection generation model. Based on the variant call classification or prediction, the call recalibration system can also confirm or update various sequencing metrics of previously generated genotype calls, such as call quality, genotype associated with the call, genotype quality associated with the genotype, PHRED scaled likelihood (PL), and / or other metrics with corresponding fields. By utilizing the call recalibration machine learning model to update the sequencing metrics, the call recalibration system can improve the confidence or reliability of the updated genotype call or confirmed genotype call at a specific genomic coordinate.

[0024] As mentioned above, in some embodiments, the detection recalibration system identifies sequencing metrics for previously generated genotype calls. For example, the detection recalibration system extracts or determines sequencing metrics for a sample nucleotide sequence from one or more existing sequencing data files based on one or more existing sequencing data files. In detail, in certain specific implementations, the detection recalibration system extracts or determines different types of sequencing metrics associated with different sources from one or more existing sequencing data files. For example, the detection recalibration system extracts or determines sequencing metrics based on reads, including metrics of nucleotide reads derived from sample nucleotide sequences. In some embodiments, for example, the detection recalibration system extracts sequencing metrics based on reads from sequencing data files including nucleotide reads of sample nucleotide sequences, such as alignment data files (e.g., binary alignment maps (BAM) files or reference-oriented compressed alignment maps (CRAM) files).

[0025] In addition, in some embodiments, the call recalibration system extracts or determines the sequencing metrics generated by the call model generated via the variant caller or other call generation model, such as variables that are internal to the call recalibration system and are not accessible to other systems or other parties (e.g., proprietary quality scores, base contexts, read filtering, proprietary hypothesis scores, and other metrics). In some specific implementations, the call recalibration system extracts at least some of the sequencing metrics generated by the call model from a genotype call data file such as a variant call format (VCF) file or a genomic variant call format (gVCF) file.

[0026] In addition to sequencing metrics based on reads or generated by detection models, in some specific implementations, the detection recalibration system derives or reconstructs one or more sequencing metrics in the sequencing metrics, such as by reconstructing sequencing metrics generated by one or more detection models that are not explicitly written to the sequencing data file (stored in the sequencing data file) from other information stored in the sequencing data file. In fact, in some cases, the detection recalibration system determines the sequencing metrics generated by the detection model in the form of variant detection sequencing metrics and mapping and alignment sequencing metrics, some of which are derived from one or more existing sequencing data files in various formats or otherwise determined. For example, in some embodiments, the detection recalibration system estimates the alignment of each read in a sequencing data file (e.g., an alignment data file) with a reference genome using Concise Specific Gap Alignment Report (CIGAR) rather than relying on a hidden Markov model (HMM) score for each read.

[0027] Furthermore, in some embodiments, the call recalibration system extracts or determines sequencing metrics from external sources identified according to one or more external databases, the sequencing metrics from these external sources indicating various nucleotide attributes, mapping challenges, and genomic sequences associated with sequencing biases. Alternatively or additionally, the call recalibration system extracts or determines sequencing metrics from external sources stored within an existing sequencing data file.

[0028] In certain embodiments, by processing the extracted sequencing metrics or the reconstructed sequencing metrics, the call recalibration system generates a set of predictive classifications, based on which the system can modify or improve a given genotype call or a field associated with the given genotype call. More specifically, in some embodiments, the call recalibration system uses a call recalibration machine learning model to generate a set of variant call classifications based on the sequencing metrics, which affect or reflect the accuracy of identifying variants at specific genomic coordinates. Depending on the type of genomic coordinates, the call recalibration system can use a specially trained version of the call recalibration machine learning model to, for example, generate (i) variant call classifications for multi-allelic coordinates that are different from (ii) certain variant call classifications from different versions of the call recalibration machine learning model for haploid coordinates or reference coordinates that would be false homozygous.

[0029] For example, when an existing genotype call is used to generate a variant call classification for a multi-allelic genomic coordinate, the call recalibration system can use the call recalibration machine learning model to generate a set of variant call classifications, which variant call classifications include: (i) the reference probability that the genotype call includes a homozygous reference genotype at the multi-allelic genomic coordinate; (ii) the probability of a zygosity error that the genotype call includes a genotype zygosity error at the multi-allelic genomic coordinate; and (iii) the probability of a true positive variant that the genotype call constitutes a true positive variant at the multi-allelic genomic coordinate. For another example, for a haploid genomic coordinate with an existing genotype call, the call recalibration system can use the call recalibration machine learning model to generate a set of variant call classifications, which variant call classifications include: (i) a first genotype probability of a first genotype at the genomic coordinate; and (ii) a second genotype probability of a second genotype at the genomic coordinate. Additionally, for reference coordinates that will be homozygous, the call recalibration system can utilize the call recalibration machine learning model to generate a set of variant call classifications, which variant call classifications include: (i) a false positive probability that the genotype call is a false positive variant; (ii) a zygosity error probability that the genotype call includes a genotype zygosity error (e.g., the probability of identifying the correct alternative allele but with a genotype zygosity error (e.g., 0 / 1 instead of 1 / 1 or 1 / 1 instead of 0 / 1), or the probability of incorrectly identifying the genotype of a nucleotide base call); and (iii) a true positive probability (e.g., a homozygous alternative classification indicating the probability that the genotype call includes a true positive variant).

[0030] Based on the variant call classification, the call recalibration system can confirm, modify or update the genotype call or sequencing metric corresponding to one or more genotype calls (e.g., variant calls or non-variant calls) of the genomic coordinates. For example, the call recalibration system uses the variant call classification to update the genotype data field within the genotype call data file (e.g., variant call format file or other base call output file) indicating or representing the updated genotype call with improved accuracy. As noted above, in certain specific implementations, the call recalibration system updates the genotype call of specific genomic coordinates such as multi-allelic genomic coordinates, haploid genomic coordinates, and / or homozygous reference coordinates that will be incorrectly identified (e.g., genomic coordinates that were previously incorrectly identified by the variant caller as exhibiting a homozygous reference genotype).

[0031] For example, in some embodiments, the call recalibration system utilizes (i) sequencing metrics extracted or determined from one or more existing sequencing data files and (ii) a call recalibration machine learning model to modify data fields corresponding to existing variant call files (or other genotype call data files) for genotype calls. For example, the call recalibration system updates one or more of the base call quality metrics, genotype probability metrics, genotype likelihood metrics, or genotype quality metrics for genotype calls in corresponding fields of the VCF or other sequencing data files. When the call recalibration system determines that the modified base call quality metric (e.g., Q score) or other confidence score fails to meet a threshold, the call recalibration system may annotate the genotype call within the recalibrated VCF or other recalibrated sequencing data file to indicate that the modified metric or score falls below a base call quality threshold or other metric or score threshold.

[0032] As mentioned above, the call recalibration system provides several advantages, benefits and / or improvements over existing sequencing systems (including variant detectors and other sequencing data analysis software). For example, the call recalibration system confirms or modifies genotype calls (or corresponding sequencing metrics) with less computational runtime than existing sequencing systems that implement machine learning-based variant detectors. For example, by extracting sequencing metrics from existing sequencing data files to analyze genotype calls and associated sequencing data, the call recalibration system significantly improves processing runtime relative to existing sequencing systems that reanalyze nucleotide read data using new or updated call generation machine learning models. In some specific implementations, for example, the call recalibration system exhibits a 65% reduction in runtime for sequencing each genomic sample compared to reanalyzing the corresponding sequencing data using an existing call generation machine learning model. The present disclosure further illustrates the following corresponding to at least FIG. 2A to FIG. 2B and Figure 7 of such improved computational runtime.

[0033] The efficiency and speed improvements of the detection recalibration system are particularly obvious relative to the variant detector based on machine learning using a deep learning architecture. As described above, some existing sequencing systems utilize computationally expensive and slow neural network architectures (e.g., deep learning architectures such as convolutional neural networks), which require many hours (e.g., 5-8 hours in the case of executing multiple processors on a server) and a large amount of computing resources to even implement and generate files with variant calls from sequencing runs. This deep learning architecture may also require several days (or weeks) to train. In contrast, the detection recalibration system utilizes a relatively lightweight, fast architecture for detecting and recalibrating machine learning models. Contrary to the many hours across multiple processors required for existing sequencing systems, in many cases, the detection recalibration system requires less than 10 minutes of runtime on a general-purpose CPU to recalibrate the nucleotide base calls of the sample nucleotide sequence. Therefore, the detection recalibration system is much faster and computationally inexpensive than many deep learning methods for variant calls.

[0034] In addition to accelerated computer processing, in some embodiments, the detection recalibration system increases processing flexibility, using which the sequencing system can use a machine learning model to determine, modify or update genotype detection or corresponding sequencing metrics. As noted above, some existing variant detectors based on machine learning are, for example, run exclusively on field programmable gate arrays (FPGAs) or other hardware accelerators. In contrast, in one or more embodiments, the detection recalibration machine learning model of the detection recalibration system can be run on a general processing unit, such as but not limited to one or more of a central processing unit (CPU) or a graphics processing unit (GPU). By training the detection recalibration machine learning model to modify and / or update the genotype detection in the existing sequencing data file, the detection recalibration system can be implemented with significantly fewer computing resources than the existing sequencing system that generates or regenerates genotype detection using the detection generation machine learning model. Therefore, the detection recalibration system can also be implemented with fewer processing cores and less processing memory. In one or more specific implementations, for example, the call recalibration system has demonstrated the aforementioned faster runtime while requiring one-third of the processing cores and half of the processing memory as compared to reanalysis with existing machine learning-based variant callers, resulting in reduced costs. The present disclosure further exemplifies the following disclosure regarding at least Figure 7 of such improved processing flexibility.

[0035] In addition to improved runtime and flexibility, the detection recalibration system also improves the accuracy of genotype detection or corresponding sequencing metrics of existing sequencing data files from genomic samples. In one or more embodiments, for example, based on sequencing metrics extracted from one or more existing sequencing data files, the detection recalibration system can use the detection recalibration machine learning model to update the genotype detection or the corresponding base detection quality metric, genotype probability metric, genotype possibility metric or genotype quality metric of the genotype detection. By using the detection recalibration machine learning model to update the genotype detection based on the extracted sequencing metrics, the detection recalibration system can improve the accuracy of genotype detection at biallelic genomic coordinates, multi-allelic genomic coordinates or haploid coordinates. The detection recalibration system can also recover (i.e., correct) false negative variant detection and false positive variant detection reported in existing sequencing data files. The present disclosure further illustrates the following about at least FIG. 8A to FIG. 8B of this type of improved accuracy.

[0036] As suggested in the foregoing discussion, the present disclosure utilizes a variety of terms to describe the features and advantages of the detection recalibration system. Additional details regarding the meaning of these terms used in the present disclosure are provided below. As used in the present disclosure, for example, the term "sample nucleotide sequence" or "sample sequence" refers to a nucleotide sequence isolated or extracted from a sample organism (or a copy of such an isolated or extracted sequence). Specifically, the sample nucleotide sequence includes a fragment of a nucleic acid polymer that is isolated or extracted from a sample organism and consists of nitrogen-containing heterocyclic bases. For example, the sample nucleotide sequence may include a fragment or molecule of deoxyribonucleic acid (DNA), ribonucleic acid (RNA), or other polymeric forms of nucleic acids or chimeric or hybrid forms of nucleic acids described below. More specifically, in some cases, the sample nucleotide sequence is present in a sample prepared or separated by a kit and received by a sequencing device.

[0037] Relatedly, as used herein, the term "genomic sample" refers to a target genome or a portion of a genome that is subjected to determination or sequencing. For example, a genomic sample includes one or more nucleotide sequences (or a copy of such a separated or extracted sequence) separated or extracted from a sample organism. Specifically, a genomic sample includes a full genome separated or extracted (in whole or in part) from a sample organism and composed of nitrogen-containing heterocyclic bases. A genomic sample may include fragments or molecules of deoxyribonucleic acid (DNA), ribonucleic acid (RNA), or other polymeric forms of nucleic acids or chimeric or heterozygous forms of nucleic acids described below. In some cases, a genomic sample is present in a sample prepared or separated by a kit and received by a sequencing device.

[0038] As further used herein, the term "genotype detection" refers to determining or predicting the specific genotype of a genomic sample at a genomic locus. Specifically, genotype detection may include predicting the specific genotype of a genomic sample relative to a reference genome or reference sequence at a genomic coordinate or genomic region. For example, in some cases, genotype detection includes determining or predicting that a genomic sample includes both a nuclear base and a complementary nuclear base at a genomic coordinate, and the genomic coordinate is homozygous or heterozygous for a reference base or variant (for example, a homozygous reference base is expressed as 0|0, or heterozygous for a variant on a specific chain, expressed as 0|1). Therefore, genotype detection may include predicting variants or reference bases of one or more alleles of a genomic sample, and indicating the zygosity of a variant or a reference base. Genotype detection is typically determined for genomic coordinates or genomic regions, at which SNPs, insertions, deletions or other variants have been identified for an organism population.

[0039] As further used herein, the term "nucleotide base call" (or simply "base call") refers to the determination or prediction of a specific nucleobase (or nucleobase pair) of a genomic coordinate of an oligonucleotide (e.g., a nucleotide read) or a sample genome during a sequencing cycle. Specifically, a nucleobase call can indicate: (i) the determination or prediction of the type of nucleobase that has been incorporated into an oligonucleotide on a nucleotide sample slide (e.g., a read-based nucleobase call); or (ii) the determination or prediction of the type of nucleobase present at a genomic coordinate or region within a genome, including variant calls or non-variant calls in a digital output file. In some cases, for a nucleotide read, a nucleobase call includes determining or predicting a nucleobase based on an intensity value generated by a fluorescently labeled nucleotide of an oligonucleotide added to a nucleotide sample slide (e.g., in a cluster of a flow cell). Alternatively, a nucleobase call includes determining or predicting a nucleobase based on chromatographic peaks or current changes generated by nucleotides passing through a nanopore of a nucleotide sample slide. In contrast, based on the nucleotide reads corresponding to the genomic coordinates, the nucleobase call may also include the nucleobase at the genomic coordinates of the sample genome of the final predicted variant call file (VCF) or another base call output file. Thus, the nucleobase call may include base calls corresponding to the genomic coordinates and the reference genome, such as an indication of a variant or non-variant at a specific position corresponding to the reference genome. In practice, the nucleobase call may refer to a variant call, including but not limited to a single nucleotide variant (SNV), an insertion or deletion (indel), or a base call as part of a structural variant. As mentioned above, a single nucleobase call may be an adenine (A) call, a cytosine (C) call, a guanine (G) call, or a thymine (T) call, or a uracil (U) call.

[0040] Relatedly, as used herein, the term "nucleotide read" refers to a sequence of one or more nucleotide bases (or nucleobase pairs) inferred from all or part of a sample nucleotide sequence (e.g., a sample genomic sequence, complementary DNA). Specifically, a nucleotide read includes a sequence determined or predicted based on a sequencing library corresponding to a genomic sample from a nucleobase call of a nucleotide fragment (or a monoclonal nucleotide fragment group). For example, in some embodiments, a call recalibration system determines nucleotide reads by generating nucleobase calls of nucleobases passing through a nanopore of a nucleotide sample slide, determined via fluorescent labeling, or determined based on holes in a circulation pool. In some cases, a nucleotide read may refer to a specific type of read, such as a nucleotide read synthesized from a sample library fragment shorter than a threshold number of nucleobases (e.g., an SBS read). In these or other cases, another type of nucleotide read may refer to (i) an assembled nucleotide read that has been assembled from shorter nucleotide reads to form a contiguous sequence that satisfies a threshold number of nucleobases (e.g., an assembled nucleotide read), (ii) a cycle consensus sequencing (CCS) read that satisfies a threshold number of nucleobases, or (iii) a nanopore long read that satisfies a threshold number of nucleobases.

[0041] As described above, in some embodiments, the detection recalibration system determines sequencing metrics for nucleotide base calls of nucleotide reads. As used herein, the term "sequencing metric" refers to a quantitative measurement or score that indicates the degree to which a single nucleotide base call (or sequence of nucleotide base calls) is aligned, compared, or quantified relative to a genomic coordinate or genomic region of a reference genome, relative to a nucleotide base call from a nucleotide read, or relative to external genome sequencing or genomic structure. For example, a sequencing metric includes a quantitative measurement or score indicating the extent to which: (i) a single nucleotide base call aligns, maps, or covers a genomic coordinate or reference base of a reference genome; (ii) a nucleotide base call is compared to a reference or alternative nucleotide read in terms of mapping, mismatch, base call quality, or other raw sequencing metrics; or (iii) a genomic coordinate or region corresponding to a nucleotide base call exhibits mappability, repetitive base call content, DNA structure, or other generalized metrics.

[0042] Along these lines, the detection recalibration system determines various types of sequencing metrics from different sources, such as sequencing metrics based on reads, sequencing metrics from external sources, and sequencing metrics generated by detection models. As used herein, the term "sequencing metrics based on reads" refers to sequencing metrics of nucleotide reads derived from sample nucleotide sequences. For example, sequencing metrics based on reads include sequencing metrics determined by applying statistical tests to detect differences between reference sequences and nucleotide reads. In some embodiments, sequencing metrics based on reads may include comparative mapping quality distribution metrics indicating comparisons between mapping qualities or comparative mismatch count metrics indicating comparisons between mismatch counts. In some cases, sequencing metrics based on reads may correspond to genotype calls generated according to different read types (such as assembled nucleotide reads and / or SBS reads).

[0043] In contrast, "sequencing metrics of an external source" refers to sequencing metrics identified or obtained from one or more external databases. For example, sequencing metrics of an external source include metrics related to nucleotide mappability, replication timing, or DNA structure that can be obtained outside of the detection recalibration system.

[0044] In addition, the term "sequencing metrics generated by the detection model" refers to internal, model-specific sequencing metrics generated or extracted by the detection generation model. For example, the sequencing metrics generated by the detection model include variant detection sequencing metrics extracted or determined via the variant detector component of the detection generation model and mapping and alignment sequencing metrics extracted or determined via the mapping and alignment component of the detection generation model. As noted above, the sequencing metrics generated by the detection model may include alignment metrics that quantify the degree of alignment of nucleotide reads to the genomic coordinates of a reference genome or other example nucleic acid sequence, such as a deletion size metric or a mapping quality metric. In addition, the sequencing metrics generated by the detection model may include depth metrics that quantify the depth of nuclear base detection of nucleotide reads at the genomic coordinates of a reference genome or other example nucleic acid sequence, such as a forward-reverse depth metric or a normalized depth metric. The sequencing metrics generated by the detection model may also include detection quality metrics that quantify the quality or accuracy of nuclear base detection, such as nuclear base detection quality metrics, detectability metrics, or somatic cell quality metrics.

[0045] As used herein, the term "base call quality metric" refers to a particular score or other measure that indicates the accuracy of a nucleobase call. Specifically, a base call quality metric includes a value that indicates the likelihood that one or more predicted nucleobase calls for a genomic coordinate contain an error. For example, in certain implementations, a base call quality metric may include a Q score (e.g., PHil's Read EDitor (PHRED) quality score) that predicts the probability of error for any given nucleobase call. For example, a quality score (or Q score) may indicate that the probability of an incorrect nucleobase call at a genomic coordinate is equal to 1:100 for a Q20 score, 1:1,000 for a Q30 score, 1:10,000 for a Q40 score, and so on.

[0046] Relatedly, in some embodiments, the detection recalibration system can generate a sequencing metric by modifying or updating a previous metric. Such a "reengineered sequencing metric" may refer to a sequencing metric that has been updated, modified, amplified, refined, or reengineered to measure or compare a nuclear base call (e.g., a nuclear base call for a read, genotype, or variant call) relative to other nuclear base calls, standards, or references, or for targeting a specific goal or task. For example, the reengineered sequencing metric may include a modification of the original sequencing metric or a combination of the original (e.g., unmodified) sequencing metrics. In some embodiments, for example, the detection recalibration system generates one or more of a sequencing metric based on a read, a sequencing metric from an external source, and / or a sequencing metric generated by a detection model as a reengineered sequencing metric. In some cases, the reengineered sequencing metric refers to a sequencing metric generated by the detection recalibration system and is therefore proprietary or internal to the detection recalibration system and unavailable to a third-party system. Example reengineered sequencing metrics include a comparative mapping quality distribution metric indicating a comparison between a mapping quality distribution associated with a reference sequence and alternative supporting nucleotide reads or a comparative base quality metric indicating a comparison between base qualities of a reference sequence and alternative supporting nucleotide reads.

