[{"data":1,"prerenderedAt":2279},["ShallowReactive",2],{"navigation":3,"/genomics-platform/about-our-data/file-formats-and-sequencing-information":421,"/genomics-platform/about-our-data/file-formats-and-sequencing-information-surround":2276},[4,19,25,131,197],{"title":5,"_path":6,"children":7,"icon":18},"Overview","/overview",[8,9,12,15],{"title":5,"_path":6},{"title":10,"_path":11},"About our Ecosystem","/overview/ecosystem",{"title":13,"_path":14},"Citing St. Jude Cloud","/overview/citing-stjude-cloud",{"title":16,"_path":17},"Frequently Asked Questions","/overview/faq","sjc-icon:child-logo",{"title":20,"_path":21,"children":22,"icon":24},"CC4K","/cc4k",[23],{"title":5,"_path":21},"sjc-icon:ontology-tree",{"title":26,"_path":27,"children":28,"icon":130},"Genomics Platform","/genomics-platform",[29,49,62,80,99],{"title":30,"_path":31,"children":32},"Getting Started","/genomics-platform/getting-started",[33,35,38,41,44,46],{"title":5,"_path":34},"/genomics-platform/getting-started/overview",{"title":36,"_path":37},"Accounts and Billing","/genomics-platform/getting-started/accounts-and-billing",{"title":39,"_path":40},"Making a Data Request","/genomics-platform/getting-started/making-a-data-request",{"title":42,"_path":43},"Filling Out the DAA","/genomics-platform/getting-started/filling-out-the-daa",{"title":16,"_path":45},"/genomics-platform/getting-started/faq",{"title":47,"_path":48},"Glossary","/genomics-platform/getting-started/glossary",{"title":50,"_path":51,"children":52},"About Our Data","/genomics-platform/about-our-data",[53,56,59],{"title":54,"_path":55},"Data Sets and Data Access Units","/genomics-platform/about-our-data/data-sets-and-data-access-units",{"title":57,"_path":58},"File Formats and Sequencing Information","/genomics-platform/about-our-data/file-formats-and-sequencing-information",{"title":60,"_path":61},"Metadata and Clinical Information","/genomics-platform/about-our-data/metadata-and-clinical-information",{"title":63,"_path":64,"children":65},"Managing Data","/genomics-platform/managing-data",[66,68,71,74,77],{"title":5,"_path":67},"/genomics-platform/managing-data/overview",{"title":69,"_path":70},"Upload/Download Data (Local)","/genomics-platform/managing-data/upload-download-data-local",{"title":72,"_path":73},"Upload/Download Data (Cluster)","/genomics-platform/managing-data/upload-download-data-cluster",{"title":75,"_path":76},"Upload/Download Data (DNAnexus)","/genomics-platform/managing-data/upload-download-data-dnanexus",{"title":78,"_path":79},"Renewing Your DAA","/genomics-platform/managing-data/renewing-your-daa",{"title":81,"_path":82,"children":83},"Analyzing Data","/genomics-platform/analyzing-data",[84,87,90,93,96],{"title":85,"_path":86},"Command Line Interaction","/genomics-platform/analyzing-data/command-line-interaction",{"title":88,"_path":89},"Running Our Workflows","/genomics-platform/analyzing-data/running-our-workflows",{"title":91,"_path":92},"Creating a Cloud Application","/genomics-platform/analyzing-data/creating-a-cloud-app",{"title":94,"_path":95},"Interactive Nodes","/genomics-platform/analyzing-data/interactive-nodes",{"title":97,"_path":98},"Visualizing NGS Data","/genomics-platform/analyzing-data/visualizing-ngs-data",{"title":100,"_path":101,"children":102},"Workflow Guides","/genomics-platform/workflow-guides",[103,106,109,112,115,118,121,124,127],{"title":104,"_path":105},"ChIP-Seq Peak Calling","/genomics-platform/workflow-guides/chipseq",{"title":107,"_path":108},"cis-X","/genomics-platform/workflow-guides/cisx",{"title":110,"_path":111},"MethylationToActivity","/genomics-platform/workflow-guides/methylation-to-activity",{"title":113,"_path":114},"Mutational Signatures","/genomics-platform/workflow-guides/mutational-signatures",{"title":116,"_path":117},"Rapid RNA-Seq","/genomics-platform/workflow-guides/rapid-rnaseq",{"title":119,"_path":120},"RNA-Seq Expression Classification","/genomics-platform/workflow-guides/rnaseq-expression-classification",{"title":122,"_path":123},"SEAseq","/genomics-platform/workflow-guides/seaseq",{"title":125,"_path":126},"SequencErr","/genomics-platform/workflow-guides/sequencerr",{"title":128,"_path":129},"WARDEN Differential Gene Expression","/genomics-platform/workflow-guides/warden","sjc-icon:genomics-platform",{"title":132,"_path":133,"children":134,"icon":196},"PeCan","/pecan",[135,149,156,174,181,190],{"title":5,"_path":136,"children":137},"/pecan/overview",[138,140,143,146],{"title":30,"_path":139},"/pecan/overview/getting-started",{"title":141,"_path":142},"Methods and Data","/pecan/overview/methods-and-data",{"title":144,"_path":145},"Videos","/pecan/overview/videos",{"title":147,"_path":148},"FAQ","/pecan/overview/faq",{"title":150,"_path":151,"children":152},"Cohort Building","/pecan/cohort-building",[153],{"title":154,"_path":155},"Create Custom Cohorts","/pecan/cohort-building/cohort-building",{"title":157,"_path":158,"children":159},"Data Facets","/pecan/data-facets",[160,163,165,168,171],{"title":161,"_path":162},"Variants","/pecan/data-facets/variants",{"title":113,"_path":164},"/pecan/data-facets/mutational-signatures",{"title":166,"_path":167},"Expression","/pecan/data-facets/expression",{"title":169,"_path":170},"Histology","/pecan/data-facets/histology",{"title":172,"_path":173},"Use Cases","/pecan/data-facets/use-cases",{"title":175,"_path":176,"children":177},"Accessibility","/pecan/accessibility",[178],{"title":179,"_path":180},"Keyboard Shortcuts","/pecan/accessibility/keyboard-shortcuts",{"title":182,"_path":183,"children":184},"PeCan PIE","/pecan/pecan-pie",[185,188],{"title":186,"_path":187},"What is PIE","/pecan/pecan-pie/what-is-pie",{"title":147,"_path":189},"/pecan/pecan-pie/faq",{"title":191,"_path":192,"children":193},"Release Notes","/pecan/release-notes",[194],{"title":195,"_path":192},"PeCan Release Notes","sjc-icon:pecan",{"title":198,"_path":199,"children":200,"icon":420},"Visualization Community","/visualization-community",[201,215,246,307,411],{"title":5,"_path":202,"children":203},"/visualization-community/overview",[204,207,210,213],{"title":205,"_path":206},"What is Visualization Community","/visualization-community/overview/what-is-visualization-community",{"title":208,"_path":209},"What are ProteinPaint and GenomePaint","/visualization-community/overview/what-are-proteinpaint-and-genome-paint",{"title":211,"_path":212},"Data Types","/visualization-community/overview/data-types-and-graphs",{"title":147,"_path":214},"/visualization-community/overview/faq",{"title":30,"_path":216,"children":217},"/visualization-community/getting-started",[218,220,223,226,229,232,235,238,241,243],{"title":5,"_path":219},"/visualization-community/getting-started/overview",{"title":221,"_path":222},"How to Sign-in","/visualization-community/getting-started/how-to-sign-in",{"title":224,"_path":225},"How to Use the VisEditor","/visualization-community/getting-started/how-to-use-the-viseditor",{"title":227,"_path":228},"Tracks and Apps","/visualization-community/getting-started/tracks-and-apps",{"title":230,"_path":231},"Manage Your Data","/visualization-community/getting-started/manage-your-data",{"title":233,"_path":234},"Collections & Communities","/visualization-community/getting-started/collections-and-communities",{"title":236,"_path":237},"Public vs. Private Visualizations","/visualization-community/getting-started/public-vs-private-visualizations",{"title":239,"_path":240},"Embedding","/visualization-community/getting-started/embedding",{"title":144,"_path":242},"/visualization-community/getting-started/videos",{"title":244,"_path":245},"NEW Data Download","/visualization-community/getting-started/new-data-download",{"title":247,"_path":248,"children":249},"Code Block Library","/visualization-community/code-block-library",[250,253,256,259,262,265,268,271,274,277,280,283,286,289,292,295,298,301,304],{"title":251,"_path":252},"Code Block Basics","/visualization-community/code-block-library/code-block-basics",{"title":254,"_path":255},"Allelic Imbalance","/visualization-community/code-block-library/allelic-imbalance",{"title":257,"_path":258},"Arc","/visualization-community/code-block-library/arc",{"title":260,"_path":261},"BAM","/visualization-community/code-block-library/bam",{"title":263,"_path":264},"BigWig","/visualization-community/code-block-library/bigwig",{"title":266,"_path":267},"BigWig Stranded","/visualization-community/code-block-library/bigwig-stranded",{"title":269,"_path":270},"Expression Rank","/visualization-community/code-block-library/expression-rank",{"title":272,"_path":273},"Hi-C","/visualization-community/code-block-library/hi-c",{"title":275,"_path":276},"Heatmap","/visualization-community/code-block-library/heatmap",{"title":278,"_path":279},"JSON BED","/visualization-community/code-block-library/json-bed",{"title":281,"_path":282},"Lollipop","/visualization-community/code-block-library/lollipop",{"title":284,"_path":285},"MA Volcano","/visualization-community/code-block-library/ma-volcano",{"title":287,"_path":288},"Profile Gene