[{"data":1,"prerenderedAt":2025},["ShallowReactive",2],{"navigation":3,"/genomics-platform/workflow-guides/rnaseq-expression-classification":421,"/genomics-platform/workflow-guides/rnaseq-expression-classification-surround":2022},[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":120,"_dir":422,"_draft":423,"_partial":423,"_locale":424,"title":119,"description":424,"body":425,"_type":2016,"_id":2017,"_source":2018,"_file":2019,"_stem":2020,"_extension":2021},"workflow-guides",false,"",{"type":426,"children":427,"toc":1991},"root",[428,436,453,460,511,517,522,591,636,642,647,742,748,792,799,813,819,833,839,861,867,928,934,939,971,997,1011,1017,1022,1034,1043,1056,1078,1084,1096,1102,1113,1149,1201,1207,1212,1299,1304,1312,1317,1591,1596,1604,1610,1623,1635,1643,1648,1656,1661,1669,1674,1682,1702,1710,1716,1721,1726,1731,1736,1750,1756,1761,1767,1772,1777,1783,1797,1805,1811,1816,1886,1892,1897,1950,1956,1968,1974,1985],{"type":429,"tag":430,"props":431,"children":433},"element","h2",{"id":432},"overview",[434],{"type":435,"value":5},"text",{"type":429,"tag":437,"props":438,"children":439},"p",{},[440,442,451],{"type":435,"value":441},"St. Jude Cloud provides functionality for generating RNA-Seq Expression Classification plots.\nThis workflow allows plotting of RNA-Seq data by running through the St. Jude Cloud normalization ",{"type":429,"tag":443,"props":444,"children":448},"a",{"href":445,"rel":446},"https://stjudecloud.github.io/rfcs/0001-rnaseq-workflow-v2.0.0.html",[447],"nofollow",[449],{"type":435,"value":450},"pipeline",{"type":435,"value":452},".\nThe generated count data is then compared to a reference set of data from a cohort of St. Jude samples and a plot is produced.",{"type":429,"tag":454,"props":455,"children":457},"h3",{"id":456},"requirements",[458],{"type":435,"value":459},"Requirements",{"type":429,"tag":461,"props":462,"children":463},"ul",{},[464,470,491],{"type":429,"tag":465,"props":466,"children":467},"li",{},[468],{"type":435,"value":469},"The RNA-Seq Expression Classification pipeline reference data uses sequencing data from fresh, frozen tissue samples.\nIt has not been evaluated for use with sequencing data generated from formalin-fixed paraffin-embedded (FFPE) specimens.",{"type":429,"tag":465,"props":471,"children":472},{},[473,475,481,483,489],{"type":435,"value":474},"If running the count-based pipeline, alignment must be done against the ",{"type":429,"tag":443,"props":476,"children":478},{"href":477},"ftp://ftp.ncbi.nlm.nih.gov/genomes/all/GCA/000/001/405/GCA_000001405.15_GRCh38/seqs_for_alignment_pipelines.ucsc_ids/GCA_000001405.15_GRCh38_no_alt_analysis_set.fna.gz",[479],{"type":435,"value":480},"GRCh38_no_alt reference",{"type":435,"value":482},".\nIt should use parameters as specified in our ",{"type":429,"tag":443,"props":484,"children":486},{"href":445,"rel":485},[447],[487],{"type":435,"value":488},"RNA-Seq workflow",{"type":435,"value":490}," to minimize any discrepancies caused by differing alignment specification.",{"type":429,"tag":465,"props":492,"children":493},{},[494,496,501,503,509],{"type":435,"value":495},"If running the count-based pipeline, feature counts should be generated with htseq-count as described in our ",{"type":429,"tag":443,"props":497,"children":499},{"href":445,"rel":498},[447],[500],{"type":435,"value":488},{"type":435,"value":502},".\nThis pipeline uses ",{"type":429,"tag":443,"props":504,"children":506},{"href":505},"ftp://ftp.ebi.ac.uk/pub/databases/gencode/Gencode_human/release_31/gencode.v31.annotation.gtf.gz",[507],{"type":435,"value":508},"Gencode v31",{"type":435,"value":510}," annotations.",{"type":429,"tag":454,"props":512,"children":514},{"id":513},"inputs",[515],{"type":435,"value":516},"Inputs",{"type":429,"tag":437,"props":518,"children":519},{},[520],{"type":435,"value":521},"The input can be either of the two entries below, based on whether you want to start with a counts file or a BAM file.",{"type":429,"tag":523,"props":524,"children":525},"table",{},[526,550],{"type":429,"tag":527,"props":528,"children":529},"thead",{},[530],{"type":429,"tag":531,"props":532,"children":533},"tr",{},[534,540,545],{"type":429,"tag":535,"props":536,"children":537},"th",{},[538],{"type":435,"value":539},"Name",{"type":429,"tag":535,"props":541,"children":542},{},[543],{"type":435,"value":544},"Description",{"type":429,"tag":535,"props":546,"children":547},{},[548],{"type":435,"value":549},"Example",{"type":429,"tag":551,"props":552,"children":553},"tbody",{},[554,573],{"type":429,"tag":531,"props":555,"children":556},{},[557,563,568],{"type":429,"tag":558,"props":559,"children":560},"td",{},[561],{"type":435,"value":562},"BAM file",{"type":429,"tag":558,"props":564,"children":565},{},[566],{"type":435,"value":567},"Aligned reads file from human RNA-Seq",{"type":429,"tag":558,"props":569,"children":570},{},[571],{"type":435,"value":572},"Sample.bam",{"type":429,"tag":531,"props":574,"children":575},{},[576,581,586],{"type":429,"tag":558,"props":577,"children":578},{},[579],{"type":435,"value":580},"Counts file",{"type":429,"tag":558,"props":582,"children":583},{},[584],{"type":435,"value":585},"htseq-count output feature counts file from human RNA-Seq",{"type":429,"tag":558,"props":587,"children":588},{},[589],{"type":435,"value":590},"Sample.counts.txt",{"type":429,"tag":592,"props":593,"children":596},"callout",{"color":594,"icon":595},"orange","i-heroicons-exclamation-circle",[597],{"type":429,"tag":437,"props":598,"children":599},{},[600,606,610,612,617,619,626,628,634],{"type":429,"tag":601,"props":602,"children":603},"strong",{},[604],{"type":435,"value":605},"Warning",{"type":429,"tag":607,"props":608,"children":609},"br",{},[],{"type":435,"value":611},"\nIf you provide counts data to the counts-based pipeline,  it ",{"type":429,"tag":601,"props":613,"children":614},{},[615],{"type":435,"value":616},"must",{"type":435,"value":618}," be aligned to ",{"type":429,"tag":620,"props":621,"children":623},"code",{"className":622},[],[624],{"type":435,"value":625},"GRCh38_no_alt",{"type":435,"value":627},".\nRunning a sample aligned to any other reference genome is not supported.