[0047] As further used herein, the term "genomic coordinates" (or sometimes simply "coordinates") refers to a specific position or orientation of a nucleobase within a genome (e.g., a genome of an organism or a reference genome). In some cases, the genomic coordinates include an identifier for a specific chromosome of the genome and an identifier for the orientation of the nucleobase within the specific chromosome. For example, one or more genomic coordinates may include a chromosome number, name, or other identifier (e.g., chr1 or chrX) and one or more specific orientations, such as a numbered orientation after the chromosome identifier (e.g., chr1:1234570 or chr1:1234570-1234870). In some cases, genomic coordinates refer to genomic coordinates on sex chromosomes (e.g., chrX or chrY). Therefore, the detection recalibration system can determine the genotype probability and / or variant detection classification for genotype detection (e.g., variant detection) of genomic coordinates on sex chromosomes. In addition, in some specific implementations, the genomic coordinates refer to the source of the reference genome (e.g., mt for mitochondrial DNA reference genome or SARS-CoV-2 for SARS-CoV-2 virus reference genome) and the position of the base in the source of the reference genome (e.g., mt: 16568 or SARS-CoV-2: 29001). In contrast, in some cases, the genomic coordinates refer to the position of the base in the reference genome without mentioning the chromosome or source (e.g., 29727).

[0048] Relatedly, as used herein, the term "multi-allelic genomic coordinates" refers to genomic coordinates associated with three or more alleles. For example, multi-allelic genomic coordinates include genomic coordinates of a nucleotide sequence, wherein the nucleotide reads indicate three or more possible alleles corresponding to the coordinates, such as a reference allele, a first alternative allele, a second alternative allele, etc. In some cases, multi-allelic genomic coordinates correspond to genomic coordinates in which reads are piled up or insertions occur. For example, multi-allelic genomic coordinates can show multi-allelic genotypes (such as 1 / 2 genotypes), wherein the first allele at the coordinates corresponds to an allele from a first alternative nucleotide sequence, and the second allele corresponds to an allele from a second alternative nucleotide sequence.

[0049] As noted above, the genomic coordinates within a nucleotide sequence can show different genotypes. For example, "homozygous reference genotype" refers to a genotype (expressed as 0 / 0) where two nucleotide bases at a given coordinate of a sample nucleotide sequence match a reference sequence or a reference genome. For another example, "homozygous alternative genotype" refers to a genotype (expressed as 1 / 1) where two nucleotide bases at a given coordinate are different from the reference nucleotide bases of a reference sequence or a reference genome. For another example, "heterozygous genotype" refers to a genotype where the nucleotide bases at a given coordinate are different. In some cases, a heterozygous genotype includes a genotype (expressed as 0 / 1 or 1 / 0) where one nucleotide base matches a reference nucleotide base and another nucleotide base matches a reference nucleotide base. For multi-allelic genomic coordinates, a genotype can show a nucleotide base different from a reference nucleotide base of a reference genome from more than one alternative nucleotide base. For example, a multi-allelic heterozygous genotype can be represented as 1 / 2, where one nucleotide base call matches a first alternative nucleotide base that is different from a reference nucleotide base and another nucleotide base call matches a second alternative nucleotide base that is different from the reference nucleotide base.

[0050] As mentioned above, genome coordinates include reference genome positions. Such positions may be within a specific reference genome. As used herein, the term "reference genome" refers to a digital nucleic acid sequence assembled as a representative example (or multiple representative examples) of genes and other genetic sequences of an organism. Regardless of sequence length, in some cases, a reference genome represents an example set of genes or a set of nucleic acid sequences determined by scientists to represent a specific species in a digital nucleic acid sequence of an organism. For example, a linear human reference genome may be GRCh38 or other versions of a reference genome from a genome reference consortium. In addition, a reference genome may include a reference map genome containing a linear reference genome and a path representing a nucleic acid sequence from an ancestral haplotype, such as an Illumina DRAGEN map reference genome hg19.

[0051] As mentioned above, the detection recalibration system can use a machine learning model to modify the sequencing metrics and update the genotype detection. As used herein, the term "machine learning model" refers to a computer algorithm or a collection of computer algorithms that automatically improve a specific task through experience based on data use. For example, a machine learning model can use one or more learning techniques to improve accuracy and / or effectiveness. Example machine learning models include various types of decision trees, support vector machines, Bayesian networks, or neural networks. In some cases, the detection recalibration machine learning model is a series of gradient boosted decision trees (e.g., XGBoost algorithm), while in other cases, the detection recalibration machine learning model is a random forest model, a multilayer perceptron, a linear regression, a support vector machine, a deep table learning architecture, a deep learning transformer (e.g., a table transformer based on self-attention) or a logistic regression.

[0052] In some cases, the detection recalibration system generates an output using a detection recalibration machine learning model for confirming, modifying or updating genotype detection based on the extracted sequencing metrics. As used herein, the term "detection recalibration machine learning model" refers to a machine learning model that generates variant detection classifications. For example, in some cases, the detection recalibration machine learning model is trained to generate various probabilities or predicted variant detection classifications indicating genotype detection (e.g., variant detection) based on the extracted sequencing metrics. Therefore, in some cases, the detection recalibration machine learning model is a variant detection recalibration machine learning model. In some cases, the detection recalibration machine learning model is a series of gradient boosting decision trees (e.g., XGBoost algorithm or Treelite algorithm for decision tree ensembles), and in other cases, the detection recalibration machine learning model is a random forest model, a multilayer perceptron, a linear regression, a support vector machine, a deep table learning architecture, a deep learning transformer (e.g., a table transformer based on self-attention) or a logistic regression. In certain embodiments, the detection recalibration machine learning model includes multiple sub-models or operates in conjunction with another detection recalibration machine learning model. For example, a first call recalibration machine learning model (e.g., an ensemble of gradient boosted trees) generates a first set of variant call classifications, and a second call recalibration machine learning model (e.g., a random forest) generates a second set of variant call classifications.

[0053] Relatedly, the term "variant call classification" refers to a predictive classification from a call recalibration machine learning model that indicates a probability, score, or other quantitative metric associated with some aspect of a genotype call based on one or more sequencing metrics extracted from one or more sequencing data files. Depending on the application of the call recalibration machine learning model, the variant call classification may include a specialized prediction. In some cases, the variant call classification for a bi-allelic genomic coordinate includes: (i) a false positive probability that a genotype call is a false positive; (ii) a genotype error probability that the genotype of the genotype call is incorrect; and (iii) a true positive probability that the genotype call is a true positive. For example, in an embodiment of a genotype call for generating multi-allelic genomic coordinates, the variant call classification may include: (i) a reference probability that a genotype call includes a homozygous reference genotype at a multi-allelic genomic coordinate; (ii) a zygosity error probability that the genotype call includes a genotype zygosity error at a multi-allelic genomic coordinate; and (iii) a true positive variant probability that the genotype call constitutes a true positive variant at a multi-allelic genomic coordinate.

[0054] In an embodiment for generating a genotype call for a haploid genomic coordinate, a variant call classification may include: (i) a first genotype probability of a first genotype at the genomic coordinate; and (ii) a second genotype probability of a second genotype at the genomic coordinate. As proposed above, the first genotype probability may be the probability that the genotype at the genomic coordinate is a haploid reference genotype, and the second genotype probability may be the probability that the genotype at the genomic coordinate is a haploid alternative genotype. In these or other embodiments (such as embodiments for generating a genotype call for a genomic coordinate indicated as exhibiting a homozygous reference genotype), a variant call classification may include: (i) a false positive probability or a homozygous reference classification indicating that the genotype call is a false positive or homozygous reference genotype, respectively; (ii) a zygosity error probability or a heterozygous genotype classification indicating that the genotype (e.g., an indication of a heterozygous genotype or a homozygous genotype of a variant call at a specific position) is incorrect or is a probability of a heterozygous genotype, respectively; and / or (iii) a true positive classification or a homozygous alternative classification indicating that the genotype call is a true positive or homozygous alternative genotype, respectively. In some cases, the variant call classification thus represents an intermediate scoring metric and / or the predicted probability that the genotype of the genotype call is accurate.

[0055] Therefore, as further used herein, the term "genotype probability" refers to the possibility, probability or score of a specific genotype at a genomic coordinate or genomic region. For example, the genotype probability includes the possibility of a homozygous reference genotype at one or more genomic coordinates, the possibility of a heterozygous variant genotype, or the possibility of a homozygous variant genotype. In some cases, the genotype probability may refer to the posterior genotype probability. Therefore, in some cases, the genotype probability determined by the detection recalibration machine learning model may be presented in (or modified to be presented in) a posterior genotype probability (GP) field of a VCF or other sequencing data file (such as a recalibrated VCF or other recalibrated sequencing data file). Depending on the application of the detection recalibration machine learning model (such as for predicting SNPs), the genotype probability may include a special prediction.

[0056] As mentioned, in some embodiments, the detection recalibration machine learning model may include a neural network. The term "neural network" refers to a machine learning model that can be trained and / or adjusted based on inputs to determine classification or approximate unknown functions. For example, a neural network includes a model of interconnected artificial neurons (e.g., organized in layers) that communicate and learn to approximate complex functions and generate outputs (e.g., generated digital images) based on multiple inputs provided to the neural network. In some cases, a neural network refers to an algorithm (or set of algorithms) that implements deep learning techniques to model high-level abstractions in data. For example, a neural network may include a convolutional neural network, a recursive neural network (e.g., an LSTM), a graph neural network, a self-attention transformer neural network, or a generative adversarial neural network.

[0057] As described above, the detection recalibration system can generate variant detection classifications indicating or reflecting the possibility of identifying variants at genomic coordinates. As used herein, the term "variant" refers to one or more nucleobases that are not aligned, different or changed with a corresponding nucleobase (or multiple nucleobases) in a reference sequence or reference genome. For example, variants include SNPs, insertions and deletions, or structural variants, which indicate nucleobases different from the nucleobases in the corresponding genomic coordinates of the reference sequence in the sample nucleotide sequence. According to these ideas, "variant nucleotide base detection" (or simply "variant detection") refers to the nucleotide base detection of variants including specific genomic coordinates. On the contrary, "non-variant nucleotide base detection" (or simply "non-variant detection") refers to the nucleotide base detection of non-variants including genomic coordinates.

[0058] As mentioned, in one or more embodiments, the detection recalibration system extracts or determines sequencing metrics from one or more existing sequencing data files. As used herein, the term "sequencing data file" refers to a digital file comprising genetic sequencing information about genotype calls or nucleotide reads generated by one or more genome sequencing procedures. Such sequencing information may include, for example, nucleotide reads, alignment and mapping information, nucleotide reads at one or more genomic coordinates, and the like. In some embodiments, the detection recalibration system accesses multiple sequencing data files to extract or determine sequencing metrics, such as alignment data files and genotype detection data files. In one or more embodiments, the detection recalibration system accesses sequencing data files including all sequencing information in the above-mentioned sequencing information merged into a single file.

[0059] As mentioned, in some embodiments, the call recalibration system modifies data fields corresponding to a genotype call data file (such as a variant call file). As used herein, the term "genotype call data file" refers to a digital file indicating or representing one or more genotype calls (e.g., including reference calls and / or variant calls) compared to a reference genome and other information related to the genotype call (e.g., variant call). For example, a genotype call data file may include a variant call file, such as, but not limited to, a variant call format (VCF) file (and a genomic variant call format (gVCF) file). Alternatively, for example, a genotype call data file may include a general feature format (GFF), a genomic variant format (GVF), or other suitable data files including genotype calls of a sample nucleotide sequence.

[0060] As further used herein, a "variant call file" refers to a specific genotype call data file including a text file format that contains information about variants at specific genomic coordinates. For example, a variant call file may include a meta information row, a header row, and a data row, wherein each data row contains information about a single genotype call (e.g., a single variant). As further described below, the call recalibration system can generate different versions of a genotype call data file, including a pre-filtered variant call file or a post-filtered variant call file, wherein the pre-filtered variant call file includes variant genotype calls that pass or fail a quality filter of a base call quality metric, and the post-filtered variant call file includes variant genotype calls that pass a quality filter but excludes variant genotype calls that fail a quality filter.

[0061] As further mentioned, in one or more embodiments, the one or more sequencing data files from which the detection recalibration system extracts or determines sequencing metrics include an alignment data file that contains information from read processing and mapping procedures. As used herein, the term "alignment data file" refers to a digital file of mapping and alignment information of nucleotide reads of a sample nucleotide sequence. For example, the alignment data file may include a binary alignment map (BAM) file, a reference-oriented compressed alignment map (CRAM) file, or another file indicating nucleotide reads of a sample nucleotide sequence.

[0062] In some embodiments, the detection recalibration system modifies the data fields corresponding to the metrics of the genotype detection associated with the variant detection file, such as the fields of detection quality, genotype and genotype quality. As used herein, when used relative to the data fields in the variant detection file, the term "detection quality" refers to a measure or indication of the possibility or probability that a variant is present at a given position. Therefore, the detection quality field (or QUAL field) corresponding to the VCF file may include a base detection quality metric such as a PHRED scale quality or Q score, which indicates that the genomic coordinates of the sample genome include the probability of the variant. Similarly, when used relative to a field, "genotype quality" refers to the possibility or probability that a specific predicted genotype of a nuclear base detection is correct.

[0063] As noted, in some embodiments, the call recalibration system extracts or determines sequencing metrics from one or more sequencing data files (such as a genotype call data file containing genotype calls output by a call generation model). As used herein, the term "call generation model" refers to a probability model that generates sequencing data based on nucleotide reads of a sample nucleotide sequence, and the sequencing data includes nuclear base calls, variant calls and / or genotype calls and associated metrics. Therefore, in some cases, the call generation model can be a variant call generation model. For example, in some cases, the call generation model refers to a Bayesian probability model that generates variant calls based on nucleotide reads of a sample nucleotide sequence. Such a model can process or analyze sequencing metrics corresponding to read stacking (e.g., multiple nucleotide reads corresponding to a single genomic coordinate), including mapping quality, base quality, and various assumptions, including foreign reads, missing reads, joint detection, and the like. The call generation model can also include multiple components, including but not limited to different software applications or components for mapping and alignment, sorting, repeat marking, calculating read stacking depth, and variant calls. In some cases, the call generation model refers to the ILLUMINA DRAGEN model for variant calling functions and mapping and alignment functions (e.g., DRAGEN variant caller or "DRAGEN VC").

[0064] The following paragraphs describe the detection recalibration system with respect to illustrative drawings that illustrate example embodiments and implementations. For example, Figure 1 A schematic diagram of a system environment (or "environment") 100 in which a call recalibration system 106 operates according to one or more embodiments is shown. As shown, the environment 100 includes one or more server devices 102 connected to client devices 108 and sequencing devices 114 via a network 112. Figure 1 An embodiment of the checkout recalibration system 106 is shown, but the present disclosure describes alternative embodiments and configurations below.

[0065] like Figure 1 As shown, server device 102, client device 108, and sequencing device 114 can communicate with each other via network 112. Network 112 includes any suitable network over which computing devices can communicate. Fig.10 The example network is discussed in more detail.

[0066] like Figure 1 As indicated, sequencing equipment 114 includes equipment for sequencing nucleic acid polymers. In some embodiments, sequencing equipment 114 analyzes nucleic acid fragments or oligonucleotides extracted from genomic samples to generate nucleotide reads or other data directly or indirectly on sequencing equipment 114 using methods and systems implemented by computers (described herein). More specifically, sequencing equipment 114 receives and analyzes nucleic acid sequences extracted from genomic samples in nucleotide sample slides (e.g., circulation cells). In one or more embodiments, sequencing equipment 114 utilizes SBS to sequence nucleic acid polymers into nucleotide reads. As a supplement or alternative to communicating across network 112, in some embodiments, sequencing equipment 114 bypasses network 112 and communicates directly with client device 108.

[0067] like Figure 1 As further indicated, the server device 102 can generate, receive, analyze, store, and transmit electronic data, such as data used to determine nucleotide base calls or sequence nucleic acid polymers. Figure 1 As shown, the sequencing device 114 may send (and the server device 102 may receive) call data from the sequencing device 114. The server device 102 may also communicate with the client device 108. Specifically, the server device 102 may send data to the client device 108, the data including a sequencing data file, such as a genotype call data file or an alignment data file, or other information indicating nucleotide base calls, sequencing metrics, error data, or other metrics associated with nucleotide base calls or genotype calls.

[0068] In some embodiments, the server device 102 comprises a distributed server collection, wherein the server device 102 comprises a number of server devices distributed across the network 112 and located in the same or different physical locations. In addition, the server device 102 may include a content server, an application server, a communication server, a web hosting server, or another type of server. In some cases, the server device 102 is located at the same physical location as the sequencing device 114.

[0069] like Figure 1 As further shown, the server device 102 may include a sequencing system 104. Typically, the sequencing system 104 analyzes call data such as sequencing metrics received from the sequencing device 114 to determine the nucleotide base sequence of the nucleic acid polymer. For example, the sequencing system 104 may receive raw data from the sequencing device 114 and may determine the nucleotide base sequence of a sample nucleotide sequence (e.g., a genomic sample). In some embodiments, the sequencing system 104 determines the sequence of nucleotide bases in DNA and / or RNA fragments or oligonucleotides. In addition to processing and determining the sequence of the nucleic acid polymer, the sequencing system 104 also generates a genotype call data file (such as a variant call file) indicating one or more genotype calls and / or variant calls of one or more genomic coordinates.

[0070] As mentioned, and as Figure 1 As illustrated, the detection recalibration system 106 analyzes the detection data, such as the sequencing metrics from the sequencing device 114 stored in the existing sequencing data file, to recalibrate (e.g., by the detection generation model) the genotype detection of the sample nucleotide sequence previously generated. The detection recalibration system 106 includes a detection recalibration machine learning model. In some embodiments, the detection recalibration system 106 determines the sequencing metrics for the sample nucleotide sequence based on the information stored in the existing sequencing data file. Based on the data derived or prepared from the sequencing metrics, the detection recalibration system 106 trains and applies the detection recalibration machine learning model to recalibrate the genotype detection of the sample sequence corresponding to the genomic coordinates. The detection recalibration system 106 further utilizes the detection recalibration machine learning model to generate a set of variant detection classifications to update or modify the genotype detection (e.g., variant detection). Based on such data, for example, the detection recalibration system 106 can update the data field corresponding to the genotype detection data file (such as a variant detection file) to update the genotype detection (e.g., variant detection) to improve accuracy. In some embodiments, the call recalibration system 106 outputs an updated variant call file (or other format of genotype call data file) having modified or updated genotype calls and / or variant calls.

[0071] like Figure 1As further illustrated and indicated in the , the client device 108 can generate, store, receive, and send digital data. Specifically, the client device 108 can receive sequencing metrics from the sequencing device 114. In addition, the client device 108 can communicate with the server device 102 to receive genotype call data files (such as variant call files) including genotype calls and / or other metrics (such as call quality, genotype indication, and genotype quality). The client device 108 can accordingly present or display information related to genotype calls to a user associated with the client device 108 within a graphical user interface.

[0072] Figure 1 The client device 108 illustrated in the example may include various types of client devices. For example, in some embodiments, the client device 108 includes a non-mobile device, such as a desktop computer or a server, or other types of client devices. In other embodiments, the client device 108 includes a mobile device, such as a laptop, a tablet computer, a mobile phone, or a smart phone. Fig.10 Additional details regarding client device 108 are discussed.

[0073] like Figure 1 As further illustrated in FIG. 1 , the client device 108 includes a sequencing application 110. The sequencing application 110 may be a web application or a native application (e.g., a mobile application, a desktop application) stored and executed on the client device 108. The sequencing application 110 may include instructions that, when executed, cause the client device 108 to receive data from the call recalibration system 106 and present data from the variant call file and / or the updated variant call file for display at the client device 108. In addition, the sequencing application 110 may direct the client device 108 to display a visualization of a sequencing metric for a nucleotide base call or a genotype call.

[0074] like Figure 1As further illustrated in , the detection recalibration system 106 can be located on the client device 108 as part of the sequencing application 110 or on the sequencing device 114. Therefore, in some embodiments, the detection recalibration system 106 is implemented by being located (e.g., completely or partially located) on the client device 108. In yet other embodiments, the detection recalibration system 106 is implemented by one or more other components of the environment 100, such as the sequencing device 114. Specifically, the detection recalibration system 106 can be implemented in a variety of different ways across the server device 102, the network 112, the client device 108, and the sequencing device 114. For example, the detection recalibration system 106 can be downloaded from the server device 102 to the client device 108 and / or the sequencing device 114, wherein all or part of the functionality of the detection recalibration system 106 is executed at each corresponding device within the environment 100.