Value","/visualization-community/code-block-library/profile-gene-value",{"title":290,"_path":291},"RNA Splice Junction","/visualization-community/code-block-library/rna-splice-junction",{"title":293,"_path":294},"Single Cell","/visualization-community/code-block-library/single-cell",{"title":296,"_path":297},"Splice Junctions Cohort","/visualization-community/code-block-library/splice-junctions-cohort",{"title":299,"_path":300},"Track List and Facet Table","/visualization-community/code-block-library/track-list-and-facet-table",{"title":302,"_path":303},"t-SNE","/visualization-community/code-block-library/t-sne",{"title":305,"_path":306},"VCF","/visualization-community/code-block-library/vcf",{"title":308,"_path":309,"children":310},"ProteinPaint","/visualization-community/proteinpaint",[311,313,316,318,321,324,327,330,333,336,339,342,345,348,351,354,357,360,363,366,369,372,375,378,381,384,387,390,393,396,399,402,405,408],{"title":308,"_path":312},"/visualization-community/proteinpaint/proteinpaint",{"title":314,"_path":315},"Introduction","/visualization-community/proteinpaint/introduction",{"title":30,"_path":317},"/visualization-community/proteinpaint/getting-started",{"title":319,"_path":320},"Loading Datasets","/visualization-community/proteinpaint/loading-datasets",{"title":322,"_path":323},"Viewing SNV/Indel Mutations","/visualization-community/proteinpaint/viewing-snv-indel-mutations",{"title":325,"_path":326},"Viewing Gene Fusions","/visualization-community/proteinpaint/viewing-gene-fusions",{"title":328,"_path":329},"Viewing Expression Data","/visualization-community/proteinpaint/viewing-expression-data",{"title":331,"_path":332},"Filtering Mutations","/visualization-community/proteinpaint/filtering-mutations",{"title":334,"_path":335},"Exporting Figures and Data","/visualization-community/proteinpaint/exporting-figures-and-data",{"title":337,"_path":338},"Using the Gene Table","/visualization-community/proteinpaint/using-the-gene-table",{"title":340,"_path":341},"Using the Sample Table","/visualization-community/proteinpaint/using-the-sample-table",{"title":343,"_path":344},"Using the Heatmap","/visualization-community/proteinpaint/using-the-heatmap",{"title":346,"_path":347},"Using Disease Pie Charts","/visualization-community/proteinpaint/using-disease-pie-charts",{"title":349,"_path":350},"Stratifying Mutations by Cancer Subtype","/visualization-community/proteinpaint/stratifying-mutations-by-cancer-subtype",{"title":352,"_path":353},"SNV and Indel","/visualization-community/proteinpaint/snv-and-indel",{"title":355,"_path":356},"SV and fusion transcript","/visualization-community/proteinpaint/sv-and-fusion-transcript",{"title":358,"_path":359},"Copy Number Variants","/visualization-community/proteinpaint/copy-number-variants",{"title":361,"_path":362},"Internal tandem duplications","/visualization-community/proteinpaint/internal-tandem-duplications",{"title":364,"_path":365},"Intragenic deletion","/visualization-community/proteinpaint/intragenic-deletion",{"title":367,"_path":368},"Truncation, N-loss, or C-loss","/visualization-community/proteinpaint/truncation",{"title":370,"_path":371},"JSON-BED","/visualization-community/proteinpaint/json-bed",{"title":373,"_path":374},"Splice Junction","/visualization-community/proteinpaint/splice-junction",{"title":376,"_path":377},"Profile-Gene-Value","/visualization-community/proteinpaint/profile-gene-value",{"title":379,"_path":380},"Bampile","/visualization-community/proteinpaint/bampile",{"title":382,"_path":383},"Add Custom Protein Domains","/visualization-community/proteinpaint/add-custom-protein-domains",{"title":385,"_path":386},"Using Custom Tracks","/visualization-community/proteinpaint/using-custom-tracks",{"title":388,"_path":389},"Visualize Your Mutation Data","/visualization-community/proteinpaint/visualize-your-mutation-data",{"title":391,"_path":392},"Loading SNV/Indel Mutations from a File","/visualization-community/proteinpaint/loading-mutations-from-file",{"title":394,"_path":395},"Uploaded Mutation Data User Interface","/visualization-community/proteinpaint/uploaded-mutation-data",{"title":397,"_path":398},"Loading a TCGA MAF File","/visualization-community/proteinpaint/loading-tcga-maf-file",{"title":400,"_path":401},"Using a VCF File","/visualization-community/proteinpaint/using-vcf-file",{"title":403,"_path":404},"Embedding ProteinPaint","/visualization-community/proteinpaint/embedding-proteinpaint",{"title":406,"_path":407},"URL Parameters","/visualization-community/proteinpaint/url-parameters",{"title":409,"_path":410},"Organizing Data into a Study View","/visualization-community/proteinpaint/study-view",{"title":412,"_path":413,"children":414},"GenomePaint","/visualization-community/genomepaint",[415,417],{"title":412,"_path":416},"/visualization-community/genomepaint/genomepaint",{"title":418,"_path":419},"GenomePaint User Guide","/visualization-community/genomepaint/genomepaint-user-guide","sjc-icon:viz",{"_path":58,"_dir":422,"_draft":423,"_partial":423,"_locale":424,"title":57,"description":424,"body":425,"_type":2270,"_id":2271,"_source":2272,"_file":2273,"_stem":2274,"_extension":2275},"about-our-data",false,"",{"type":426,"children":427,"toc":2257},"root",[428,437,443,597,604,618,624,664,669,675,689,950,964,985,992,997,1002,1007,1014,1088,1094,1161,1167,1206,1232,1245,1250,1256,1339,1364,1376,1382,1419,1448,1476,1481,1487,1498,1503,1509,1532,1606,1612,1635,1641,1647,1658,1663,1669,1723,2251],{"type":429,"tag":430,"props":431,"children":433},"element","h2",{"id":432},"file-formats",[434],{"type":435,"value":436},"text","File Formats",{"type":429,"tag":438,"props":439,"children":440},"p",{},[441],{"type":435,"value":442},"St. Jude Cloud hosts both raw genomic data files and processed results files:",{"type":429,"tag":444,"props":445,"children":446},"table",{},[447,471],{"type":429,"tag":448,"props":449,"children":450},"thead",{},[451],{"type":429,"tag":452,"props":453,"children":454},"tr",{},[455,461,466],{"type":429,"tag":456,"props":457,"children":458},"th",{},[459],{"type":435,"value":460},"File Type",{"type":429,"tag":456,"props":462,"children":463},{},[464],{"type":435,"value":465},"Short Description",{"type":429,"tag":456,"props":467,"children":468},{},[469],{"type":435,"value":470},"Details",{"type":429,"tag":472,"props":473,"children":474},"tbody",{},[475,498,527,548,569],{"type":429,"tag":452,"props":476,"children":477},{},[478,483,488],{"type":429,"tag":479,"props":480,"children":481},"td",{},[482],{"type":435,"value":260},{"type":429,"tag":479,"props":484,"children":485},{},[486],{"type":435,"value":487},"DNA-seq hg38 aligned BAM files produced by Microsoft Genomics Service or a pipeline with results highly consistent with those from Microsoft Genomics Service, as verified by SNP genotype concordance. RNA-seq BAM files produced by STAR 2-pass mapping.",{"type":429,"tag":479,"props":489,"children":490},{},[491],{"type":429,"tag":492,"props":493,"children":495},"a",{"href":494},"#bam-files",[496],{"type":435,"value":497},"Click here",{"type":429,"tag":452,"props":499,"children":500},{},[501,506,519],{"type":429,"tag":479,"props":502,"children":503},{},[504],{"type":435,"value":505},"gVCF",{"type":429,"tag":479,"props":507,"children":508},{},[509,517],{"type":429,"tag":492,"props":510,"children":514},{"href":511,"rel":512},"https://samtools.github.io/hts-specs/VCFv4.2.pdf",[513],"nofollow",[515],{"type":435,"value":516},"Genomic VCF",{"type":435,"value":518}," were either produced by Microsoft Genomics Service or a pipeline with results highly consistent with those from Microsoft Genomics Service, as verified by SNP genotype concordance.",{"type":429,"tag":479,"props":520,"children":521},{},[522],{"type":429,"tag":492,"props":523,"children":525},{"href":524},"#gvcf-files",[526],{"type":435,"value":497},{"type":429,"tag":452,"props":528,"children":529},{},[530,535,540],{"type":429,"tag":479,"props":531,"children":532},{},[533],{"type":435,"value":534},"Somatic VCF",{"type":429,"tag":479,"props":536,"children":537},{},[538],{"type":435,"value":539},"Curated list of somatic variants produced by the St. Jude somatic variant analysis pipeline.",{"type":429,"tag":479,"props":541,"children":542},{},[543],{"type":429,"tag":492,"props":544,"children":546},{"href":545},"#somatic-vcf-files",[547],{"type":435,"value":497},{"type":429,"tag":452,"props":549,"children":550},{},[551,556,561],{"type":429,"tag":479,"props":552,"children":553},{},[554],{"type":435,"value":555},"CNV",{"type":429,"tag":479,"props":557,"children":558},{},[559],{"type":435,"value":560},"List of somatic copy number alterations produced by St. Jude CONSERTING pipeline.",{"type":429,"tag":479,"props":562,"children":563},{},[564],{"type":429,"tag":492,"props":565,"children":567},{"href":566},"#cnv-files",[568],{"type":435,"value":497},{"type":429,"tag":452,"props":570,"children":571},{},[572,577,589],{"type":429,"tag":479,"props":573,"children":574},{},[575],{"type":435,"value":576},"Feature Counts",{"type":429,"tag":479,"props":578,"children":579},{},[580,582],{"type":435,"value":581},"Curated list of read counts mapped to each gene produced by ",{"type":429,"tag":492,"props":583,"children":586},{"href":584,"rel":585},"https://htseq.readthedocs.io/en/master/",[513],[587],{"type":435,"value":588},"HTSeq",{"type":429,"tag":479,"props":590,"children":591},{},[592],{"type":429,"tag":492,"props":593,"children":595},{"href":594},"#feature-counts-files",[596],{"type":435,"value":497},{"type":429,"tag":598,"props":599,"children":601},"h3",{"id":600},"bam-files",[602],{"type":435,"value":603},"BAM files",{"type":429,"tag":438,"props":605,"children":606},{},[607,609,616],{"type":435,"value":608},"In St. Jude Cloud, we store aligned sequence reads in BAM file format for whole genome sequencing, whole exome sequencing, and RNA-Seq.