Merge pull request #555 from d3b-center/v15-subset-files

V15 subset files (2/2)
d3b-center · Mar 1, 2024 · 3f47859 · 3f47859
2 parents 5567109 + c4993a3
commit 3f47859
Show file tree

Hide file tree

Showing 5 changed files with 72 additions and 32 deletions.
diff --git a/.github/workflows/run_analysis.yml b/.github/workflows/run_analysis.yml
@@ -9,7 +9,14 @@ jobs:
     name: Run Analysis - Consensus CN Manta
     runs-on: ubuntu-latest
     steps:
-      - uses: actions/checkout@v3
+      - uses: actions/checkout@v4
+      - name: free disk space
+        run: |
+          sudo swapoff -a
+          sudo rm -f /swapfile
+          sudo apt clean
+          docker rmi $(docker image ls -aq)
+          df -h
       - name: Download Data for Consensus CN Manta
         uses: docker://pgc-images.sbgenomics.com/d3b-bixu/open-pedcan:latest
         with:
@@ -27,7 +34,14 @@ jobs:
     needs: consensus_cn_manta
     runs-on: ubuntu-latest
     steps:
-      - uses: actions/checkout@v3
+      - uses: actions/checkout@v4
+      - name: free disk space
+        run: |
+          sudo swapoff -a
+          sudo rm -f /swapfile
+          sudo apt clean
+          docker rmi $(docker image ls -aq)
+          df -h
       - name: Download Data for Consensus CN
         uses: docker://pgc-images.sbgenomics.com/d3b-bixu/open-pedcan:latest
         with:
@@ -131,6 +145,7 @@ jobs:
 
           - name: Mutational signatures
             entrypoint: mutational-signatures/run_mutational_signatures.sh
+            openpbta_testing: 1
 
           #- name: Immune Deconvolution
           #  entrypoint: immune-deconv/run-immune-deconv.sh
@@ -161,8 +176,14 @@ jobs:
           #  entrypoint: rnaseq-batch-correct/run_ruvseq.sh
 
     steps:
-      - uses: actions/checkout@v3
-
+      - uses: actions/checkout@v4
+      - name: free disk space
+        run: |
+          sudo swapoff -a
+          sudo rm -f /swapfile
+          sudo apt clean
+          docker rmi $(docker image ls -aq)
+          df -h
       - name: Download Data
         uses: docker://pgc-images.sbgenomics.com/d3b-bixu/open-pedcan:latest
         with:

diff --git a/analyses/create-subset-files/biospecimen_ids_for_subset.RDS b/analyses/create-subset-files/biospecimen_ids_for_subset.RDS
diff --git a/analyses/create-subset-files/run_create_subset_files.sh b/analyses/create-subset-files/run_create_subset_files.sh
@@ -8,7 +8,7 @@ set -o pipefail
 
 # Set defaults for release and biospecimen file name
 BIOSPECIMEN_FILE=${BIOSPECIMEN_FILE:-biospecimen_ids_for_subset.RDS}
-RELEASE=${RELEASE:-v14}
+RELEASE=${RELEASE:-v15}
 NUM_MATCHED=${NUM_MATCHED:-15}
 
 # This option controls whether or not the two larger MAF files are skipped as

diff --git a/analyses/mutational-signatures/run_mutational_signatures.sh b/analyses/mutational-signatures/run_mutational_signatures.sh
@@ -9,41 +9,59 @@ set -o pipefail
 # Set the working directory to the directory of this file
 cd "$(dirname "${BASH_SOURCE[0]}")"
 
+
 # In CI we'll run an abbreviated version of the de novo signatures extraction
 ABBREVIATED_MUTSIGS=${OPC_QUICK_MUTSIGS:-0}
 
+# Run only consensus testing file in CI, since tumor only snv is large
+IS_CI=${OPENPBTA_TESTING:-0}
+
+if [[ "$IS_CI" -eq "1" ]]
+
+then
+
+  echo "Run the SBS mutational signatures analysis using existing signatures on consensus SNV"
+  Rscript -e "rmarkdown::render('01-known_signatures.Rmd', params = list(snv_file = \"snv-consensus-plus-hotspots.maf.tsv.gz\", output_Folder = \"ConsensusSNV\"), clean = TRUE)"
+  mv 01-known_signatures.nb.html 01-ConsensusSNV_known_signatures.nb.html
+
+  echo "Run the mutational signatures analysis using COSMIC DBS signatures (v3.3) on consensus SNV"
+  Rscript -e "rmarkdown::render('02-cosmic_dbs_signatures.Rmd', params = list(snv_file = \"snv-consensus-plus-hotspots.maf.tsv.gz\", output_Folder = \"ConsensusSNV\"), clean = TRUE)"
+  mv 02-cosmic_dbs_signatures.nb.html 02-ConsensusSNV_cosmic_dbs_signatures.nb.html
 