[0075] like Figure 1 As further illustrated in , environment 100 includes database 116. Database 116 can store information such as sequencing data files 118, sample nucleotide sequences, nucleotide reads, nucleotide base calls, genotype calls (e.g., variant calls), and sequencing metrics. In some embodiments, server device 102, client device 108, and / or sequencing device 114 (e.g., via network 112) communicate with database 116 to store and / or access information such as sequencing data files 118, sample nucleotide sequences, nucleotide reads, nucleotide base calls, genotype calls (e.g., variant calls), and sequencing metrics. In some cases, database 116 also stores one or more models, such as a call recalibration machine learning model.

[0076] although Figure 1 The components of the environment 100 are illustrated as communicating via the network 112, but in some implementations, the components of the environment 100 may also communicate directly with each other, bypassing the network 112. For example, and as previously mentioned, in some implementations, the client device 108 communicates directly with the sequencing device 114. Additionally, in some embodiments, the client device 108 communicates directly with the callout recalibration system 106. Furthermore, the callout recalibration system 106 may access one or more databases housed on or accessed by the server device 102 or located elsewhere in the environment 100.

[0077] As mentioned above, the call recalibration system 106 can generate modified or updated genotype calls based on information extracted or determined from one or more existing sequencing data files. As also mentioned, in some specific implementations, the call recalibration system 106 exhibits improved efficiency and / or accuracy over existing sequencing systems in generating recalibrated and / or improved genotype calls for previously analyzed sample nucleotide sequences.

[0078] To further illustrate, Figure 2A An overview of the existing sequencing system generating updated sequencing data for a previously analyzed sample nucleotide sequencing system is shown. Specifically, Figure 2A Two existing call generation models (call generation model 204a and updated call generation model 204b) are shown, which generate genotype calls based on base call data 202 and output the corresponding genotype calls to corresponding sequencing data files 210a and updated sequencing data files 210b.

[0079] As shown in the illustrated example, existing methods for updating genotype calls and other sequencing information may include reanalyzing data from a sequencing device (such as base call data 202) using an updated call generation model (e.g., a newer call generation model that exhibits improved results) (such as updated call generation model 204b). As mentioned above, in some cases, the updated call generation model 204b includes an updated version of a machine learning-based variant detector that is lacking in the call generation model 204a. In some cases, many sequencing data files (e.g., sequencing data files that include nucleotide base reads of thousands of sample nucleotide sequences) are updated in this manner, thereby requiring a large amount of computing resources to reprocess the base call data for each of the previously analyzed genomic samples.

[0080] For example, as illustrated, analysis of base call data 202 by call generation model 204a includes read processing and mapping procedures 206a and genotype call procedures 208a. When newly analyzed by updated call generation model 204b, the updated analysis typically requires execution of updated read processing and mapping procedures 206b and updated genotype call procedures 208b.

[0081] In contrast, Figure 2BAs shown, the call recalibration system 106 confirms, updates, or modifies genotype calls based on information extracted or determined from an existing sequencing data file 210a previously generated by a call generation model 204a. In other words, the call recalibration system 106 generates a recalibrated sequencing data file 210c without directly reprocessing the base call data 202. Instead, as shown, the call recalibration system 106 utilizes a call recalibration machine learning model 212 to generate a recalibrated sequencing data file 210c based on sequencing metrics extracted or determined from the existing data file 210a. Therefore, by utilizing the trained call recalibration machine learning model 212 to update the sequencing data within the existing sequencing data file 210a, the call recalibration system 106 utilizes the call generation model 204a's previous analysis of the base call data 202, including read segment processing and mapping 206a and genotype calling 208a. As shown in FIG. Figure 7 As shown in the other figures, the detection recalibration system 106 generally follows Figure 2B The procedures in Figure 2A to save significant computer processing runtime and expand the flexibility of processor types used for variant calling.

[0082] As noted above, the call recalibration system 106 can generate variant call classifications based on sequencing metrics extracted or determined from one or more existing sequencing data files. Specifically, the call recalibration system 106 can utilize a call recalibration machine learning model to determine variant call classifications based on the extracted sequencing metrics, and can determine or update various metrics associated with genotype calls based on the generated variant call classifications. Figure 3 An example overview of the call recalibration system 106 determining a variant call classification based on extracted sequencing metrics according to one or more embodiments is illustrated.

[0083] like Figure 3As illustrated in , the detection recalibration system 106 performs action 302 to receive one or more existing sequencing data files. Specifically, in some embodiments, the detection recalibration system 106 receives a first sequencing data file including data of nucleotide reads, such as an alignment data file (e.g., a BAM file or a CRAM file). In addition, in some embodiments, the detection recalibration system 106 receives a second sequencing data file, such as a genotype call data file (e.g., a VCF file or a gVCF file) having one or more genotype calls at one or more genomic coordinates. Alternatively, in one or more embodiments, the detection recalibration system 106 may receive the aforementioned sequencing data in one or more sequencing data files of an alternative format, such as but not limited to a single sequencing data file having data of nucleotide reads and genotype calls. In addition, in some embodiments, the detection recalibration system 106 receives one or more sequencing data files with additional sequencing information, as further discussed below with respect to subsequent figures.

[0084] like Figure 3 As further illustrated in , the detection recalibration system 106 performs action 304 to extract sequencing metrics from one or more sequencing data files received during action 302. Specifically, the detection recalibration system 106 extracts or determines sequencing metrics, such as read-based sequencing metrics and detection-based sequencing metrics. For example, the detection recalibration system 106 extracts or determines sequencing metrics indicating various attributes or data associated with various genotype calls from a sample nucleotide sequence (e.g., a genomic sample). In some embodiments, the detection recalibration system 106 determines or extracts different sequencing metrics for generating genotype calls associated with different variant types (such as SNPs and indels). In addition, in some embodiments and as Figure 3 As shown, the detection recalibration system 106 performs action 306 to access or receive sequencing metrics from an external source. FIG. 4A to FIG. 4C Additional details are provided regarding determining various types of sequencing metrics.

[0085] like Figure 3 As further illustrated in , the call recalibration system 106 performs action 308 to generate a variant call classification. More specifically, the call recalibration system 106 uses the call recalibration machine learning model to generate (or update or improve) the variant call classification based on the extracted sequencing metrics. In detail, in some embodiments, the call recalibration system 106 uses the call recalibration machine learning model to process or analyze one or more extracted sequencing metrics and generate a set of classifications (e.g., predicted probabilities associated with genotypes). For example, the call recalibration system 106 uses the call recalibration machine learning model to generate a variant call classification ( Figure 3, “Class 1,” “Class 2,” and “Class 3” in the that indicate certain probabilities associated with the genotypes for the corresponding genotype calls based on sequencing metrics.

[0086] In some embodiments, the detection recalibration system 106 generates different variant detection classifications for different applications and / or for different genomic coordinates. For example, by using different versions of the detection recalibration machine learning model, the detection recalibration system 106 generates a first set of variant detection classifications for multi-allelic genomic coordinates, generates a second set of variant detection classifications for haploid genomic coordinates, and generates a third set of variant detection classifications for genomic coordinates indicated as exhibiting a homozygous reference genotype. In certain embodiments, the detection recalibration system 106 generates the same variant detection classifications for different applications and / or for different genomic coordinates, but utilizes them in different ways or utilizes different information associated with the variant detection classification. Additional details on generating variant detection classifications are provided below with reference to subsequent figures.

[0087] like Figure 3 As further illustrated in , the detection recalibration system 106 also performs action 310 to generate one or more recalibrated sequencing data files. For example, the detection recalibration system 106 determines modified or updated genotype calls (e.g., variant calls) based on the variant call classification, and indicates any such modifications in the recalibrated sequencing data file (e.g., in an updated VCF file). More specifically, the detection recalibration system 106 modifies or updates the genotype calls of the sample nucleotide sequences at the genomic coordinates within the reference genome. In order to determine the updated or modified genotype calls, in some embodiments, the detection recalibration system 106 edits or updates certain existing genotype calls (i.e., from the sequencing data file received at action 302) based on the variant call classification generated by the detection recalibration machine learning model.

[0088] In detail, the call recalibration system 106 extracts or determines sequencing metrics (e.g., one or more of the same sequencing metrics used to generate variant call classifications) to analyze genotype calls from the extracted sequencing metrics. For example, the call recalibration system 106 applies multiple Bayesian probability models or algorithms to derive various probabilities of different nucleotide bases, quality metrics, mapping metrics, joint metrics, and other data occurring within the sample nucleotide sequence. Based on the probability model, the call recalibration system 106 determines an updated genotype call indicating a pair of predicted nucleotide bases for the genomic sample at corresponding genomic coordinates (e.g., a call indicating a difference or the same as a reference base from a reference genome).

[0089] like Figure 3As further illustrated in , in some specific implementations, the call recalibration system 106 utilizes the variant call classification (e.g., as determined via action 308) to generate, recalibrate, modify, or enhance existing genotype calls. In detail, the call recalibration system 106 utilizes the probability associated with the variant call classification to determine or update certain metrics associated with the genotype call. For example, the call recalibration system 106 modifies data fields corresponding to a sequencing data file (e.g., a genotype call data file, such as a variant call file) for metrics such as call quality, genotype, and genotype quality (or other metrics as described below).

[0090] In some cases, the detection recalibration system 106 is extrapolated according to the variant detection classification to determine the metric corresponding to the existing sequencing data file, such as the detection quality, genotype and genotype quality associated with the genotype detection. For example, by utilizing the zygosity error probability, the detection recalibration system 106 can correct some errors in the existing genotype detection or associated with the existing genotype detection. In fact, if the detection recalibration system 106 determines the high false positive probability of the genotype detection, the detection recalibration system 106 uses the detection recalibration machine learning model to be used as a variant filter, to modify (for example, reduce) the detection quality associated with the genotype detection. For example, in the case where the system previously would filter out heterozygous / homozygous (het / hom) errors or double penalty points for heterozygous / homozygous (het / hom) errors (for example, in the case where the system generates incorrect genotype detections thereby further causing the correct genotype detection to be missed), the detection recalibration system 106 utilizes the zygosity error probability to modify the genotype and / or genotype quality of the genotype detection.

[0091] Relatedly, in some embodiments, the detection recalibration system 106 generates updated genotype calls at biallelic (or other types) genomic coordinates by determining to change an existing genotype call from a homozygous genotype call to a heterozygous genotype call, from a heterozygous genotype call to a homozygous genotype call, from a variant call to a reference call, from a reference call to a variant call, or any combination of the foregoing. For illustration, in some specific implementations, the detection recalibration system 106 changes a heterozygous variant genotype call or a homozygous variant genotype call reported in one or more sequencing data files to a homozygous reference genotype call at a genomic coordinate. In another specific implementation, the detection recalibration system 106 changes a homozygous reference genotype call or a homozygous variant genotype call reported in one or more sequencing data files to a heterozygous variant genotype call at a genomic coordinate. In yet another specific implementation, the call recalibration system 106 changes a heterozygous variant genotype call or a homozygous reference genotype call reported in one or more sequencing data files to a homozygous variant genotype call at the genomic coordinates.

[0092] In certain embodiments, the call recalibration system 106 considers a single variant call classification to modify a data field of a genotype call (e.g., call quality, genotype, or genotype quality). In contrast, in some embodiments, the call recalibration system 106 considers multiple variant call classifications at once (e.g., in a weighted combination) to modify or update one or more data fields of call quality, genotype, and / or genotype quality. Additional details on generating and modifying genotype calls are provided below with reference to subsequent figures.

[0093] As mentioned above, in some specific implementations, the detection recalibration system 106 is not necessarily limited to modifying or updating a single genotype detection included in one or more sequencing data files. For example, in one or more embodiments, the detection recalibration system 106 for extracting sequencing metrics for genotype detection, generating variant detection classifications for the genotype detection, and / or modifying the genotype detection based on the variant detection classification extracts sequencing metrics for specific genotype detection from one or more sequencing data files. By utilizing the detection recalibration machine learning model, the detection recalibration system 106 generates one or more variant detection classifications indicating the accuracy of the specific genotype detection indicated by one or more sequencing data files. In some specific implementations, based on one or more additional variant detection classifications, the detection recalibration system 106 modifies or updates the base detection quality metric (e.g., Q score), genotype probability metric, genotype possibility metric, or genotype quality metric for a specific genotype detection. For example, in some embodiments, the call recalibration system 106 determines a modified base call quality metric, a modified genotype probability metric, a modified genotype likelihood metric, or a modified genotype quality metric for a particular genotype call that falls below a base call quality threshold or other corresponding threshold. Based on the modified base call quality metric not satisfying the base call quality threshold, the call recalibration system 106 annotates the particular genotype call within the recalibrated sequencing data file to indicate that the modified base call quality metric falls below the base call quality threshold. Similarly, based on the modified genotype probability metric, the modified genotype likelihood metric, or the modified genotype quality metric not satisfying the genotype probability threshold, the genotype likelihood threshold, or the genotype quality threshold, respectively, the call recalibration system 106 annotates the particular genotype call within the recalibrated sequencing data file to indicate that the modified genotype probability metric, the modified genotype likelihood metric, or the modified genotype quality metric falls below the corresponding threshold.

[0094] As mentioned above, in certain described embodiments, the call recalibration system 106 extracts sequencing metrics for nucleotide base calls or genotype calls at specific genomic coordinates. Specifically, the call recalibration system 106 extracts sequencing metrics from one or more sequencing data files corresponding to calls of existing nucleotide reads from a sample nucleotide sequence, such as read-based sequencing metrics, sequencing metrics from external sources, and sequencing metrics generated by a call model. FIG. 4A to FIG. 4C The extraction of sequencing metrics according to one or more embodiments is illustrated. Specifically, Figure 4A The example shows a sequencing data file (alignment data file 406 and genotype call data file 410) receiving sequencing data of nucleotide read segments 402 having a sample nucleotide sequence. Figure 4B Determining an externally sourced sequencing metric 414 is illustrated, and Figure 4C Extracting sequencing metrics 416 and generating a recalibrated sequencing data file 422 are illustrated.

[0095] like Figure 4A As illustrated in , the detection recalibration system 106 accesses, retrieves or otherwise obtains nucleotide reads 402. Specifically, in some embodiments, the nucleotide reads 402 are previously determined using a sequencing device 114 that includes nucleotide base calls from a region of a sample nucleotide sequence (e.g., a sample genome). For example, nucleotide reads 402 can be generated using sequencing by synthesis (SBS) technology and / or Sanger sequencing technology to determine nucleotide base calls of oligonucleotide clusters based on holes in a circulation pool and / or via fluorescent labeling. More specifically, nucleotide reads 402 are generated using cluster generation and SBS chemistry to sequence millions or billions of clusters in a circulation pool. During the SBS chemistry, for each cluster, the detected nucleotide base calls from the nucleotide reads 402 are stored and, in some embodiments, are directly provided to the detection recalibration system 106 for each sequencing cycle via real-time analysis (RTA) software.

[0096] like Figure 4A As further illustrated in FIG. 4 , in some embodiments, an alignment data file 406 (such as a BAM file or a CRAM file) is generated by read processing and mapping 404. For example, read processing and mapping 404 includes using real-time analysis (RTA) software to store base call data in the form of individual base call data files (or BCLs). In some cases, read processing and mapping 404 also includes converting the BCL files (e.g., via BCL to FASTQ conversion) into sequence data to be analyzed by a call generation model 408 to determine genotype calls for nucleotide reads 402.

[0097] Specifically, in certain embodiments, read segment processing and mapping 404 include nucleotide read segment and reference genome alignment or receive information related to the read segment alignment. Specifically, read segment processing and mapping 404 determine which (which) nucleotide bases of a given read segment are aligned with which genome coordinate of the reference sequence (or receive information indicating the alignment). Different read segments have different lengths and include different nucleotide bases. Therefore, in some cases, read segment processing and mapping 404 include analyzing each nucleotide of each read segment, to determine the position of the read segment "fitting" about the reference sequence (or receive information indicating the position), such as the position of the base in the read segment and the base alignment in the reference. In some cases, read segment processing and mapping 404 include many read segments at the alignment single genome coordinate, therefore causing the read segment to pile up.

[0098] In certain embodiments, the call recalibration system 106 performs additional statistical tests to determine or detect differences between metrics associated with the reference nucleotide sequence and metrics associated with the alternative supporting nucleotide reads. Through these statistical tests, the call recalibration system 106 reengineers the raw sequencing metrics to determine the read-based sequencing metrics. In some cases, the call recalibration system 106 extracts raw sequencing metrics that include one or more of the following: (i) an alignment metric for quantifying the alignment of a sample nucleotide sequence with the genomic coordinates of an example nucleotide sequence (e.g., a reference genome or a nucleotide sequence from an ancestral haplotype); (ii) a depth metric for quantifying the depth of nucleotide base calls of a sample nucleotide sequence at the genomic coordinates of an example nucleotide sequence; or (iii) a call quality metric for quantifying the quality of nucleotide base calls (e.g., genotype calls) of a sample nucleotide sequence at the genomic coordinates of an example nucleotide sequence. For example, the call recalibration system 106 extracts a mapping quality metric (e.g., Figure 4A metric), a soft clipping metric, or other alignment metric that measures the alignment of a sample sequence to a reference genome. For example, the call recalibration system 106 extracts a forward-reverse depth metric (or other such depth metric) or a detectability metric (or other such call quality metric) for variant genotype calls.

[0099] As just mentioned, in some embodiments, the detection recalibration system 106 reengineers the raw sequencing metrics extracted from the alignment data file 406 (or other sequencing data files) to generate read-based sequencing metrics that are more informative for comparing metrics associated with a reference nucleotide sequence and metrics associated with various supporting alternative nucleotide reads. For example, the detection recalibration system 106 extracts various metrics of a sample sequence related to a reference sequence, and further extracts various metrics of a sample sequence related to alternative support sequences. In addition, in some embodiments, the detection recalibration system 106 performs a comparative analysis between metrics associated with a reference sequence and metrics associated with alternative support reads.

[0100] For example, the call recalibration system 106 compares the way in which nucleotide bases of a sample nucleotide sequence (e.g., a sample genome) are mapped to a reference sequence with the way in which nucleotide bases are mapped to various alternative supporting reads. In some cases, the call recalibration system 106 determines a mapping quality associated with the reference sequence to compare with a mapping quality associated with the alternative supporting reads. For example, the call recalibration system 106 determines mapping quality statistics that reflect differences in the distribution of reads supporting the reference sequence versus reads supporting alternative alleles.

[0101] In these or other cases, the call recalibration system 106 determines mismatch counts between the sample sequence and the reference sequence and between the reference sequence and the alternative support reads. The call recalibration system 106 further compares the mismatch counts to extract a comparative mismatch count metric. In addition, the call recalibration system 106 determines a soft clipping metric of the sample sequence with respect to the reference sequence, and further extracts a soft clipping metric with respect to the alternative support reads. The call recalibration system 106 also compares the soft clipping metric between the reference sequence and the alternative support reads to generate a comparative soft clipping metric. Further, the call recalibration system 106 compares base call quality metrics with respect to the reference sequence and the alternative support reads and / or compares query positions of the sample sequence with respect to the reference sequence with those query positions with respect to the alternative support reads.

[0102] like Figure 4A and Figure 4CAs further illustrated in FIG. 4 , the call recalibration system 106 utilizes comparisons and / or other statistical tests to extract read-based sequencing metrics from the information in the alignment data file 406 (or other sequencing data files), the read-based sequencing metrics including: i) a comparison mapping quality distribution metric indicating a mapping quality distribution comparing a mapping quality associated with a reference sequence and a mapping quality associated with an alternative support read; ii) a comparison secondary mapping alignment metric indicating a comparison between secondary mappings associated with bases in the reference sequence and bases in the alternative support read; iii) a comparison mismatch count metric indicating a comparison between mismatched nucleotide bases associated with the reference sequence and mismatched bases associated with the alternative support read; iv) a comparison soft clipping metric indicating a comparison between a soft clipping metric associated with the reference sequence and a soft clipping metric associated with the alternative support read; v) one or more comparison read depth metrics indicating a comparison between a nucleotide read 402 and a base. The invention also provides a method for determining the comparison between the read depth of a nucleotide read 401 and one or more average read depths (e.g., a local average read depth at a particular genomic coordinate and a global average read depth across multiple genomic coordinates in a region); vi) one or more comparative base quality metrics indicating a comparison between base quality associated with a reference sequence and base quality associated with alternative support reads (e.g., for overall base quality, early base quality, and late base quality in nucleotide read 402); vii) a comparative query position metric indicating a comparison between a query position associated with a reference sequence and a query position associated with an alternative support read; viii) one or more contextual information metrics indicating homopolymers and periodicity of nucleotide base calls; ix) a strand deviation metric indicating a strand deviation associated with one or more nucleotide reads in nucleotide read 402; and x) a read direction deviation metric indicating a read direction deviation associated with nucleotide read 402. In some cases, the call recalibration system 106 extracts or reengineers additional or alternative read-based sequencing metrics from information stored in the alignment data file 406 (or other sequencing data files).