\nFor more information on SAM/BAM files, please refer to the ",{"type":429,"tag":492,"props":610,"children":613},{"href":611,"rel":612},"https://samtools.github.io/hts-specs/SAMv1.pdf",[513],[614],{"type":435,"value":615},"SAM/BAM specification",{"type":435,"value":617},".\nFor research samples, we require the standard 30X coverage for whole genome and 100X for whole exome sequencing.\nFor clinical samples, we require higher coverage, 45X, for whole genome sequencing due to tumor purity issues found in clinical tumor specimens.\nFor RNA-Seq, since only a subset of genes are expressed in a specific tissue, we require 30% of the exons to have 20X coverage in order to ensure that at least 30% of the expressed genes have sufficient coverage.",{"type":429,"tag":598,"props":619,"children":621},{"id":620},"gvcf-files",[622],{"type":435,"value":623},"gVCF files",{"type":429,"tag":438,"props":625,"children":626},{},[627,629,636,638,644,646,653,655,662],{"type":435,"value":628},"gVCF files generated before January 2025 were produced by the Microsoft Genomics Service.\ngVCF files are derived from the BAM files produced above as called by ",{"type":429,"tag":492,"props":630,"children":633},{"href":631,"rel":632},"https://gatk.broadinstitute.org/hc/en-us/articles/30332006386459-HaplotypeCaller",[513],[634],{"type":435,"value":635},"GATK's haplotype caller",{"type":435,"value":637},".\nWe defer to ",{"type":429,"tag":492,"props":639,"children":641},{"href":511,"rel":640},[513],[642],{"type":435,"value":643},"the official specification document",{"type":435,"value":645}," from the Broad Institute, as well as ",{"type":429,"tag":492,"props":647,"children":650},{"href":648,"rel":649},"https://gatk.broadinstitute.org/hc/en-us/articles/360035531812-GVCF-Genomic-Variant-Call-Format",[513],[651],{"type":435,"value":652},"this discussion",{"type":435,"value":654}," on the difference between VCF and gVCF files.\nFor more information about how Microsoft Genomics produces gVCF files or any other questions regarding data generation, please refer to the official ",{"type":429,"tag":492,"props":656,"children":659},{"href":657,"target":658},"/files/genomics-platform/about-our-data/file-formats-and-sequencing-information/msgen-whitepaper-0.7.pdf","_blank",[660],{"type":435,"value":661},"Microsoft Genomics white paper",{"type":435,"value":663},".",{"type":429,"tag":438,"props":665,"children":666},{},[667],{"type":435,"value":668},"gVCF files produced after Microsoft Genomics Service was retired in January 2025 use a pipeline with results highly consistent with those from Microsoft Genomics Service, as verified by SNP genotype concordance of 99.9 % across a random sample set (n=6).\nThe workflow uses the hg38m1x reference genome and incorporates Microsoft’s optimized versions of ms_opt fork of bwa and GATK for alignment and variant calling.\ngVCFs generated from this pipeline include all positions in the reference genome, rather than only those identified through active-region calculations.",{"type":429,"tag":598,"props":670,"children":672},{"id":671},"somatic-vcf-files",[673],{"type":435,"value":674},"Somatic VCF files",{"type":429,"tag":438,"props":676,"children":677},{},[678,680,687],{"type":435,"value":679},"Somatic VCF files available on St. Jude Cloud have been generated when possible for tumor samples where a matching patient normal sample has also been sequenced.\nThese include samples from the Pediatric Cancer Genome Project (PCGP), Clinical Pilot, and Genomes 4 Kids (G4K) ",{"type":429,"tag":492,"props":681,"children":684},{"href":682,"rel":683},"https://platform.stjude.cloud/data/cohorts/pediatric-cancer",[513],[685],{"type":435,"value":686},"cohorts",{"type":435,"value":688},".\nThese somatic VCF files contain hg38 coordinate SNV/Indel variant calls generated by the St. Jude somatic variant analysis pipeline outlined below:",{"type":429,"tag":690,"props":691,"children":692},"ol",{},[693,725,755,778,792,797,802,814,839,844,862,879,901],{"type":429,"tag":694,"props":695,"children":696},"li",{},[697,699,706,708,715,717,723],{"type":435,"value":698},"Whole genome (WGS) and/or Whole exome (WES) sequencing data were aligned to hg19 using ",{"type":429,"tag":492,"props":700,"children":703},{"href":701,"rel":702},"http://bio-bwa.sourceforge.net/",[513],[704],{"type":435,"value":705},"bwa backtrack",{"type":435,"value":707}," (",{"type":429,"tag":709,"props":710,"children":712},"code",{"className":711},[],[713],{"type":435,"value":714},"bwa aln",{"type":435,"value":716}," + ",{"type":429,"tag":709,"props":718,"children":720},{"className":719},[],[721],{"type":435,"value":722},"bwa sampe",{"type":435,"value":724},") using default parameters.*",{"type":429,"tag":694,"props":726,"children":727},{},[728,730,737,739,745,747,753],{"type":435,"value":729},"Post processing of aligned reads was performed using ",{"type":429,"tag":492,"props":731,"children":734},{"href":732,"rel":733},"https://broadinstitute.github.io/picard/",[513],[735],{"type":435,"value":736},"Picard",{"type":435,"value":738}," ",{"type":429,"tag":709,"props":740,"children":742},{"className":741},[],[743],{"type":435,"value":744},"CleanSam",{"type":435,"value":746}," and ",{"type":429,"tag":709,"props":748,"children":750},{"className":749},[],[751],{"type":435,"value":752},"MarkDuplicates",{"type":435,"value":754},".*",{"type":429,"tag":694,"props":756,"children":757},{},[758,760,767,769,776],{"type":435,"value":759},"Variants were called using the ",{"type":429,"tag":492,"props":761,"children":764},{"href":762,"rel":763},"https://academic.oup.com/bioinformatics/article/27/6/865/236751",[513],[765],{"type":435,"value":766},"Bambino",{"type":435,"value":768}," variant caller (you can download Bambino ",{"type":429,"tag":492,"props":770,"children":773},{"href":771,"rel":772},"http://ftp.stjude.org/pub/software/conserting/bambino-1.0.jar",[513],[774],{"type":435,"value":775},"here",{"type":435,"value":777},").*",{"type":429,"tag":694,"props":779,"children":780},{},[781,783,790],{"type":435,"value":782},"If RNA-Sequencing was performed on a tumor sample, we assessed the presence of any WGS/WES called variants within a ",{"type":429,"tag":492,"props":784,"children":787},{"href":785,"rel":786},"https://www.nature.com/articles/ng.2938",[513],[788],{"type":435,"value":789},"StrongARM",{"type":435,"value":791}," aligned RNA-Seq BAM file.*",{"type":429,"tag":694,"props":793,"children":794},{},[795],{"type":435,"value":796},"In some Clinical Pilot cohort study cases, validation by custom capture was performed, in which case the read counts of that experiment were reported.*",{"type":429,"tag":694,"props":798,"children":799},{},[800],{"type":435,"value":801},"Variants were post-processed using an in-house post-processing pipeline that cleans and annotates variants. This pipeline is not currently publicly available.*",{"type":429,"tag":694,"props":803,"children":804},{},[805,807,813],{"type":435,"value":806},"Depending on the cohort, either all variants were manually reviewed by analysts (PCGP cohort) or a subset comprising all coding variants were manually reviewed (Clinical Pilot and G4K).\nThis resulted in the assignment of a validation status for each variant ",{"type":429,"tag":492,"props":808,"children":810},{"href":809},"#sample-variant-validation-and-filtering",[811],{"type":435,"value":812},"(see below)",{"type":435,"value":663},{"type":429,"tag":694,"props":815,"children":816},{},[817,819],{"type":435,"value":818},"Variant filtering:\n",{"type":429,"tag":820,"props":821,"children":822},"ul",{},[823,828],{"type":429,"tag":694,"props":824,"children":825},{},[826],{"type":435,"value":827},"For patient samples where a complete set of variants have been manually curated and reported as part of an existing publication, the published set of variants was considered the complete set of variants for that patient tumor sample, and used to populate the associated somatic VCF file.\nThis includes samples belonging to the Clinical Pilot cohort study and some of the PCGP cohort studies.",{"type":429,"tag":694,"props":829,"children":830},{},[831,833,837],{"type":435,"value":832},"For currently unpublished patient tumor samples, we filtered variants based on metrics derived from the in-house post-processing pipeline and the input of analysts ",{"type":429,"tag":492,"props":834,"children":835},{"href":809},[836],{"type":435,"value":812},{"type":435,"value":838},".