\nMaybe more importantly, we do not check the genome build of the BAM, so errors in computation or the results can occur.\nIf your sample is ",{"type":429,"tag":629,"props":630,"children":631},"em",{},[632],{"type":435,"value":633},"not",{"type":435,"value":635}," aligned to this genome build, we recommend submitting the sample to the realignment-based workflow.",{"type":429,"tag":454,"props":637,"children":639},{"id":638},"outputs",[640],{"type":435,"value":641},"Outputs",{"type":429,"tag":437,"props":643,"children":644},{},[645],{"type":435,"value":646},"The RNA-Seq Expression Classification pipeline produces the following outputs:",{"type":429,"tag":523,"props":648,"children":649},{},[650,669],{"type":429,"tag":527,"props":651,"children":652},{},[653],{"type":429,"tag":531,"props":654,"children":655},{},[656,660,664],{"type":429,"tag":535,"props":657,"children":658},{},[659],{"type":435,"value":539},{"type":429,"tag":535,"props":661,"children":662},{},[663],{"type":435,"value":544},{"type":429,"tag":535,"props":665,"children":666},{},[667],{"type":435,"value":668},"Pipeline Version",{"type":429,"tag":551,"props":670,"children":671},{},[672,690,708,725],{"type":429,"tag":531,"props":673,"children":674},{},[675,680,685],{"type":429,"tag":558,"props":676,"children":677},{},[678],{"type":435,"value":679},"Interactive expression plot (.html)",{"type":429,"tag":558,"props":681,"children":682},{},[683],{"type":435,"value":684},"Visualization of RNA-Seq data",{"type":429,"tag":558,"props":686,"children":687},{},[688],{"type":435,"value":689},"all",{"type":429,"tag":531,"props":691,"children":692},{},[693,698,703],{"type":429,"tag":558,"props":694,"children":695},{},[696],{"type":435,"value":697},"Aligned BAM (.bam)",{"type":429,"tag":558,"props":699,"children":700},{},[701],{"type":435,"value":702},"BAM file produced by our RNA-Seq pipeline for the input samples.",{"type":429,"tag":558,"props":704,"children":705},{},[706],{"type":435,"value":707},"Realignment",{"type":429,"tag":531,"props":709,"children":710},{},[711,716,721],{"type":429,"tag":558,"props":712,"children":713},{},[714],{"type":435,"value":715},"Feature read counts (.txt)",{"type":429,"tag":558,"props":717,"children":718},{},[719],{"type":435,"value":720},"Read counts for the Gencode features.",{"type":429,"tag":558,"props":722,"children":723},{},[724],{"type":435,"value":707},{"type":429,"tag":531,"props":726,"children":727},{},[728,733,738],{"type":429,"tag":558,"props":729,"children":730},{},[731],{"type":435,"value":732},"Gene list (.txt)",{"type":429,"tag":558,"props":734,"children":735},{},[736],{"type":435,"value":737},"List of genes used in analysis (if a fixed list not specified)",{"type":429,"tag":558,"props":739,"children":740},{},[741],{"type":435,"value":689},{"type":429,"tag":454,"props":743,"children":745},{"id":744},"workflow-steps",[746],{"type":435,"value":747},"Workflow Steps",{"type":429,"tag":749,"props":750,"children":751},"ol",{},[752,778,787],{"type":429,"tag":465,"props":753,"children":754},{},[755,761,763,768,770,776],{"type":429,"tag":756,"props":757,"children":758},"span",{},[759],{"type":435,"value":760},"Only for realignment workflow",{"type":435,"value":762}," The aligned BAM is converted to FASTQ and is aligned to ",{"type":429,"tag":620,"props":764,"children":766},{"className":765},[],[767],{"type":435,"value":625},{"type":435,"value":769}," using ",{"type":429,"tag":443,"props":771,"children":773},{"href":445,"rel":772},[447],[774],{"type":435,"value":775},"standard STAR mapping",{"type":435,"value":777},".",{"type":429,"tag":465,"props":779,"children":780},{},[781,785],{"type":429,"tag":756,"props":782,"children":783},{},[784],{"type":435,"value":760},{"type":435,"value":786}," A feature count (.counts.txt) file is produced for comparison to St. Jude Cloud reference data.",{"type":429,"tag":465,"props":788,"children":789},{},[790],{"type":435,"value":791},"A visualization for genomic features is produced.",{"type":429,"tag":793,"props":794,"children":796},"h4",{"id":795},"mapping",[797],{"type":435,"value":798},"Mapping",{"type":429,"tag":437,"props":800,"children":801},{},[802,804,811],{"type":435,"value":803},"We use the ",{"type":429,"tag":443,"props":805,"children":808},{"href":806,"rel":807},"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC3530905/",[447],[809],{"type":435,"value":810},"STAR aligner",{"type":435,"value":812}," to rapidly map reads to the GRCh38 human reference genome.",{"type":429,"tag":793,"props":814,"children":816},{"id":815},"feature-counts",[817],{"type":435,"value":818},"Feature Counts",{"type":429,"tag":437,"props":820,"children":821},{},[822,824,831],{"type":435,"value":823},"We use ",{"type":429,"tag":443,"props":825,"children":828},{"href":826,"rel":827},"https://htseq.readthedocs.io/en/latest/counting.html",[447],[829],{"type":435,"value":830},"htseq-count",{"type":435,"value":832}," to produce genomic feature counts.",{"type":429,"tag":793,"props":834,"children":836},{"id":835},"visualization",[837],{"type":435,"value":838},"Visualization",{"type":429,"tag":437,"props":840,"children":841},{},[842,844,851,853,860],{"type":435,"value":843},"A t-Distributed Stochastic Neighbor Embedding (t-SNE) visualization is produced using ",{"type":429,"tag":443,"props":845,"children":848},{"href":846,"rel":847},"https://github.com/jkrijthe/Rtsne",[447],[849],{"type":435,"value":850},"Rtsne",{"type":435,"value":852},".