-# Run the SBS mutational signatures analysis using existing signatures on consensus SNV
-Rscript -e "rmarkdown::render('01-known_signatures.Rmd', params = list(snv_file = \"snv-consensus-plus-hotspots.maf.tsv.gz\", output_Folder = \"ConsensusSNV\"), clean = TRUE)"
-mv 01-known_signatures.nb.html 01-ConsensusSNV_known_signatures.nb.html
+  echo "Run analysis of adult CNS mutational signatures on consensus SNV"
+  Rscript --vanilla 03-fit_cns_signatures.R \
+    --snv_file snv-consensus-plus-hotspots.maf.tsv.gz \
+    --output_Folder ConsensusSNV 
 
-# Run the SBS mutational signatures analysis using existing signatures on tumor only SNV
-Rscript -e "rmarkdown::render('01-known_signatures.Rmd', params = list(snv_file = \"snv-mutect2-tumor-only-plus-hotspots.maf.tsv.gz\", output_Folder = \"TumorOnlySNV\"), clean = TRUE)"
-mv 01-known_signatures.nb.html 01-TumorOnly_known_signatures.nb.html
+else 
 
-# Run the mutational signatures analysis using COSMIC DBS signatures (v3.3)
-Rscript -e "rmarkdown::render('02-cosmic_dbs_signatures.Rmd', params = list(snv_file = \"snv-consensus-plus-hotspots.maf.tsv.gz\", output_Folder = \"ConsensusSNV\"), clean = TRUE)"
-mv 02-cosmic_dbs_signatures.nb.html 02-ConsensusSNV_cosmic_dbs_signatures.nb.html
+  # Run the SBS mutational signatures analysis using existing signatures on consensus SNV
+  Rscript -e "rmarkdown::render('01-known_signatures.Rmd', params = list(snv_file = \"snv-consensus-plus-hotspots.maf.tsv.gz\", output_Folder = \"ConsensusSNV\"), clean = TRUE)"
+  mv 01-known_signatures.nb.html 01-ConsensusSNV_known_signatures.nb.html
+
+  # Run the SBS mutational signatures analysis using existing signatures on tumor only SNV
+  Rscript -e "rmarkdown::render('01-known_signatures.Rmd', params = list(snv_file = \"snv-mutect2-tumor-only-plus-hotspots.maf.tsv.gz\", output_Folder = \"TumorOnlySNV\"), clean = TRUE)"
+  mv 01-known_signatures.nb.html 01-TumorOnly_known_signatures.nb.html
 
-Rscript -e "rmarkdown::render('02-cosmic_dbs_signatures.Rmd', params = list(snv_file = \"snv-mutect2-tumor-only-plus-hotspots.maf.tsv.gz\", output_Folder = \"TumorOnlySNV\"), clean = TRUE)"
-mv 02-cosmic_dbs_signatures.nb.html 02-TumorOnly_cosmic_dbs_signatures.nb.html
+  # Run the mutational signatures analysis using COSMIC DBS signatures (v3.3)
+  Rscript -e "rmarkdown::render('02-cosmic_dbs_signatures.Rmd', params = list(snv_file = \"snv-consensus-plus-hotspots.maf.tsv.gz\", output_Folder = \"ConsensusSNV\"), clean = TRUE)"
+  mv 02-cosmic_dbs_signatures.nb.html 02-ConsensusSNV_cosmic_dbs_signatures.nb.html
 
-# Run analysis of adult CNS mutational signatures
-Rscript --vanilla 03-fit_cns_signatures.R \
-  --snv_file snv-consensus-plus-hotspots.maf.tsv.gz \
-  --output_Folder ConsensusSNV 
+  Rscript -e "rmarkdown::render('02-cosmic_dbs_signatures.Rmd', params = list(snv_file = \"snv-mutect2-tumor-only-plus-hotspots.maf.tsv.gz\", output_Folder = \"TumorOnlySNV\"), clean = TRUE)"
+  mv 02-cosmic_dbs_signatures.nb.html 02-TumorOnly_cosmic_dbs_signatures.nb.html
 