[0103] In addition to read-based sequencing metrics, such as Figure 4A and Figure 4C, the call recalibration system 106 extracts the sequencing metrics generated by the call model from the genotype call data file 410 generated by the call generation model 408. For example, the call generation model 408 determines the sequence data based on the read processing and mapping 404. In some cases, the call generation model 408 generates the sequence data as part of one or more digital files such as a BCL file and a FASTQ file.

[0104] In order to generate such files, in some embodiments, the sequencing device 114 (or the detection generation model 408) utilizes cluster generation and SBS chemical reactions to sequence millions or billions of clusters in the circulation pool. During the SBS chemical reaction, for each cluster, the sequencing device 114 (or the detection generation model 408) stores the nucleotide base calls from the nucleotide reads 402 of each sequencing cycle via real-time analysis (RTA) software. The sequencing device 114 (or the detection generation model 408) further stores the base call data in the form of a separate base call data file (or BCL) using RTA software. In some cases, the sequencing device 114 (or the detection generation model 408) (e.g., via BCL to FASTQ conversion) further converts the BCL file into sequence data. For example, the sequencing device 114 (or the detection generation model 408) generates a FASTQ file based on the nucleotide reads 402, wherein the FASTQ file includes sequence data.

[0105] In some cases, call generation model 408 generates sequence data for each cluster that passes the initial quality filter based on the sample sequence. For example, call generation model 408 generates an entry for each cluster, where each entry includes four rows (or four items of sequence data): i) a sequence identifier with information about the sequencing run and cluster; ii) nucleotide base calls that make up the sequence (e.g., a sequence of A calls, C calls, T calls, G calls, and / or N calls); iii) a separator (e.g., a "+" sign); and iv) a base call quality metric that indicates the probability (Phred+33 encoding) of the correctness of the nucleotide base call.

[0106] like Figure 4AAs further illustrated in , the call generation model 408 processes or analyzes the sequence data to generate genotype calls. In fact, in some embodiments, the call recalibration system 106 extracts the sequencing metrics generated by the call model by reengineering the original sequencing metrics (e.g., the original sequencing metrics in the sequence data used by the call generation model 408 and stored in one or more sequencing data files such as BCL files or FASTQ files). Specifically, the call generation model 408 includes a mapping and alignment component for mapping and aligning nucleotide base calls from the sequence data. In addition, the call generation model 408 includes a variant call component to generate genotype calls (e.g., reference base calls such as variant calls or non-variant calls) based on the sequence data, and the genotype calls are stored in a genotype call data file 410 (e.g., a VCF or gVCF file). In some cases, the call recalibration system 106 extracts the sequencing metrics generated by the call generation model that have previously been generated using the mapping and alignment components of the call generation model 408 and the variant call component by accessing the genotype call data file 410.

[0107] To illustrate examples of sequencing metrics generated by a calling model, in some cases, the call recalibration system 106 extracts (variant calling metrics that include one or more of the following: i) base call quality metrics (e.g., DRAGEN 408; ii) a foreign read detection metric generated by the call model (e.g., a foreign read detection (FRD) score) that indicates the probability that one or more nucleotide reads in the pile of nucleotide reads 402 are foreign reads (e.g., their true position is elsewhere in the reference sequence); iii) a base quality degradation metric generated by the call model (e.g., a base quality degradation (BQD) score) that indicates the probability of base quality degradation based on one or more of strand bias, error orientation in a line, or low average base quality of a subset of nucleotide reads 402; iv) average read depth; v) indel statistics (e.g., polymerase chain reaction or "PCR" curves); and / or vi) hidden Markov chain sequence information. HMM statistics (or Concise Gap-Specific Alignment Report (CIGAR) to reconstruct HMM statistics); vii) a secondary alignment metric indicating the probability that a secondary genotype call is correct; viii) a base context metric indicating context information of the nucleotides surrounding the genotype call; iv) a nearby call metric indicating proximity to the genotype call (e.g., adjacent to the genotype call or within a threshold separation from the genotype call); x) a joint detection metric indicating the probability of detecting a joint corresponding to two or more overlapping nucleotide base calls; xii) a read filtering metric indicating a threshold quality metric or other metric for filtering out nucleotide base calls with low mapping quality, base quality, or other quality metrics; or other variant call metrics, etc. In some cases, the call recalibration system 106 extracts sequencing metrics generated by the call model from internal (e.g., proprietary and model-specific) variables that reflect interacting processing pathways, corner cases, and difficult predictions / decisions.

[0108] Although not in Figure 4A or Figure 4C, but the sequencing metrics generated by the call model include, but are not limited to, variant call metrics extracted via the variant call component of the call generation model 408 and stored in (or otherwise determined from) an existing version of the genotype call data file 410. In addition to or in lieu of the examples of sequencing metrics generated by the call generation model described above, in some cases, the call recalibration system 106 (e.g., via metric reengineering) extracts or generates variant call metrics that include one or more of the following: i) the number of samples in the population; ii) the number of reads processed to generate genotype calls, the number of variants (e.g., SNPs, indels, and MNPs); iii) the number of bi-allelic sites (e.g., genomic coordinates containing two observed alleles); iv) the number of multi-allelic sites (e.g., the number of sites in the variant call file containing three or more observed alleles); v) the number of SNPs; vi) the number of different types of indels (e.g., homozygous insertions, heterozygous insertions, and heterozygous deletions); vii) heterozygous indels (e.g., insertions + deletions); , insertion+SNP or deletion+SNP); viiii) the number of de novo SNPs (e.g., SNPs with a de novo quality metric that meets a threshold level); ix) the number of de novo indels (e.g., indels with a de novo quality metric that meets a threshold level); x) the number of de novo MNPs (e.g., MNPs with a de novo quality metric that meets a threshold level); xi) the number of SNPs in a first chromosome divided by the number of SNPs in a second chromosome; xii) the number of SNP transitions; xiii) the number of SNP transversions; xiv) the number of heterozygous variants; xv) the number of homozygous variants; xvi) the ratio between the number of heterozygous variants and the number of homozygous variants; xvii) the number of variants detected within a dbSNP reference file; and / or xviii) the total number of variants detected within the dbSNP file minus the number of variants detected within the dbSNP file.

[0109] Additionally, the sequencing metrics generated by the call model may include mapping and alignment sequencing metrics, which are extracted via the mapping and alignment components of the call generation model 408 and stored in an existing version of the genotype call data file 410 and / or the alignment data file 406. For example, the call recalibration system 106 extracts or generates mapping and alignment metrics (e.g., via metric reengineering) that include one or more of the following: i) the number of total input reads; ii) the number of duplicate flagged reads; iii) the number of duplicate flagged reads and paired reads removed; iv) the number of unique reads; v) the number of reads with sequencing pairs; vi) the number of reads without sequencing pairs; vii) an indication of reads that failed quality checks; viii) an indication of mapped reads; ix) the number of unique and mapped reads; x) the number of unmapped reads; xi) the number of single reads (e.g., where a read is mapped but a paired read cannot be read); xii) the number of paired reads; xiii) the number of properly paired reads (e.g., where one Both reads in a pair are mapped and fall within an acceptable range of each other based on an estimated insert length distribution); xiv) the number of discordant reads (e.g., reads that are not properly paired); xv) the number of paired reads that map to different chromosomes; xvi) the number of paired reads that map to different chromosomes that also have a mapping quality metric of 10 or greater; xvii) the percentage of reads within R1 and R2 with indels; xviii) the percentage of soft-clipped bases in R1 and R2; xix) the number of mismatched bases in R1 and R2; xx) the number of bases (e.g., total and / or in R1 or R2) with a base quality of at least 30; xxi) the number of alignments (e.g., total alignments, secondary alignments, and / or supplemental alignments); xxii) estimated read lengths; and xxiii) estimated sample contamination.

[0110] Now turn Figure 4BIn some cases, the call recalibration system 106 generates, extracts, or determines an externally sourced sequencing metric 414. Specifically, the call recalibration system 106 determines the externally sourced sequencing metric 414 based on one or more databases external to the call recalibration system 106, such as a sequencing information database 412 (e.g., database 116). For example, the call recalibration system 106 accesses sequencing metrics that are generic or generally applicable to sequenced nucleotides. In addition, the call recalibration system 106 accesses or determines sequencing information about a specific reference sequence (e.g., stored in a sequencing information database 412). In some cases, the call recalibration system 106 determines sequencing metrics 414 from external sources, which include: i) a mappability metric that indicates the ease or difficulty of mapping a particular nucleotide sequence (or a particular nucleotide read or nucleotide base call); ii) a guanine-cytosine content metric that indicates the count (or dropout rate or mean) of guanine-cytosine content in a reference nucleotide sequence (e.g., a reference genome); iii) a replication timing metric that indicates the time required to replicate a particular number of nucleotides from a reference sequence; iv) one or more DNA structure metrics that indicate the DNA structure of a reference sequence (e.g., a reference genome); v) a conservation metric that indicates a measure of sequence conservation across multiple species (e.g., a measure of changes relative to a mean); and / or other sequencing metrics from external sources.

[0111] As mentioned above (for example, Figure 3 ) and as discussed in Figure 4C As illustrated in FIG. 1 , the call recalibration system 106 extracts the previously generated data from various sequencing and base calling processes (such as read segment processing and mapping 404 and from the call generation model 408 (see FIG. 1 ). Figure 4A ) is performed by the base calling system 106 to extract sequencing metrics 416 from the sequencing data file generated by the base calling performed by the base calling system 106. Specifically, the call recalibration system 106 uses the call recalibration machine learning model 418 to generate variant call classifications 420, and based on the variant call classifications 420, generates a recalibrated sequencing data file 422 as an output.

[0112] In one or more embodiments, the detection recalibration system 106 extracts (reconstructs) additional or alternative sequencing metrics from one or more sequencing data files, including sequencing metrics based on reads, sequencing metrics generated by detection models, and / or sequencing metrics from external sources. For example, the detection recalibration system 106 extracts the sequencing metrics in the following table, wherein each of these metrics belongs to one or more of sequencing metrics based on reads, sequencing metrics generated by detection models, and / or sequencing metrics from external sources.

[0113]

[0114]

[0115]

[0116] As mentioned above, in certain described embodiments, the detection recalibration system 106 generates a set of machine learning predictions for different variant types using the above sequencing metrics. Specifically, in some embodiments, the detection recalibration system 106 generates genotype probabilities (for SNPs) using a detection recalibration machine learning model, or generates variant detection classifications (for insertions and deletions) corresponding to various genomic coordinates using another detection recalibration machine learning model. In addition, the detection recalibration system 106 updates or modifies genotype detection by generating updated genotype detection data files such as variant detection files (e.g., recalibrated variant detection files) based on genotype probabilities and / or variant detection classifications.

[0117] According to one or more embodiments, FIG. 5A to FIG. 5C The call recalibration system 106 is illustrated as generating one or both of genotype probabilities and variant call classifications, generating genotype calls based on such probabilities and / or classifications, and generating a recalibrated or updated variant call file including the genotype calls based on such probabilities and / or classifications. For example, Figure 5A The call recalibration system 106 according to one or more embodiments is illustrated using a call recalibration machine learning model to generate genotype probabilities for (biallelic) SNPs based on sequencing metrics corresponding to existing genotype calls. Figure 5B The call recalibration system 106 according to one or more embodiments uses a call recalibration machine learning model to generate a variant call classification for an indel (or multi-allelic SNP or a variant type other than a biallelic SNP) based on sequencing metrics corresponding to existing genotype calls. Thereafter, Figure 5C The call recalibration system 106 is illustrated to generate an updated variant call file including recalibrated genotype calls based on genotype probabilities and / or variant call classifications according to one or more embodiments.

[0118] like Figure 5AAs illustrated in , the call recalibration system 106 identifies the genomic coordinate 502. For example, the call recalibration system 106 identifies the genomic coordinate 502 based on the nucleobase calls corresponding to the sample nucleotide sequence or based on the haplotype data corresponding to the genomic coordinate 502. In some cases, the call recalibration system 106 identifies the genomic coordinate 502 by determining (i) one or more nucleobase calls from nucleotide reads covering the genomic coordinate and (ii) one or more nucleobase calls satisfy one or more threshold sequencing metrics (e.g., a base call quality metric of Q30). Additionally or alternatively, in some embodiments, the call recalibration system 106 identifies the genomic coordinate 502 based on a database including a haplotype reference panel associated with a particular genomic coordinate. Regardless of the identification method, in some cases, the call recalibration system 106 uses information from one or more sequencing data files 503 (such as information previously generated and stored by a call generation model (e.g., a variant caller as part of the call generation model)) to identify the genomic coordinate 502.

[0119] In addition, the sequencing data file 503 accessed by the call recalibration system 106 also includes existing genotype calls (e.g., genotype calls generated by the call generation model and stored in the variant call file). In detail, the sequencing data file 503 includes information determined by the call generation model (e.g., DRAGEN VC detector) to generate existing genotype calls, thereby predicting the presence (or absence) of a variant (or a specific genotype) at the genomic coordinate 502. As described, the call generation model generates existing genotype calls by analyzing or processing sequencing metrics 504 (or a subset of sequencing metrics 504, such as sequencing metrics based on reads and sequencing metrics from external sources), which can also be used for the call recalibration system 106 from the sequencing data file 503. In addition, the call generation model generates and stores (e.g., in a genotype call data file) some of the sequencing metrics 504 (e.g., sequencing metrics generated by the call model) as part of predicting existing genotype calls.

[0120] In practice, the call recalibration system 106 extracts (or reconstructs) sequencing metrics 504 for the genomic coordinates 502 from one or more existing sequencing data files. Specifically, the call recalibration system 106 extracts sequencing metrics associated with nucleotide reads, generated by a call generation model, or retrieved from another external source, as described above. Based on the sequencing metrics 504, the call recalibration system 106 further generates genotype probabilities 508, which together can indicate a measure of confidence or probability that the genomic coordinates 502 include or exhibit a SNP. The genotype probabilities 508 represent examples of variant call classifications.

[0121] Specifically, Figure 5A As shown, the call recalibration system 106 utilizes the call recalibration machine learning model 506 to generate genotype probabilities 508. For example, the call recalibration machine learning model 506 analyzes or processes the extracted sequencing metrics 504 and the existing genotype calls as input to generate genotype probabilities 508 as outputs, which genotype probabilities include: i) a first genotype probability 510 that the existing genotype call is a homozygous reference genotype at genomic coordinate 502 (e.g., "L(0 / 0)@chr5:4"); ii) a second genotype probability 512 that the existing genotype call is a heterozygous variant genotype at genomic coordinate 502 (e.g., "L(0 / l)@chr5:4"); and iii) a third genotype probability 514 that the existing genotype call is a homozygous variant genotype at genomic coordinate 502 (e.g., "L(l / l)@chr5:4").

[0122] As mentioned, the call recalibration system 106 generates genotype probabilities 508 to predict whether a SNP occurs at a genomic coordinate 502. In some embodiments, to predict whether an indel occurs at a genomic coordinate, the call recalibration system 106 generates different machine learning prediction sets. Specifically, the call recalibration system 106 generates variant call classifications that indicate the presence (or absence) of an indel (or a multi-allelic SNP or another variant type other than a biallelic SNP) at the genomic coordinates of the sample sequence.

[0123] like Figure 5BAs shown, the call recalibration system 106 utilizes the call recalibration machine learning model 520 to generate a variant call classification 522. In detail, the call recalibration system 106 utilizes the call recalibration machine learning model 520 to generate a variant call classification 522 based on the sequencing metrics 518 extracted (or reconstructed) from the sequencing data file 517 and the existing genotype calls associated with the genomic coordinates 516. For example, in some embodiments, the call recalibration system 106 identifies multi-allelic genomic coordinates such as genomic coordinates 516, and feeds the sequencing metrics for the multi-allelic genomic coordinates to the call recalibration machine learning model 520. In fact, similar to the above discussion on generating genotype probabilities for biallelic SNPs, the call recalibration system 106 also extracts (or reconstructs) sequencing metrics 518 associated with the genomic coordinates 516, which include sequencing metrics based on reads, sequencing metrics generated by the call model, and sequencing metrics from external sources. For example, the call recalibration system 106 analyzes a subset of sequencing metrics 518 (e.g., read-based sequencing metrics and / or sequencing metrics from an external source) extracted from the sequencing data file 517 for use in determining an existing genotype call (e.g., indicating a particular genotype or variant at the genomic coordinate 516). In some cases, when the sequencing data file 517 is generated, the call generation model generates a subset of sequencing metrics 518 (e.g., sequencing metrics generated by the call model) associated with the genomic coordinate 516.

[0124] In generating variant call classifications 522 for genomic coordinates 516, the call recalibration system 106 utilizes the call recalibration machine learning model 520. Specifically, the call recalibration system 106 utilizes the call recalibration machine learning model 520 to generate: (i) a true positive variant probability 524 that an existing genotype call (e.g., an initial VCF file from a sequencing data file 517) is a true positive variant call at genomic coordinates 516; (ii) a zygosity error probability 528 that an existing genotype call (e.g., an initial VCF file from a sequencing data file 517) includes a genotype zygosity error at genomic coordinates 516; and (iii) a reference probability 532 that an existing genotype call at genomic coordinates 516 is a homozygous reference genotype (or a false positive). In some cases, the variant call classifications 522 are mutually exclusive.

[0125] like Figure 5BAs further shown, the true positive variant probability 524 is represented by "TP". The symbol "TP" represents the probability that the input (x) is a true positive variant in an existing genotype detection data file (e.g., an initial VCF file of the sequencing data file 517) of the sequencing data file 517, where "TP" can be expressed as P(tp|x)). In contrast, the zygosity error probability 528 is represented by "HH". The symbol "TP&HH" represents the probability that the input (x) is not a true positive and is a het-hom error in an existing genotype detection data file (e.g., an initial VCF file of the sequencing data file 517). In addition, the reference probability 532 is represented by "FP", which indicates the probability that the input (x) is a false positive and can be expressed as P(fp|x)).

[0126] To elaborate on the probability of zygosity error 528, the detection recalibration system 106 determines the probability that the predicted genotype at the genomic coordinate 516 (e.g., an existing genotype call) is an incorrect genotype (e.g., a genotype incorrectly identified by the detection generation model) or includes an incorrect allele. In some cases, the detection recalibration system 106 determines the probability that there is a zygosity error (e.g., a het / hom error) at the genomic coordinate 516 (e.g., where the alternative base is correct but the genotype is incorrect) based on the sequencing metric 518, or the probability that the nuclear base call represents a completely incorrect genotype or an error allele in the existing genotype call. For example, when determining the probability of the presence of a zygosity error, the detection recalibration system 106 determines the probability that the alternative base call represented as "1" is correct but the genotype is incorrect, such as incorrectly determining a 0 / 1 genotype call (e.g., A / T) instead of a correct 1 / 1 genotype call (e.g., T / T) (or vice versa in the case where the correct genotype call is 0 / 1).

[0127] The call recalibration system 106 can repair the inaccuracies of existing sequencing systems, where incorrect calls are often indels, by determining the zygosity error probability 528. Specifically, the call recalibration system 106 can more accurately generate genotype calls corresponding to the genomic coordinates of indels, where an existing sequencing system would determine that the genotype call represents an incorrect genotype representing an incorrect allele resulting from a long insertion or deletion sequence.

[0128] like Figure 5BAs further illustrated in FIG. 5 , the call recalibration system 106 utilizes the call recalibration machine learning model 520 to generate a true positive variant probability 524. Specifically, the call recalibration system 106 generates the true positive variant probability 524 based on the sequencing metric 518 of the existing genotype call at the genomic coordinate 516. In some cases, the true positive variant probability indicates the probability of the correct variant call genotype at the genomic coordinate 516. For example, the call recalibration system 106 generates the probability that the existing genotype call of the genomic coordinate 516 is correct as determined by the call generation model and stored in the sequencing data file 517.

[0129] Continue to Figure 5C In some embodiments, the call recalibration system 106 uses the genotype probabilities 508 and / or the variant call classifications 522 to update one or more data fields or variant call file fields ("VCF" fields) associated with a variant call file (e.g., a sequencing data file accessed by the call recalibration system 106). For example, the call recalibration system 106 generates a recalibrated genotype call data file 536 (in this case, a recalibrated variant call file) based on the genotype probabilities 508. In some cases, the call recalibration system 106 generates a single recalibrated variant call file that combines data from the genotype probabilities 508 for SNPs and from the variant call classifications 522 for indels (e.g., updated genotype calls and / or updated sequencing metrics).