\nYou can find the t-SNE paper ",{"type":429,"tag":443,"props":854,"children":857},{"href":855,"rel":856},"https://jmlr.org/papers/volume9/vandermaaten08a/vandermaaten08a.pdf",[447],[858],{"type":435,"value":859},"here",{"type":435,"value":777},{"type":429,"tag":454,"props":862,"children":864},{"id":863},"cost-estimation",[865],{"type":435,"value":866},"Cost Estimation",{"type":429,"tag":523,"props":868,"children":869},{},[870,891],{"type":429,"tag":527,"props":871,"children":872},{},[873],{"type":429,"tag":531,"props":874,"children":875},{},[876,881,886],{"type":429,"tag":535,"props":877,"children":878},{},[879],{"type":435,"value":880},"Workflow Name",{"type":429,"tag":535,"props":882,"children":883},{},[884],{"type":435,"value":885},"Per sample cost",{"type":429,"tag":535,"props":887,"children":888},{},[889],{"type":435,"value":890},"Outliers",{"type":429,"tag":551,"props":892,"children":893},{},[894,912],{"type":429,"tag":531,"props":895,"children":896},{},[897,902,907],{"type":429,"tag":558,"props":898,"children":899},{},[900],{"type":435,"value":901},"Realignment workflow",{"type":429,"tag":558,"props":903,"children":904},{},[905],{"type":435,"value":906},"$3-10",{"type":429,"tag":558,"props":908,"children":909},{},[910],{"type":435,"value":911},"$25",{"type":429,"tag":531,"props":913,"children":914},{},[915,920,925],{"type":429,"tag":558,"props":916,"children":917},{},[918],{"type":435,"value":919},"Feature read counts workflow",{"type":429,"tag":558,"props":921,"children":922},{},[923],{"type":435,"value":924},"$0.30-0.40",{"type":429,"tag":558,"props":926,"children":927},{},[],{"type":429,"tag":430,"props":929,"children":931},{"id":930},"running-the-workflow",[932],{"type":435,"value":933},"Running the Workflow",{"type":429,"tag":454,"props":935,"children":937},{"id":936},"getting-started",[938],{"type":435,"value":30},{"type":429,"tag":592,"props":940,"children":941},{"color":594,"icon":595},[942],{"type":429,"tag":437,"props":943,"children":944},{},[945,949,952,954,958,959,964,966,970],{"type":429,"tag":601,"props":946,"children":947},{},[948],{"type":435,"value":605},{"type":429,"tag":607,"props":950,"children":951},{},[],{"type":435,"value":953},"\nIf you provide counts data to the counts-based pipeline, it ",{"type":429,"tag":601,"props":955,"children":956},{},[957],{"type":435,"value":616},{"type":435,"value":618},{"type":429,"tag":620,"props":960,"children":962},{"className":961},[],[963],{"type":435,"value":625},{"type":435,"value":965},".\nRunning a sample aligned to any other reference genome is not supported.\nMaybe more importantly, we do not check the genome build of the sample, so errors in computation or the results can occur.\nIf your sample is ",{"type":429,"tag":629,"props":967,"children":968},{},[969],{"type":435,"value":633},{"type":435,"value":635},{"type":429,"tag":437,"props":972,"children":973},{},[974,976,982,984,990,992],{"type":435,"value":975},"We provide two versions of the RNA-Seq Expression Classification workflow depending on desired input.\nThe full workflow allows a user to upload a sample in BAM format.\nThat sample will then be converted to ",{"type":429,"tag":620,"props":977,"children":979},{"className":978},[],[980],{"type":435,"value":981},"FASTQ",{"type":435,"value":983}," format, aligned with ",{"type":429,"tag":620,"props":985,"children":987},{"className":986},[],[988],{"type":435,"value":989},"STAR",{"type":435,"value":991}," two-pass alignment, and feature counts generated with ",{"type":429,"tag":620,"props":993,"children":995},{"className":994},[],[996],{"type":435,"value":830},{"type":429,"tag":437,"props":998,"children":999},{},[1000,1002,1009],{"type":435,"value":1001},"To get started, you need to navigate to the ",{"type":429,"tag":443,"props":1003,"children":1006},{"href":1004,"rel":1005},"https://platform.stjude.cloud/workflows/rnaseq-expression-classification",[447],[1007],{"type":435,"value":1008},"RNA-Seq Expression Classification workflow page",{"type":435,"value":1010},".\nYou'll need to click the \"Start\" button in the left hand pane.\nThis creates a cloud workspace in DNAnexus with the same name as the workflow.\nAfter this, you will be able to upload your input files to that workspace.",{"type":429,"tag":454,"props":1012,"children":1014},{"id":1013},"obtaining-reference-data",[1015],{"type":435,"value":1016},"Obtaining reference data",{"type":429,"tag":437,"props":1018,"children":1019},{},[1020],{"type":435,"value":1021},"Reference feature count data is vended to the project folder along with the workflow.\nIt can be found in the “counts” folder.",{"type":429,"tag":437,"props":1023,"children":1024},{},[1025,1027],{"type":435,"value":1026},"Reference data can also be retrieved through the ",{"type":429,"tag":443,"props":1028,"children":1031},{"href":1029,"rel":1030},"https://platform.stjude.cloud/data/publications?publication_accession=SJC-PB-1020",[447],[1032],{"type":435,"value":1033},"Genomics Platform Data Browser",{"type":429,"tag":437,"props":1035,"children":1036},{},[1037],{"type":429,"tag":1038,"props":1039,"children":1042},"img",{"alt":1040,"src":1041},"requesting St. Jude Cloud paper","/img/genomics-platform/workflow-guides/rnaseq-expression-classification/Requesting-StJudeCloud-paper.gif",[],{"type":429,"tag":437,"props":1044,"children":1045},{},[1046,1048,1054],{"type":435,"value":1047},"These must then be provided to the workflow through the ",{"type":429,"tag":620,"props":1049,"children":1051},{"className":1050},[],[1052],{"type":435,"value":1053},"reference_counts",{"type":435,"value":1055}," parameter.\nBy default, all reference files will be used by the app, but this can be restricted to one of the three tumor types [Blood, Brain, Solid] through the app settings.",{"type":429,"tag":592,"props":1057,"children":1058},{"color":594,"icon":595},[1059],{"type":429,"tag":437,"props":1060,"children":1061},{},[1062,1066,1069,1071,1077],{"type":429,"tag":601,"props":1063,"children":1064},{},[1065],{"type":435,"value":605},{"type":429,"tag":607,"props":1067,"children":1068},{},[],{"type":435,"value":1070},"\nThe RNA-Seq Expression Classification workflow does not allow the same sample name to be included more than once.\nIf data from multiple projects is requested through St. Jude Cloud Genomics Platform, a sample may be included more than once.\nWe offer an opinionated deduplication method at ",{"type":429,"tag":443,"props":1072,"children":1075},{"href":1073,"rel":1074},"https://github.com/stjudecloud/utilities",[447],[1076],{"type":435,"value":1073},{"type":435,"value":777},{"type":429,"tag":454,"props":1079,"children":1081},{"id":1080},"executing-the-workflow",[1082],{"type":435,"value":1083},"Executing the Workflow",{"type":429,"tag":437,"props":1085,"children":1086},{},[1087,1089,1094],{"type":435,"value":1088},"Once you've uploaded data to your cloud workspace, click \"Launch Tool\" on the workflow's landing page.