nci-cidc-schemas 0.28.1__py2.py3-none-any.whl → 0.28.2__py2.py3-none-any.whl

cidc_schemas/ngs_pipeline_api/wes/wes_tumor_only_output_API.json

@@ -0,0 +1,213 @@
+{
+  "run id": [
+    {
+      "file_path_template": "analysis/{run id}_error.yaml",
+      "short_description": "yaml file that specifies error codes for files",
+      "long_description": "Explanation of all files which are expected to be empty due to a failed/missing module.",
+      "filter_group": "",
+      "file_purpose": "Analysis view",
+      "optional": true,
+      "tumor_only_assay": true
+    },
+    {
+      "file_path_template": "analysis/msisensor2/{run id}/{run id}_msisensor2.txt",
+      "short_description": "msisensor2: microsatellite instability calculation",
+      "long_description": "Microsatellite instability calculation using msisensor2 (https://github.com/niu-lab/msisensor2)",
+      "filter_group": "msisensor2",
+      "file_purpose": "Analysis view",
+      "optional": false,
+      "tumor_only_assay": true
+    },
+    {
+      "file_path_template": "analysis/neoantigen/{run id}/combined/{run id}.filtered.tsv",
+      "short_description": "neaontigen: list of predicted neoantigens",
+      "long_description": "The combined MHC class I and II predicted neoantigens using the pVACseq software.  The column definitions are given here (ref: https://pvactools.readthedocs.io/en/latest/pvacseq/output_files.html)",
+      "filter_group": "neoantigen",
+      "file_purpose": "Analysis view",
+      "optional": false,
+      "tumor_only_assay": true
+    },
+    {
+      "file_path_template": "analysis/report.tar.gz",
+      "short_description": "wes report: wes summary html report",
+      "long_description": "This is a gzipped file of the report directory, which contains the report.html file.  After unzipping the file, the user can load report/report.html into any browser to view the WES Summary Report.  The report contains run information (i.e. wes software version used to run the analysis as well as the software version of the major tools) as well as summarizations of sample quality, copy number variation, somatic variants, and HLA-type/neoantigen predictions.",
+      "filter_group": "report",
+      "file_purpose": "Analysis view",
+      "optional": false,
+      "tumor_only_assay": true
+    },
+    {
+      "file_path_template": "analysis/report/WES_Meta/02_WES_Run_Version.tsv",
+      "short_description": "wes pipeline version- INTERNAL ONLY- for reproducibility",
+      "long_description": "wes pipeline version- INTERNAL ONLY- for reproducibility",
+      "filter_group": "report",
+      "file_purpose": "Miscellaneous",
+      "optional": false,
+      "tumor_only_assay": true
+    },
+    {
+      "file_path_template": "analysis/report/config.yaml",
+      "short_description": "wes pipeline config file- INTERNAL ONLY- for reproducibility",
+      "long_description": "wes pipeline config file- INTERNAL ONLY- for reproducibility",
+      "filter_group": "report",
+      "file_purpose": "Miscellaneous",
+      "optional": false,
+      "tumor_only_assay": true
+    },
+    {
+      "file_path_template": "analysis/report/metasheet.csv",
+      "short_description": "wes pipeline metasheet file- INTERNAL ONLY- for reproducibility",
+      "long_description": "wes pipeline metasheet file- INTERNAL ONLY- for reproducibility",
+      "filter_group": "report",
+      "file_purpose": "Miscellaneous",
+      "optional": false,
+      "tumor_only_assay": true
+    },
+    {
+      "file_path_template": "analysis/report/json/{run id}.wes.json",
+      "short_description": "wes sample json for cohort report generation-INTERNAL ONLY",
+      "long_description": "wes sample json for cohort report generation-INTERNAL ONLY",
+      "filter_group": "report",
+      "file_purpose": "Miscellaneous",
+      "optional": false,
+      "tumor_only_assay": true
+    },
+    {
+      "file_path_template": "analysis/rna/{run id}/{run id}.haplotyper.rna.vcf.gz",
+      "short_description": "rna: Variants called from RNA-seq data",
+      "long_description": "RNA-seq variants called using the Sentieon RNA Variant Calling pipeline(https://support.sentieon.com/manual/RNA_call/rna/).  Sentieon's Haplotyper algorithm was used for the variant calling.",