[0130] As shown, the detection recalibration system 106 generates updated VCF fields 534, which indicate or correspond to updated sequencing metrics for existing genotype calls. Specifically, the detection recalibration system 106 generates a set of updated VCF fields 534 based on the genotype probability 508 of the genomic coordinate set. In addition, the detection recalibration system 106 generates another set of updated VCF fields 534 based on the variant call classification 522 for a different genomic coordinate set. In some cases, the detection recalibration system 106 only modifies or updates certain VCF fields based on the genotype probability 508 and / or the variant call classification 522 and does not update other fields.

[0131] In other cases, the call recalibration system 106 does not update the VCF fields. For example, when a genotype call is updated or modified, the call recalibration system 106 does not update certain fields, such as the genotype (GT) field, based on the genotype probability 508 and / or the variant call classification 522. In fact, in some cases, the call recalibration system 106 does not modify or update the GT field because there may not be enough information to determine the new or updated genotype at the genomic coordinate.

[0132] To illustrate one embodiment, Figure 5C Depicted is a call recalibration system 106 generating an updated VCF field 534 for a 1 / 2 genotype (GT), where cytosine represents a reference base at a genomic coordinate corresponding to an allele of a reference genome (shown as "Ref: C") and thymine represents a first alternative base at a genomic coordinate of a different allele ("Alt: T"). Figure 5C Only examples of possible reference bases and possible alternative bases at genomic coordinates are depicted. The call recalibration system 106 can generate genotype probabilities 508 and variant call classifications 522 to modify corresponding sequencing metrics for various other reference bases and alternative bases at genomic coordinates in the VCF field.

[0133] like Figure 5C As further illustrated in , the detection recalibration system 106 generates an updated base call quality metric in the base call quality (QUAL) field. More specifically, the detection recalibration system 106 modifies or updates the base call quality metric based on the genotype probability 508 and / or the variant detection classification 522 to indicate the accuracy of the genotype detection. As shown, the updated base call quality field indicates the QUAL score 48 of the variant at the corresponding genomic coordinate. In this example, the updated base call quality metric (e.g., QUAL score 48) represents the score of any type of variant at the corresponding genomic coordinate. In addition, the detection recalibration system 106 generates a modified or updated genotype quality (GQ) field. For example, based on the variant detection classification 522, the detection recalibration system 106 generates a modified or updated genotype quality metric that indicates the possibility or probability that the predicted genotype at the genomic coordinate is correct. As shown, for example, the updated genotype quality field indicates a genotype quality metric for genotype calls having heterozygous genotypes at multi-allelic coordinates (eg, a GQ score of 4 for genotype 1 / 2).

[0134] In one or more embodiments, the detection recalibration system 106 further generates or updates the genotype probability field, and (in some cases) uses the genotype probability field to rank alleles. In detail, the detection recalibration system 106 generates the GT field of update by sorting the candidate genotype detection at the genome coordinate according to the corresponding probability attributable to the genome coordinate 502. For example, the detection recalibration system 106 determines the probability associated with multiple genotypes, wherein each diploid genotype is composed of a pair of alleles. For example, the detection recalibration system 106 determines the relative probability attributable to the multi-allelic genome coordinate associated with multiple alleles (e.g., from a reference genome, a first alternative allele and a second alternative allele).

[0135] In some embodiments, the call recalibration system 106 also (or alternatively) generates metrics for a PHRED scaled likelihood (PL) field as part of the updated VCF fields. For example, the call recalibration system 106 generates metrics for a PL field that can indicate a genotype, such as a homozygous reference genotype, a heterozygous genotype, and a homozygous alternative genotype (e.g., having PL field designations 9 / 0 / 3, respectively).

[0136] In one or more embodiments, the call recalibration system 106 generates allele-specific probabilities or likelihoods based on the relative probabilities of genotype calls corresponding to alleles from the call generation model and any other (non-reference) genotypes identified by the call recalibration machine learning model. For example, in some embodiments, the call recalibration system 106 indicates a relative probability score for each allele of a corresponding genotype call in a PL field corresponding to a normalized PHRED scaled likelihood of an indicated genotype and / or a genotype probability (GL) field indicating a logarithmic scaled likelihood (e.g., log10 scale) of data (e.g., sequencing metrics) given a called genotype.

[0137] As a motivation for modifying certain VCF fields of SNPs, in some cases, the call recalibration system 106 utilizes the call recalibration machine learning model to generate genotype probabilities 508 (whose probabilities sum to 1). Specifically, the call recalibration machine learning model may generate a first genotype probability 510 as 0.1, a second genotype probability 512 as 0.2, and a third genotype probability 514 as 0.7. In such examples, based on the genotype probabilities 508, the call recalibration system 106 generates an updated genotype probability field by updating the GT field, the GP field, and the PL field using a combination of information from the call recalibration machine learning model and the sequencing data file previously generated by the call generation model.

[0138] like Figure 5CAs further illustrated in , the detection recalibration system 106 updates the PL fields for different genotypes (GT). According to the normalized scale of the PL scores, a relatively low score for a genotype (e.g., PL 0) indicates a relatively high probability that the genotype is present at the genomic coordinates; and a relatively high score for a genotype (e.g., PL 101) indicates a relatively low probability that the genotype is present at the genomic coordinates. For example, the detection recalibration system 106 determines that the PL score for the 0 / 0 genotype is 111, the PL score for the 0 / 1 genotype is 52, and the PL score for the 1 / 1 genotype is 52. Therefore, in Figure 5C , a PL score of 52 indicates the genotype with the highest likelihood or the selected genotype (eg, 0 / 1 and 1 / 1 genotypes), and a PL score of 111 indicates the lowest likelihood (eg, 0 / 0 genotype).

[0139] In some cases, the call recalibration system 106 generates an updated genotype probability field as a ranking of multiple alleles identified via a call generation model (without utilizing a call recalibration machine learning model). In other cases, the call recalibration system 106 utilizes a specialized version of a call recalibration machine learning model that is trained to generate an updated genotype probability field based on the genotype probability 508 and / or variant call classification 522.

[0140] like Figure 5C As further illustrated in , the call recalibration system 106 generates or updates a genotype call data file, such as an initial variant call file, to create a recalibrated genotype call data file 536. For example, the call recalibration system 106 generates a recalibrated genotype call data file 536 based on the updated VCF fields 534 corresponding to the genotype probabilities 508 and the variant call classifications 522, respectively. Thus, the call recalibration system 106 generates a recalibrated genotype call data file 536 for SNP genotype calls based on the genotype probabilities 508. As noted above, in some embodiments, the call recalibration system 106 generates a recalibrated genotype call data file that merges data for SNPs and indels from both the genotype probabilities 508 and the variant call classifications 522.

[0141] The call recalibration system 106 can generate a recalibrated genotype call data file 536 to include updated VCF fields 534, which include base call quality metrics, genotype quality metrics, and / or updated genotype probability fields. For example, the call recalibration system 106 selects VCF fields from existing genotype calls generated by the call generation model to include in the recalibrated genotype call data file. However, in some embodiments, the call recalibration system 106 does not select fields, but instead generates new VCF fields for the recalibrated genotype call data file by processing the genotype probabilities 508 and variant call classifications 522 using the call recalibration machine learning model.

[0142] As mentioned, in some cases, the detection recalibration system 106 only updates certain fields, while other fields such as the genotype (GT) field remain unchanged. For example, the detection recalibration system 106 updates the genotype quality field and the base detection quality field. For other data fields such as the normalized PHRED scaled likelihood (PL) and the posterior genotype probability (GP) of the genotype, the detection recalibration system 106: (i) maintains the field as it is; (ii) removes the field; or (iii) updates the field for reflecting the detected genotype and the GQ of category 0 output 0 / 0. In some cases, the detection recalibration system 106 maintains the relative probability of other genotypes relative to the detected genotype to ensure consistent updates and that the detected genotype is the highest. In certain embodiments, by only updating the values ​​of 0 / 0 and 1 / 2, the detection recalibration system 106 maintains the distance of other genotypes from the detected genotype. By updating only certain fields, the call recalibration system can more efficiently generate (recalibrated and / or merged) genotype call data files, without having to regenerate entirely new genotype call data files (as some prior systems do) and / or update every field (even those that have not changed due to new predictions).

[0143] Within (or as a result of generating) a recalibrated genotype call data file, the call recalibration system 106 may include or update one or more output genotype calls (e.g., variant calls) associated with the genomic coordinates, as determined based on the updated VCF fields 534. In practice, to generate updated genotype calls, the call recalibration system 106 may predict nucleobases from candidate alleles at the genomic coordinates (e.g., based on their respective probabilities and metrics indicated by the recalibrated variant call file). Thus, the call recalibration system 106 may generate a recalibrated genotype call data file 536 that includes updated genotype calls for specific genomic coordinates or confirmed genotype calls for specific genomic coordinates. Similarly, the call recalibration system 106 can generate a recalibrated genotype call data file 536, which includes one or more of a modified base call quality metric, a modified genotype probability metric, a modified genotype metric, a modified genotype likelihood metric, or a modified genotype quality metric for a confirmed or modified genotype call.

[0144] As mentioned above, in certain embodiments, the call recalibration system 106 trains or adjusts the call recalibration machine learning model (e.g., the call recalibration machine learning model 418, 506, or 520). Specifically, the call recalibration system 106 uses an iterative training process to fit the call recalibration machine learning model by adjusting or adding decision trees or learning parameters that produce accurate variant call classifications (e.g., variant call classifications 420, genotype probabilities 508, or variant call classifications 522). For example, Figure 6 A training detection recalibration machine learning model according to one or more embodiments is illustrated.

[0145] like Figure 6 As illustrated in FIG. 1 , the call recalibration system 106 accesses a sample sequencing data file 620 (e.g., a sequencing data file generated using an existing call generation model such as the call generation model 204a), extracts (or reconstructs) sample sequencing metrics 604 from the sample sequencing data file 620, and receives or obtains some metrics (e.g., metrics from an external source) from a database 602 (e.g., database 116). For example, the call recalibration system 106 extracts (or reconstructs) sample sequencing metrics, which include metrics based on sample reads, sequencing metrics from external sources of the sample, and sequencing metrics generated by the sample call model.

[0146] As mentioned, in some embodiments, the call recalibration system 106 reconstructs at least some of the call model-generated metrics that are not stored in the provided sample sequencing file but are utilized by the call generation model. Figure 6 As shown, the call recalibration system 106 determines (i.e., derives) at least some of the call model generated metrics based on alternative information within the sequencing data file to determine the reconstructed call model generated metrics. For example, in some embodiments, the call recalibration system 106 reconstructs certain call model generated metrics, such as hidden Markov model (HMM) statistics utilized by the call generation model, from other information within the sequencing data file (such as Concise Specific Gap Alignment Report (CIGAR) string output or other sequencing information).

[0147] In some cases, the sample sequencing data files 620 have corresponding reference truth variant call files 616 associated with them, wherein the reference truth variant call files 616 indicate the actual genotype calls and their various metrics generated by the sample sequencing metrics 604. For example, the call recalibration system 106 utilizes a reference truth variant call file from a training data set of the Food and Drug Administration (referred to as the PrecisionFDA data set). In some cases, the sample sequencing metrics 604 include a subset of sample sequencing metrics for each genotype call in the reference truth variant call file 616. The reference truth variant call file 616 may have reference truth variant calls (e.g., genotype metrics in a genotype field) and / or reference truth base calls corresponding to each subset of the sample sequencing metrics.

[0148] like Figure 6 As further illustrated in , the detection recalibration system 106 generates a predicted variant call classification 608 based on the extracted sample sequencing metrics 604. Specifically, the detection recalibration system 106 generates a predicted variant call classification 608 using the detection recalibration machine learning model 606. In fact, in some embodiments, the detection recalibration machine learning model 606 generates a set of three predicted variant call classifications 608, which include a predicted false positive probability, a predicted zygosity error probability, and a predicted true positive classification. The predicted variant call classification 608 can take the form of any of the above-mentioned variant call classifications accordingly.

[0149] Based on the predicted variant call classification 608, the call recalibration system 106 determines the genotype call and generates a modified variant call file 610 including the modified or updated genotype call and the corresponding field. As noted above, the call recalibration system 106 can utilize (i) the existing genotype call generated by the call generation model and included in the sample sequencing data file 620 and (ii) the call recalibration machine learning model 606 to modify the data fields of the variant call file (e.g., of the sample sequencing data file 620) corresponding to the genotype call. Such modified or recalibrated values ​​are output in the modified variant call file 610 by, for example, the call recalibration machine learning model 606. For example, the call recalibration system 106 determines the recalibrated values ​​of specific metrics within the modified variant call file 610, including base call quality metrics (QUAL), genotype metrics (GT), and genotype quality metrics (GQ).

[0150] like Figure 6 As further illustrated in , the call recalibration system 106 performs a comparison 612. Specifically, the call recalibration system 106 performs a comparison 612 between (i) the variant genotype calls and / or data fields in the modified variant call file 610 and (ii) the variant genotype calls and / or data fields in the reference truth variant call file 616. In some embodiments, the call recalibration system 106 uses a loss function 614 to compare the variant genotype calls and / or data fields from the two variant call files (e.g., to determine an error or loss measure between them). For example, in the case where the call recalibration machine learning model 606 is an ensemble of gradient boosted trees, the call recalibration system 106 uses a mean squared error loss function (e.g., for regression) and / or a logarithmic loss function (e.g., for classification) as the loss function 614.

[0151] In contrast, in embodiments where the call recalibration machine learning model 606 is a neural network, the call recalibration system 106 may utilize a cross entropy loss function, an L1 loss function, or a mean squared error loss function as the loss function 614. For example, the call recalibration system 106 utilizes the loss function 614 to determine the differences between the variant genotype calls and / or data fields from the modified variant call file 610 and the reference truth variant call file 616.

[0152] like Figure 6As further illustrated in , the detection recalibration system 106 performs model fitting 618. Specifically, the detection recalibration system 106 fits the detection recalibration machine learning model 606 based on the comparison 612. For example, the detection recalibration system 106 performs modifications or adjustments to the detection recalibration machine learning model 606 to reduce the loss metric from the loss function 614 in subsequent training iterations.

[0153] For gradient boosted trees or Treelite, for example, the call recalibration system 106 trains the call recalibration machine learning model 606 according to the gradient of the error determined by the loss function 614. For example, the call recalibration system 106 solves a (e.g., infinite-dimensional) convex optimization problem while regularizing the objective to avoid overfitting. In some implementations, the call recalibration system 106 scales the gradient to emphasize corrections for underrepresented classes (e.g., where there are significantly more true positive variant calls than false positive variant calls).

[0154] In some embodiments, as part of solving the optimization problem, the call recalibration system 106 adds new weak learners (e.g., new boosted trees) to the call recalibration machine learning model 606 in each successive training iteration. For example, the call recalibration system 106 finds a feature (e.g., a sequencing metric) that minimizes the loss from the loss function 614 and adds the feature to the tree of the current iteration or begins building a new tree using the feature.

[0155] In addition to or in lieu of gradient boosting decision trees, the call recalibration system 106 trains logistic regression to learn parameters for generating one or more variant call classifications, such as true positive classifications. To avoid overfitting, the call recalibration system 106 further performs regularization based on hyperparameters such as learning rate, stochastic gradient boosting, number of trees, tree depth, complexity penalty, and L1 / L2 regularization.

[0156] In an embodiment where the detection recalibration machine learning model 606 is a neural network, the detection recalibration system 106 performs model fitting 618 by modifying the internal parameters (e.g., weights) of the detection recalibration machine learning model 606 to reduce the loss metric of the loss function 614. In effect, the detection recalibration system 106 modifies the way the detection recalibration machine learning model 606 analyzes data and passes data between layers and neurons by modifying the internal network parameters. Thus, over multiple iterations, the detection recalibration system 106 improves the accuracy of the detection recalibration machine learning model 606.

[0157] In fact, in some cases, the detection recalibration system 106 repeats Figure 6, for multiple iterations. For example, the call recalibration system 106 repeats iterative training by selecting a new set of sequencing metrics for each genotype call and a corresponding benchmark truth genotype call in a corresponding benchmark truth variant call file. The call recalibration system 106 further generates a new set of predicted variant call classifications and a new modified variant call file within each iteration. As described above, the call recalibration system 106 also compares the variant genotype calls and / or data fields from the modified variant call file for each iteration with the corresponding variant genotype calls and / or data fields from the corresponding benchmark truth variant call file, and further performs model fitting 618. The call recalibration system 106 repeats this process until the call recalibration machine learning model 606 generates a predicted variant call classification that produces variant calls that meet the threshold loss metric. In some embodiments, the call recalibration system 106 performs for homozygous reference coordinates. Figure 6 The training process is performed to update or modify variant calls at these coordinates and thereby recover false negative variant calls (based on simulating haploid data based on diploid data and modifying the call recalibration inputs and outputs of the machine learning model 606, as described).

[0158] As mentioned above, in certain described embodiments, the detection recalibration system 106 improves computational efficiency compared to existing sequencing systems. For example, Figure 7 A table depicting computational efficiency improvements associated with a checkout recalibration system is illustrated in accordance with one or more embodiments.

[0159] As previously mentioned, some existing sequencing systems that utilize variant callers based on machine learning models must reprocess raw sequencing data (e.g., nucleotide reads from BCL files) to generate updated genotype calls for sample nucleotide sequences (e.g., genomic samples). In addition, some existing sequencing systems require computer arrays with hardware accelerators such as field programmable gate arrays (FPGAs) to execute variant callers based on machine learning models. In contrast, as discussed in detail above, the call recalibration system 106 utilizes a call recalibration machine learning model that is operable on any processor to recalibrate existing genotype calls based on sequencing metrics extracted or determined from one or more existing sequencing data files (e.g., sequencing data files generated by a previous call generation model) without reprocessing the raw sequencing metrics (e.g., nucleotide reads from BCL files).

[0160] like Figure 7As indicated in the table of , in at least one specific implementation, the existing sequencing system requires an average of 20 minutes for each genome sample to reprocess the base call data of the corresponding genome sample. Despite the implementation of a large FPGA-equipped computer with 48 parallel processing units and 256GB of memory, such existing sequencing systems require 20 minutes for each genome sample. Figure 7 As further indicated in the table of , in at least one specific implementation, the call recalibration system 106 utilizes the call recalibration machine learning model to process genomic samples in an average of 7 minutes per genomic sample to generate a recalibrated sequencing data file. By extracting sequencing metrics for genotype calls from existing sequencing data files, and utilizing the call recalibration machine learning model to generate variant call classifications that facilitate updating previously generated genotype calls and / or corresponding sequencing metrics, the call recalibration system 106 increases computer processing speed by more than 2 times relative to existing sequencing systems that perform the same basic task. Rather than limiting the call recalibration machine learning model to FPGAs or other reconfigurable arrays, the call recalibration system 106 extends the implementation to any processor, such as Figure 7 The general CPU array shown includes 16 processors and 128GB of memory. Figure 7 As shown in the comparative experimental results provided in , the detection recalibration system 106 significantly improves the efficiency compared with the existing sequencing system.

[0161] As mentioned above, in certain described embodiments, the call recalibration system 106 improves both efficiency and accuracy compared to existing sequencing systems. FIG. 8A to FIG. 8B A bar graph depicting the improvement in accuracy associated with detecting a recalibration system 106 is illustrated according to one or more embodiments. Specifically, FIG. 8A to FIG. 8B The comparative experimental results of various sequencing systems running various sample genome sequences are illustrated.

[0162] For example, Fig. 8A A bar graph comparing the performance of identifying single nucleotide variants (SNPs) within various genomic datasets (i.e., portions of the HG001-HG007 human genome datasets) is illustrated. The illustrated bar graph depicts the results of a previous version of a call generation model labeled "v3.7.8" (e.g., call generation model 204a), an updated version of a call generation machine learning model labeled "v4.0.3" (e.g., updated call generation model 204b), and a call recalibration system 106 labeled "v4.2," which utilizes the call recalibration machine learning model to recalibrate nucleotide base reads generated by the previous version of the call generation model.

[0163] like Fig. 8A and Figure 8B As shown, the call recalibration system 106 outperforms the previous call generation model, resulting in fewer false positives (FPs) and false negatives (FNs) when identifying SNPs within each genomic data set. In addition, the call recalibration system 106 utilizes the call recalibration machine learning model to perform similarly to the updated call generation model while improving its efficiency (e.g., as described above with respect to Figure 7 In addition, when using an alternative format of the sequencing data file, the call recalibration system 106 provides similar results. As shown, when using BAM files, the FP and FN results of SNP calls are similar to those using CRAM files.