\nA dropdown will present the different presets for running the workflow.\nHere, you can select whether you wish to start with a counts file or a BAM file.\nOnce the workflow has been vended, ",{"type":429,"tag":601,"props":1090,"children":1091},{},[1092],{"type":435,"value":1093},"copy",{"type":435,"value":1095}," the workflow to the project containing the reference data.",{"type":429,"tag":454,"props":1097,"children":1099},{"id":1098},"uploading-data",[1100],{"type":435,"value":1101},"Uploading data",{"type":429,"tag":437,"props":1103,"children":1104},{},[1105,1107,1112],{"type":435,"value":1106},"The RNA-Seq Expression Classification pipeline takes either a htseq-count count file or a GRCh38_no_alt aligned BAM from human RNA-Seq.\nYou can upload your input file(s) through the command line.\nSee ",{"type":429,"tag":443,"props":1108,"children":1109},{"href":70},[1110],{"type":435,"value":1111},"Uploading Data from your Local Computer",{"type":435,"value":777},{"type":429,"tag":437,"props":1114,"children":1115},{},[1116,1118,1124,1126,1132,1134,1139,1141,1147],{"type":435,"value":1117},"Once you have the ",{"type":429,"tag":620,"props":1119,"children":1121},{"className":1120},[],[1122],{"type":435,"value":1123},"dx",{"type":435,"value":1125}," toolkit, to upload a sample HTSeq count file ",{"type":429,"tag":620,"props":1127,"children":1129},{"className":1128},[],[1130],{"type":435,"value":1131},"sample.counts.txt",{"type":435,"value":1133}," to the ",{"type":429,"tag":620,"props":1135,"children":1137},{"className":1136},[],[1138],{"type":435,"value":513},{"type":435,"value":1140}," folder of the ",{"type":429,"tag":620,"props":1142,"children":1144},{"className":1143},[],[1145],{"type":435,"value":1146},"project-rnaseq",{"type":435,"value":1148}," cloud project, you could use the following command:",{"type":429,"tag":1150,"props":1151,"children":1155},"pre",{"className":1152,"code":1153,"language":1154,"meta":424,"style":424},"language-bash shiki shiki-themes material-theme-lighter material-theme material-theme-palenight","dx upload sample.counts.txt --destination \"project-rnaseq:/inputs/\"\n","bash",[1156],{"type":429,"tag":620,"props":1157,"children":1158},{"__ignoreMap":424},[1159],{"type":429,"tag":756,"props":1160,"children":1163},{"class":1161,"line":1162},"line",1,[1164,1169,1175,1180,1185,1191,1196],{"type":429,"tag":756,"props":1165,"children":1167},{"style":1166},"--shiki-light:#E2931D;--shiki-default:#FFCB6B;--shiki-dark:#FFCB6B",[1168],{"type":435,"value":1123},{"type":429,"tag":756,"props":1170,"children":1172},{"style":1171},"--shiki-light:#91B859;--shiki-default:#C3E88D;--shiki-dark:#C3E88D",[1173],{"type":435,"value":1174}," upload",{"type":429,"tag":756,"props":1176,"children":1177},{"style":1171},[1178],{"type":435,"value":1179}," sample.counts.txt",{"type":429,"tag":756,"props":1181,"children":1182},{"style":1171},[1183],{"type":435,"value":1184}," --destination",{"type":429,"tag":756,"props":1186,"children":1188},{"style":1187},"--shiki-light:#39ADB5;--shiki-default:#89DDFF;--shiki-dark:#89DDFF",[1189],{"type":435,"value":1190}," \"",{"type":429,"tag":756,"props":1192,"children":1193},{"style":1171},[1194],{"type":435,"value":1195},"project-rnaseq:/inputs/",{"type":429,"tag":756,"props":1197,"children":1198},{"style":1187},[1199],{"type":435,"value":1200},"\"\n",{"type":429,"tag":454,"props":1202,"children":1204},{"id":1203},"preparing-input-data",[1205],{"type":435,"value":1206},"Preparing input data",{"type":429,"tag":437,"props":1208,"children":1209},{},[1210],{"type":435,"value":1211},"To run an input sample, certain properties need to be set on the file.\nThese should be specified on the HTSeq count file for the counts-based pipeline or on the BAM file for the realignment-based workflow.",{"type":429,"tag":523,"props":1213,"children":1214},{},[1215,1231],{"type":429,"tag":527,"props":1216,"children":1217},{},[1218],{"type":429,"tag":531,"props":1219,"children":1220},{},[1221,1226],{"type":429,"tag":535,"props":1222,"children":1223},{},[1224],{"type":435,"value":1225},"Property Name",{"type":429,"tag":535,"props":1227,"children":1228},{},[1229],{"type":435,"value":1230},"Values",{"type":429,"tag":551,"props":1232,"children":1233},{},[1234,1247,1260,1273,1286],{"type":429,"tag":531,"props":1235,"children":1236},{},[1237,1242],{"type":429,"tag":558,"props":1238,"children":1239},{},[1240],{"type":435,"value":1241},"sample_name",{"type":429,"tag":558,"props":1243,"children":1244},{},[1245],{"type":435,"value":1246},"should match file name up to first period (\".\")",{"type":429,"tag":531,"props":1248,"children":1249},{},[1250,1255],{"type":429,"tag":558,"props":1251,"children":1252},{},[1253],{"type":435,"value":1254},"library_type",{"type":429,"tag":558,"props":1256,"children":1257},{},[1258],{"type":435,"value":1259},"PolyA or Total",{"type":429,"tag":531,"props":1261,"children":1262},{},[1263,1268],{"type":429,"tag":558,"props":1264,"children":1265},{},[1266],{"type":435,"value":1267},"read_length",{"type":429,"tag":558,"props":1269,"children":1270},{},[1271],{"type":435,"value":1272},"integer, in bp",{"type":429,"tag":531,"props":1274,"children":1275},{},[1276,1281],{"type":429,"tag":558,"props":1277,"children":1278},{},[1279],{"type":435,"value":1280},"strandedness",{"type":429,"tag":558,"props":1282,"children":1283},{},[1284],{"type":435,"value":1285},"Stranded-Forward, Stranded-Reverse, Unstranded",{"type":429,"tag":531,"props":1287,"children":1288},{},[1289,1294],{"type":429,"tag":558,"props":1290,"children":1291},{},[1292],{"type":435,"value":1293},"pairing",{"type":429,"tag":558,"props":1295,"children":1296},{},[1297],{"type":435,"value":1298},"Paired-end or Single-end",{"type":429,"tag":437,"props":1300,"children":1301},{},[1302],{"type":435,"value":1303},"Properties can be set at the job-level for all input files that do not have properties set.\nThese function as defaults and will not override existing values on files.