+      "filter_group": "rna",
+      "file_purpose": "Analysis view",
+      "optional": true,
+      "tumor_only_assay": true
+    },
+    {
+      "file_path_template": "analysis/rna/{run id}/{run id}_tnscope.output.twist.neoantigen.vep.rna.vcf",
+      "short_description": "rna: Shared RNA and WES variants that is used for neoantigen prediction when RNA-seq data is provided with the WES run",
+      "long_description": "Variants file representing the common variants between RNA (haplotyper.rna.vcf.gz) and WES data (output.twist.neoantigen.vep.vcf).",
+      "filter_group": "rna",
+      "file_purpose": "Analysis view",
+      "optional": true,
+      "tumor_only_assay": true
+    },
+    {
+      "file_path_template": "analysis/somatic/{run id}/{run id}_tnscope.output.vcf.gz",
+      "short_description": "somatic variants: vcf file of somatic variants",
+      "long_description": "VCF file of somatic variants using one of the following the Sentieon somatic callers {tnscope (default), tnhaplotyper2, tnsnv}.\n\nTNscope algorithm- https://support.sentieon.com/manual/usages/general/#tnscope-algorithm\nTNhaplotyper2- https://support.sentieon.com/manual/usages/general/#tnhaplotyper2-algorithm\nTNsnv - https://support.sentieon.com/manual/usages/general/#tnsnv-algorithm",
+      "filter_group": "somatic",
+      "file_purpose": "Analysis view",
+      "optional": false,
+      "tumor_only_assay": true
+    },
+    {
+      "file_path_template": "analysis/somatic/{run id}/{run id}_tnscope.output.twist.vcf",
+      "short_description": "somatic variants: vcf file of somatic variants in TWIST targed capture region",
+      "long_description": "VCF file of variants that fall within the TWIST excome capture regions.  bcftools is used to filter reads in output.vcf.gz that intersect with the TWIST capture regions.",
+      "filter_group": "somatic",
+      "file_purpose": "Analysis view",
+      "optional": false,
+      "tumor_only_assay": true
+    },
+    {
+      "file_path_template": "analysis/somatic/{run id}/{run id}_tnscope.output.twist.maf",
+      "short_description": "somatic variants: maf file of somatic variants in TWIST targed capture region",
+      "long_description": "MAF file of variants that fall within the TWIST excome capture regions generated using vcf2maf tool (https://github.com/mskcc/vcf2maf). VEP was used to annotate twist.vcf file, which was then used as input to vcf2maf.  NOTE: Some columns in this maf file may be affected by the ExACdb assembly compatibility issue discussed in the WES pipeline overview page (https://cidc.nci.nih.gov/pipelines/wes).",
+      "filter_group": "somatic",
+      "file_purpose": "Analysis view",
+      "optional": false,
+      "tumor_only_assay": true
+    },
+    {
+      "file_path_template": "analysis/somatic/{run id}/{run id}_tnscope.output.twist.filtered.vcf",
+      "short_description": "somatic variants: vcf file of somatic variants in TWIST targed capture region filtered by PASS column",
+      "long_description": "VCF file of variants that fall within the TWIST excome capture regions filtered to remove vairants where the PASS column contained one of the following- germline-risk, low_t_alt_frac, t_lod_fstar, or triallelic_site",
+      "filter_group": "somatic",
+      "file_purpose": "Analysis view",
+      "optional": false,
+      "tumor_only_assay": true
+    },
+    {
+      "file_path_template": "analysis/somatic/{run id}/{run id}_tnscope.output.twist.filtered.maf",
+      "short_description": "somatic variants: maf file of somatic variants in TWIST targed capture region filtered by PASS column",
+      "long_description": "MAF file generated by converting twist.filtered.vcf to maf using VEP to annotate variants and vcf2maf to do the conversion.  NOTE: Some columns in this maf file may be affected by the ExACdb assembly compatibility issue discussed in the WES pipeline overview page (https://cidc.nci.nih.gov/pipelines/wes).",
+      "filter_group": "somatic",
+      "file_purpose": "Analysis view",
+      "optional": false,
+      "tumor_only_assay": true
+    },
+    {
+      "file_path_template": "analysis/tcellextrect/{run id}/{run id}_tcellextrect.txt",