[0164] With Fig. 8A In a similar way, Figure 8B A bar graph comparing the performance of identifying variants including insertions or deletions (indels) within various genomic datasets (i.e., portions of the HG001-HG007 human genome datasets) is illustrated. The illustrated bar graph depicts the results of a previous version of a call generation model labeled "v3.7.8" (e.g., call generation model 204a), an updated version of a call generation machine learning model labeled "v4.0.3" (e.g., updated call generation model 204b), and a call recalibration system 106 labeled "v4.2," which utilizes the call recalibration machine learning model to recalibrate nucleotide base reads generated by the previous version of the call generation model.

[0165] As shown, the call recalibration system 106 outperforms the previous call generation model, resulting in fewer false positives (FPs) and false negatives (FNs) when identifying indels within each genomic dataset. In addition, the call recalibration system 106 utilizes the call recalibration machine learning model to perform similarly to the updated call generation model while improving its efficiency (e.g., as described above with respect to Figure 7 In addition, when using an alternative format of the sequencing data file, the call recalibration system 106 provides similar results. As shown, when using the BAM file as input to determine the sequencing metrics, the FP and FN results of the indel call are similar to the results of using the CRAM file as input to determine the sequencing metrics.

[0166] Now turn to Fig. 9 , which illustrates an example flow chart of a series of actions for generating a recalibrated sequencing data file with updated genotype calls or variant calls based on variant call classification from a call recalibration machine learning model according to one or more embodiments. Fig. 9 The actions according to one embodiment are illustrated, but alternative embodiments may omit, add, reorder, and / or modify Fig. 9 Any action shown. Fig. 9 The actions of may be performed as part of a method. Alternatively, a non-transitory computer-readable storage medium may include a computer program that, when executed by one or more processors, causes a computing device to perform Fig. 9 In some further embodiments, the system includes at least one processor and a non-transitory computer-readable medium, which includes instructions that, when executed by the one or more processors, cause the system to perform Fig. 9 instructions for actions.

[0167] like Fig. 9 As shown, a series of actions 900 includes an action 902 of accessing a sequencing data file, an action 904 of extracting sequencing metrics for a genotype call, an action 906 of generating a variant call classification for the genotype call, and an action 908 of generating a recalibrated sequencing data file. For example, a series of actions 900 may include actions for performing any of the operations described in the following clauses:

[0168] Clause 1. A method comprising:

[0169] For a sample nucleotide sequence, access one or more sequencing data files, wherein the sequencing data files include nucleotide reads at genomic coordinates and genotype call data;

[0170] extracting sequencing metrics for the nucleotide reads or the genotype calls from the one or more sequencing data files;

[0171] recalibrating the machine learning model using the calls and based on the sequencing metrics, generating one or more variant call classifications indicating the accuracy of the genotype calls within the one or more sequencing data files; and

[0172] Based on the one or more variant call classifications, a recalibrated sequencing data file is generated, the recalibrated sequencing data file comprising updated genotype calls at the genomic coordinates of the sample nucleotide sequence.

[0173] Clause 2. The method of clause 1, wherein generating the one or more variant call classifications comprises generating the one or more variant call classifications without simultaneously generating the genotype calls using a call generation model.

[0174] Clause 3. A method according to any one of clauses 1 to 2, wherein extracting the sequencing metrics used for the genotype calling comprises: extracting one or more read-based sequencing metrics from an alignment data file of the one or more sequencing data files.

[0175] Clause 4. A method according to any one of clauses 1 to 3, wherein extracting the sequencing metrics comprises: extracting one or more read-based sequencing metrics or sequencing metrics generated by a calling model for the genotype call from a genotype call data file of the one or more sequencing data files, the genotype call data file comprising the genotype call.

[0176] Clause 5. The method according to any one of clauses 1 to 4, further comprising: accessing the genotype call data file by accessing a variant call format (VCF) file or a genomic variant call format (gVCF) file including variant calls and non-variant calls.

[0177] Clause 6. A method according to any one of clauses 1 to 5, wherein the genotype call data file including the genotype call is generated on a computing device executing a hardware accelerator, and the recalibrated sequencing data file is generated using a general purpose processing unit as at least one processor of the system.

[0178] Clause 7. A method according to any one of clauses 1 to 6, wherein the hardware accelerator comprises a field programmable gate array (FPGA) or an application-specific integrated circuit (ASIC), and the recalibrated sequencing data file is generated using one or more of a central processing unit (CPU) or a graphics processing unit (GPU).

[0179] Clause 8. The method according to any one of clauses 1 to 7, further comprising:

[0180] accessing an additional genotype calling data file generated by a version of a call generation model that is different from a version of the call generation model that generated the genotype calling data file;

[0181] extracting additional sequencing metrics for additional genotype calls at genomic coordinates of additional sample nucleotide sequences from the additional genotype call data file;

[0182] recalibrating a machine learning model using the calls and generating one or more additional variant call classifications indicative of the accuracy of the additional genotype calls within the additional genotype call data files based on the additional sequencing metrics for the additional genotype calls; and

[0183] Based on the one or more additional variant call classifications, an additional recalibrated sequencing data file is generated, the additional recalibrated sequencing data file comprising updated additional genotype calls at the genomic coordinates of the additional sample nucleotide sequences.

[0184] Clause 9. The method according to any one of clauses 1 to 8, further comprising: generating the one or more variant detection classifications by generating one or more of a false positive probability that the genotype detection is a false positive, a genotype error probability that the genotype of the genotype detection is incorrect, or a true positive probability that the genotype detection is a true positive.

[0185] Clause 10. The method according to any one of clauses 1 to 9, further comprising determining the updated genotype call by:

[0186] identifying the genomic coordinates as multi-allelic genomic coordinates;

[0187] recalibrating the machine learning model using the calls to generate the one or more variant call classifications, the one or more variant call classifications comprising one or more of: a reference probability that the genotype call comprises a homozygous reference genotype at the multi-allelic genomic coordinates; a zygosity error probability that the genotype call comprises a genotype zygosity error at the multi-allelic genomic coordinates; or a true positive variant probability that the genotype call constitutes a true positive variant at the multi-allelic genomic coordinates; and

[0188] The updated genotype call at the multi-allelic genomic coordinate is determined based on one or more of the reference probability, the zygosity error probability, or the true positive variant probability.

[0189] Clause 11. The method according to any one of clauses 1 to 10, further comprising:

[0190] modifying one or more of a base call quality metric, a genotype probability metric, a genotype metric, a genotype likelihood metric, or a genotype quality metric of the genotype call based on the one or more variant call classifications; and

[0191] The recalibrated sequencing data file is generated, the recalibrated sequencing data file comprising a modified base calling quality metric, a modified genotype probability metric, a modified genotype metric, a modified genotype likelihood metric, or a modified genotype quality metric.

[0192] Clause 12. The method according to any one of clauses 1 to 11, further comprising generating the updated genotype calls at the biallelic genomic coordinates of the sample nucleotide sequence as part of the recalibrated sequencing data file by:

[0193] determining a homozygous reference genotype call at the genomic coordinate instead of a heterozygous variant genotype call or a homozygous variant genotype call reported in the one or more sequencing data files;

[0194] determining the heterozygous variant genotype call at the genomic coordinates instead of the homozygous reference genotype call or the homozygous variant genotype call reported in the one or more sequencing data files; or

[0195] The homozygous variant genotype call at the genomic coordinate is determined instead of the heterozygous variant genotype call or the homozygous reference genotype call reported in the one or more sequencing data files.

[0196] Clause 13. The method according to any one of clauses 1 to 12, further comprising:

[0197] extracting sequencing metrics for additional genotype calls at additional genomic coordinates of the sample nucleotide sequence from the one or more sequencing data files;

[0198] recalibrating a machine learning model using the calls and generating one or more additional variant call classifications indicative of the accuracy of the additional genotype calls within the one or more sequencing data files based on the sequencing metrics for the additional genotype calls;

[0199] modifying a base call quality metric for the additional genotype calls based on the one or more additional variant call classifications to generate a modified base call quality metric that is below a base call quality threshold; and

[0200] The additional genotype calls are annotated to indicate that the modified base call quality metric is below the base call quality threshold.

[0201] Clause 14. The method according to any one of clauses 1 to 13, further comprising:

[0202] extracting sequencing metrics for additional genotype calls at additional genomic coordinates of the sample nucleotide sequence from the one or more sequencing data files;

[0203] recalibrating a machine learning model using the calls and generating one or more additional variant call classifications indicative of the accuracy of the additional genotype calls within the one or more sequencing data files based on the sequencing metrics for the additional genotype calls; and

[0204] The genotype calls at the additional genomic coordinates of the sample nucleotide sequence are confirmed based on the one or more additional variant call classifications.

[0205] Clause 15. The method of any one of clauses 1 to 14, further comprising training the detection recalibration machine learning model by:

[0206] generating a plurality of recalibrated sequencing data files from a plurality of sequencing data files corresponding to a plurality of known genomes;

[0207] comparing updated genotype calls from the plurality of recalibrated sequencing data files to known variants of the plurality of known genomes; and

[0208] Parameters of the call recalibration machine learning model are adjusted based on the differences between the updated genotype calls and the known variants.

[0209] Clause 16. A method comprising:

[0210] For a sample nucleotide sequence, access one or more sequencing data files, the one or more sequencing data files comprising genotype calls at genomic coordinates;

[0211] extracting sequencing metrics for the genotype calling from the one or more sequencing data files;

[0212] recalibrating the machine learning model using the calls and based on the sequencing metrics, generating one or more variant call classifications indicating the accuracy of the genotype calls within the one or more sequencing data files; and

[0213] Based on the one or more variant call classifications, a recalibrated sequencing data file is generated, the recalibrated sequencing data file comprising updated genotype calls at the genomic coordinates of the sample nucleotide sequence.

[0214] Clause 17. The method according to clause 16, further comprising:

[0215] accessing an alignment data file of the one or more sequencing data files, the alignment data file comprising nucleotide reads corresponding to the genomic coordinates of the sample nucleotide sequence; and

[0216] One or more read-based sequencing metrics among the sequencing metrics are extracted from the alignment data file, the one or more read-based sequencing metrics corresponding to the nucleotide reads.

[0217] Clause 18. The method of any one of clauses 16 to 17, further comprising generating the one or more variant call classifications without simultaneously generating the genotype calls using a call generation model.

[0218] Clause 19. A method according to any one of clauses 16 to 18, wherein extracting the sequencing metrics comprises: extracting one or more read-based sequencing metrics or sequencing metrics generated by a call model for the genotype call from a genotype call data file of the one or more sequencing data files, wherein the genotype call data file comprises the genotype call.

[0219] Clause 20. A method according to any one of clauses 16 to 19, further comprising: accessing the genotype call data file by accessing a variant call format (VCF) file or a genomic variant call format (gVCF) file including variant calls and non-variant calls.

[0220] Clause 21. A method according to any one of clauses 16 to 20, wherein the genotype call data file including the genotype call is generated on a computing device executing a hardware accelerator, and the recalibrated sequencing data file is generated using a general purpose processing unit as at least one processor of the system.

[0221] Clause 22. A method according to any one of clauses 16 to 21, wherein the hardware accelerator comprises a field programmable gate array (FPGA) or an application-specific integrated circuit (ASIC), and the recalibrated sequencing data file is generated using one or more of a central processing unit (CPU) or a graphics processing unit (GPU).

[0222] Clause 23. The method according to any one of clauses 16 to 22, further comprising:

[0223] accessing an additional genotype calling data file generated by a version of a call generation model that is different from a version of the call generation model that generated the genotype calling data file;

[0224] extracting additional sequencing metrics for additional genotype calls at genomic coordinates of additional sample nucleotide sequences from the additional genotype call data file;

[0225] recalibrating a machine learning model using the calls and generating one or more additional variant call classifications indicative of the accuracy of the additional genotype calls within the additional genotype call data files based on the additional sequencing metrics for the additional genotype calls; and

[0226] Based on the one or more additional variant call classifications, an additional recalibrated sequencing data file is generated, the additional recalibrated sequencing data file comprising updated additional genotype calls at the genomic coordinates of the additional sample nucleotide sequences.

[0227] Clause 24. The method according to any one of clauses 16 to 23, further comprising: generating the one or more variant detection classifications by generating one or more of a false positive probability that the genotype detection is a false positive, a genotype error probability that the genotype of the genotype detection is incorrect, or a true positive probability that the genotype detection is a true positive.

[0228] Clause 25. The method of any one of clauses 16 to 24, further comprising determining the updated genotype call by:

[0229] identifying the genomic coordinates as multi-allelic genomic coordinates;

[0230] recalibrating the machine learning model using the calls to generate the one or more variant call classifications, the one or more variant call classifications comprising one or more of: a reference probability that the genotype call comprises a homozygous reference genotype at the multi-allelic genomic coordinates; a zygosity error probability that the genotype call comprises a genotype zygosity error at the multi-allelic genomic coordinates; or a true positive variant probability that the genotype call constitutes a true positive variant at the multi-allelic genomic coordinates; and

[0231] The updated genotype call at the multi-allelic genomic coordinate is determined based on one or more of the reference probability, the zygosity error probability, or the true positive variant probability.

[0232] Clause 26. The method according to any one of clauses 16 to 25, further comprising:

[0233] modifying one or more of a base call quality metric, a genotype probability metric, a genotype metric, a genotype likelihood metric, or a genotype quality metric of the genotype call based on the one or more variant call classifications; and

[0234] The recalibrated sequencing data file is generated, the recalibrated sequencing data file comprising a modified base calling quality metric, a modified genotype probability metric, a modified genotype metric, a modified genotype likelihood metric, or a modified genotype quality metric.

[0235] Clause 27. The method of any one of clauses 16 to 26, further comprising generating the updated genotype calls at the biallelic genomic coordinates of the sample nucleotide sequence as part of the recalibrated sequencing data file by:

[0236] determining a homozygous reference genotype call at the genomic coordinate instead of a heterozygous variant genotype call or a homozygous variant genotype call reported in the one or more sequencing data files;

[0237] determining the heterozygous variant genotype call at the genomic coordinates instead of the homozygous reference genotype call or the homozygous variant genotype call reported in the one or more sequencing data files; or

[0238] The homozygous variant genotype call at the genomic coordinate is determined instead of the heterozygous variant genotype call or the homozygous reference genotype call reported in the one or more sequencing data files.

[0239] Clause 28. The method according to any one of clauses 16 to 27, further comprising:

[0240] extracting sequencing metrics for additional genotype calls at additional genomic coordinates of the sample nucleotide sequence from the one or more sequencing data files;

[0241] recalibrating a machine learning model using the calls and generating one or more additional variant call classifications indicative of the accuracy of the additional genotype calls within the one or more sequencing data files based on the sequencing metrics for the additional genotype calls;

[0242] modifying a base call quality metric for the additional genotype calls based on the one or more additional variant call classifications to generate a modified base call quality metric that is below a base call quality threshold; and

[0243] The additional genotype calls are annotated to indicate that the modified base call quality metric is below the base call quality threshold.

[0244] Clause 29. The method according to any one of clauses 16 to 28, further comprising:

[0245] extracting sequencing metrics for additional genotype calls at additional genomic coordinates of the sample nucleotide sequence from the one or more sequencing data files;

[0246] recalibrating a machine learning model using the calls and generating one or more additional variant call classifications indicative of the accuracy of the additional genotype calls within the one or more sequencing data files based on the sequencing metrics for the additional genotype calls; and

[0247] The genotype calls at the additional genomic coordinates of the sample nucleotide sequence are confirmed based on the one or more additional variant call classifications.

[0248] Clause 30. The method of any one of clauses 16 to 29, further comprising training the detection recalibration machine learning model by:

[0249] generating a plurality of recalibrated sequencing data files from a plurality of sequencing data files corresponding to a plurality of known genomes;

[0250] comparing updated genotype calls from the plurality of recalibrated sequencing data files to known variants of the plurality of known genomes; and

[0251] Parameters of the call recalibration machine learning model are adjusted based on the differences between the updated genotype calls and the known variants.

[0252] Clause 31. A method according to any one of clauses 16 to 30, wherein:

[0253] Generating the one or more variant call classifications comprises: generating the one or more variant call classifications for one or more candidate indels using the call recalibration machine learning model trained with insertion or deletion (indel) training data; and

[0254] Generating the recalibrated sequencing data file includes: generating the updated genotype call based on the one or more variant call classifications for the one or more candidate indels, the updated genotype call indicating the presence or absence of an indel at the genomic coordinates of the sample nucleotide sequence.

[0255] Clause 32. A method according to any one of clauses 16 to 31, wherein:

[0256] Generating the one or more variant call classifications comprises: generating the one or more variant call classifications for one or more candidate SNVs using the call recalibration machine learning model trained with single nucleotide variant (SNV) training data; and

[0257] Generating the recalibrated sequencing data file includes: generating the updated genotype call based on the one or more variant call classifications for the one or more candidate SNVs, the updated genotype call indicating the presence or absence of the SNV at the genomic coordinates of the sample nucleotide sequence.

[0258] Methods described herein can be used in combination with multiple nucleic acid sequencing techniques. Particularly suitable techniques are those in which nucleic acids are attached to fixed positions in an array so that their relative positions do not change and in which the array is repeatedly imaged. Embodiments in which images are obtained in different color channels (e.g., matching different markers for distinguishing a nucleotide base type from another nucleotide base type) are particularly suitable. In some embodiments, the process for determining the nucleotide sequence of a target nucleic acid (i.e., nucleic acid polymer) can be an automated process. Preferred embodiments include sequencing by synthesis (SBS) technology.

[0259] SBS techniques generally include enzymatic extension of nascent nucleic acid chains by repeated addition of nucleotides to the template strand. In traditional SBS methods, a single nucleotide monomer can be provided to the target nucleotide in the presence of a polymerase in each delivery. However, in the methods described herein, more than one type of nucleotide monomer can be provided to the target nucleic acid in the presence of a polymerase in the delivery.

[0260] SBS can utilize nucleotide monomers with terminator parts or lack nucleotide monomers of any terminator parts.The method using the nucleotide monomer lacking terminator includes for example pyrophosphate sequencing and the sequencing of nucleotides using gamma-phosphate labeling, as described in further detail below.In the method using the nucleotide monomer lacking terminator, the number of nucleotides added in each cycle is usually variable, and the number depends on the mode of template sequence and nucleotide delivery.For the SBS technology utilizing the nucleotide monomer with terminator part, terminator can be effectively irreversible under the sequencing conditions used, such as the situation of traditional Sanger sequencing utilizing dideoxynucleotides, or terminator can be reversible, such as the situation of the sequencing method developed by Solexa (now Illumina, Inc.).

[0261] The SBS technique can utilize nucleotide monomers with a labeling portion or nucleotide monomers lacking a labeling portion. Thus, incorporation events can be detected based on the following items: properties of the label, such as the fluorescence of the label; properties of the nucleotide monomer, such as molecular weight or charge; byproducts of the incorporated nucleotide, such as the release of pyrophosphate; and the like. In embodiments where two or more different nucleotides are present in the sequencing reagent, the different nucleotides may be distinguishable from each other, or alternatively, the two or more different labels may be indistinguishable under the detection technology used. For example, different nucleotides present in the sequencing reagent may have different labels, and they may be distinguished using appropriate optical devices, as exemplified by the sequencing method developed by Solexa (now Illumina, Inc.).

[0262] Preferred embodiments include pyrophosphate sequencing technology. Pyrophosphate sequencing detects the release of inorganic pyrophosphate (PPi) when a specific nucleotide is incorporated into a nascent chain (Ronaghi, M., Karamohamed, S., Pettersson, B., Uhlen, M., and Nyren, P. (1996), "Real-time DNA sequencing using detection of pyrophosphate release.", Analytical Biochemistry 242 (1), 84-9; Ronaghi, M. (2001), "Pyrosequencing sheds light on DNA sequencing.", Genome Res. 11 (1), 3-11; Ronaghi, M., Uhlen, M., and Nyren, P. (1998), "A sequencing method based on real-time pyrophosphate.", Science 281 (5375), 363; U.S. Pat. No. 6,210,891; U.S. Pat. No. 6,258,568 and U.S. Pat. No. 6,274,320, the disclosures of which are incorporated herein by reference in their entirety). In pyrophosphate sequencing, the released PPi can be detected by being immediately converted into ATP by adenosine triphosphate (ATP) sulfurylase, and the level of ATP generated is detected by photons generated by luciferase. The nucleic acid to be sequenced can be attached to a feature in an array, and the array can be imaged to capture the chemiluminescent signal generated by the incorporation of nucleotides at the feature of the array. The image can be obtained after the array is treated with a specific nucleotide type (e.g., A, T, C or G). The images obtained after adding each nucleotide type will differ in which features in the array are detected. These differences in the image reflect the different sequence contents of the features on the array. However, the relative position of each feature will remain unchanged in the image. The images can be stored, processed and analyzed using the methods described herein. For example, images obtained after treating the array with each different nucleotide type can be processed in the same manner as exemplified herein for images obtained from different detection channels for a reversible terminator-based sequencing method.

