Update snakemake to 8.24

LUMC · Oct 24, 2024 · 86d3ddb · 86d3ddb
1 parent 78dd35b
commit 86d3ddb
Show file tree

Hide file tree

Showing 10 changed files with 50 additions and 49 deletions.
diff --git a/CHANGELOG.rst b/CHANGELOG.rst
@@ -10,6 +10,7 @@ Changelog
 **********
 v2.2.0-dev
 **********
+* Update snakemake to version 8.23. **Important: re-build the conda environment**
 
 **********
 v2.1.1

diff --git a/Snakefile b/Snakefile
@@ -129,7 +129,7 @@ rule create_summary:
         fusion_json=fusion.module_output.json,
         snv_indels_json=align.module_output.json,
         itd_json=itd.module_output.json,
-        scr=srcdir("scripts/create_summary.py"),
+        scr=workflow.source_path("scripts/create_summary.py"),
     params:
         pipeline_ver=PIPELINE_VERSION,
     output:
@@ -154,11 +154,12 @@ rule generate_report:
     """Generates a PDF report of the essential results."""
     input:
         summary=rules.create_summary.output.js,
-        css=srcdir("report/assets/style.css"),
-        templates=srcdir("report/templates"),
-        imgs=srcdir("report/assets/img"),
-        toc=srcdir("report/assets/toc.xsl"),
-        scr=srcdir("scripts/generate_report.py"),
+        css=workflow.source_path("report/assets/style.css"),
+        toc=workflow.source_path("report/assets/toc.xsl"),
+        scr=workflow.source_path("scripts/generate_report.py"),
+    params:
+        templates="report/templates",
+        imgs="report/assets/img",
     output:
         "{sample}/hamlet_report.{sample}.pdf",
     log:
@@ -168,8 +169,8 @@ rule generate_report:
     shell:
         """
         python3 {input.scr} \
-            --templates-dir {input.templates} \
-            --imgs-dir {input.imgs} \
+            --templates-dir {params.templates} \
+            --imgs-dir {params.imgs} \
             --css-path {input.css} \
             --toc-path {input.toc} \
             {input.summary} \
@@ -181,11 +182,12 @@ rule generate_html_report:
     """Generates a HTML report of the essential results, used for testing only"""
     input:
         summary=rules.create_summary.output.js,
-        css=srcdir("report/assets/style.css"),
-        templates=srcdir("report/templates"),
-        imgs=srcdir("report/assets/img"),
-        toc=srcdir("report/assets/toc.xsl"),
-        scr=srcdir("scripts/generate_report.py"),
+        css=workflow.source_path("report/assets/style.css"),
+        toc=workflow.source_path("report/assets/toc.xsl"),
+        scr=workflow.source_path("scripts/generate_report.py"),
+    params:
+        templates="report/templates",
+        imgs="report/assets/img",
     output:
         "{sample}/hamlet_report.{sample}.html",
     log:
@@ -195,8 +197,8 @@ rule generate_html_report:
     shell:
         """
         python3 {input.scr} \
-            --templates-dir {input.templates} \
-            --imgs-dir {input.imgs} \
+            --templates-dir {params.templates} \
+            --imgs-dir {params.imgs} \
             --css-path {input.css} \
             --toc-path {input.toc} \
             {input.summary} \
@@ -208,7 +210,7 @@ rule multiqc:
     input:
         qc_stats=qc_seq.module_output.multiqc_files,
         snv_indel_stats=align.module_output.multiqc_files,
-        config=srcdir("cfg/multiqc.yml"),
+        config=workflow.source_path("cfg/multiqc.yml"),
     params:
         filelist="multiqc_filelist.txt",
         depth=2,

