feat: Handle trimmed fastqs plus additional fixes (#252)

* feat: Handle trimmed fastqs * update github action * update github action * temp update all actions * Update to stable github action
snakemake-workflows · Aug 7, 2023 · 13ae724 · 13ae724
1 parent 520e361
commit 13ae724
Show file tree

Hide file tree

Showing 4 changed files with 32 additions and 19 deletions.
diff --git a/.github/workflows/main.yml b/.github/workflows/main.yml
@@ -29,7 +29,7 @@ jobs:
     steps:
     - uses: actions/checkout@v2
     - name: Lint workflow
-      uses: snakemake/snakemake-github-action@v1.24.0
+      uses: snakemake/snakemake-github-action@v1.25.0
       with:
         directory: .
         snakefile: workflow/Snakefile
@@ -50,21 +50,23 @@ jobs:
         directory: .test
         snakefile: workflow/Snakefile
         args: "--configfile .test/config-simple/config.yaml --use-conda --show-failed-logs -j 10 --conda-cleanup-pkgs cache"
+        show-disk-usage-on-error: true
 
     - name: Test testcase generation
       uses: snakemake/snakemake-github-action@v1
       with:
         directory: .test
         snakefile: workflow/Snakefile
         args: "results/testcases/a/freebayes/IX:314200 --configfile .test/config-simple/config.yaml --use-conda --show-failed-logs -j 10 --conda-cleanup-pkgs cache"
+        show-disk-usage-on-error: true
 
     - name: Test report
       uses: snakemake/snakemake-github-action@v1
       with:
         directory: .test
         snakefile: workflow/Snakefile
         args: "--configfile .test/config-simple/config.yaml --report report.zip"
-
+        show-disk-usage-on-error: true
 
     - name: Test workflow (local FASTQs, target regions)
       uses: snakemake/snakemake-github-action@v1
@@ -74,6 +76,7 @@ jobs:
         args: "--configfile .test/config-target-regions/config.yaml --use-conda --show-failed-logs -j 10 --conda-cleanup-pkgs cache"
         stagein: |
           rm -rf .test/results
+        show-disk-usage-on-error: true
 
     - name: Test workflow (local FASTQs, multiple target regions BED files)
       uses: snakemake/snakemake-github-action@v1
@@ -83,6 +86,7 @@ jobs:
         args: "--configfile .test/config-target-regions/config_multiple_beds.yaml --use-conda --show-failed-logs -j 10 --conda-cleanup-pkgs cache"
         stagein: |
           rm -rf .test/results
+        show-disk-usage-on-error: true
 
     - name: Test workflow (local FASTQs, no candidate filtering)
       uses: snakemake/snakemake-github-action@v1
@@ -92,6 +96,7 @@ jobs:
         args: "--configfile .test/config-no-candidate-filtering/config.yaml --dryrun --use-conda --show-failed-logs -j 10 --conda-cleanup-pkgs cache"
         stagein: |
           rm -rf .test/results
+        show-disk-usage-on-error: true
 
     - name: Test workflow (local FASTQs primer)
       uses: snakemake/snakemake-github-action@v1
@@ -101,6 +106,7 @@ jobs:
         args: "--configfile .test/config_primers/config.yaml --use-conda --show-failed-logs -j 10 --conda-cleanup-pkgs cache"
         stagein: |
           rm -rf .test/results
+        show-disk-usage-on-error: true
 
     - name: Test workflow (SRA FASTQs)
       uses: snakemake/snakemake-github-action@v1
@@ -110,3 +116,4 @@ jobs:
         args: "--configfile .test/config-sra/config.yaml --show-failed-logs --use-conda -n -j 10 --conda-cleanup-pkgs cache"
         stagein: |
           rm -rf .test/results
+        show-disk-usage-on-error: true
diff --git a/workflow/rules/annotation.smk b/workflow/rules/annotation.smk
@@ -43,7 +43,7 @@ rule annotate_variants:
         "logs/vep/{group}.{scatteritem}.annotate.log",
     threads: get_vep_threads()
     wrapper:
-        "v1.31.1/bio/vep/annotate"
+        "v2.2.1/bio/vep/annotate"
 
 
 # TODO What about multiple ID Fields?

diff --git a/workflow/rules/candidate_calling.smk b/workflow/rules/candidate_calling.smk
@@ -4,8 +4,8 @@ rule freebayes:
         ref_idx=genome_fai,
         regions="results/regions/{group}.expanded_regions.filtered.bed",
         # you can have a list of samples here
-        samples=lambda w: get_group_bams(w),
-        indexes=lambda w: get_group_bams(w, bai=True),
+        alns=lambda w: get_group_bams(w),
+        idxs=lambda w: get_group_bams(w, bai=True),
     output:
         "results/candidate-calls/{group}.freebayes.bcf",
     log:
@@ -19,7 +19,7 @@ rule freebayes:
         ),
     threads: max(workflow.cores - 1, 1)  # use all available cores -1 (because of the pipe) for calling
     wrapper:
-        "v1.19.0/bio/freebayes"
+        "v2.3.0/bio/freebayes"
 
 
 rule delly:

diff --git a/workflow/rules/common.smk b/workflow/rules/common.smk
@@ -796,12 +796,16 @@ def get_untrimmed_fastqs(wc):
 
 
 def get_trimmed_fastqs(wc):
-    return expand(
-        "results/trimmed/{sample}/{unit}_{read}.fastq.gz",
-        unit=units.loc[wc.sample, "unit_name"],
-        sample=wc.sample,
-        read=wc.read,
-    )
+    if units.loc[wc.sample, "adapters"].notna().all():
+        return expand(
+            "results/trimmed/{sample}/{unit}_{read}.fastq.gz",
+            unit=units.loc[wc.sample, "unit_name"],
+            sample=wc.sample,
+            read=wc.read,
+        )
+    else:
+        fq = "fq1" if wc.read == "R1" or wc.read == "single" else "fq2"
+        return units.loc[wc.sample, fq]
 
 
 def get_umi_fastq(wc):
@@ -844,6 +848,7 @@ def get_vembrane_config(wildcards, input):
         "CANONICAL",
         "MANE_PLUS_CLINICAL",
         {"name": "clinical significance", "expr": "ANN['CLIN_SIG']"},
+        {"name": "gnomad genome af", "expr": "ANN['gnomADg_AF']"},
     ]
 
     annotation_fields.extend(
@@ -1006,13 +1011,14 @@ def get_fastqc_results(wildcards):
     )
 
     # cutadapt
-    pattern = "results/trimmed/{unit.sample_name}/{unit.unit_name}.{mode}.qc.txt"
-    yield from expand(
-        pattern, unit=sample_units[paired_end_units].itertuples(), mode="paired"
-    )
-    yield from expand(
-        pattern, unit=sample_units[~paired_end_units].itertuples(), mode="single"
-    )
+    if sample_units["adapters"].notna().all():
+        pattern = "results/trimmed/{unit.sample_name}/{unit.unit_name}.{mode}.qc.txt"
+        yield from expand(
+            pattern, unit=sample_units[paired_end_units].itertuples(), mode="paired"
+        )
+        yield from expand(
+            pattern, unit=sample_units[~paired_end_units].itertuples(), mode="single"
+        )
 
     # samtools idxstats
     yield from expand("results/qc/{sample}.bam.idxstats", sample=group_samples)