[0263] In another exemplary type of SBS, cycle sequencing is accomplished by the stepwise addition of reversible terminator nucleotides, which contain, for example, cleavable or photobleachable dye labels, as described in, for example, WO 04 / 018497 and U.S. Patent No. 7,057,026, the disclosures of which are incorporated herein by reference. The method is commercialized by Solexa (now Illumina Inc.) and is also described in WO 91 / 06678 and WO 07 / 123,744, the disclosures of each of which are incorporated herein by reference. The availability of fluorescently labeled terminators, in which termination can be reversible and the fluorescent label can be cleaved, facilitates efficient cyclic reversible termination (CRT) sequencing. Polymerases can also be co-engineered to efficiently incorporate these modified nucleotides and extend from these modified nucleotides.

[0264] Preferably, in the sequencing embodiment based on reversible terminator, the label does not substantially inhibit extension under SBS reaction conditions. However, the detection label can be removable, such as removed by cleavage or degradation. Images can be captured after the label is incorporated into the arrayed nucleic acid feature. In a specific embodiment, each cycle involves four different nucleotide types being delivered to the array simultaneously, and each nucleotide type has spectrally different labels. Four images can then be obtained, each image using a detection channel that is selective to one label in the four different labels. Alternatively, different nucleotide types can be added sequentially, and the image of the array can be obtained between each addition step. In such embodiments, each image will show the nucleic acid feature of the nucleotides that have been incorporated with a specific type. Due to the different sequence content of each feature, different feature portions are present or absent in different images. However, the relative position of the feature portion will remain unchanged in the image. The image obtained by such reversible terminator-SBS method can be stored, processed and analyzed as described herein. After the image capture step, the label can be removed, and the reversible terminator portion can be removed to perform subsequent cycles of nucleotide addition and detection. Removing labels after they have been detected in a particular cycle and before subsequent cycles can provide the advantage of reducing background signal and crosstalk between cycles. Examples of useful labeling and removal methods are set forth below.

[0265] In a specific embodiment, some or all of the nucleotide monomers may include a reversible terminator. In such embodiments, the reversible terminator / cleavable fluorophore may include a fluorophore (Metzker, Genome Res. 15: 1767-1776 (2005), which is incorporated herein by reference) connected to a ribose moiety via a 3' ester bond. Other methods have separated terminator chemistry from the cleavage of a fluorescent label (Ruparel et al., Proc Natl Acad Sci USA 102: 5932-7 (2005), which is incorporated herein by reference in its entirety). Ruparel et al. describe the development of reversible terminators that use small 3' allyl groups to block extension, but can be easily deblocked by a short treatment with a palladium catalyst. The fluorophore is attached to the base via a photocleavable linker that can be easily cleaved by exposure to long wavelength ultraviolet light for 30 seconds. Therefore, disulfide reduction or photocleavage can be used as a cleavable linker. Another method of reversible termination is to use natural termination, which occurs after a bulky dye is placed on a dNTP. The presence of a charged bulky dye on a dNTP can act as an efficient terminator by steric hindrance and / or electrostatic hindrance. Unless the dye is removed, the presence of an incorporation event prevents further incorporation. The cracking of the dye removes the fluorophore and effectively reverses termination. The example of modified nucleotides is also described in U.S. Patent No. 7,427,673 and U.S. Patent No. 7,057,026, the disclosure of which is incorporated herein by reference in its entirety.

[0266] Additional exemplary SBS systems and methods that may be utilized with the methods and systems described herein are described in U.S. Patent Application Publication No. 2007 / 0166705, U.S. Patent Application Publication No. 2006 / 0188901, U.S. Patent No. 7,057,026, U.S. Patent Application Publication No. 2006 / 0240439, U.S. Patent Application Publication No. 2006 / 0281109, PCT Publication No. WO 05 / 065814, U.S. Patent Application Publication No. 2005 / 0100900, PCT Publication No. WO 06 / 064199, PCT Publication No. WO 07 / 010,251, U.S. Patent Application Publication No. 2012 / 0270305, and U.S. Patent Application Publication No. 2013 / 0260372, the disclosures of which are incorporated herein by reference in their entireties.

[0267] Some embodiments can use the detection of four different nucleotides using less than four different marks.For example, the method and system described in the material of the U.S. Patent Application Publication No. 2013 / 0079232 incorporated can be used to perform SBS.As a first example, a pair of nucleotide types can be detected at the same wavelength, but based on the intensity difference of a member in the pair relative to another member, or based on a member in the pair causing a change (for example, by chemical modification, photochemical modification or physical modification) that a signal that is obvious compared with the signal of another member of the pair detected appears or disappears.As a second example, three of the four different nucleotide types can be detected under specific conditions, and the fourth nucleotide type lacks a mark (for example, the minimum detection caused by background fluorescence, etc.) that can be detected under those conditions or detected minimally under those conditions.The first three nucleotide types can be determined to be incorporated into nucleic acid based on the existence of its corresponding signal, and the fourth nucleotide type can be determined to be incorporated into nucleic acid based on the absence of any signal or the minimum detection of any signal.As a third example, a nucleotide type can include a mark detected in two different channels, and other nucleotide types are detected in no more than one channel. The above three exemplary configurations are not considered mutually exclusive and can be used in various combinations. An exemplary embodiment combining all three examples is a fluorescence-based SBS method that uses a first nucleotide type detected in a first channel (e.g., dATP with a label detected in the first channel when excited by a first excitation wavelength), a second nucleotide type detected in a second channel (e.g., dCTP with a label detected in the second channel when excited by a second excitation wavelength), a third nucleotide type detected in both the first channel and the second channel (e.g., dTTP with at least one label detected in both channels when excited by the first excitation wavelength and / or the second excitation wavelength), and a fourth nucleotide type that lacks a label detected or minimally detected in either channel (e.g., dGTP without a label).

[0268] In addition, as described in the materials of incorporated U.S. Patent Application Publication No. 2013 / 0079232, a single channel can be used to obtain sequencing data. In such so-called single dye sequencing methods, a first nucleotide type is marked, but the mark is removed after the first image is generated, and a second nucleotide type is marked only after the first image is generated. A third nucleotide type retains its mark in both the first image and the second image, and a fourth nucleotide type remains unmarked in both images.

[0269] Some embodiments can utilize sequencing technology while connecting. Such technology utilizes DNA ligase to incorporate oligonucleotides and recognize the incorporation of such oligonucleotides. Oligonucleotides generally have different labels related to the identity of specific nucleotides in the sequence of oligonucleotide hybridization. As with other SBS methods, images can be obtained after the array of nucleic acid feature parts is treated with labeled sequencing reagents. Each image will show the nucleic acid feature parts of the labeling that has been incorporated into a specific type. Due to the different sequence content of each feature part, different feature parts are present or absent in different images, but the relative orientation of the feature parts will remain unchanged in the image. The images obtained by the sequencing method based on connection can be stored, processed and analyzed as described herein. Exemplary SBS systems and methods that can be used with the methods and systems described herein are described in U.S. Patent No. 6,969,488, U.S. Patent No. 6,172,218 and U.S. Patent No. 6,306,597, and the disclosures of these patents are incorporated herein by reference in their entirety.

[0270] Some embodiments may utilize nanopore sequencing (Deamer, DW and Akeson, M., "Nanopores and nucleic acids: prospects for ultrarapid sequencing.", Trends Biotechnol. 18, 147-151 (2000); Deamer, D. and D. Branton, "Characterization of nucleic acids by nanopore analysis.", Acc. Chem. Res. 35: 817-825 (2002); Li, J., M. Gershow, D. Stein, E. Brandin and JA Golovchenko, "DNA molecules and configurations in a solid-state nanopore microscope", Nat. Mater., 2: 611-615 (2003), the disclosures of which are incorporated herein by reference in their entirety). In such embodiments, the target nucleic acid passes through the nanopore. The nanopore may be a synthetic pore or a biological membrane protein, such as α-hemolysin. As the target nucleic acid passes through the nanopore, each base pair can be identified by measuring the fluctuations in the conductivity of the pore. (U.S. Pat. No. 7,001,792; Soni, GV and Meller, "A. Progress toward ultrafast DNA sequencing using solid-state nanopores.", Clin. Chem. 53, 1996-2001 (2007); Healy, K., "Nanopore-based single-molecule DNA analysis.", Nanomed., 2, 459-481 (2007); Cockroft, SL, Chu, J., Amorin, M. and Ghadiri, MR, "A single-molecule nanopore device detects DNA polymerase activity with single-nucleotide resolution.", J. Am. Chem. Soc. 130, 818-820 (2008), the disclosures of which are incorporated herein by reference in their entirety). The data obtained from nanopore sequencing can be stored, processed and analyzed as described herein. In particular, according to the exemplary processing of optical images and other images described herein, the data can be processed like an image.

[0271] Some embodiments may utilize methods involving real-time monitoring of DNA polymerase activity. Nucleotide incorporation may be detected by fluorescence resonance energy transfer (FRET) interactions between a polymerase carrying a fluorophore and a γ-phosphate labeled nucleotide, as described, for example, in U.S. Pat. No. 7,329,492 and U.S. Pat. No. 7,211,414 (each of which is incorporated herein by reference), or may be detected with a zero-mode waveguide, as described, for example, in U.S. Pat. No. 7,315,019 (which is incorporated herein by reference), and may be detected with fluorescent nucleotide analogs and engineered polymerases, as described, for example, in U.S. Pat. No. 7,405,281 and U.S. Patent Application Publication No. 2008 / 0108082 (each of which is incorporated herein by reference). Illumination can be limited to a volume of magnitude around the surface-tethered polymerase, so that incorporation of fluorescently labeled nucleotides can be observed with low background (Levene, MJ et al., "Zero-mode waveguides for single-molecule analysis at high concentrations.", Science 299, 682-686 (2003); Lundquist, PM et al., "Parallelconfocal detection of single molecules in real time.", Opt. Lett. 33, 1026-1028 (2008); Korlach, J. et al., "Selective aluminum passivation for targeted immobilization of single DNA polymerase molecules in zero-mode waveguide nanostructures.", Proc. Natl. Acad. Sci. USA 105, 1176-1181 (2008), the disclosures of which are incorporated herein by reference in their entirety). Images obtained by such methods can be stored, processed, and analyzed as described herein.

[0272] Some SBS embodiments include detecting the proton released when nucleotides are incorporated into extension products. For example, sequencing based on the detection of releasing protons can use the commercially available electrical detectors and related technologies available from Ion Torrent company (Guilford, CT, it is a Life Technologies subsidiary) or the sequencing methods and systems described in US2009 / 0026082A1, US2009 / 0127589A1, US2010 / 0137143A1 or US 2010 / 0282617A1, each of which is incorporated herein by reference. The method for amplifying target nucleic acids using kinetic exclusion set forth herein can be easily applied to substrates for detecting protons. More specifically, the method set forth herein can be used to produce amplicon clone colonies for detecting protons.

[0273] The above-mentioned SBS method can be advantageously carried out in a variety of formats so that a plurality of different target nucleic acids are manipulated simultaneously. In a specific embodiment, different target nucleic acids can be processed in a common reaction vessel or on the surface of a specific substrate. This allows to conveniently deliver sequencing reagents, remove unreacted reagents and detect incorporation events in a variety of ways. In the embodiment using the target nucleic acid of surface binding, the target nucleic acid can be an array format. In the array format, the target nucleic acid can be attached to the surface in a spatially distinguishable manner generally. The target nucleic acid can be attached by direct covalent attachment, attached to beads or other particles or attached to a polymerase or other molecules attached to the surface to combine. The array can include a single copy of the target nucleic acid at each site (also referred to as a feature portion), or multiple copies with the same sequence can be present at each site or feature portion. Multiple copies can be produced by an amplification method (such as bridge amplification or emulsion PCR as described in further detail below).

[0274] The methods described herein may use arrays having features at any of a variety of densities, including, for example, at least about 10 features / cm2, 100 features / cm2, 500 features / cm2, 1,000 features / cm2, 5,000 features / cm2, 10,000 features / cm2, 50,000 features / cm2, 100,000 features / cm2, 1,000,000 features / cm2, 5,000,000 features / cm2, or more.

[0275] The advantage of the method described herein is that they provide rapid and effective detection of multiple target nucleic acids in parallel. Therefore, the present disclosure provides an integrated system that can use technology known in the art (such as those illustrated above) to prepare and detect nucleic acids. Therefore, the integrated system of the present disclosure may include a fluid assembly that can deliver amplification reagents and / or sequencing reagents to one or more fixed DNA fragments, and the system includes components such as pumps, valves, reservoirs, fluid pipelines, etc. The circulation cell can be configured for and / or for detecting target nucleic acids in the integrated system. Exemplary circulation cells are described in, for example, US2010 / 0111768A1 and U.S. Serial No. 13 / 273,666, each of which is incorporated herein by reference. As illustrated for the circulation cell, one or more fluid assemblies of the integrated system can be used for amplification method and detection method. Taking nucleic acid sequencing embodiment as an example, one or more fluid assemblies of the integrated system can be used for the amplification method described herein and for delivering sequencing reagents in sequencing method (such as those illustrated above). Alternatively, the integrated system may include a separate fluid system to perform amplification method and perform detection method. Examples of integrated sequencing systems capable of producing amplified nucleic acids and also determining nucleic acid sequences include, but are not limited to, MiSeq TM The ELISA platform (Illumina, Inc., San Diego, CA) and the apparatus described in U.S. Ser. No. 13 / 273,666, which is incorporated herein by reference.

[0276] The above-mentioned sequencing system sequences the nucleic acid polymers present in the sample received by the sequencing device. As defined herein, "sample" and its derivatives are used in their broadest sense, including any specimens, cultures, etc. suspected of containing a target. In some embodiments, the sample includes nucleic acids in the form of DNA, RNA, PNA, LNA, chimeric or hybrid forms. The sample may include any biological, clinical, surgical, agricultural, atmospheric or aquatic animal and plant specimens containing one or more nucleic acids. The term also includes any isolated nucleic acid sample, such as genomic DNA, fresh frozen or formalin-fixed paraffin-embedded nucleic acid specimens. It is also envisioned that the sample may come from: a single individual, a collection of nucleic acid samples from genetically related members, a nucleic acid sample from a genetically unrelated member, a nucleic acid sample (matched therewith) from a single individual (such as a tumor sample and a normal tissue sample), or a sample from a single source containing two different forms of genetic material (such as maternal DNA and fetal DNA obtained from a maternal subject), or there is contaminating bacterial DNA in a sample containing plant or animal DNA. In some embodiments, the source of nucleic acid material may include nucleic acids obtained from newborns, such as nucleic acids commonly used for newborn screening.

[0277] Nucleic acid samples may include high molecular weight substances, such as genomic DNA (gDNA). Samples may include low molecular weight substances, such as nucleic acid molecules obtained from FFPE samples or archived DNA samples. In another embodiment, low molecular weight substances include DNA of enzymatic fragmentation or mechanical fragmentation. Samples may include cell-free circulating DNA. In some embodiments, samples may include nucleic acid molecules obtained from biopsy tissue, tumor, scrapings, swabs, blood, mucus, urine, plasma, semen, hair, laser capture microdissection, surgical resection and other clinical or laboratory samples. In some embodiments, samples may be epidemiological samples, agricultural samples, forensic samples or pathogenic samples. In some embodiments, samples may include nucleic acid molecules obtained from animals (such as humans or mammalian sources). In another embodiment, samples may include nucleic acid molecules obtained from non-mammalian sources (such as plants, bacteria, viruses or fungi). In some embodiments, the source of nucleic acid molecules may be archived or extinct samples or species.

[0278] In addition, the methods and compositions disclosed herein can be used to amplify nucleic acid samples with low-quality nucleic acid molecules, such as degraded and / or fragmented genomic DNA from forensic samples. In one embodiment, forensic samples may include nucleic acids obtained from crime scenes, nucleic acids obtained from missing persons DNA databases, nucleic acids obtained from laboratories associated with forensic investigations, or include forensic samples obtained by law enforcement agencies, one or more military services, or any such personnel. Nucleic acid samples can be purified samples or lysates containing crude DNA, such as from oral swabs, paper, fabrics, or other substrates that can be impregnated with saliva, blood, or other body fluids. Therefore, in some embodiments, the nucleic acid sample may include a small amount of DNA (such as genomic DNA), or a fragmented portion of DNA. In some embodiments, the target sequence may be present in one or more body fluids, wherein body fluids include but are not limited to blood, sputum, plasma, semen, urine, and serum. In some embodiments, the target sequence may be obtained from the victim's hair, skin, tissue sample, autopsy, or remains. In some embodiments, nucleic acids comprising one or more target sequences may be obtained from dead animals or humans. In some embodiments, the target sequence may include a nucleic acid obtained from non-human DNA (such as microbial, plant, or insect DNA). In some embodiments, the target sequence or amplified target sequence is directed to the purpose of human identification. In some embodiments, the disclosure as a whole relates to methods for identifying the characteristics of forensic samples. In some embodiments, the disclosure as a whole relates to human identification methods using one or more target-specific primers disclosed herein or one or more target-specific primers designed using the primer design standards outlined herein. In one embodiment, a forensic sample or human identification sample containing at least one target sequence can be amplified using any one or more target-specific primers disclosed herein or using the primer standards outlined herein.

[0279] The components of the detection recalibration system 106 may include software, hardware, or both. For example, the components of the detection recalibration system 106 may include one or more instructions stored on a computer-readable storage medium and executable by a processor of one or more computing devices (e.g., client device 108). When executed by one or more processors, the computer-executable instructions of the detection recalibration system 106 may cause the computing device to perform the bubble detection method described herein. Alternatively, the components of the detection recalibration system 106 may include hardware, such as a dedicated processing device for performing a certain function or group of functions. Additionally or alternatively, the components of the detection recalibration system 106 may include a combination of computer-executable instructions and hardware.

[0280] In addition, the components of the detection recalibration system 106 that perform the functions described herein with respect to the detection recalibration system 106 may be implemented, for example, as part of a stand-alone application, a module of an application, a plug-in of an application, one or more library functions that can be called by other applications, and / or a cloud computing model. Therefore, the components of the detection recalibration system 106 can be implemented as part of a stand-alone application on a personal computing device or a mobile device. Additionally or alternatively, the components of the detection recalibration system 106 can be implemented in any application that provides sequencing services, including but not limited to Illumina BaseSpace, Illumina DRAGEN, or Illumina TruSight software. "Illumina", "BaseSpace", "DRAGEN", and "TruSight" are registered trademarks or trademarks of Illumina, Inc. in the United States and / or other countries.

[0281] As discussed in more detail below, embodiments of the present disclosure may include or utilize a special-purpose or general-purpose computer including computer hardware (such as, for example, one or more processors and system memory). Embodiments within the scope of the present disclosure also include physical and other computer-readable media for carrying or storing computer-executable instructions and / or data structures. Specifically, one or more of the processes described herein may be implemented at least in part as instructions embodied in a non-transitory computer-readable medium and executable by one or more computing devices (e.g., any of the media content access devices described herein). In general, a processor (e.g., a microprocessor) receives instructions from a non-transitory computer-readable medium (e.g., a memory, etc.) and executes those instructions, thereby performing one or more processes, including one or more of the processes described herein.

[0282] Computer readable media can be any available media that can be accessed by a general or special purpose computer system. A computer readable medium that stores computer executable instructions is a non-transitory computer readable storage medium (device). A computer readable medium that carries computer executable instructions is a transmission medium. Therefore, by way of example and not limitation, embodiments of the present disclosure may include at least two distinct types of computer readable media: a non-transitory computer readable storage medium (device) and a transmission medium.

[0283] Non-transitory computer-readable storage media (devices) include RAM, ROM, EEPROM, CD-ROM, solid-state drives (SSD) (e.g., RAM-based), flash memory, phase-change memory (PCM), other types of memory, other optical disk storage devices, magnetic disk storage devices or other magnetic storage devices, or any other media that can be used to store desired program code means in the form of computer-executable instructions or data structures and which can be accessed by a general or special purpose computer.

[0284] "Network" is defined as one or more data links that enable the transmission of electronic data between computer systems and / or modules and / or other electronic devices. When information is transferred or provided to a computer via a network or another communication connection (hardwired, wireless, or a combination of hardwired or wireless), the computer appropriately regards the connection as a transmission medium. The transmission medium may include a network and / or data link, which can be used to carry the desired program code means in the form of computer executable instructions or data structures, and which can be accessed by general or special computers. The above combinations should also be included in the scope of computer-readable media.