\nThe options are limited to values in our reference cohort to ensure reliable results.",{"type":429,"tag":437,"props":1305,"children":1306},{},[1307],{"type":429,"tag":1038,"props":1308,"children":1311},{"alt":1309,"src":1310},"dx optinos","/img/genomics-platform/workflow-guides/rnaseq-expression-classification/dx_options.png",[],{"type":429,"tag":437,"props":1313,"children":1314},{},[1315],{"type":435,"value":1316},"If a more granular control of covariates is needed, the input files can be annotated directly with properties.\nTo input properties in DNAnexus, you can either use the web UI or the command line interface.\nHere, we provide a command line snippet to set properties on a file.",{"type":429,"tag":1150,"props":1318,"children":1320},{"className":1152,"code":1319,"language":1154,"meta":424,"style":424},"# you can run the following code snippet after filling in your values\n# to successfully prepare the file.\n\nfile_id=\u003CDNAnexus file ID> # file ID or file path\ndx set_properties $file_id sample_name=\"\u003Cvalue>\" # Should match the file name up to the first period character\ndx set_properties $file_id strandedness=\"\u003Cvalue>\" # Stranded-Forward, Stranded-Reverse, or Unstranded\ndx set_properties $file_id library_type=\"\u003Cvalue>\" # PolyA or Total\ndx set_properties $file_id read_length=\"\u003Cvalue>\" # Integer number of base pairs in reads (e.g. 101, 126)\ndx set_properties $file_id pairing=\"\u003Cvalue>\" # Paired-end or Single-end\n",[1321],{"type":429,"tag":620,"props":1322,"children":1323},{"__ignoreMap":424},[1324,1333,1342,1352,1397,1439,1477,1515,1553],{"type":429,"tag":756,"props":1325,"children":1326},{"class":1161,"line":1162},[1327],{"type":429,"tag":756,"props":1328,"children":1330},{"style":1329},"--shiki-light:#90A4AE;--shiki-light-font-style:italic;--shiki-default:#546E7A;--shiki-default-font-style:italic;--shiki-dark:#676E95;--shiki-dark-font-style:italic",[1331],{"type":435,"value":1332},"# you can run the following code snippet after filling in your values\n",{"type":429,"tag":756,"props":1334,"children":1336},{"class":1161,"line":1335},2,[1337],{"type":429,"tag":756,"props":1338,"children":1339},{"style":1329},[1340],{"type":435,"value":1341},"# to successfully prepare the file.\n",{"type":429,"tag":756,"props":1343,"children":1345},{"class":1161,"line":1344},3,[1346],{"type":429,"tag":756,"props":1347,"children":1349},{"emptyLinePlaceholder":1348},true,[1350],{"type":435,"value":1351},"\n",{"type":429,"tag":756,"props":1353,"children":1355},{"class":1161,"line":1354},4,[1356,1362,1367,1372,1377,1382,1387,1392],{"type":429,"tag":756,"props":1357,"children":1359},{"style":1358},"--shiki-light:#90A4AE;--shiki-default:#EEFFFF;--shiki-dark:#BABED8",[1360],{"type":435,"value":1361},"file_id",{"type":429,"tag":756,"props":1363,"children":1364},{"style":1187},[1365],{"type":435,"value":1366},"=\u003C",{"type":429,"tag":756,"props":1368,"children":1369},{"style":1171},[1370],{"type":435,"value":1371},"DNAnexus",{"type":429,"tag":756,"props":1373,"children":1374},{"style":1166},[1375],{"type":435,"value":1376}," file",{"type":429,"tag":756,"props":1378,"children":1379},{"style":1171},[1380],{"type":435,"value":1381}," I",{"type":429,"tag":756,"props":1383,"children":1384},{"style":1358},[1385],{"type":435,"value":1386},"D",{"type":429,"tag":756,"props":1388,"children":1389},{"style":1187},[1390],{"type":435,"value":1391},">",{"type":429,"tag":756,"props":1393,"children":1394},{"style":1329},[1395],{"type":435,"value":1396}," # file ID or file path\n",{"type":429,"tag":756,"props":1398,"children":1400},{"class":1161,"line":1399},5,[1401,1405,1410,1415,1420,1425,1430,1434],{"type":429,"tag":756,"props":1402,"children":1403},{"style":1166},[1404],{"type":435,"value":1123},{"type":429,"tag":756,"props":1406,"children":1407},{"style":1171},[1408],{"type":435,"value":1409}," set_properties",{"type":429,"tag":756,"props":1411,"children":1412},{"style":1358},[1413],{"type":435,"value":1414}," $file_id ",{"type":429,"tag":756,"props":1416,"children":1417},{"style":1171},[1418],{"type":435,"value":1419},"sample_name=",{"type":429,"tag":756,"props":1421,"children":1422},{"style":1187},[1423],{"type":435,"value":1424},"\"",{"type":429,"tag":756,"props":1426,"children":1427},{"style":1171},[1428],{"type":435,"value":1429},"\u003Cvalue>",{"type":429,"tag":756,"props":1431,"children":1432},{"style":1187},[1433],{"type":435,"value":1424},{"type":429,"tag":756,"props":1435,"children":1436},{"style":1329},[1437],{"type":435,"value":1438}," # Should match the file name up to the first period character\n",{"type":429,"tag":756,"props":1440,"children":1442},{"class":1161,"line":1441},6,[1443,1447,1451,1455,1460,1464,1468,1472],{"type":429,"tag":756,"props":1444,"children":1445},{"style":1166},[1446],{"type":435,"value":1123},{"type":429,"tag":756,"props":1448,"children":1449},{"style":1171},[1450],{"type":435,"value":1409},{"type":429,"tag":756,"props":1452,"children":1453},{"style":1358},[1454],{"type":435,"value":1414},{"type":429,"tag":756,"props":1456,"children":1457},{"style":1171},[1458],{"type":435,"value":1459},"strandedness=",{"type":429,"tag":756,"props":1461,"children":1462},{"style":1187},[1463],{"type":435,"value":1424},{"type":429,"tag":756,"props":1465,"children":1466},{"style":1171},[1467],{"type":435,"value":1429},{"type":429,"tag":756,"props":1469,"children":1470},{"style":1187},[1471],{"type":435,"value":1424},{"type":429,"tag":756,"props":1473,"children":1474},{"style":1329},[1475],{"type":435,"value":1476}," # Stranded-Forward, Stranded-Reverse, or Unstranded\n",{"type":429,"tag":756,"props":1478,"children":1480},{"class":1161,"line":1479},7,[1481,1485,1489,1493,1498,1502,1506,1510],{"type":429,"tag":756,"props":1482,"children":1483},{"style":1166},[1484],{"type":435,"value":1123},{"type":429,"tag":756,"props":1486,"children":1487},{"style":1171},[1488],{"type":435,"value":1409},{"type":429,"tag":756,"props":1490,"children":1491},{"style":1358},[1492],{"type":435,"value":1414},{"type":429,"tag":756,"props":1494,"children":1495},{"style":1171},[1496],{"type":435,"value":1497},"library_type=",{"type":429,"tag":756,"props":1499,"children":1500},{"style":1187},[1501],{"type":435,"value":1424},{"type":429,"tag":756,"props":1503,"children":1504},{"style":1171},[1505],{"type":435,"value":1429},{"type":429,"tag":756,"props":1507,"children":1508},{"style":1187},[1509],{"type":435,"value":1424},{"type":429,"tag":756,"props":1511,"children":1512},{"style":1329},[1513],{"type":435,"value":1514}," # PolyA