-Rscript --vanilla 03-fit_cns_signatures.R \
-  --snv_file snv-mutect2-tumor-only-plus-hotspots.maf.tsv.gz \
-  --output_Folder TumorOnlySNV 
-
-# Run mutational signature summary of hypermutant tumors
-## skip script 04 if it is on GitHub CI
-if [ "$CI" = true ]; then
-  echo "Running in GitHub CI"
-else
-  echo "Not running in GitHub CI"
+  # Run analysis of adult CNS mutational signatures
+  Rscript --vanilla 03-fit_cns_signatures.R \
+    --snv_file snv-consensus-plus-hotspots.maf.tsv.gz \
+    --output_Folder ConsensusSNV 
+
+  Rscript --vanilla 03-fit_cns_signatures.R \
+    --snv_file snv-mutect2-tumor-only-plus-hotspots.maf.tsv.gz \
+    --output_Folder TumorOnlySNV 
+
   Rscript -e "rmarkdown::render('04-explore_hypermutators.Rmd', params = list(output_Folder = \"ConsensusSNV\"), clean = TRUE)"
+
   ## Tumor only result did not have sample passing the filter. Therefore, 04 script is not running for tumor only
   #Rscript -e "rmarkdown::render('04-explore_hypermutators.Rmd', params = list(output_Folder = \"TumorOnlySNV\"), clean = TRUE)"
+
 fi
diff --git a/doc/data-files-description.md b/doc/data-files-description.md
@@ -40,8 +40,9 @@ This document contains information about all data files associated with this pro
 |`fusion-putative-oncogenic.tsv` | Analysis file | [`fusion_filtering`](https://github.com/d3b-center/OpenPedCan-analysis/tree/master/analyses/fusion_filtering) | Filtered and prioritized fusions
 |`gene-counts-rsem-expected_count-collapsed.rds` | Analysis file | PBTA+GMKF+TARGET [`collapse-rnaseq`](https://github.com/d3b-center/OpenPedCan-analysis/tree/dev/analyses/collapse-rnaseq) | Gene expression - RSEM expected_count for each samples collapsed to gene symbol (gene-level)
 |`gene-expression-rsem-tpm-collapsed.rds` | Analysis file | PBTA+GMKF+TARGET [`collapse-rnaseq`](https://github.com/d3b-center/OpenPedCan-analysis/tree/dev/analyses/collapse-rnaseq) | Gene expression - RSEM TPM for each samples collapsed to gene symbol (gene-level)
-|`tcga-gene-expression-rsem-tpm-collapsed.rds` | Modified reference file | TCGA samples lifted from GENCODE v27 to v39 | Gene expression - RSEM TPM for each samples collapsed to gene symbol (gene-level)
-|`gtex-gene-expression-rsem-tpm-collapsed.rds` | Modified reference file | GTEX v8 release lifted to GENCODE v39 | Gene expression - RSEM TPM for each samples collapsed to gene symbol (gene-level)
+|`tcga_gene-counts-rsem-expected_count-collapsed.rds` | Modified reference file | TCGA samples lifted from GENCODE v27 to v39 | Gene expression - RSEM counts for each samples collapsed to gene symbol (gene-level)
+|`tcga_gene-expression-rsem-tpm-collapsed.rds` | Modified reference file | TCGA samples lifted from GENCODE v27 to v39 | Gene expression - RSEM TPM for each samples collapsed to gene symbol (gene-level)
+|`gtex_gene-expression-rsem-tpm-collapsed.rds` | Modified reference file | GTEX v8 release lifted to GENCODE v39 | Gene expression - RSEM TPM for each samples collapsed to gene symbol (gene-level)
 |`gtex_gene-counts-rsem-expected_count-collapsed.rds` | Modified reference file | GTEX v8 release lifted to GENCODE v39 | Gene expression - RSEM counts for each samples collapsed to gene symbol (gene-level)
 |`WGS.hg38.lancet.300bp_padded.bed` | Reference Target/Baits File | [SNV and INDEL calling](https://github.com/AlexsLemonade/OpenPBTA-manuscript/blob/master/content/03.methods.md#snv-and-indel-calling) | WGS.hg38.lancet.unpadded.bed file with each region padded by 300 bp
 |`WGS.hg38.lancet.unpadded.bed` | Reference Regions File | [SNV and INDEL calling](https://github.com/AlexsLemonade/OpenPBTA-manuscript/blob/master/content/03.methods.md#snv-and-indel-calling) |  hg38 WGS regions created using UTR, exome, and start/stop codon features of the GENCODE 31 reference, augmented with PASS variant calls from Strelka2 and Mutect2