\nThis includes the patient samples in the G4K study, along with some unpublished PCGP and Clinical Pilot cohort study samples.",{"type":429,"tag":694,"props":840,"children":841},{},[842],{"type":435,"value":843},"Variants were exported from a database and converted to VCF format.",{"type":429,"tag":694,"props":845,"children":846},{},[847,849,854,855,861],{"type":435,"value":848},"Variant coordinates were lifted over to GRCh38_no_alt using ",{"type":429,"tag":492,"props":850,"children":852},{"href":732,"rel":851},[513],[853],{"type":435,"value":736},{"type":435,"value":738},{"type":429,"tag":709,"props":856,"children":858},{"className":857},[],[859],{"type":435,"value":860},"LiftoverVcf",{"type":435,"value":663},{"type":429,"tag":694,"props":863,"children":864},{},[865,867,878],{"type":435,"value":866},"Variants were normalized using ",{"type":429,"tag":492,"props":868,"children":871},{"href":869,"rel":870},"https://genome.sph.umich.edu/wiki/Vt#Normalization",[513],[872],{"type":429,"tag":709,"props":873,"children":875},{"className":874},[],[876],{"type":435,"value":877},"vt normalize",{"type":435,"value":663},{"type":429,"tag":694,"props":880,"children":881},{},[882,884,891,893,899],{"type":435,"value":883},"Variants were annotated using ",{"type":429,"tag":492,"props":885,"children":888},{"href":886,"rel":887},"https://ensembl.org/info/docs/tools/vep/index.html",[513],[889],{"type":435,"value":890},"VEP v100",{"type":435,"value":892}," and the ",{"type":429,"tag":709,"props":894,"children":896},{"className":895},[],[897],{"type":435,"value":898},"--everything",{"type":435,"value":900}," flag.",{"type":429,"tag":694,"props":902,"children":903},{},[904,906,919,921],{"type":435,"value":905},"VCFs were compressed with bgzip and tabix indexed, then validated using ",{"type":429,"tag":492,"props":907,"children":910},{"href":908,"rel":909},"https://vcftools.github.io/perl_module.html#vcf-validator",[513],[911,913],{"type":435,"value":912},"VCFtools' ",{"type":429,"tag":709,"props":914,"children":916},{"className":915},[],[917],{"type":435,"value":918},"vcf-validator",{"type":435,"value":920},".\n",{"type":429,"tag":820,"props":922,"children":923},{},[924],{"type":429,"tag":694,"props":925,"children":926},{},[927,928,933,935,948],{"type":435,"value":912},{"type":429,"tag":709,"props":929,"children":931},{"className":930},[],[932],{"type":435,"value":918},{"type":435,"value":934}," is outdated, and is being replaced with ",{"type":429,"tag":492,"props":936,"children":939},{"href":937,"rel":938},"https://gatk.broadinstitute.org/hc/en-us/articles/30332075857819-ValidateVariants",[513],[940,942],{"type":435,"value":941},"GATK's ",{"type":429,"tag":709,"props":943,"children":945},{"className":944},[],[946],{"type":435,"value":947},"ValidateVariants",{"type":435,"value":949}," in future versions of the pipeline.",{"type":429,"tag":438,"props":951,"children":952},{},[953,955,962],{"type":435,"value":954},"* For more detailed information on steps 1-6, see the ",{"type":429,"tag":492,"props":956,"children":959},{"href":957,"rel":958},"https://www.nature.com/articles/s41467-018-06485-7",[513],[960],{"type":435,"value":961},"Clinical Pilot paper",{"type":435,"value":963}," where they are described in depth.",{"type":429,"tag":965,"props":966,"children":969},"callout",{"color":967,"icon":968},"orange","i-heroicons-exclamation-circle",[970],{"type":429,"tag":438,"props":971,"children":972},{},[973,979,983],{"type":429,"tag":974,"props":975,"children":976},"strong",{},[977],{"type":435,"value":978},"Warning",{"type":429,"tag":980,"props":981,"children":982},"br",{},[],{"type":435,"value":984},"\nPlease note, as indicated above, that the somatic variants recorded in these VCF files were called using hg19 aligned WGS/WES/RNA-Seq sequencing data, and not from the hg38 BAMs available elsewhere on St. Jude Cloud.",{"type":429,"tag":986,"props":987,"children":989},"h4",{"id":988},"sample-variant-validation-and-filtering",[990],{"type":435,"value":991},"Sample Variant Validation and Filtering",{"type":429,"tag":438,"props":993,"children":994},{},[995],{"type":435,"value":996},"The validation_status field indicates the status of validating the presence and origin (somatic/germline) of the variant using an orthogonal methodology.\nNote that this doesn't imply anything regarding variant significance, pathogenicity, or relation to disease.\nTypically, validation is performed either by secondary sequencing using a custom capture panel designed around the called variants (common in research studies) or by cross-validation using simultaneous sequencing by WGS, WES, and/or RNA-Seq (used in clinical genomics).",{"type":429,"tag":438,"props":998,"children":999},{},[1000],{"type":435,"value":1001},"For validation by a secondary method, \"valid\" indicates the variant was validated by the secondary method, \"putative\" indicates that the secondary method could neither confirm nor invalidate the variant (e.g. due to lack of read coverage by the secondary method), and \"invalid\" indicates a negative result from the secondary method.",{"type":429,"tag":438,"props":1003,"children":1004},{},[1005],{"type":435,"value":1006},"Cross-validation of variant data across multiple sequencing methodologies (WGS, WES, RNA-Seq etc) has been used across clinical genomics studies (Clinical Pilot, G4K, and RTCG). Here SNVs and indels are first manually reviewed and called as \"Good\" or \"Bad\" for each sequencing methodology.\nTo make this assessment, the analyst considers 1) computationally generated quality metrics and tags assigned to the variant based on read counts, base qualities, and realignment; and 2) manual inspection of tumor and germline read evidence within sequencing data from the given sequencing platform.\nThe assigned validation status is determined based on the observed support for the variant across each of the sequencing methodologies as follows:",{"type":429,"tag":1008,"props":1009,"children":1011},"h5",{"id":1010},"freshfrozen-samples",[1012],{"type":435,"value":1013},"Fresh/Frozen Samples",{"type":429,"tag":444,"props":1015,"children":1016},{},[1017,1033],{"type":429,"tag":448,"props":1018,"children":1019},{},[1020],{"type":429,"tag":452,"props":1021,"children":1022},{},[1023,1028],{"type":429,"tag":456,"props":1024,"children":1025},{},[1026],{"type":435,"value":1027},"Designation",{"type":429,"tag":456,"props":1029,"children":1030},{},[1031],{"type":435,"value":1032},"Criteria",{"type":429,"tag":472,"props":1034,"children":1035},{},[1036,1049,1062,1075],{"type":429,"tag":452,"props":1037,"children":1038},{},[1039,1044],{"type":429,"tag":479,"props":1040,"children":1041},{},[1042],{"type":435,"value":1043},"Valid",{"type":429,"tag":479,"props":1045,"children":1046},{},[1047],{"type":435,"value":1048},"Good in both WGS and WES",{"type":429,"tag":452,"props":1050,"children":1051},{},[1052,1057],{"type":429,"tag":479,"props":1053,"children":1054},{},[1055],{"type":435,"value":1056},"Likely Valid",{"type":429,"tag":479,"props":1058,"children":1059},{},[1060],{"type":435,"value":1061},"Good in WGS and RNA-Seq, but not WES (though not validated, the high fidelity of WGS means these have a high probability of being valid)",{"type":429,"tag":452,"props":1063,"children":1064},{},[1065,1070],{"type":429,"tag":479,"props":1066,"children":1067},{},[1068],{"type":435,"value":1069},"Putative",{"type":429,"tag":479,"props":1071,"children":1072},{},[1073],{"type":435,"value":1074},"Good in WGS only or Good in both WES and RNA-Seq",{"type":429,"tag":452,"props":1076,"children":1077},{},[1078,1083],{"type":429,"tag":479,"props":1079,"children":1080},{},[1081],{"type":435,"value":1082},"Invalid",{"type":429,"tag":479,"props":1084,"children":1085},{},[1086],{"type":435,"value":1087},"any other combination of assignments",{"type":429,"tag":1008,"props":1089,"children":1091},{"id":1090},"ffpe-samples",[1092],{"type":435,"value":1093},"FFPE samples",{"type":429,"tag":444,"props":1095,"children":1096},{},[1097,1111],{"type":429,"tag":448,"props":1098,"children":1099},{},[1100],{"type":429,"tag":452,"props":1101,"children":1102},{},[1103,1107],{"type":429,"tag":456,"props":1104,"children":1105},{},[1106],{"type":435,"value":1027},{"type":429,"tag":456,"props":1108,"children":1109},{},[1110],{"type":435,"value":1032},{"type":429,"tag":472,"props":1112,"children":1113},{},[1114,1126,1138,1150],{"type":429,"tag":452,"props":1115,"children":1116},{},[1117,1121],{"type":429,"tag":479,"props":1118,"children":1119},{},[1120],{"type":435,"value":1043},{"type":429,"tag":479,"props":1122,"children":1123},{},[1124],{"type":435,"value":1125},"Good in both WES and RNA",{"type":429,"tag":452,"props":1127,"children":1128},{},[1129,1133],{"type":429,"tag":479,"props":1130,"children":1131},{},[1132],{"type":435,"value":1056},{"type":429,"tag":479,"props":1134,"children":1135},{},[1136],{"type":435,"value":1137},"Good in WES but not RNA-Seq",{"type":429,"tag":452,"props":1139,"children":1140},{},[1141,1145],{"type":429,"tag":479,"props":1142,"children":1143},{},[1144],{"type":435,"value":1069},{"type":429,"tag":479,"props":1146,"children":1147},{},[1148],{"type":435,"value":1149},"Generally not used",{"type":429,"tag":452,"props":1151,"children":1152},{},[1153,1157],{"type":429,"tag":479,"props":1154,"children":1155},{},[1156],{"type":435,"value":1082},{"type":429,"tag":479,"props":1158,"children":1159},{},[1160],{"type":435,"value":1087},{"type":429,"tag":986,"props":1162,"children":1164},{"id":1163},"pre-annotation",[1165],{"type":435,"value":1166},"Pre-annotation",{"type":429,"tag":438,"props":1168,"children":1169},{},[1170,1172,1178,1180,1187,1189,1196,1198,1205],{"type":435,"value":1171},"As part of our post-processing pipeline, variants are processed by a variety of in-silico pathogenicity prediction algorithms that default VEP doesn't provide.