Merge pull request #429 from lilab-bcb/yiming

Add --localcores option to cellranger and spaceranger commands
lilab-bcb · Feb 11, 2025 · 48161f8 · 48161f8
2 parents da5311a + ebd61e6
commit 48161f8
Show file tree

Hide file tree

Showing 10 changed files with 61 additions and 13 deletions.
diff --git a/.github/workflows/womtools-check.yml b/.github/workflows/womtools-check.yml
@@ -0,0 +1,42 @@
+name: Womtools
+
+on:
+  pull_request:
+    branches:
+      - master
+
+jobs:
+  validate:
+    runs-on: ubuntu-latest
+
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@v2
+        with:
+          ref: ${{ github.event.pull_request.head.ref }}
+          repository: ${{ github.repository }}
+          fetch-depth: 0  # Fetch all history
+
+      - name: Set up Java
+        uses: actions/setup-java@v3
+        with:
+          distribution: 'temurin'
+          java-version: '21'
+
+      - name: Fetch Womtool
+        run: |
+          curl -L -o womtool.jar https://github.com/broadinstitute/cromwell/releases/download/87/womtool-87.jar
+
+      - name: List modified files
+        id: diff
+        run: echo "files=$(git diff --name-only ${{ github.event.pull_request.base.sha }} ${{ github.event.pull_request.head.sha }} | tr '\n' ' ')" >> $GITHUB_ENV
+
+      - name: Validate WDL files using Womtool
+        run: |
+          for file in ${{ env.files }}
+          do
+            if [[ $file == *.wdl ]]; then
+              echo "Validating $file"
+              java -jar womtool.jar validate "$file"
+            fi
+          done
diff --git a/workflows/cellranger/cellranger_arc_count.wdl b/workflows/cellranger/cellranger_arc_count.wdl
@@ -153,7 +153,8 @@ task run_cellranger_arc_count {
                     check_call(call_args)
                 fout.write(os.path.abspath(target) + ',' + samples[i] + ',' + ('Gene Expression' if data_types[i] == 'rna' else 'Chromatin Accessibility') + '\n')
 
-        call_args = ['cellranger-arc', 'count', '--id=results', '--libraries=libraries.csv', '--reference=genome_dir', '--jobmode=local']
+        mem_size = re.findall(r"\d+", "~{memory}")[0]
+        call_args = ['cellranger-arc', 'count', '--id=results', '--libraries=libraries.csv', '--reference=genome_dir', '--jobmode=local', '--localcores=~{num_cpu}', '--localmem='+mem_size]
         if '~{gex_exclude_introns}' == 'true':
             call_args.append('--gex-exclude-introns')
         if '~{no_bam}' == 'true':

diff --git a/workflows/cellranger/cellranger_atac_aggr.wdl b/workflows/cellranger/cellranger_atac_aggr.wdl
@@ -133,7 +133,8 @@ task run_cellranger_atac_aggr {
                 counts.append(library_id)
                 fout.write(library_id + "," + current_dir + '/' + library_id + "/fragments.tsv.gz," + current_dir + '/' + library_id + "/singlecell.csv\n")
 
-        call_args = ['cellranger-atac', 'aggr', '--id=results', '--reference=genome_dir', '--csv=aggr.csv', '--normalize=~{normalize}', '--jobmode=local']
+        mem_size = re.findall(r"\d+", "~{memory}")[0]
+        call_args = ['cellranger-atac', 'aggr', '--id=results', '--reference=genome_dir', '--csv=aggr.csv', '--normalize=~{normalize}', '--jobmode=local', '--localcores=~{num_cpu}', '--localmem='+mem_size]
         if '~{secondary}' != 'true':
             call_args.append('--nosecondary')
         else:

diff --git a/workflows/cellranger/cellranger_atac_count.wdl b/workflows/cellranger/cellranger_atac_count.wdl
@@ -137,7 +137,8 @@ task run_cellranger_atac_count {
                 check_call(call_args)
             fastqs.append(target)
 
-        call_args = ['cellranger-atac', 'count', '--id=results', '--reference=genome_dir', '--fastqs=' + ','.join(fastqs), '--sample=~{sample_id}', '--jobmode=local']
+        mem_size = re.findall(r"\d+", "~{memory}")[0]
+        call_args = ['cellranger-atac', 'count', '--id=results', '--reference=genome_dir', '--fastqs=' + ','.join(fastqs), '--sample=~{sample_id}', '--jobmode=local', '--localcores=~{num_cpu}', '--localmem='+mem_size]
         if '~{force_cells}' != '':
             call_args.append('--force-cells=~{force_cells}')
         if '~{dim_reduce}' != '':

diff --git a/workflows/cellranger/cellranger_count.wdl b/workflows/cellranger/cellranger_count.wdl
@@ -224,7 +224,7 @@ task run_cellranger_count {
                 fastqs_dirs.append(target)
 
         mem_size = re.findall(r"\d+", "~{memory}")[0]
-        call_args = ['cellranger', 'count', '--id=results', '--transcriptome=genome_dir', '--chemistry=~{chemistry}', '--jobmode=local', '--localmem='+mem_size]
+        call_args = ['cellranger', 'count', '--id=results', '--transcriptome=genome_dir', '--chemistry=~{chemistry}', '--jobmode=local', '--localcores=~{num_cpu}', '--localmem='+mem_size]
 
         if samples is None: # not Feature Barcode
             call_args.extend(['--sample=~{sample_id}', '--fastqs=' + ','.join(fastqs_dirs)])

diff --git a/workflows/cellranger/cellranger_create_reference.wdl b/workflows/cellranger/cellranger_create_reference.wdl
@@ -22,8 +22,8 @@ workflow cellranger_create_reference {
 
