v19-release

doc/release-notes.md

@@ -1,5 +1,139 @@
 # release notes
 ## current release
+### release-v19-20210423
+- release date: 2021-04-23
+- status: available
+- changes:
+  - Remove per BS_JXF8A2A6 due to mis-identification per [#862](https://github.com/AlexsLemonade/OpenPBTA-analysis/issues/862)
+    - Updates:
+      - pbta-fusion-starfusion.tsv.gz
+      - pbta-fusion-arriba.tsv.gz
+      - pbta-gene-expression-rsem-fpkm.stranded.rds
+      - pbta-gene-counts-rsem-expected_count.stranded.rds
+      - pbta-gene-expression-rsem-tpm.stranded.rds
+      - pbta-gene-expression-kallisto.stranded.rds
+      - pbta-isoform-counts-rsem-expected_count.stranded.rds
+      - pbta-gene-expression-rsem-fpkm-collapsed.stranded.rds
+      - pbta-isoform-expression-rsem-tpm.stranded.rds
+      - independent-specimens.rnaseq.primary-plus-stranded.tsv
+      - pbta-star-log-final.tar.gz
+      - pbta-star-log-manifest.tsv
+      - pbta-mend-qc-manifest.tsv
+      - pbta-mend-qc-results.tar.gz
+      - pbta-fusion-putative-oncogenic.tsv
+      - pbta-fusion-recurrently-fused-genes-byhistology.tsv
+      - pbta-fusion-recurrently-fused-genes-bysample.tsv
+      - independent-specimens.rnaseq.primary-plus-stranded.tsv
+      - fusion_summary_ewings_foi.tsv
+      - fusion_summary_lgat_foi.tsv
+      - fusion_summary_ependymoma_foi.tsv 
+      - fusion_summary_embryonal_foi.tsv
+  - Add INDEL renormalization of MAF files per [#1024](https://github.com/AlexsLemonade/OpenPBTA-analysis/issues/1024)
+    - Updates:
+      - pbta-snv-strelka2.vep.maf.gz
+      - pbta-snv-lancet.vep.maf.gz            
+      - pbta-snv-vardict.vep.maf.gz            
+      - pbta-snv-mutect2.vep.maf.gz 
+      - pbta-tcga-snv-strelka2.vep.maf.gz    
+      - pbta-tcga-snv-mutect2.vep.maf.gz       
+      - pbta-tcga-snv-lancet.vep.maf.gz 
+  - Update pbta-histologies.tsv:
+    - Add `PFS_days` to `pbta-histologies.tsv` file per [#963](https://github.com/AlexsLemonade/OpenPBTA-analysis/issues/963) 
+    - Pull latest clinical data
+    - Rerun molecular subtyping modules to date
+    - Update PNOC003 `cohort` to "PNOC" for inclusion of later PNOC trial samples
+    - Update `CNS_region` from manual review per [#1025](https://github.com/AlexsLemonade/OpenPBTA-analysis/issues/1025)
+  - Add `pbta-mb-pathology-subtypes.tsv` containing pathology report molecular subtypes for medulloblastoma to be used as a "truth" set for medulloblastoma classifier testing per [#746](https://github.com/AlexsLemonade/OpenPBTA-analysis/issues/746)
+- folder structure:
+```
+data
+└── release-v19-20210423
+    ├── consensus_seg_annotated_cn_autosomes.tsv.gz
+    ├── consensus_seg_annotated_cn_x_and_y.tsv.gz
+    ├── data-files-description.md
+    ├── fusion_summary_embryonal_foi.tsv
+    ├── fusion_summary_ependymoma_foi.tsv
+    ├── fusion_summary_ewings_foi.tsv
+    ├── fusion_summary_lgat_foi.tsv
+    ├── independent-specimens.rnaseq.primary-plus-polya.tsv
+    ├── independent-specimens.rnaseq.primary-plus-stranded.tsv
+    ├── independent-specimens.wgs.primary-plus.tsv
+    ├── independent-specimens.wgs.primary.tsv
+    ├── independent-specimens.wgswxs.primary-plus.tsv
+    ├── independent-specimens.wgswxs.primary.tsv
+    ├── intersect_cds_lancet_strelka_mutect_WGS.bed
+    ├── intersect_cds_lancet_WXS.bed
+    ├── intersect_strelka_mutect_WGS.bed
+    ├── md5sum.txt
+    ├── pbta-cnv-cnvkit-gistic.zip
+    ├── pbta-cnv-cnvkit.seg.gz
+    ├── pbta-cnv-consensus-gistic.zip
+    ├── pbta-cnv-consensus.seg.gz
+    ├── pbta-cnv-controlfreec.tsv.gz