\nWe include those results as VCF ",{"type":429,"tag":709,"props":1173,"children":1175},{"className":1174},[],[1176],{"type":435,"value":1177},"INFO",{"type":435,"value":1179}," tags when applicable.\nNote that they were performed on the hg19 coordinates.\nAlgorithms include ",{"type":429,"tag":492,"props":1181,"children":1184},{"href":1182,"rel":1183},"https://genome.cshlp.org/content/19/9/1553.abstract",[513],[1185],{"type":435,"value":1186},"Likelihood Ratio Test (LRT)",{"type":435,"value":1188},", MutationAssessor, ",{"type":429,"tag":492,"props":1190,"children":1193},{"href":1191,"rel":1192},"http://www.mutationtaster.org/info/documentation.html",[513],[1194],{"type":435,"value":1195},"MutationTaster",{"type":435,"value":1197},", and ",{"type":429,"tag":492,"props":1199,"children":1202},{"href":1200,"rel":1201},"http://fathmm.biocompute.org.uk/about.html",[513],[1203],{"type":435,"value":1204},"FATHMM",{"type":435,"value":663},{"type":429,"tag":965,"props":1207,"children":1210},{"color":1208,"icon":1209},"blue","i-heroicons-document-text-solid",[1211],{"type":429,"tag":438,"props":1212,"children":1213},{},[1214,1219,1222,1224,1230],{"type":429,"tag":974,"props":1215,"children":1216},{},[1217],{"type":435,"value":1218},"Note",{"type":429,"tag":980,"props":1220,"children":1221},{},[],{"type":435,"value":1223},"\nThe URL for MutationAssessor (",{"type":429,"tag":709,"props":1225,"children":1227},{"className":1226},[],[1228],{"type":435,"value":1229},"https://mutationassessor.org/r3",{"type":435,"value":1231},") is no longer responding.",{"type":429,"tag":438,"props":1233,"children":1234},{},[1235,1237,1243],{"type":435,"value":1236},"Bambino represents indels in a format incompatible with the VCF specification.\nWhen we convert variants to VCFs, we store the original Bambino representation in the ",{"type":429,"tag":709,"props":1238,"children":1240},{"className":1239},[],[1241],{"type":435,"value":1242},"bambino_representation",{"type":435,"value":1244}," tag of the info field.\nNote that this entry is always in hg19 coordinates.",{"type":429,"tag":438,"props":1246,"children":1247},{},[1248],{"type":435,"value":1249},"Where possible, allele counts and read depths for each variant are determined across each sequencing type available for the associated patient tumor-normal pair.\nThese can include WGS, WES, RNA-Seq, and validation-capture (VALCAP) data.\nThese data are stored in the sample columns of the VCF.",{"type":429,"tag":986,"props":1251,"children":1253},{"id":1252},"processing-tools",[1254],{"type":435,"value":1255},"Processing tools",{"type":429,"tag":438,"props":1257,"children":1258},{},[1259,1261,1272,1273,1284,1286,1292,1294,1305,1307,1313,1315,1321,1322,1328,1330,1337],{"type":435,"value":1260},"The newly created hg19 coordinate VCFs are lifted over using ",{"type":429,"tag":492,"props":1262,"children":1264},{"href":732,"rel":1263},[513],[1265,1267],{"type":435,"value":1266},"Picard ",{"type":429,"tag":709,"props":1268,"children":1270},{"className":1269},[],[1271],{"type":435,"value":860},{"type":435,"value":920},{"type":429,"tag":492,"props":1274,"children":1277},{"href":1275,"rel":1276},"http://hgdownload.soe.ucsc.edu/goldenPath/hg19/liftOver/hg19ToHg38.over.chain.gz",[513],[1278],{"type":429,"tag":709,"props":1279,"children":1281},{"className":1280},[],[1282],{"type":435,"value":1283},"hg19ToHg38.over.chain",{"type":435,"value":1285}," is used as the chain file and ",{"type":429,"tag":709,"props":1287,"children":1289},{"className":1288},[],[1290],{"type":435,"value":1291},"GRCh38_no_alt.fa",{"type":435,"value":1293}," is used as the reference.\nThe hg38 build includes some reference contigs not present in the GRCh38_no_alt build, so variants which would map to one of those alternate sequences are excluded from the VCFs.\nVariants which fail Picard liftover may be reviewed by an analyst and lifted over manually.\n",{"type":429,"tag":492,"props":1295,"children":1298},{"href":1296,"rel":1297},"http://samtools.github.io/bcftools/bcftools.html",[513],[1299],{"type":429,"tag":709,"props":1300,"children":1302},{"className":1301},[],[1303],{"type":435,"value":1304},"bcftools annotate",{"type":435,"value":1306}," is used to document the reference file and exact liftover command used in the VCF's header.\nNote that hg19 alleles and coordinates are stored by Picard in the ",{"type":429,"tag":709,"props":1308,"children":1310},{"className":1309},[],[1311],{"type":435,"value":1312},"OriginalAlleles",{"type":435,"value":1314},", ",{"type":429,"tag":709,"props":1316,"children":1318},{"className":1317},[],[1319],{"type":435,"value":1320},"OriginalContig",{"type":435,"value":1197},{"type":429,"tag":709,"props":1323,"children":1325},{"className":1324},[],[1326],{"type":435,"value":1327},"OriginalStart",{"type":435,"value":1329}," info tags within the final VCF file.\nPlease also note that there is a bug in the version of Picard we use (version 2.18.29) which rarely truncates some of the VCF's format and sample fields.\nThese are fields which we use to store read counts and depths for each sequencing type (WGS, WES, RNA-Seq, VALCAP).\nA ",{"type":429,"tag":492,"props":1331,"children":1334},{"href":1332,"rel":1333},"https://github.com/broadinstitute/picard/issues/1558",[513],[1335],{"type":435,"value":1336},"bug report",{"type":435,"value":1338}," has been filed with Picard.\nIn the current version of the pipeline we recover the dropped entries from the original hg19 VCF.\nWhile searching for and correcting these entries, we also reorder the FORMAT and genotype fields to a logical ordering, as opposed to the alphabetical output order of Picard.",{"type":429,"tag":438,"props":1340,"children":1341},{},[1342,1347,1349,1355,1357,1362],{"type":429,"tag":709,"props":1343,"children":1345},{"className":1344},[],[1346],{"type":435,"value":877},{"type":435,"value":1348}," is used to obtain consistent representations of all variants which may have multiple equivalent forms.\nIf VT modifies a variant, it records the original form in the ",{"type":429,"tag":709,"props":1350,"children":1352},{"className":1351},[],[1353],{"type":435,"value":1354},"OLD_VARIANT",{"type":435,"value":1356}," info tag. ",{"type":429,"tag":492,"props":1358,"children":1360},{"href":869,"rel":1359},[513],[1361],{"type":435,"value":497},{"type":435,"value":1363}," to read about variant normalization.",{"type":429,"tag":438,"props":1365,"children":1366},{},[1367,1369,1375],{"type":435,"value":1368},"For a full description of the annotations VEP determines for each variant, see the ",{"type":429,"tag":492,"props":1370,"children":1372},{"href":886,"rel":1371},[513],[1373],{"type":435,"value":1374},"VEP documentation",{"type":435,"value":663},{"type":429,"tag":986,"props":1377,"children":1379},{"id":1378},"naming-convention",[1380],{"type":435,"value":1381},"Naming convention",{"type":429,"tag":438,"props":1383,"children":1384},{},[1385,1387,1393,1395,1401,1403,1409,1411,1417],{"type":435,"value":1386},"Somatic VCFs are the result of a paired tumor-normal analysis and are named to indicate the samples used in that analysis.\nWe use the tumor sample name followed by the germline sample name.\nUsually, the tumor and germline sample names share the same initial prefix, and in this case we do not repeat the prefix.\nFor example, an analysis with tumor sample ",{"type":429,"tag":709,"props":1388,"children":1390},{"className":1389},[],[1391],{"type":435,"value":1392},"SJOS0123_D",{"type":435,"value":1394}," and germline sample ",{"type":429,"tag":709,"props":1396,"children":1398},{"className":1397},[],[1399],{"type":435,"value":1400},"SJOS0123_G",{"type":435,"value":1402}," becomes ",{"type":429,"tag":709,"props":1404,"children":1406},{"className":1405},[],[1407],{"type":435,"value":1408},"SJOS0123_D_G",{"type":435,"value":1410},".\nIn some rare cases, the prefix differs.