+      "short_description": "tcell: TCell fraction estimates generated by TcellExTRECT",
+      "long_description": "TCell fraction estimates generated by the TcellExTRECT software (https://github.com/McGranahanLab/TcellExTRECT)",
+      "filter_group": "tcell",
+      "file_purpose": "Analysis view",
+      "optional": false,
+      "tumor_only_assay": true
+    }
+  ],
+  "tumor cimac id": [
+    {
+      "file_path_template": "analysis/align/{tumor cimac id}/{tumor cimac id}.sorted.dedup.bam",
+      "short_description": "alignment: bam file with deduplicated reads",
+      "long_description": "Aligned reads were sorted and marked duplicates were removed using the Sentieon Dedup tool (https://support.sentieon.com/manual/usages/general/#dedup-algorithm)",
+      "filter_group": "alignment",
+      "file_purpose": "Source view",
+      "optional": false,
+      "tumor_only_assay": true
+    },
+    {
+      "file_path_template": "analysis/align/{tumor cimac id}/{tumor cimac id}.sorted.dedup.bam.bai",
+      "short_description": "alignment: index file for deduplicated bam",
+      "long_description": "Bam index file for deduplicated bam file generated by the Sentieon Dedup tool (https://support.sentieon.com/manual/usages/general/#dedup-algorithm)",
+      "filter_group": "alignment",
+      "file_purpose": "Source view",
+      "optional": false,
+      "tumor_only_assay": true
+    },
+    {
+      "file_path_template": "analysis/align/{tumor cimac id}/{tumor cimac id}_recalibrated.bam",
+      "short_description": "alignment: Base Qualtiy Score Recalibration (BQSR) bam file",
+      "long_description": "The Sentieon QualCal (https://support.sentieon.com/manual/usages/general/#qualcal-algorithm) is used to perform BSQR and remove any technical artifacts in the base quality scores.",
+      "filter_group": "alignment",
+      "file_purpose": "Source view",
+      "optional": false,
+      "tumor_only_assay": true
+    },
+    {
+      "file_path_template": "analysis/align/{tumor cimac id}/{tumor cimac id}_recalibrated.bam.bai",
+      "short_description": "alignment: index file for Base Qualtiy Score Recalibration (BQSR) bam file",
+      "long_description": "Index file for the BQSR bam file",
+      "filter_group": "alignment",
+      "file_purpose": "Source view",
+      "optional": false,
+      "tumor_only_assay": true
+    },
+    {
+      "file_path_template": "analysis/hlahd/{tumor cimac id}/result/{tumor cimac id}_final.result.txt",
+      "short_description": "hla: MHC Class I and II results (using HLA-HD)",
+      "long_description": "Predicted MHC Class II and II results using the HLA-HD software (https://www.genome.med.kyoto-u.ac.jp/HLA-HD/).  Chromosome 6 reads from the deduplicated bam file were extracted and fed into the HLA-HD prediction algorithm.",
+      "filter_group": "HLA",
+      "file_purpose": "Analysis view",
+      "optional": false,
+      "tumor_only_assay": true
+    },
+    {
+      "file_path_template": "analysis/optitype/{tumor cimac id}/{tumor cimac id}_result.tsv",
+      "short_description": "hla: MHC Class I results (using OptiType)",
+      "long_description": "Predicted MHC Class I alleles using the Optitype software (https://github.com/FRED-2/OptiType).  Chromosome 6 reads from the deduplicated bam file were extracted and fed into the Optitype prediction algorithm.",
+      "filter_group": "HLA",
+      "file_purpose": "Analysis view",
+      "optional": false,
+      "tumor_only_assay": true
+    },
+    {
+      "file_path_template": "analysis/xhla/{tumor cimac id}/report-{tumor cimac id}-hla.json",
+      "short_description": "hla: MHC Class I and II results (using xhla)",
+      "long_description": "Predicted MHC Class I and II results using the xHLA software(https://github.com/humanlongevity/HLA).  Chromosome 6 reads from the deduplicated bam file were extracted and fed into the xHLA prediction algorithm.",
+      "filter_group": "HLA",
+      "file_purpose": "Analysis view",
+      "optional": false,
+      "tumor_only_assay": true
+    }
+  ]
+}

{nci_cidc_schemas-0.28.1.dist-info → nci_cidc_schemas-0.28.2.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: nci_cidc_schemas
-Version: 0.28.1
+Version: 0.28.2
 Summary: The CIDC data model and tools for working with it.