[0285] Additionally, upon reaching various computer system components, program code means in the form of computer executable instructions or data structures may be automatically transferred from a transmission medium to a non-transitory computer readable storage medium (device) (or vice versa). For example, a computer executable instruction or data structure received over a network or data link may be buffered in RAM within a network interface module (e.g., NIC), and then ultimately transferred to the computer system RAM and / or to a less volatile computer storage medium (device) at the computer system. Thus, it should be understood that a non-transitory computer readable storage medium (device) may be included in a computer system component that also (or even primarily) utilizes a transmission medium.

[0286] Computer executable instructions include, for example, instructions and data that make a general-purpose computer, a special-purpose computer, or a special-purpose processing device perform certain functions or groups of functions when executed at a processor. In some embodiments, computer executable instructions are executed on a general-purpose computer to turn a general-purpose computer into a special-purpose computer that implements an element of the present disclosure. Computer executable instructions can be, for example, binary numbers, intermediate format instructions such as assembly language, or even source code. Although the subject matter has been described in a language specific to structural features and / or method actions, it should be understood that the subject matter defined in the appended claims is not necessarily limited to the described features or actions. On the contrary, the described features and actions are disclosed as an example form of implementing the claims.

[0287] Those skilled in the art will appreciate that the present disclosure can be practiced in a network computing environment with many types of computer system configurations, including personal computers, desktop computers, portable computers, message processors, handheld devices, multiprocessor systems, microprocessor-based or programmable consumer electronics, network PCs, minicomputers, mainframe computers, mobile phones, PDAs, tablet computers, pagers, routers, switches, etc. The present disclosure can also be practiced in a distributed system environment, where both local and remote computer systems linked by a network (by a hardwired data link, a wireless data link, or a combination of hardwired and wireless data links) perform tasks. In a distributed system environment, program modules can be located in both local and remote memory storage devices.

[0288] Embodiments of the present disclosure may also be implemented in a cloud computing environment. In this specification, "cloud computing" is defined as a model for implementing on-demand network access to a shared pool of configurable computing resources. For example, cloud computing may be employed in the marketplace to provide ubiquitous and convenient on-demand access to a shared pool of configurable computing resources. A shared pool of configurable computing resources may be quickly provisioned via virtualization and released with low management effort or service provider interaction, and then scaled accordingly.

[0289] The cloud computing model may consist of various characteristics, such as, for example, on-demand self-service, broad network access, resource pooling, rapid elasticity, metered services, etc. The cloud computing model may also exhibit various service models, such as, for example, software as a service (SaaS), platform as a service (PaaS), and infrastructure as a service (IaaS). The cloud computing model may also be deployed using different deployment models, such as private cloud, community cloud, public cloud, hybrid cloud, etc. In this specification and in the claims, a "cloud computing environment" is an environment in which cloud computing is employed.

[0290] Fig.10 A block diagram of a computing device 1000 that can be configured to perform one or more of the above processes is illustrated. It will be appreciated that one or more computing devices such as computing device 1000 can implement the call recalibration system 106 and the sequencing system 104. Fig.10 As shown, computing device 1000 may include a processor 1002, memory 1004, storage device 1006, I / O interface 1008, and communication interface 1010 that may be communicatively coupled via communication infrastructure 1012. In some embodiments, computing device 1000 may include Fig.10 Those shown may have fewer or more components. The following paragraphs describe in more detail Fig.10 Components of computing device 1000 are shown.

[0291] In one or more embodiments, the processor 1002 includes hardware for executing instructions such as those constituting a computer program. As an example and not by way of limitation, in order to execute instructions for dynamically modifying a workflow, the processor 1002 may retrieve (or fetch) instructions from an internal register, an internal cache, a memory 1004, or a storage device 1006, and decode and execute them. The memory 1004 may be a volatile or non-volatile memory for storing data, metadata, and programs executed by the processor. The storage device 1006 includes a storage device for storing data or instructions for executing the methods described herein, such as a hard disk, a flash drive, or other digital storage device.

[0292] I / O interface 1008 allows a user to provide input to computing device 1000, receive output from the computing device and otherwise transfer data to the computing device and receive data from the computing device. I / O interface 1008 may include a combination of a mouse, a keypad or keyboard, a touch screen, a camera, an optical scanner, a network interface, a modem, other known I / O devices or such I / O interfaces. I / O interface 1008 may include one or more devices for presenting output to a user, including but not limited to a graphics engine, a display (e.g., a display screen), one or more output drivers (e.g., a display driver), one or more audio speakers and one or more audio drivers. In certain embodiments, I / O interface 1008 is configured to provide graphics data to the display for presentation to the user. Graphics data may represent one or more graphical user interfaces and / or may serve any other graphics content of a specific implementation.

[0293] The communication interface 1010 may include hardware, software, or both. In any case, the communication interface 1010 may provide one or more interfaces for communication (such as, for example, packet-based communication) between the computing device 1000 and one or more other computing devices or networks. As an example and not by way of limitation, the communication interface 1010 may include a network interface controller (NIC) or network adapter for communicating with an Ethernet or other wired-based network, or a wireless NIC (WNIC) or wireless adapter for communicating with a wireless network such as WI-FI.

[0294] Additionally, the communication interface 1010 can facilitate communication with various types of wired or wireless networks. The communication interface 1010 can also facilitate communication using various communication protocols. The communication infrastructure 1012 can also include hardware, software, or both that couple components of the computing device 1000 to each other. For example, the communication interface 1010 can use one or more networks and / or protocols to enable multiple computing devices connected through a specific infrastructure to communicate with each other to perform one or more aspects of the processes described herein. For illustration, a sequencing process can allow multiple devices (e.g., a client device, a sequencing device, and a server device) to exchange information such as sequencing data and error notifications.

[0295] In the foregoing description, the present disclosure has been described with reference to specific exemplary embodiments thereof. Various embodiments and aspects of the present disclosure are described with reference to the details discussed herein, and the accompanying drawings illustrate various embodiments. The above description and drawings are illustrative of the present disclosure and should not be construed as limiting the present disclosure. Many specific details are described to provide a thorough understanding of the various embodiments of the present disclosure.

[0296] The present disclosure can be embodied in other specific forms without departing from its spirit or essential characteristics. The described embodiments should be considered as only illustrative and non-restrictive in all aspects. For example, the methods described herein can be performed with fewer or more steps / actions, or the steps / actions can be performed in different orders. Additionally, the steps / actions described herein can be repeated or performed in parallel with each other or in parallel with different examples of the same or similar steps / actions. Therefore, the scope of the application is indicated by the attached claims rather than the aforementioned description. All changes within the equivalent meaning and scope of the claims will be included within their scope.

Claims

1. A system, comprising: at least one processor; and A non-transitory computer readable medium comprising instructions that, when executed by the at least one processor, cause the system to: For a sample nucleotide sequence, access one or more sequencing data files, wherein the sequencing data files include nucleotide reads at genomic coordinates and genotype call data; extracting sequencing metrics for the nucleotide reads or the genotype calls from the one or more sequencing data files; Recalibrate the machine learning model using the calls and based on the sequencing metrics, generating one or more variant call classifications indicating the accuracy of the genotype calls within the one or more sequencing data files; and Based on the one or more variant call classifications, a recalibrated sequencing data file is generated, the recalibrated sequencing data file comprising updated genotype calls at the genomic coordinates of the sample nucleotide sequence.

2. The system of claim 1, further comprising instructions that, when executed by the at least one processor, cause the system to perform the following operations: generate the one or more variant call classifications without simultaneously generating the genotype calls using a call generation model.

3. The system of claim 1 , wherein extracting the sequencing metrics for the genotype calling comprises: One or more read-based sequencing metrics are extracted from the aligned data files of the one or more sequencing data files.

4. The system of claim 1 , wherein extracting the sequencing metric comprises: One or more read-based sequencing metrics or calling model-generated sequencing metrics for the genotype calls are extracted from a genotype calling data file of the one or more sequencing data files, the genotype calling data file including the genotype calls.

5. The system of claim 4, further comprising instructions that, when executed by the at least one processor, cause the system to perform the following operations: access the genotype call data file by accessing a variant call format (VCF) file or a genomic variant call format (gVCF) file that includes variant calls and non-variant calls.

6. A system according to claim 4, wherein the genotype call data file including the genotype call is generated on a computing device executing a hardware accelerator, and the recalibrated sequencing data file is generated using a general purpose processing unit as the at least one processor of the system.

7. The system of claim 6, wherein the hardware accelerator comprises a field programmable gate array (FPGA) or an application specific integrated circuit (ASIC), and the recalibrated sequencing data file is generated using one or more of a central processing unit (CPU) or a graphics processing unit (GPU).

8. The system of claim 4, further comprising instructions that, when executed by the at least one processor, cause the system to: accessing an additional genotype calling data file generated by a version of a call generation model that is different from a version of the call generation model that generated the genotype calling data file; extracting additional sequencing metrics for additional genotype calls at genomic coordinates of additional sample nucleotide sequences from the additional genotype call data file; recalibrating the machine learning model using the calls and generating one or more additional variant call classifications indicative of the accuracy of the additional genotype calls within the additional genotype call data files based on the additional sequencing metrics for the additional genotype calls; and Based on the one or more additional variant call classifications, an additional recalibrated sequencing data file is generated, the additional recalibrated sequencing data file comprising updated additional genotype calls at the genomic coordinates of the additional sample nucleotide sequences.

9. The system of claim 1, further comprising instructions which, when executed by the at least one processor, cause the system to perform the following operations: generate the one or more variant call classifications by generating one or more of a false positive probability that the genotype call is a false positive, a genotype error probability that the genotype of the genotype call is incorrect, or a true positive probability that the genotype call is a true positive.

10. The system of claim 1, further comprising instructions that, when executed by the at least one processor, cause the system to determine the updated genotype call by: identifying the genomic coordinates as multi-allelic genomic coordinates; recalibrating the machine learning model using the calls to generate the one or more variant call classifications, the one or more variant call classifications comprising one or more of: a reference probability that the genotype call comprises a homozygous reference genotype at the multi-allelic genomic coordinates; a zygosity error probability that the genotype call comprises a genotype zygosity error at the multi-allelic genomic coordinates; or a true positive variant probability that the genotype call constitutes a true positive variant at the multi-allelic genomic coordinates; and The updated genotype call at the multi-allelic genomic coordinate is determined based on one or more of the reference probability, the zygosity error probability, or the true positive variant probability.

11. The system of claim 1 , further comprising instructions that, when executed by the at least one processor, cause the system to: modifying one or more of a base call quality metric, a genotype probability metric, a genotype metric, a genotype likelihood metric, or a genotype quality metric of the genotype call based on the one or more variant call classifications; and The recalibrated sequencing data file is generated, the recalibrated sequencing data file comprising a modified base calling quality metric, a modified genotype probability metric, a modified genotype metric, a modified genotype likelihood metric, or a modified genotype quality metric.

12. The system of claim 1, further comprising instructions that, when executed by the at least one processor, cause the system to generate the updated genotype calls at the biallelic genomic coordinates of the sample nucleotide sequence as part of the recalibrated sequencing data file by: determining a homozygous reference genotype call at the genomic coordinate instead of a heterozygous variant genotype call or a homozygous variant genotype call reported in the one or more sequencing data files; determining the heterozygous variant genotype call at the genomic coordinates instead of the homozygous reference genotype call or the homozygous variant genotype call reported in the one or more sequencing data files; or The homozygous variant genotype call at the genomic coordinate is determined instead of the heterozygous variant genotype call or the homozygous reference genotype call reported in the one or more sequencing data files.

13. The system of claim 1, further comprising instructions that, when executed by the at least one processor, cause the system to: extracting sequencing metrics for additional genotype calls at additional genomic coordinates of the sample nucleotide sequence from the one or more sequencing data files; recalibrating a machine learning model using the calls and generating one or more additional variant call classifications indicative of the accuracy of the additional genotype calls within the one or more sequencing data files based on the sequencing metrics for the additional genotype calls; modifying a base call quality metric for the additional genotype calls based on the one or more additional variant call classifications to generate a modified base call quality metric that is below a base call quality threshold; and The additional genotype calls are annotated to indicate that the modified base call quality metric is below the base call quality threshold.

14. The system of claim 1, further comprising instructions that, when executed by the at least one processor, cause the system to: extracting sequencing metrics for additional genotype calls at additional genomic coordinates of the sample nucleotide sequence from the one or more sequencing data files; recalibrating a machine learning model using the calls and generating one or more additional variant call classifications indicative of the accuracy of the additional genotype calls within the one or more sequencing data files based on the sequencing metrics for the additional genotype calls; and The genotype calls at the additional genomic coordinates of the sample nucleotide sequence are confirmed based on the one or more additional variant call classifications.

15. The system of claim 1, further comprising instructions that, when executed by the at least one processor, cause the system to train the detection recalibration machine learning model by: generating a plurality of recalibrated sequencing data files from a plurality of sequencing data files corresponding to a plurality of known genomes; comparing updated genotype calls from the plurality of recalibrated sequencing data files to known variants of the plurality of known genomes; and Parameters of the call recalibration machine learning model are adjusted based on the differences between the updated genotype calls and the known variants.

16. A system, comprising: at least one processor; and A non-transitory computer readable medium storing instructions that, when executed by the at least one processor, cause the system to: For a sample nucleotide sequence, access one or more sequencing data files, the one or more sequencing data files comprising genotype calls at genomic coordinates; extracting sequencing metrics for the genotype calling from the one or more sequencing data files; recalibrating the machine learning model using the calls and based on the sequencing metrics, generating one or more variant call classifications indicating the accuracy of the genotype calls within the one or more sequencing data files; and Based on the one or more variant call classifications, a recalibrated sequencing data file is generated, the recalibrated sequencing data file comprising updated genotype calls at the genomic coordinates of the sample nucleotide sequence.

17. The system of claim 16, further comprising instructions that, when executed by the at least one processor, cause the system to: accessing an alignment data file of the one or more sequencing data files, the alignment data file comprising nucleotide reads corresponding to the genomic coordinates of the sample nucleotide sequence; and One or more read-based sequencing metrics among the sequencing metrics are extracted from the alignment data file, the one or more read-based sequencing metrics corresponding to the nucleotide reads.

18. The system of claim 16, further comprising instructions that, when executed by the at least one processor, cause the system to perform the following operations: generate the one or more variant call classifications without utilizing a call generation model to simultaneously generate the genotype calls.

19. The system of claim 16, wherein extracting the sequencing metric comprises: One or more read-based sequencing metrics or calling model-generated sequencing metrics for the genotype calls are extracted from a genotype calling data file of the one or more sequencing data files, the genotype calling data file including the genotype calls.

20. The system of claim 19, further comprising instructions that, when executed by the at least one processor, cause the system to perform the following operations: access the genotype call data file by accessing a variant call format (VCF) or genomic variant call format (gVCF) file that includes variant calls and non-variant calls.

21. A system according to claim 19, wherein the genotype call data file including the genotype call is generated on a computing device executing a hardware accelerator, and the recalibrated sequencing data file is generated using a general purpose processing unit as the at least one processor of the system.

22. The system of claim 21, wherein the hardware accelerator comprises a field programmable gate array (FPGA) or an application specific integrated circuit (ASIC), and the recalibrated sequencing data file is generated using one or more of a central processing unit (CPU) or a graphics processing unit (GPU).

23. The system of claim 19, further comprising instructions that, when executed by the at least one processor, cause the system to: accessing an additional genotype calling data file generated by a version of a call generation model that is different from a version of the call generation model that generated the genotype calling data file; extracting additional sequencing metrics for additional genotype calls at genomic coordinates of additional sample nucleotide sequences from the additional genotype call data file; recalibrating the machine learning model using the calls and generating one or more additional variant call classifications indicative of the accuracy of the additional genotype calls within the additional genotype call data files based on the additional sequencing metrics for the additional genotype calls; and Based on the one or more additional variant call classifications, an additional recalibrated sequencing data file is generated, the additional recalibrated sequencing data file comprising updated additional genotype calls at the genomic coordinates of the additional sample nucleotide sequences.

24. The system of claim 16, further comprising instructions that, when executed by the at least one processor, cause the system to perform the following operations: generate the one or more variant call classifications by generating one or more of a false positive probability that the genotype call is a false positive, a genotype error probability that the genotype of the genotype call is incorrect, or a true positive probability that the genotype call is a true positive.

25. The system of claim 16, further comprising instructions that, when executed by the at least one processor, cause the system to determine the updated genotype call by: identifying the genomic coordinates as multi-allelic genomic coordinates; recalibrating the machine learning model using the calls to generate the one or more variant call classifications, the one or more variant call classifications comprising one or more of: a reference probability that the genotype call comprises a homozygous reference genotype at the multi-allelic genomic coordinates; a zygosity error probability that the genotype call comprises a genotype zygosity error at the multi-allelic genomic coordinates; or a true positive variant probability that the genotype call constitutes a true positive variant at the multi-allelic genomic coordinates; and The updated genotype call at the multi-allelic genomic coordinate is determined based on one or more of the reference probability, the zygosity error probability, or the true positive variant probability.

26. The system of claim 16, further comprising instructions that, when executed by the at least one processor, cause the system to: modifying one or more of a base call quality metric, a genotype probability metric, a genotype metric, a genotype likelihood metric, or a genotype quality metric of the genotype call based on the one or more variant call classifications; and The recalibrated sequencing data file is generated, the recalibrated sequencing data file comprising the modified base calling quality metric, the modified genotype probability metric, the modified genotype metric, the modified genotype likelihood metric, or the modified genotype quality metric.

27. The system of claim 16, further comprising instructions that, when executed by the at least one processor, cause the system to generate the updated genotype calls at the biallelic genomic coordinates of the sample nucleotide sequence as part of the recalibrated sequencing data file by: determining a homozygous reference genotype call at the genomic coordinate instead of a heterozygous variant genotype call or a homozygous variant genotype call reported in the one or more sequencing data files; determining the heterozygous variant genotype call at the genomic coordinates instead of the homozygous reference genotype call or the homozygous variant genotype call reported in the one or more sequencing data files; or The homozygous variant genotype call at the genomic coordinate is determined instead of the heterozygous variant genotype call or the homozygous reference genotype call reported in the one or more sequencing data files.

28. The system of claim 16, further comprising instructions that, when executed by the at least one processor, cause the system to: extracting sequencing metrics for additional genotype calls at additional genomic coordinates of the sample nucleotide sequence from the one or more sequencing data files; recalibrating a machine learning model using the calls and generating one or more additional variant call classifications indicative of the accuracy of the additional genotype calls within the one or more sequencing data files based on the sequencing metrics for the additional genotype calls; modifying a base call quality metric for the additional genotype calls based on the one or more additional variant call classifications to generate a modified base call quality metric that is below a base call quality threshold; and The additional genotype calls are annotated to indicate that the modified base call quality metric is below the base call quality threshold.

29. The system of claim 16, further comprising instructions that, when executed by the at least one processor, cause the system to: extracting sequencing metrics for additional genotype calls at additional genomic coordinates of the sample nucleotide sequence from the one or more sequencing data files; recalibrating a machine learning model using the calls and generating one or more additional variant call classifications indicative of the accuracy of the additional genotype calls within the one or more sequencing data files based on the sequencing metrics for the additional genotype calls; and The genotype calls at the additional genomic coordinates of the sample nucleotide sequence are confirmed based on the one or more additional variant call classifications.

30. The system of claim 16, further comprising instructions that, when executed by the at least one processor, cause the system to train the detection recalibration machine learning model by: generating a plurality of recalibrated sequencing data files from a plurality of sequencing data files corresponding to a plurality of known genomes; comparing updated genotype calls from the plurality of recalibrated sequencing data files to known variants of the plurality of known genomes; and Parameters of the call recalibration machine learning model are adjusted based on the differences between the updated genotype calls and the known variants.

31. The system of claim 16, further comprising instructions that, when executed by the at least one processor, cause the system to: generating the one or more variant call classifications for one or more candidate indels using the call recalibration machine learning model trained with insertion or deletion (indel) training data; and Based on the one or more variant call classifications for the one or more candidate indels, the updated genotype call is generated, the updated genotype call indicating the presence or absence of an indel at the genomic coordinates of the sample nucleotide sequence.

32. The system of claim 16, further comprising instructions that, when executed by the at least one processor, cause the system to: generating the one or more variant call classifications for one or more candidate SNVs using the call recalibration machine learning model trained with single nucleotide variant (SNV) training data; and Based on the one or more variant call classifications for the one or more candidate SNVs, the updated genotype call is generated, the updated genotype call indicating the presence or absence of the SNV at the genomic coordinates of the sample nucleotide sequence.

Images