or Total\n",{"type":429,"tag":756,"props":1516,"children":1518},{"class":1161,"line":1517},8,[1519,1523,1527,1531,1536,1540,1544,1548],{"type":429,"tag":756,"props":1520,"children":1521},{"style":1166},[1522],{"type":435,"value":1123},{"type":429,"tag":756,"props":1524,"children":1525},{"style":1171},[1526],{"type":435,"value":1409},{"type":429,"tag":756,"props":1528,"children":1529},{"style":1358},[1530],{"type":435,"value":1414},{"type":429,"tag":756,"props":1532,"children":1533},{"style":1171},[1534],{"type":435,"value":1535},"read_length=",{"type":429,"tag":756,"props":1537,"children":1538},{"style":1187},[1539],{"type":435,"value":1424},{"type":429,"tag":756,"props":1541,"children":1542},{"style":1171},[1543],{"type":435,"value":1429},{"type":429,"tag":756,"props":1545,"children":1546},{"style":1187},[1547],{"type":435,"value":1424},{"type":429,"tag":756,"props":1549,"children":1550},{"style":1329},[1551],{"type":435,"value":1552}," # Integer number of base pairs in reads (e.g. 101, 126)\n",{"type":429,"tag":756,"props":1554,"children":1556},{"class":1161,"line":1555},9,[1557,1561,1565,1569,1574,1578,1582,1586],{"type":429,"tag":756,"props":1558,"children":1559},{"style":1166},[1560],{"type":435,"value":1123},{"type":429,"tag":756,"props":1562,"children":1563},{"style":1171},[1564],{"type":435,"value":1409},{"type":429,"tag":756,"props":1566,"children":1567},{"style":1358},[1568],{"type":435,"value":1414},{"type":429,"tag":756,"props":1570,"children":1571},{"style":1171},[1572],{"type":435,"value":1573},"pairing=",{"type":429,"tag":756,"props":1575,"children":1576},{"style":1187},[1577],{"type":435,"value":1424},{"type":429,"tag":756,"props":1579,"children":1580},{"style":1171},[1581],{"type":435,"value":1429},{"type":429,"tag":756,"props":1583,"children":1584},{"style":1187},[1585],{"type":435,"value":1424},{"type":429,"tag":756,"props":1587,"children":1588},{"style":1329},[1589],{"type":435,"value":1590}," # Paired-end or Single-end\n",{"type":429,"tag":437,"props":1592,"children":1593},{},[1594],{"type":435,"value":1595},"The file ID can be retrieved from the DNAnexus web interface.\nClick on the file of interest and the file ID is displayed in the sidebar.",{"type":429,"tag":437,"props":1597,"children":1598},{},[1599],{"type":429,"tag":1038,"props":1600,"children":1603},{"alt":1601,"src":1602},"file id","/img/genomics-platform/workflow-guides/rnaseq-expression-classification/file_id.png",[],{"type":429,"tag":454,"props":1605,"children":1607},{"id":1606},"hooking-up-inputs",[1608],{"type":435,"value":1609},"Hooking up inputs",{"type":429,"tag":437,"props":1611,"children":1612},{},[1613,1615,1621],{"type":435,"value":1614},"You will need to select reference counts files from your project.\nThese can be specified in the ",{"type":429,"tag":620,"props":1616,"children":1618},{"className":1617},[],[1619],{"type":435,"value":1620},"reference counts",{"type":435,"value":1622}," data input.",{"type":429,"tag":437,"props":1624,"children":1625},{},[1626,1628,1633],{"type":435,"value":1627},"When specifying the ",{"type":429,"tag":620,"props":1629,"children":1631},{"className":1630},[],[1632],{"type":435,"value":1053},{"type":435,"value":1634},", select all HTSeq count files in the reference dataset.\nFor the St. Jude Cloud paper dataset, there are 1576 total files to select.",{"type":429,"tag":437,"props":1636,"children":1637},{},[1638],{"type":429,"tag":1038,"props":1639,"children":1642},{"alt":1640,"src":1641},"input selections","/img/genomics-platform/workflow-guides/rnaseq-expression-classification/input-selections.png",[],{"type":429,"tag":437,"props":1644,"children":1645},{},[1646],{"type":435,"value":1647},"The UI will then display the number of selected reference files.",{"type":429,"tag":437,"props":1649,"children":1650},{},[1651],{"type":429,"tag":1038,"props":1652,"children":1655},{"alt":1653,"src":1654},"input selected","/img/genomics-platform/workflow-guides/rnaseq-expression-classification/input-selected.png",[],{"type":429,"tag":437,"props":1657,"children":1658},{},[1659],{"type":435,"value":1660},"Next, you'll need to hook up either the counts file or the BAM file you uploaded in the upload data section.\nIn this example, we are using the counts-based version of the pipeline, so you can hook up the inputs by clicking on the input_counts slot and selecting the respective files.\nIf you are using the realignment-based workflow, the process is similar with BAM input.",{"type":429,"tag":437,"props":1662,"children":1663},{},[1664],{"type":429,"tag":1038,"props":1665,"children":1668},{"alt":1666,"src":1667},"new ui","/img/genomics-platform/workflow-guides/rnaseq-expression-classification/rnaseq-expression-workflow-new-ui.png",[],{"type":429,"tag":437,"props":1670,"children":1671},{},[1672],{"type":435,"value":1673},"Additionally, a parameter selecting the tissue type to compare against can be selected.\nThe available options are \"Blood Cancer\", \"Brain Tumor\", and \"Solid Tumor\".\nBased on the selection, a reference collection of tumors of that type will be selected from St. Jude Cloud data and the input samples will be compared against this reference collection.",{"type":429,"tag":437,"props":1675,"children":1676},{},[1677],{"type":429,"tag":1038,"props":1678,"children":1681},{"alt":1679,"src":1680},"new ui options","/img/genomics-platform/workflow-guides/rnaseq-expression-classification/rnaseq-expression-workflow-options-new-ui.png",[],{"type":429,"tag":437,"props":1683,"children":1684},{},[1685,1687,1692,1694,1700],{"type":435,"value":1686},"If running the realignment workflow, the input file should be specified as a BAM to realign.\nHTSeq will run on the realigned BAM and the result will be passed into the t-SNE app for plotting against the reference data.\nThe reference data should be specified in the ",{"type":429,"tag":620,"props":1688,"children":1690},{"className":1689},[],[1691],{"type":435,"value":1053},{"type":435,"value":1693}," parameter as an array of HTSeq count files.