         # Which docker registry to use
         String docker_registry = "quay.io/cumulus"
-        # 8.0.1, 8.0.0, 7.2.0, 7.1.0, 7.0.1, 7.0.0, 6.1.2, 6.1.1
-        String cellranger_version = "8.0.1"
+        # 9.0.0, 8.0.1, 8.0.0, 7.2.0, 7.1.0, 7.0.1, 7.0.0, 6.1.2, 6.1.1
+        String cellranger_version = "9.0.0"
 
         # Disk space in GB
         Int disk_space = 100
@@ -308,7 +308,7 @@ task run_cellranger_mkref {
             else:
                 break
 
-        call_args.extend(['--nthreads=~{num_cpu}', '--memgb=' + mem_digit])
+        call_args.extend(['--nthreads=~{num_cpu}', '--memgb=' + mem_digit, '--localcores=~{num_cpu}', '--localmem=' + mem_digit])
         if '~{ref_version}' != '':
             call_args.append('--ref-version=~{ref_version}')
 

diff --git a/workflows/cellranger/cellranger_multi.wdl b/workflows/cellranger/cellranger_multi.wdl
@@ -273,7 +273,7 @@ task run_cellranger_multi {
                 raise Exception("Cannot locate CMO or FRP sample file!")
 
         mem_size = re.findall(r"\d+", "~{memory}")[0]
-        call_args = ['cellranger', 'multi', '--id=results', '--csv=multi.csv', '--jobmode=local', '--localmem='+mem_size]
+        call_args = ['cellranger', 'multi', '--id=results', '--csv=multi.csv', '--jobmode=local', '--localcores=~{num_cpu}', '--localmem='+mem_size]
         print(' '.join(call_args))
         check_call(call_args)
         CODE

diff --git a/workflows/cellranger/cellranger_vdj.wdl b/workflows/cellranger/cellranger_vdj.wdl
@@ -131,7 +131,7 @@ task run_cellranger_vdj {
             fastqs.append(target)
 
         mem_size = re.findall(r"\d+", "~{memory}")[0]
-        call_args = ['cellranger', 'vdj', '--chain=~{chain}', '--id=results', '--reference=ref_dir', '--fastqs=' + ','.join(fastqs), '--sample=~{sample_id}', '--jobmode=local', '--localmem='+mem_size]
+        call_args = ['cellranger', 'vdj', '--chain=~{chain}', '--id=results', '--reference=ref_dir', '--fastqs=' + ','.join(fastqs), '--sample=~{sample_id}', '--jobmode=local', '--localcores=~{num_cpu}', '--localmem='+mem_size]
         if '~{denovo}' != 'false':
             call_args.append('--denovo')
         print(' '.join(call_args))

diff --git a/workflows/cellranger/cellranger_vdj_create_reference.wdl b/workflows/cellranger/cellranger_vdj_create_reference.wdl
@@ -16,8 +16,8 @@ workflow cellranger_vdj_create_reference {
 
         # Which docker registry to use
         String docker_registry = "quay.io/cumulus"
-        # 8.0.0, 7.2.0 7.1.0, 7.0.1, 7.0.0, 6.1.2, 6.1.1
-        String cellranger_version = "8.0.0"
+        # 9.0.0, 8.0.0, 7.2.0 7.1.0, 7.0.1, 7.0.0, 6.1.2, 6.1.1
+        String cellranger_version = "9.0.0"
 
         # Disk space in GB
         Int disk_space = 100
@@ -84,6 +84,7 @@ task run_cellranger_vdj_create_reference {
 
         python <<CODE
         import os
+        import re
         from subprocess import check_call
 
         # Unzip fa if needed.
@@ -104,7 +105,8 @@ task run_cellranger_vdj_create_reference {
             check_call(call_args)
             gtf_file = root
 
-        call_args = ['cellranger', 'mkvdjref', '--genome=~{genome}', '--fasta=' + fa_file, '--genes=' + gtf_file]
+        mem_size = re.findall(r"\d+", "~{memory}")[0]
+        call_args = ['cellranger', 'mkvdjref', '--genome=~{genome}', '--fasta=' + fa_file, '--genes=' + gtf_file, '--jobmode=local', '--localcores=1', '--localmem='+mem_size]
 
         if '~{ref_version}' != '':
             call_args.append('--ref-version=~{ref_version}')

diff --git a/workflows/spaceranger/spaceranger_count.wdl b/workflows/spaceranger/spaceranger_count.wdl
@@ -209,7 +209,8 @@ task run_spaceranger_count {
                 check_call(call_args)
             fastqs.append('~{sample_id}_' + str(i))
 
-        call_args = ['spaceranger', 'count', '--id=results', '--transcriptome=genome_dir', '--fastqs=' + ','.join(fastqs), '--sample=~{sample_id}', '--jobmode=local']
+        mem_size = re.findall(r"\d+", "~{memory}")[0]
+        call_args = ['spaceranger', 'count', '--id=results', '--transcriptome=genome_dir', '--fastqs=' + ','.join(fastqs), '--sample=~{sample_id}', '--jobmode=local', '--localcores=~{num_cpu}', '--localmem='+mem_size]
 
         localmem = "".join(filter(str.isdigit, "~{memory}"))
         call_args.append("--localmem=" + localmem)