+    ├── pbta-fusion-arriba.tsv.gz
+    ├── pbta-fusion-putative-oncogenic.tsv
+    ├── pbta-fusion-recurrently-fused-genes-byhistology.tsv
+    ├── pbta-fusion-recurrently-fused-genes-bysample.tsv
+    ├── pbta-fusion-starfusion.tsv.gz
+    ├── pbta-gene-counts-rsem-expected_count.polya.rds
+    ├── pbta-gene-counts-rsem-expected_count.stranded.rds
+    ├── pbta-gene-expression-kallisto.polya.rds
+    ├── pbta-gene-expression-kallisto.stranded.rds
+    ├── pbta-gene-expression-rsem-fpkm-collapsed.polya.rds
+    ├── pbta-gene-expression-rsem-fpkm-collapsed.stranded.rds
+    ├── pbta-gene-expression-rsem-fpkm.polya.rds
+    ├── pbta-gene-expression-rsem-fpkm.stranded.rds
+    ├── pbta-gene-expression-rsem-tpm.polya.rds
+    ├── pbta-gene-expression-rsem-tpm.stranded.rds
+    ├── pbta-histologies.tsv    
+    ├── pbta-histologies-base.tsv
+    ├── pbta-isoform-counts-rsem-expected_count.polya.rds
+    ├── pbta-isoform-counts-rsem-expected_count.stranded.rds
+    ├── pbta-isoform-expression-rsem-tpm.polya.rds
+    ├── pbta-isoform-expression-rsem-tpm.stranded.rds
+    ├── pbta-mend-qc-manifest.tsv
+    ├── pbta-mend-qc-results.tar.gz
+    ├── pbta-snv-consensus-mutation.maf.tsv.gz
+    ├── pbta-snv-consensus-mutation-tmb-all.tsv
+    ├── pbta-snv-consensus-mutation-tmb-coding.tsv
+    ├── pbta-snv-lancet.vep.maf.gz
+    ├── pbta-snv-mutect2.vep.maf.gz
+    ├── pbta-snv-scavenged-hotspots.maf.tsv.gz
+    ├── pbta-snv-strelka2.vep.maf.gz
+    ├── pbta-snv-vardict.vep.maf.gz
+    ├── pbta-star-log-final.tar.gz
+    ├── pbta-star-log-manifest.tsv
+    ├── pbta-sv-manta.tsv.gz
+    ├── pbta-tcga-manifest.tsv
+    ├── pbta-tcga-snv-lancet.vep.maf.gz
+    ├── pbta-tcga-snv-mutect2.vep.maf.gz
+    ├── pbta-tcga-snv-strelka2.vep.maf.gz
+    ├── release-notes.md
+    ├── StrexomeLite_hg38_liftover_100bp_padded.bed
+    ├── StrexomeLite_Targets_CrossMap_hg38_filtered_chr_prefixed.bed
+    ├── WGS.hg38.lancet.300bp_padded.bed
+    ├── WGS.hg38.lancet.unpadded.bed
+    ├── WGS.hg38.mutect2.vardict.unpadded.bed
+    ├── WGS.hg38.strelka2.unpadded.bed
+    ├── WGS.hg38.vardict.100bp_padded.bed
+    ├── WXS.hg38.100bp_padded.bed
+    ├── WXS.hg38.lancet.400bp_padded.bed
+    ├── intersected_whole_exome_agilent_designed_120_AND_tcga_6k_genes.Gh38.bed
+    ├── intersected_whole_exome_agilent_plus_tcga_6k_AND_tcga_6k_genes.Gh38.bed
+    ├── tcga_6k_genes.targetIntervals.Gh38.bed
+    ├── tcga_6k_genes.targetIntervals.bed
+    ├── tcga-snv-consensus-snv.maf.tsv.gz
+    ├── tcga-snv-mutation-tmb-all.tsv
+    ├── tcga-snv-mutation-tmb-coding.tsv
+    ├── whole_exome_agilent_1.1_refseq_plus_3_boosters.targetIntervals.Gh38.bed
+    ├── whole_exome_agilent_1.1_refseq_plus_3_boosters.targetIntervals.bed
+    ├── whole_exome_agilent_designed_120.targetIntervals.Gh38.bed
+    ├── whole_exome_agilent_designed_120.targetIntervals.bed
+    ├── whole_exome_agilent_plus_tcga_6k.targetIntervals.Gh38.bed
+    └── whole_exome_agilent_plus_tcga_6k.targetIntervals.bed
+```
+
+## archived release
 ### release-v18-20201123
 - release date: 2020-11-23
 - status: available

download-data.sh

@@ -4,8 +4,8 @@ set -o pipefail
 
 # Use the OpenPBTA bucket as the default.
 URL=${OPENPBTA_URL:-https://s3.amazonaws.com/kf-openaccess-us-east-1-prd-pbta/data}
-RELEASE=${OPENPBTA_RELEASE:-release-v18-20201123}
-PREVIOUS=${OPENPBTA_RELEASE:-release-v17-20200908}
+RELEASE=${OPENPBTA_RELEASE:-release-v19-20210423}
+PREVIOUS=${OPENPBTA_RELEASE:-release-v18-20201123}
 
 # Remove old symlinks in data
 find data -type l -delete