 Home-page: https://github.com/NCI-CIDC/cidc-schemas
 Author: NCI

{nci_cidc_schemas-0.28.1.dist-info → nci_cidc_schemas-0.28.2.dist-info}/RECORD

@@ -1,4 +1,4 @@
-cidc_schemas/__init__.py,sha256=4lhMRxh2IN3Z7QsxgbJxJiGSha0cwykVNIFIpM6JMCI,135
+cidc_schemas/__init__.py,sha256=dMTFW_ybl5DgOcuxwoI6PTPfawBCG_1eI-2rx8jd4kY,135
 cidc_schemas/cli.py,sha256=gWiktRlraNH8Q0zNUae9dohKjPwBmcY0BJwdcQ_fIic,4099
 cidc_schemas/constants.py,sha256=RULs7pGuBAVq1teXymrfbVsK23ZowJvLuZlv0KcjL-Y,698
 cidc_schemas/json_validation.py,sha256=4UxcYrofXlDT-Lz6uiQGO1Jwz5bRs0mN_UH4p_A84ks,23262
@@ -9,6 +9,23 @@ cidc_schemas/template_writer.py,sha256=Lk5hw05owoLLsGXimd2H8FSyqBZ2_HpC5wCWw-Xxm
 cidc_schemas/unprism.py,sha256=TOD3CSGkgNnTtT-OeCCE3Ihlam84lr8XGOmtdSy2lL8,13545
 cidc_schemas/util.py,sha256=P-889E64I3i9iroxw5qORguzr09Ac7tsgzsoGeGsfwM,4716
 cidc_schemas/metaschema/strict_meta_schema.json,sha256=3FiS0r2dAXgfPsruJwZYbQoQnHhC_yl-3mclX8gfiQU,6428
+cidc_schemas/ngs_pipeline_api/__init__.py,sha256=Z_ZBeaNmnc-AKW1dnuT8vFN6Re3YcKne6kjE00xvHds,867
+cidc_schemas/ngs_pipeline_api/output_API.schema.json,sha256=jqEcIpBRDy6r9TPgnRMSRX_UyZ-5bSfST46B-6eo67c,1453
+cidc_schemas/ngs_pipeline_api/atacseq/atacseq.md,sha256=AM6C54du9dTsn4mZP_j0Z_OOjoeQnAmFMiTSjV-vto4,3884
+cidc_schemas/ngs_pipeline_api/atacseq/atacseq_output_API.json,sha256=23XiUq-G_w608yl6-IV3kiYveAGWe5UjHbGcGfqSmuM,2186
+cidc_schemas/ngs_pipeline_api/atacseq/imgs/atacseq.png,sha256=MDIo5LyUjR_bT1mvJwNjXbGLGTU8hIyBvV9fzLw6Hpg,708487
+cidc_schemas/ngs_pipeline_api/rna/rna.md,sha256=ihNx0GBzG4blLHWdOJcymxXlZCKeVWUBP-phJQRSylI,3221
+cidc_schemas/ngs_pipeline_api/rna/rna_config.schema.json,sha256=yyn756y8WS8MJ2pR0xRg6wsiWR-BjYneOTfPcFXjS8k,691
+cidc_schemas/ngs_pipeline_api/rna/rna_output_API.json,sha256=KPib4_Nzv_7lIflU1g-X4rNarz6Uy2OHSZBtfxKWJCs,9179
+cidc_schemas/ngs_pipeline_api/rna/imgs/RIMA.png,sha256=0-0FCUj8xMTGUNkK2f7sPi0LvpPy3wk0mCT_glZ5F0A,1153150
+cidc_schemas/ngs_pipeline_api/tcr/tcr.md,sha256=q0fCrSg4O0z_oiTZcP4Vkx_Ja5lx8afkfPKlK8SlqCM,4708
+cidc_schemas/ngs_pipeline_api/tcr/imgs/TCRseq.png,sha256=62Ks2ccWqUgwVeJ1C3Mu-OUupUsJ_D4kOTHyWup-9gQ,160896
+cidc_schemas/ngs_pipeline_api/wes/wes.md,sha256=UYiHYmccCrrtAdZoyqofTWzYc027EF2rHyRksZBroyI,3830
+cidc_schemas/ngs_pipeline_api/wes/wes_config.schema.json,sha256=assQdV2ts4YPwPcKreQf12Kv1DbFhdG5Oals6li-Vz0,2530