\nThe BAM will be specified to the RNA-Seq V2 stage as ",{"type":429,"tag":620,"props":1695,"children":1697},{"className":1696},[],[1698],{"type":435,"value":1699},"input_bam",{"type":435,"value":1701},".\nThe BAM should have properties set as described above.\nThese will automatically be applied to the new HTSeq count file.",{"type":429,"tag":437,"props":1703,"children":1704},{},[1705],{"type":429,"tag":1038,"props":1706,"children":1709},{"alt":1707,"src":1708},"new ui options realignment","/img/genomics-platform/workflow-guides/rnaseq-expression-classification/rnaseq-expression-workflow-realignment-options-new-ui.png",[],{"type":429,"tag":454,"props":1711,"children":1713},{"id":1712},"optional-settings",[1714],{"type":435,"value":1715},"Optional settings",{"type":429,"tag":437,"props":1717,"children":1718},{},[1719],{"type":435,"value":1720},"An optional gene list can be specified as an input.\nThis is a single column text file with gene names.\nIf this option is specified, the list will override the default selection of the top 1000 most differentially expressed genes.",{"type":429,"tag":437,"props":1722,"children":1723},{},[1724],{"type":435,"value":1725},"By default, all tumor types (blood, brain, and solid) will be included in the analysis.\nIt is also possible to run each of the three types separately by selecting the appropriate tumor type.",{"type":429,"tag":437,"props":1727,"children":1728},{},[1729],{"type":435,"value":1730},"The workflow supports both Fresh/Frozen and FFPE inputs.\nBy default, only Fresh/Frozen samples from the reference cohort will be included.\nThis setting can be changed to run only FFPE or Fresh/Frozen + FFPE samples.",{"type":429,"tag":437,"props":1732,"children":1733},{},[1734],{"type":435,"value":1735},"It is also possible to return intermediate files from the workflow.\nIf desired, 'original_matrix' is the matrix of counts after covariates and additional metadata has been removed, 'variance_stabilized' is the matrix after running varianceStabilizingTransformation, 'batch_corrected' is the matrix after ComBat batch correction, 'tsne_output' is the matrix after Rtsne has been run and 'matrix' is the original file input to the R script for plotting.",{"type":429,"tag":437,"props":1737,"children":1738},{},[1739,1741,1748],{"type":435,"value":1740},"The expression workflow can optionally include PDX samples from the reference cohort as well as a ",{"type":429,"tag":443,"props":1742,"children":1745},{"href":1743,"rel":1744},"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC5177991/",[447],[1746],{"type":435,"value":1747},"selection of PDX models from Dana Farber Cancer Institute",{"type":435,"value":1749},".\nThe inclusion of PDX samples can facilitate selection of mouse models for followup functional experimentation.",{"type":429,"tag":454,"props":1751,"children":1753},{"id":1752},"starting-the-workflow",[1754],{"type":435,"value":1755},"Starting the workflow",{"type":429,"tag":437,"props":1757,"children":1758},{},[1759],{"type":435,"value":1760},"Once your input files are hooked up, you should be able to start the workflow by clicking the \"Run Analysis\" button in the top right hand corner of the workflow dialog.",{"type":429,"tag":454,"props":1762,"children":1764},{"id":1763},"monitoring-run-progress",[1765],{"type":435,"value":1766},"Monitoring run progress",{"type":429,"tag":437,"props":1768,"children":1769},{},[1770],{"type":435,"value":1771},"Once you have started one or more RNA-Seq Expression Classification runs, you can safely close your browser and come back later to check the status of the jobs.\nTo do this, navigate to the workflow's landing page.\nNext, click \"View Results\" then select the \"View Running Jobs\" option.\nYou will be redirected to the job monitoring page. Each job you kicked off gets one row in this table.",{"type":429,"tag":437,"props":1773,"children":1774},{},[1775],{"type":435,"value":1776},"You can click the \"+\" on any of the runs to check the status of individual steps of the RNA-Seq Expression Classification pipeline.\nOther information, such as time, cost of individual steps in the pipeline, and even viewing the job logs can accessed by clicking around the sub-items.",{"type":429,"tag":430,"props":1778,"children":1780},{"id":1779},"interpreting-results",[1781],{"type":435,"value":1782},"Interpreting Results",{"type":429,"tag":437,"props":1784,"children":1785},{},[1786,1788,1795],{"type":435,"value":1787},"Once the resulting analysis job completes, an HTML plot of the results should be available.\nThe plot is generated with the ",{"type":429,"tag":443,"props":1789,"children":1792},{"href":1790,"rel":1791},"https://www.nature.com/articles/ng.3466",[447],[1793],{"type":435,"value":1794},"ProteinPaint library",{"type":435,"value":1796},".\nThe plot can be zoomed arbitrarily and group labels can be turned on/off for manual inspection.\nUser input samples will be displayed in black marks with a label on the graph as well as an entry in the legend.",{"type":429,"tag":437,"props":1798,"children":1799},{},[1800],{"type":429,"tag":1038,"props":1801,"children":1804},{"alt":1802,"src":1803},"expression plot","/img/genomics-platform/workflow-guides/rnaseq-expression-classification/rnaseq-expression-plot.png",[],{"type":429,"tag":430,"props":1806,"children":1808},{"id":1807},"batch-effect-corrections",[1809],{"type":435,"value":1810},"Batch effect corrections",{"type":429,"tag":437,"props":1812,"children":1813},{},[1814],{"type":435,"value":1815},"When comparing numerous samples such as those included in this analysis, it is important to consider the variation in data created by obtaining from various sources and across time.\nTherefore the t-SNE visualization incorporates some batch effect corrections for the reference data.