\nFor example, with ",{"type":429,"tag":709,"props":1412,"children":1414},{"className":1413},[],[1415],{"type":435,"value":1416},"SJHM030441_D2_SJOS030441_G1",{"type":435,"value":1418},", the germline sample was taken when the patient was being treated for Osteosarcoma, but the tumor sample was taken from the same patient at the time of treatment for Acute Myeloid Leukemia; since there is no shared prefix, they are appended in full length.",{"type":429,"tag":438,"props":1420,"children":1421},{},[1422,1424,1430,1432,1438,1440,1446],{"type":435,"value":1423},"The metadata file ",{"type":429,"tag":709,"props":1425,"children":1427},{"className":1426},[],[1428],{"type":435,"value":1429},"SAMPLE_INFO.txt",{"type":435,"value":1431}," contains the exact details for which samples are included in the analysis.\nThe disease sample is under ",{"type":429,"tag":709,"props":1433,"children":1435},{"className":1434},[],[1436],{"type":435,"value":1437},"sample_name",{"type":435,"value":1439},", and the normal sample is under ",{"type":429,"tag":709,"props":1441,"children":1443},{"className":1442},[],[1444],{"type":435,"value":1445},"attr_control_sample",{"type":435,"value":1447},".\nSince these original files are from a wide-span of projects over the years, the exact sample naming conventions have changed and the VCF file names reflect those changes.",{"type":429,"tag":438,"props":1449,"children":1450},{},[1451,1453,1459,1461,1467,1469,1474],{"type":435,"value":1452},"An exception occurs when different germline samples were used in separate experiments comparing against the same disease sample.\nAll somatic VCFs may contain data from up to four different experiments; WGS, WES, RNA-Seq, and VALCAP experiments can all be presented in the same file.\nIn nearly all cases those 4 experiments will have been done using the same germline samples.\nBut rarely one analysis (i.e. WGS analysis) was done using one germline sample, and another analysis (i.e. WES analysis) was done using another germline sample.\nIn those cases we integrate the data and join the germline extensions using hyphens (",{"type":429,"tag":709,"props":1454,"children":1456},{"className":1455},[],[1457],{"type":435,"value":1458},"-",{"type":435,"value":1460},"); for example ",{"type":429,"tag":709,"props":1462,"children":1464},{"className":1463},[],[1465],{"type":435,"value":1466},"SJETV010_D_G-H",{"type":435,"value":1468},".\nThe VCF header and the metadata file ",{"type":429,"tag":709,"props":1470,"children":1472},{"className":1471},[],[1473],{"type":435,"value":1429},{"type":435,"value":1475}," will contain more details about which samples were used for which experiments.",{"type":429,"tag":438,"props":1477,"children":1478},{},[1479],{"type":435,"value":1480},"File names are not always reflective of the truth for a given sample, and the metadata should always be used during sample selection as it has been thoroughly curated by experts.",{"type":429,"tag":986,"props":1482,"children":1484},{"id":1483},"additional-caveats",[1485],{"type":435,"value":1486},"Additional Caveats",{"type":429,"tag":438,"props":1488,"children":1489},{},[1490,1492,1497],{"type":435,"value":1491},"The VCF headers will explain each annotation used, including the fields for read counts and depths of each sequencing type.\nFor more information on the variant calling format (VCF), please see the version 4.2 specification for VCF documents ",{"type":429,"tag":492,"props":1493,"children":1495},{"href":511,"rel":1494},[513],[1496],{"type":435,"value":775},{"type":435,"value":663},{"type":429,"tag":438,"props":1499,"children":1500},{},[1501],{"type":435,"value":1502},"It is possible for the same variant to be included more than once.\nThis is most commonly caused by functionally equivalent indels being called with different forms at nearby locations in the original pipeline.\nHowever once the variants are normalized, it is revealed that they are the same variant.\nWe make no attempt to select one entry when this occurs and opt to include all duplicates.\nThey may have different read evidence or validation statuses.\nThere may be other sources of these duplicates (such as liftover), but they are rare and we make no attempt to remove them.",{"type":429,"tag":598,"props":1504,"children":1506},{"id":1505},"cnv-files",[1507],{"type":435,"value":1508},"CNV files",{"type":429,"tag":438,"props":1510,"children":1511},{},[1512,1514,1521,1523,1530],{"type":435,"value":1513},"CNV files contain copy number alteration (CNA) analysis results for paired tumor-normal WGS samples.\nFiles are produced by running paired tumor-normal BAM files through the ",{"type":429,"tag":492,"props":1515,"children":1518},{"href":1516,"rel":1517},"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC4591043/",[513],[1519],{"type":435,"value":1520},"CONSERTING",{"type":435,"value":1522}," pipeline which identifies CNA through iterative analysis of (i) local segmentation by read depth within boundaries identified by structural variation (SV) breakpoints followed by (ii) segment merging and local SV analysis.\n",{"type":429,"tag":492,"props":1524,"children":1527},{"href":1525,"rel":1526},"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC3527068/",[513],[1528],{"type":435,"value":1529},"CREST",{"type":435,"value":1531}," was used to identify local SV breakpoints.\nCNV files contain the following information:",{"type":429,"tag":444,"props":1533,"children":1534},{},[1535,1551],{"type":429,"tag":448,"props":1536,"children":1537},{},[1538],{"type":429,"tag":452,"props":1539,"children":1540},{},[1541,1546],{"type":429,"tag":456,"props":1542,"children":1543},{},[1544],{"type":435,"value":1545},"Field",{"type":429,"tag":456,"props":1547,"children":1548},{},[1549],{"type":435,"value":1550},"Description",{"type":429,"tag":472,"props":1552,"children":1553},{},[1554,1567,1580,1593],{"type":429,"tag":452,"props":1555,"children":1556},{},[1557,1562],{"type":429,"tag":479,"props":1558,"children":1559},{},[1560],{"type":435,"value":1561},"chrom",{"type":429,"tag":479,"props":1563,"children":1564},{},[1565],{"type":435,"value":1566},"chromosome",{"type":429,"tag":452,"props":1568,"children":1569},{},[1570,1575],{"type":429,"tag":479,"props":1571,"children":1572},{},[1573],{"type":435,"value":1574},"loc.start",{"type":429,"tag":479,"props":1576,"children":1577},{},[1578],{"type":435,"value":1579},"start of segment",{"type":429,"tag":452,"props":1581,"children":1582},{},[1583,1588],{"type":429,"tag":479,"props":1584,"children":1585},{},[1586],{"type":435,"value":1587},"loc.end",{"type":429,"tag":479,"props":1589,"children":1590},{},[1591],{"type":435,"value":1592},"end of segment",{"type":429,"tag":452,"props":1594,"children":1595},{},[1596,1601],{"type":429,"tag":479,"props":1597,"children":1598},{},[1599],{"type":435,"value":1600},"LogRatio",{"type":429,"tag":479,"props":1602,"children":1603},{},[1604],{"type":435,"value":1605},"Log2 ratio between tumor and normal coverage",{"type":429,"tag":598,"props":1607,"children":1609},{"id":1608},"feature-counts-files",[1610],{"type":435,"value":1611},"Feature Counts files",{"type":429,"tag":438,"props":1613,"children":1614},{},[1615,1617,1624,1626,1633],{"type":435,"value":1616},"Feature counts are text files that contain counts of reads aligned to genomic features.\nSt. Jude Cloud feature files are generated using HTSeq.\nThe detailed command is documented in our ",{"type":429,"tag":492,"props":1618,"children":1621},{"href":1619,"rel":1620},"https://stjudecloud.github.io/rfcs/0001-rnaseq-workflow-v2.0.0.html#specification",[513],[1622],{"type":435,"value":1623},"RNA-Seq V2 RFC",{"type":435,"value":1625},".\nThe files contain a count of the number of reads overlapping each genomic feature, in this case, genes as specified in ",{"type":429,"tag":492,"props":1627,"children":1630},{"href":1628,"rel":1629},"https://www.gencodegenes.org/human/release_31.html",[513],[1631],{"type":435,"value":1632},"GENCODE V31",{"type":435,"value":1634},".\nSt. Jude Cloud uses the gene name as feature key.\nThe files are tab-delimited text and contain the feature key and read count for that feature.",{"type":429,"tag":430,"props":1636,"children":1638},{"id":1637},"sequencing-information",[1639],{"type":435,"value":1640},"Sequencing Information",{"type":429,"tag":598,"props":1642,"children":1644},{"id":1643},"whole-genome-and-whole-exome",[1645],{"type":435,"value":1646},"Whole Genome and Whole Exome",{"type":429,"tag":438,"props":1648,"children":1649},{},[1650,1652,1657],{"type":435,"value":1651},"Whole Genome Sequence (WGS) and Whole Exome Sequence (WES) BAM files generated before January 2025 were produced by the Microsoft Genomics Service aligned to hg38 (GRCh38 no alt analysis set).\nFor more information about how Microsoft Genomics produces BAM files or any other questions regarding data generation, please refer to ",{"type":429,"tag":492,"props":1653,"children":1654},{"href":657,"target":658},[1655],{"type":435,"value":1656},"the official Microsoft Genomics white paper",{"type":435,"value":663},{"type":429,"tag":438,"props":1659,"children":1660},{},[1661],{"type":435,"value":1662},"WGS and WES BAM files produced after Microsoft Genomics Service was retired in January 2025 are generated using a pipeline with results highly consistent with those from Microsoft Genomics Service, as verified by SNP genotype concordance of 99.9 % across a random sample set (n=6).