+cidc_schemas/ngs_pipeline_api/wes/wes_output_API.json,sha256=W-KGExZvLhxJx-ubbV5MLIzYNXefFzaEo5waWXHONx4,28898
+cidc_schemas/ngs_pipeline_api/wes/wes_output_API.py,sha256=osdqm1OVBhArItFCXpsVRLKnuTGtheCAk9QQQbl2n7c,31065
+cidc_schemas/ngs_pipeline_api/wes/wes_tumor_only_output_API.json,sha256=BxRIHrhuL-eeCRpmOrkCPsTNLZPjDATA5G6PY9_TCXQ,12173
+cidc_schemas/ngs_pipeline_api/wes/imgs/wes.png,sha256=QQPDqTUSOgaS6s0bLu2g2y_WQgVoujtwDTF9z5xZKCE,403116
 cidc_schemas/pipeline_configs/rna_level1_analysis_config.yaml.j2,sha256=6no9sFqwzb1T61RZGD-owDt2K5R8G_fPTzflV4fOroo,2832
 cidc_schemas/prism/__init__.py,sha256=J5Tj0X7Di6cyxAjaduOUp2aVyvl8UI67bgxEkgttvcU,530
 cidc_schemas/prism/constants.py,sha256=PevSn-geY8VTGMx1iXdUJ2LgoeuhEdKfIpZYk_LbzwI,4088
@@ -178,9 +195,9 @@ cidc_schemas/schemas/templates/manifests/tissue_slide_template.json,sha256=q2GmO
 cidc_schemas/schemas/templates/manifests/tumor_normal_pairing_template.json,sha256=lVJrGb28n-vyfjGBzhrzjn1lMKw1b4HXXmWtwA603v0,2797
 cidc_schemas/schemas/templates/manifests/tumor_tissue_dna_template.json,sha256=LpaoDXDS11NCa-Dv37N-tzEGomswQrx5fypkUcG7xJk,18956
 cidc_schemas/schemas/templates/manifests/tumor_tissue_rna_template.json,sha256=-gww6NCHbtbI5z7UmNSmKyPK3IqKCE8F6n4XwTAb_gk,18101
-nci_cidc_schemas-0.28.1.dist-info/licenses/LICENSE,sha256=zK77-w4rYCZBHAYJEGkcFuPXwKIsP7jMPZ2iQOXjzko,1072
-nci_cidc_schemas-0.28.1.dist-info/METADATA,sha256=IGxjB0w5Wqghr6x3I8yysZ50C6rtLwebgMnFSHjCt80,5008
-nci_cidc_schemas-0.28.1.dist-info/WHEEL,sha256=JNWh1Fm1UdwIQV075glCn4MVuCRs0sotJIq-J6rbxCU,109
-nci_cidc_schemas-0.28.1.dist-info/entry_points.txt,sha256=kSyTzXeJQrJp_2ZX0GS_NnbJR8ceQKLBSgER46PM0hs,55
-nci_cidc_schemas-0.28.1.dist-info/top_level.txt,sha256=Wwb5Cu7QrnbmSJxI2d00e3-Mir36t0jTRnSulmfhi30,13
-nci_cidc_schemas-0.28.1.dist-info/RECORD,,
+nci_cidc_schemas-0.28.2.dist-info/licenses/LICENSE,sha256=zK77-w4rYCZBHAYJEGkcFuPXwKIsP7jMPZ2iQOXjzko,1072
+nci_cidc_schemas-0.28.2.dist-info/METADATA,sha256=GKyInqelEl0ccZfhIk7i54ey1PcMYG1GtcoKYutS9lk,5008
+nci_cidc_schemas-0.28.2.dist-info/WHEEL,sha256=JNWh1Fm1UdwIQV075glCn4MVuCRs0sotJIq-J6rbxCU,109
+nci_cidc_schemas-0.28.2.dist-info/entry_points.txt,sha256=kSyTzXeJQrJp_2ZX0GS_NnbJR8ceQKLBSgER46PM0hs,55
+nci_cidc_schemas-0.28.2.dist-info/top_level.txt,sha256=Wwb5Cu7QrnbmSJxI2d00e3-Mir36t0jTRnSulmfhi30,13
+nci_cidc_schemas-0.28.2.dist-info/RECORD,,