\nCurrently we correct for batch effect based on strandedness of the RNA-Seq sample, library type, read pairing, and read length.",{"type":429,"tag":523,"props":1817,"children":1818},{},[1819,1834],{"type":429,"tag":527,"props":1820,"children":1821},{},[1822],{"type":429,"tag":531,"props":1823,"children":1824},{},[1825,1830],{"type":429,"tag":535,"props":1826,"children":1827},{},[1828],{"type":435,"value":1829},"Batch Variable",{"type":429,"tag":535,"props":1831,"children":1832},{},[1833],{"type":435,"value":1230},{"type":429,"tag":551,"props":1835,"children":1836},{},[1837,1849,1862,1874],{"type":429,"tag":531,"props":1838,"children":1839},{},[1840,1845],{"type":429,"tag":558,"props":1841,"children":1842},{},[1843],{"type":435,"value":1844},"Library Type",{"type":429,"tag":558,"props":1846,"children":1847},{},[1848],{"type":435,"value":1259},{"type":429,"tag":531,"props":1850,"children":1851},{},[1852,1857],{"type":429,"tag":558,"props":1853,"children":1854},{},[1855],{"type":435,"value":1856},"Read Length",{"type":429,"tag":558,"props":1858,"children":1859},{},[1860],{"type":435,"value":1861},"integer, in bp, e.g. 101, 126",{"type":429,"tag":531,"props":1863,"children":1864},{},[1865,1870],{"type":429,"tag":558,"props":1866,"children":1867},{},[1868],{"type":435,"value":1869},"Strandedness",{"type":429,"tag":558,"props":1871,"children":1872},{},[1873],{"type":435,"value":1285},{"type":429,"tag":531,"props":1875,"children":1876},{},[1877,1882],{"type":429,"tag":558,"props":1878,"children":1879},{},[1880],{"type":435,"value":1881},"Pairing",{"type":429,"tag":558,"props":1883,"children":1884},{},[1885],{"type":435,"value":1298},{"type":429,"tag":430,"props":1887,"children":1889},{"id":1888},"known-issues",[1890],{"type":435,"value":1891},"Known issues",{"type":429,"tag":437,"props":1893,"children":1894},{},[1895],{"type":435,"value":1896},"There are a few known cautions with the RNA-Seq Expression Classification workflow.",{"type":429,"tag":592,"props":1898,"children":1899},{"color":594,"icon":595},[1900],{"type":429,"tag":437,"props":1901,"children":1902},{},[1903,1908,1911,1913,1916,1918,1922,1923,1928,1929,1932,1934,1939,1940,1944,1945,1948],{"type":429,"tag":601,"props":1904,"children":1905},{},[1906],{"type":435,"value":1907},"Data must fit well defined values",{"type":429,"tag":607,"props":1909,"children":1910},{},[],{"type":435,"value":1912},"\nThe RNA-Seq Expression Classification pipeline reference data is based on GRCh38 aligned, Gencode v31 annotated samples from fresh, frozen tissue samples.\nIt has not been evaluated for samples that do not meet this criteria.\nThe RNA-Seq Expression Classification pipeline reference data uses sequencing data from fresh, frozen tissue samples.\nIt has not been evaluated for use with sequencing data generated from formalin-fixed paraffin-embedded (FFPE) specimens.",{"type":429,"tag":607,"props":1914,"children":1915},{},[],{"type":435,"value":1917},"\nIf running the count-based RNA-Seq Expression Classification pipeline, alignment must be done against the ",{"type":429,"tag":443,"props":1919,"children":1920},{"href":477},[1921],{"type":435,"value":480},{"type":435,"value":482},{"type":429,"tag":443,"props":1924,"children":1926},{"href":445,"rel":1925},[447],[1927],{"type":435,"value":488},{"type":435,"value":490},{"type":429,"tag":607,"props":1930,"children":1931},{},[],{"type":435,"value":1933},"\nIf running the count-based RNA-Seq Expression Classification pipeline, feature counts should be generated with htseq-count as described in our ",{"type":429,"tag":443,"props":1935,"children":1937},{"href":445,"rel":1936},[447],[1938],{"type":435,"value":488},{"type":435,"value":502},{"type":429,"tag":443,"props":1941,"children":1942},{"href":505},[1943],{"type":435,"value":508},{"type":435,"value":510},{"type":429,"tag":607,"props":1946,"children":1947},{},[],{"type":435,"value":1949},"\nBatch correction requires a minimum of two samples per batch to run properly.\nIntroducing a single sample batch by adding an input sample with a unique protocol will cause unexpected results.",{"type":429,"tag":430,"props":1951,"children":1953},{"id":1952},"frequently-asked-questions",[1954],{"type":435,"value":1955},"Frequently asked questions",{"type":429,"tag":437,"props":1957,"children":1958},{},[1959,1961,1967],{"type":435,"value":1960},"If you have any questions not covered here, feel free to email us at ",{"type":429,"tag":443,"props":1962,"children":1964},{"href":1963},"mailto:support@stjude.cloud",[1965],{"type":435,"value":1966},"support@stjude.cloud",{"type":435,"value":777},{"type":429,"tag":430,"props":1969,"children":1971},{"id":1970},"submit-batch-jobs-on-the-command-line",[1972],{"type":435,"value":1973},"Submit batch jobs on the command line",{"type":429,"tag":437,"props":1975,"children":1976},{},[1977,1979],{"type":435,"value":1978},"See ",{"type":429,"tag":443,"props":1980,"children":1982},{"href":1981},"/genomics-platform/getting-started/faq#how-can-i-run-an-analysis-workflow-on-multiple-sample-files-at-the-same-time",[1983],{"type":435,"value":1984},"How can I run an analysis workflow on multiple sample files at the same time?",{"type":429,"tag":1986,"props":1987,"children":1988},"style",{},[1989],{"type":435,"value":1990},"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":1335,"depth":1335,"links":1992},[1993,2000,2011,2012,2013,2014,2015],{"id":432,"depth":1335,"text":5,"children":1994},[1995,1996,1997,1998,1999],{"id":456,"depth":1344,"text":459},{"id":513,"depth":1344,"text":516},{"id":638,"depth":1344,"text":641},{"id":744,"depth":1344,"text":747},{"id":863,"depth":1344,"text":866},{"id":930,"depth":1335,"text":933,"children":2001},[2002,2003,2004,2005,2006,2007,2008,2009,2010],{"id":936,"depth":1344,"text":30},{"id":1013,"depth":1344,"text":1016},{"id":1080,"depth":1344,"text":1083},{"id":1098,"depth":1344,"text":1101},{"id":1203,"depth":1344,"text":1206},{"id":1606,"depth":1344,"text":1609},{"id":1712,"depth":1344,"text":1715},{"id":1752,"depth":1344,"text":1755},{"id":1763,"depth":1344,"text":1766},{"id":1779,"depth":1335,"text":1782},{"id":1807,"depth":1335,"text":1810},{"id":1888,"depth":1335,"text":1891},{"id":1952,"depth":1335,"text":1955},{"id":1970,"depth":1335,"text":1973},"markdown","content:3.genomics-platform:5.workflow-guides:6.rnaseq-expression-classification.md","content","3.genomics-platform/5.workflow-guides/6.rnaseq-expression-classification.md","3.genomics-platform/5.workflow-guides/6.rnaseq-expression-classification","md",[2023,2024],{"_path":117,"title":116,"description":424},{"_path":123,"title":122,"description":424},1791243638251]