\nThe workflow uses the hg38m1x reference genome.",{"type":429,"tag":598,"props":1664,"children":1666},{"id":1665},"rna-seq",[1667],{"type":435,"value":1668},"RNA-Seq",{"type":429,"tag":438,"props":1670,"children":1671},{},[1672,1674,1680,1682,1687,1689,1696,1698,1705,1707,1713,1715,1722],{"type":435,"value":1673},"RNA-Seq BAM files are mapped to hg38.\nFor alignment, ",{"type":429,"tag":709,"props":1675,"children":1677},{"className":1676},[],[1678],{"type":435,"value":1679},"STAR",{"type":435,"value":1681}," v2.7.1a 2-pass mapping is used.\nBelow is the ",{"type":429,"tag":709,"props":1683,"children":1685},{"className":1684},[],[1686],{"type":435,"value":1679},{"type":435,"value":1688}," command used during alignment.\nFor more information about any of the parameters used, please refer to the ",{"type":429,"tag":492,"props":1690,"children":1693},{"href":1691,"rel":1692},"https://github.com/alexdobin/STAR/blob/a22ad18600c827841e3fcd74118e9baac75669f4/doc/STARmanual.pdf",[513],[1694],{"type":435,"value":1695},"STAR manual",{"type":435,"value":1697}," for v2.7.1a.\nThe complete RNA-Seq WDL pipeline is available on ",{"type":429,"tag":492,"props":1699,"children":1702},{"href":1700,"rel":1701},"https://github.com/stjudecloud/workflows/blob/master/workflows/rnaseq/rnaseq-standard.wdl",[513],[1703],{"type":435,"value":1704},"GitHub",{"type":435,"value":1706},".\nThe STAR alignment parameters are also available on ",{"type":429,"tag":492,"props":1708,"children":1711},{"href":1709,"rel":1710},"https://github.com/stjudecloud/workflows/blob/master/tools/star.wdl",[513],[1712],{"type":435,"value":1704},{"type":435,"value":1714},".\nFor additional information about St. Jude Cloud's RNA-Seq pipeline, visit the ",{"type":429,"tag":492,"props":1716,"children":1719},{"href":1717,"rel":1718},"https://stjudecloud.github.io/rfcs/0001-rnaseq-workflow-v2.0.0.html",[513],[1720],{"type":435,"value":1721},"RFC",{"type":435,"value":663},{"type":429,"tag":1724,"props":1725,"children":1729},"pre",{"className":1726,"code":1727,"language":1728,"meta":424,"style":424},"language-bash shiki shiki-themes material-theme-lighter material-theme material-theme-palenight","STAR \\\n  --readFilesIn $(cat read_one_fastqs_sorted.txt) $(cat read_two_fastqs_sorted.txt) \\\n  --genomeDir ~{stardb_dir} \\\n  --runThreadN $n_cores \\\n  --outSAMunmapped Within \\\n  --outSAMstrandField intronMotif \\\n  --outSAMtype BAM Unsorted \\\n  --outSAMattributes NH HI AS nM NM MD XS \\\n  --outFilterMultimapScoreRange 1 \\\n  --outFilterMultimapNmax 20 \\\n  --outFilterMismatchNmax 10 \\\n  --alignIntronMax 500000 \\\n  --alignMatesGapMax 1000000 \\\n  --sjdbScore 2 \\\n  --alignSJDBoverhangMin 1 \\\n  --outFilterMatchNminOverLread 0.66 \\\n  --outFilterScoreMinOverLread 0.66 \\\n  --outFileNamePrefix ~{output_prefix + \".\"} \\\n  --twopassMode Basic \\\n  --limitBAMsortRAM ~{(memory_gb - 2) + \"000000000\"} \\\n  --outSAMattrRGline $(cat read_groups_sorted.txt)\n","bash",[1730],{"type":429,"tag":709,"props":1731,"children":1732},{"__ignoreMap":424},[1733,1750,1802,1820,1834,1852,1870,1893,1941,1960,1978,1996,2014,2032,2050,2067,2085,2102,2144,2162,2224],{"type":429,"tag":1734,"props":1735,"children":1738},"span",{"class":1736,"line":1737},"line",1,[1739,1744],{"type":429,"tag":1734,"props":1740,"children":1742},{"style":1741},"--shiki-light:#E2931D;--shiki-default:#FFCB6B;--shiki-dark:#FFCB6B",[1743],{"type":435,"value":1679},{"type":429,"tag":1734,"props":1745,"children":1747},{"style":1746},"--shiki-light:#90A4AE;--shiki-default:#EEFFFF;--shiki-dark:#BABED8",[1748],{"type":435,"value":1749}," \\\n",{"type":429,"tag":1734,"props":1751,"children":1753},{"class":1736,"line":1752},2,[1754,1760,1766,1771,1776,1781,1785,1789,1794,1798],{"type":429,"tag":1734,"props":1755,"children":1757},{"style":1756},"--shiki-light:#91B859;--shiki-default:#C3E88D;--shiki-dark:#C3E88D",[1758],{"type":435,"value":1759},"  --readFilesIn",{"type":429,"tag":1734,"props":1761,"children":1763},{"style":1762},"--shiki-light:#39ADB5;--shiki-default:#89DDFF;--shiki-dark:#89DDFF",[1764],{"type":435,"value":1765}," $(",{"type":429,"tag":1734,"props":1767,"children":1768},{"style":1741},[1769],{"type":435,"value":1770},"cat",{"type":429,"tag":1734,"props":1772,"children":1773},{"style":1756},[1774],{"type":435,"value":1775}," read_one_fastqs_sorted.txt",{"type":429,"tag":1734,"props":1777,"children":1778},{"style":1762},[1779],{"type":435,"value":1780},")",{"type":429,"tag":1734,"props":1782,"children":1783},{"style":1762},[1784],{"type":435,"value":1765},{"type":429,"tag":1734,"props":1786,"children":1787},{"style":1741},[1788],{"type":435,"value":1770},{"type":429,"tag":1734,"props":1790,"children":1791},{"style":1756},[1792],{"type":435,"value":1793}," read_two_fastqs_sorted.txt",{"type":429,"tag":1734,"props":1795,"children":1796},{"style":1762},[1797],{"type":435,"value":1780},{"type":429,"tag":1734,"props":1799,"children":1800},{"style":1746},[1801],{"type":435,"value":1749},{"type":429,"tag":1734,"props":1803,"children":1805},{"class":1736,"line":1804},3,[1806,1811,1816],{"type":429,"tag":1734,"props":1807,"children":1808},{"style":1756},[1809],{"type":435,"value":1810},"  --genomeDir",{"type":429,"tag":1734,"props":1812,"children":1813},{"style":1756},[1814],{"type":435,"value":1815}," ~{stardb_dir}",{"type":429,"tag":1734,"props":1817,"children":1818},{"style":1746},[1819],{"type":435,"value":1749},{"type":429,"tag":1734,"props":1821,"children":1823},{"class":1736,"line":1822},4,[1824,1829],{"type":429,"tag":1734,"props":1825,"children":1826},{"style":1756},[1827],{"type":435,"value":1828},"  --runThreadN",{"type":429,"tag":1734,"props":1830,"children":1831},{"style":1746},[1832],{"type":435,"value":1833}," $n_cores \\\n",{"type":429,"tag":1734,"props":1835,"children":1837},{"class":1736,"line":1836},5,[1838,1843,1848],{"type":429,"tag":1734,"props":1839,"children":1840},{"style":1756},[1841],{"type":435,"value":1842},"  --outSAMunmapped",{"type":429,"tag":1734,"props":1844,"children":1845},{"style":1756},[1846],{"type":435,"value":1847}," Within",{"type":429,"tag":1734,"props":1849,"children":1850},{"style":1746},[1851],{"type":435,"value":1749},{"type":429,"tag":1734,"props":1853,"children":1855},{"class":1736,"line":1854},6,[1856,1861,1866],{"type":429,"tag":1734,"props":1857,"children":1858},{"style":1756},[1859],{"type":435,"value":1860},"  --outSAMstrandField",{"type":429,"tag":1734,"props":1862,"children":1863},{"style":1756},[1864],{"type":435,"value":1865}," intronMotif",{"type":429,"tag":1734,"props":1867,"children":1868},{"style":1746},[1869],{"type":435,"value":1749},{"type":429,"tag":1734,"props":1871,"children":1873},{"class":1736,"line":1872},7,[1874,1879,1884,1889],{"type":429,"tag":1734,"props":1875,"children":1876},{"style":1756},[1877],{"type":435,"value":1878},"  --outSAMtype",{"type":429,"tag":1734,"props":1880,"children":1881},{"style":1756},[1882],{"type":435,"value":1883}," BAM",{"type":429,"tag":1734,"props":1885,"children":1886},{"style":1756},[1887],{"type":435,"value":1888}," Unsorted",{"type":429,"tag":1734,"props":1890,"children":1891},{"style":1746},[1892],{"type":435,"value":1749},{"type":429,"tag":1734,"props":1894,"children":1896},{"class":1736,"line":1895},8,[1897,1902,1907,1912,1917,1922,1927,1932,1937],{"type":429,"tag":1734,"props":1898,"children":1899},{"style":1756},[1900],{"type":435,"value":1901},"  --outSAMattributes",{"type":429,"tag":1734,"props":1903,"children":1904},{"style":1756},[1905],{"type":435,"value":1906}," NH",{"type":429,"tag":1734,"props":1908,"children":1909},{"style":1756},[1910],{"type":435,"value":1911}," HI",{"type":429,"tag":1734,"props":1913,"children":1914},{"style":1756},[1915],{"type":435,"value":1916}," AS",{"type":429,"tag":1734,"props":1918,"children":1919},{"style":1756},[1920],{"type":435,"value":1921}," nM",{"type":429,"tag":1734,"props":1923,"children":1924},{"style":1756},[1925],{"type":435,"value":1926}," NM",{"type":429,"tag":1734,"props":1928,"children":1929},{"style":1756},[1930],{"type":435,"value":1931}," MD",{"type":429,"tag":1734,"props":1933,"children":1934},{"style":1756},[1935],{"type":435,"value":1936}," XS",{"type":429,"tag":1734,"props":1938,"children":1939},{"style":1746},[1940],{"type":435,"value":1749},{"type":429,"tag":1734,"props":1942,"children":1944},{"class":1736,"line":1943},9,[1945,1950,1956],{"type":429,"tag":1734,"props":1946,"children":1947},{"style":1756},[1948],{"type":435,"value":1949},"  --outFilterMultimapScoreRange",{"type":429,"tag":1734,"props":1951,"children":1953},{"style":1952},"--shiki-light:#F76D47;--shiki-default:#F78C6C;--shiki-dark:#F78C6C",[1954],{"type":435,"value":1955}," 1",{"type":429,"tag":1734,"props":1957,"children":1958},{"style":1746},[1959],{"type":435,"value":1749},{"type":429,"tag":1734,"props":1961,"children":1963},{"class":1736,"line":1962},10,[1964,1969,1974],{"type":429,"tag":1734,"props":1965,"children":1966},{"style":1756},[1967],{"type":435,"value":1968},"  --outFilterMultimapNmax",{"type":429,"tag":1734,"props":1970,"children":1971},{"style":1952},[1972],{"type":435,"value":1973}," 20",{"type":429,"tag":1734,"props":1975,"children":1976},{"style":1746},[1977],{"type":435,"value":1749},{"type":429,"tag":1734,"props":1979,"children":1981},{"class":1736,"line":1980},11,[1982,1987,1992],{"type":429,"tag":1734,"props":1983,"children":1984},{"style":1756},[1985],{"type":435,"value":1986},"  --outFilterMismatchNmax",{"type":429,"tag":1734,"props":1988,"children":1989},{"style":1952},[1990],{"type":435,"value":1991}," 10",{"type":429,"tag":1734,"props":1993,"children":1994},{"style":1746},[1995],{"type":435,"value":1749},{"type":429,"tag":1734,"props":1997,"children":1999},{"class":1736,"line":1998},12,[2000,2005,2010],{"type":429,"tag":1734,"props":2001,"children":2002},{"style":1756},[2003],{"type":435,"value":2004},"  --alignIntronMax",{"type":429,"tag":1734,"props":2006,"children":2007},{"style":1952},[2008],{"type":435,"value":2009}," 500000",{"type":429,"tag":1734,"props":2011,"children":2012},{"style":1746},[2013],{"type":435,"value":1749},{"type":429,"tag":1734,"props":2015,"children":2017},{"class":1736,"line":2016},13,[2018,2023,2028],{"type":429,"tag":1734,"props":2019,"children":2020},{"style":1756},[2021],{"type":435,"value":2022},"  --alignMatesGapMax",{"type":429,"tag":1734,"props":2024,"children":2025},{"style":1952},[2026],{"type":435,"value":2027}," 1000000",{"type":429,"tag":1734,"props":2029,"children":2030},{"style":1746},[2031],{"type":435,"value":1749},{"type":429,"tag":1734,"props":2033,"children":2035},{"class":1736,"line":2034},14,[2036,2041,2046],{"type":429,"tag":1734,"props":2037,"children":2038},{"style":1756},[2039],{"type":435,"value":2040},"  --sjdbScore",{"type":429,"tag":1734,"props":2042,"children":2043},{"style":1952},[2044],{"type":435,"value":2045}," 2",{"type":429,"tag":1734,"props":2047,"children":2048},{"style":1746},[2049],{"type":435,"value":1749},{"type":429,"tag":1734,"props":2051,"children":2053},{"class":1736,"line":2052},15,[2054,2059,2063],{"type":429,"tag":1734,"props":2055,"children":2056},{"style":1756},[2057],{"type":435,"value":2058},"  --alignSJDBoverhangMin",{"type":429,"tag":1734,"props":2060,"children":2061},{"style":1952},[2062],{"type":435,"value":1955},{"type":429,"tag":1734,"props":2064,"children":2065},{"style":1746},[2066],{"type":435,"value":1749},{"type":429,"tag":1734,"props":2068,"children":2070},{"class":1736,"line":2069},16,[2071,2076,2081],{"type":429,"tag":1734,"props":2072,"children":2073},{"style":1756},[2074],{"type":435,"value":2075},"  --outFilterMatchNminOverLread",{"type":429,"tag":1734,"props":2077,"children":2078},{"style":1952},[2079],{"type":435,"value":2080}," 0.66",{"type":429,"tag":1734,"props":2082,"children":2083},{"style":1746},[2084],{"type":435,"value":1749},{"type":429,"tag":1734,"props":2086,"children":2088},{"class":1736,"line":2087},17,[2089,2094,2098],{"type":429,"tag":1734,"props":2090,"children":2091},{"style":1756},[2092],{"type":435,"value":2093},"  --outFilterScoreMinOverLread",{"type":429,"tag":1734,"props":2095,"children":2096},{"style":1952},[2097],{"type":435,"value":2080},{"type":429,"tag":1734,"props":2099,"children":2100},{"style":1746},[2101],{"type":435,"value":1749},{"type":429,"tag":1734,"props":2103,"children":2105},{"class":1736,"line":2104},18,[2106,2111,2116,2121,2126,2130,2135,2140],{"type":429,"tag":1734,"props":2107,"children":2108},{"style":1756},[2109],{"type":435,"value":2110},"  --outFileNamePrefix",{"type":429,"tag":1734,"props":2112,"children":2113},{"style":1756},[2114],{"type":435,"value":2115}," ~{output_prefix",{"type":429,"tag":1734,"props":2117,"children":2118},{"style":1756},[2119],{"type":435,"value":2120}," +",{"type":429,"tag":1734,"props":2122,"children":2123},{"style":1762},[2124],{"type":435,"value":2125}," \"",{"type":429,"tag":1734,"props":2127,"children":2128},{"style":1756},[2129],{"type":435,"value":663},{"type":429,"tag":1734,"props":2131,"children":2132},{"style":1762},[2133],{"type":435,"value":2134},"\"",{"type":429,"tag":1734,"props":2136,"children":2137},{"style":1756},[2138],{"type":435,"value":2139},"}",{"type":429,"tag":1734,"props":2141,"children":2142},{"style":1746},[2143],{"type":435,"value":1749},{"type":429,"tag":1734,"props":2145,"children":2147},{"class":1736,"line":2146},19,[2148,2153,2158],{"type":429,"tag":1734,"props":2149,"children":2150},{"style":1756},[2151],{"type":435,"value":2152},"  --twopassMode",{"type":429,"tag":1734,"props":2154,"children":2155},{"style":1756},[2156],{"type":435,"value":2157}," Basic",{"type":429,"tag":1734,"props":2159,"children":2160},{"style":1746},[2161],{"type":435,"value":1749},{"type":429,"tag":1734,"props":2163,"children":2165},{"class":1736,"line":2164},20,[2166,2171,2176,2181,2186,2191,2195,2199,2203,2207,2212,2216,2220],{"type":429,"tag":1734,"props":2167,"children":2168},{"style":1756},[2169],{"type":435,"value":2170},"  --limitBAMsortRAM",{"type":429,"tag":1734,"props":2172,"children":2173},{"style":1756},[2174],{"type":435,"value":2175}," ~{",{"type":429,"tag":1734,"props":2177,"children":2178},{"style":1762},[2179],{"type":435,"value":2180},"(",{"type":429,"tag":1734,"props":2182,"children":2183},{"style":1741},[2184],{"type":435,"value":2185},"memory_gb",{"type":429,"tag":1734,"props":2187,"children":2188},{"style":1756},[2189],{"type":435,"value":2190}," -",{"type":429,"tag":1734,"props":2192,"children":2193},{"style":1952},[2194],{"type":435,"value":2045},{"type":429,"tag":1734,"props":2196,"children":2197},{"style":1762},[2198],{"type":435,"value":1780},{"type":429,"tag":1734,"props":2200,"children":2201},{"style":1756},[2202],{"type":435,"value":2120},{"type":429,"tag":1734,"props":2204,"children":2205},{"style":1762},[2206],{"type":435,"value":2125},{"type":429,"tag":1734,"props":2208,"children":2209},{"style":1756},[2210],{"type":435,"value":2211},"000000000",{"type":429,"tag":1734,"props":2213,"children":2214},{"style":1762},[2215],{"type":435,"value":2134},{"type":429,"tag":1734,"props":2217,"children":2218},{"style":1756},[2219],{"type":435,"value":2139},{"type":429,"tag":1734,"props":2221,"children":2222},{"style":1746},[2223],{"type":435,"value":1749},{"type":429,"tag":1734,"props":2225,"children":2227},{"class":1736,"line":2226},21,[2228,2233,2237,2241,2246],{"type":429,"tag":1734,"props":2229,"children":2230},{"style":1756},[2231],{"type":435,"value":2232},"  --outSAMattrRGline",{"type":429,"tag":1734,"props":2234,"children":2235},{"style":1762},[2236],{"type":435,"value":1765},{"type":429,"tag":1734,"props":2238,"children":2239},{"style":1741},[2240],{"type":435,"value":1770},{"type":429,"tag":1734,"props":2242,"children":2243},{"style":1756},[2244],{"type":435,"value":2245}," read_groups_sorted.txt",{"type":429,"tag":1734,"props":2247,"children":2248},{"style":1762},[2249],{"type":435,"value":2250},")\n",{"type":429,"tag":2252,"props":2253,"children":2254},"style",{},[2255],{"type":435,"value":2256},"html .light .shiki span {color: var(--shiki-light);background: var(--shiki-light-bg);font-style: var(--shiki-light-font-style);font-weight: var(--shiki-light-font-weight);text-decoration: var(--shiki-light-text-decoration);}html.light .shiki span {color: var(--shiki-light);background: var(--shiki-light-bg);font-style: var(--shiki-light-font-style);font-weight: var(--shiki-light-font-weight);text-decoration: var(--shiki-light-text-decoration);}html .default .shiki span {color: var(--shiki-default);background: var(--shiki-default-bg);font-style: var(--shiki-default-font-style);font-weight: var(--shiki-default-font-weight);text-decoration: var(--shiki-default-text-decoration);}html .shiki span {color: var(--shiki-default);background: var(--shiki-default-bg);font-style: var(--shiki-default-font-style);font-weight: var(--shiki-default-font-weight);text-decoration: var(--shiki-default-text-decoration);}html .dark .shiki span {color: var(--shiki-dark);background: var(--shiki-dark-bg);font-style: var(--shiki-dark-font-style);font-weight: var(--shiki-dark-font-weight);text-decoration: var(--shiki-dark-text-decoration);}html.dark .shiki span {color: var(--shiki-dark);background: var(--shiki-dark-bg);font-style: var(--shiki-dark-font-style);font-weight: var(--shiki-dark-font-weight);text-decoration: var(--shiki-dark-text-decoration);}",{"title":424,"searchDepth":1752,"depth":1752,"links":2258},[2259,2266],{"id":432,"depth":1752,"text":436,"children":2260},[2261,2262,2263,2264,2265],{"id":600,"depth":1804,"text":603},{"id":620,"depth":1804,"text":623},{"id":671,"depth":1804,"text":674},{"id":1505,"depth":1804,"text":1508},{"id":1608,"depth":1804,"text":1611},{"id":1637,"depth":1752,"text":1640,"children":2267},[2268,2269],{"id":1643,"depth":1804,"text":1646},{"id":1665,"depth":1804,"text":1668},"markdown","content:3.genomics-platform:2.about-our-data:2.file-formats-and-sequencing-information.md","content","3.genomics-platform/2.about-our-data/2.file-formats-and-sequencing-information.md","3.genomics-platform/2.about-our-data/2.file-formats-and-sequencing-information","md",[2277,2278],{"_path":55,"title":54,"description":424},{"_path":61,"title":60,"description":424},1791243637592]