diff --git a/environment.yml b/environment.yml
@@ -6,11 +6,10 @@ channels:
   - bioconda
   - conda-forge
 dependencies:
-  - bs4=4.11
-  - peppy>=0.35
-  - pytest-workflow>=1.6.0
-  - snakemake-minimal=7.32
-  - snakefmt=0.10.0
-  - black=24.3.0
-  - sphinx=7.1.2
-  - sphinx-rtd-theme
+  - bs4=4.12
+  - peppy=0.40.7
+  - pytest-workflow=2.1.0
+  - snakemake-minimal=8.24.1
+  - snakefmt=0.10.2
+  - sphinx=8.1.3
+  - sphinx-rtd-theme=3.0.0
diff --git a/includes/expression/Snakefile b/includes/expression/Snakefile
@@ -13,7 +13,8 @@ rule bed_coverage:
     input:
         bam=get_bam,
         bed=config["bed"],
-        src=srcdir("scripts/coverage.py"),
+        src=workflow.source_path("scripts/coverage.py"),
+        gtf_file=workflow.source_path("scripts/gtf.py"),
     output:
         coverage="{sample}/expression/coverage.csv",
     log:
@@ -35,7 +36,7 @@ rule normalized_coverage:
         coverage=rules.bed_coverage.output.coverage,
         counts=get_counts,
         gtf=config["gtf"],
-        src=srcdir("scripts/expression.py"),
+        src=workflow.source_path("scripts/expression.py"),
     params:
         strand=get_strand,
         housekeeping=config["housekeeping"],

diff --git a/includes/fusion/Snakefile b/includes/fusion/Snakefile
@@ -41,8 +41,8 @@ rule arriba:
 rule filter_fusions:
     input:
         fusions="{sample}/fusion/arriba/fusions.raw.tsv",
-        to_json=srcdir("scripts/arriba2json.py"),
-        to_tsv=srcdir("scripts/json2arriba.py"),
+        to_json=workflow.source_path("scripts/arriba2json.py"),
+        to_tsv=workflow.source_path("scripts/json2arriba.py"),
         report_genes=config["report_genes"],
     output:
         json="{sample}/fusion/arriba/fusions.json",
@@ -54,8 +54,8 @@ rule filter_fusions:
         containers["arriba"]
     shell:
         """
-        {input.to_json} {input.fusions} --report-genes {input.report_genes} > {output.json} 2> {log}
-        {input.to_tsv} {output.json} > {output.tsv} 2>> {log}
+        python3 {input.to_json} {input.fusions} --report-genes {input.report_genes} > {output.json} 2> {log}
+        python3 {input.to_tsv} {output.json} > {output.tsv} 2>> {log}
         """
 
 
@@ -109,7 +109,7 @@ rule json_output:
     input:
         json="{sample}/fusion/arriba/fusions.json",
         plots="{sample}/fusion/arriba/plots",
-        src=srcdir("scripts/json-output.py"),
+        src=workflow.source_path("scripts/json-output.py"),
     output:
         json="{sample}/fusion/fusion-output.json",
     log:
@@ -119,5 +119,5 @@ rule json_output:
         containers["arriba"]
     shell:
         """
-        {input.src} {input.json} {input.plots} > {output} 2> {log}
+        python3 {input.src} {input.json} {input.plots} > {output} 2> {log}
         """
diff --git a/includes/itd/Snakefile b/includes/itd/Snakefile
@@ -153,7 +153,7 @@ rule json_output:
         flt3_plot="{sample}/itd/{sample}.flt3.png",
         kmt2a_csv="{sample}/itd/{sample}.kmt2a.csv",
         kmt2a_plot="{sample}/itd/{sample}.kmt2a.png",
-        src=srcdir("scripts/json-output.py"),
+        src=workflow.source_path("scripts/json-output.py"),
     output:
         "{sample}/itd/itd-output.json",
     log:

diff --git a/includes/qc-seq/Snakefile b/includes/qc-seq/Snakefile
@@ -71,7 +71,7 @@ rule sequali:
 rule multiqc:
     input:
         stats=module_output.multiqc_files,
-        config=srcdir("../../cfg/multiqc.yml"),
+        config=workflow.source_path("../../cfg/multiqc.yml"),
     params:
         filelist="multiqc_filelist.txt",
         depth=2,

diff --git a/includes/snv-indels/Snakefile b/includes/snv-indels/Snakefile
@@ -162,7 +162,7 @@ rule exon_cov:
         bed=".tmp.exon_cov_ref.bed",
         genome=".tmp.genome.txt",
         idm=config["ref_id_mapping"],
-        scr=srcdir("scripts/aggr_exon_cov.py"),
+        scr=workflow.source_path("scripts/aggr_exon_cov.py"),
     output:
         json="{sample}/snv-indels/{sample}.exon_cov_stats.json",
     log:
@@ -376,7 +376,7 @@ rule filter_vep:
         vep="{sample}/snv-indels/{sample}.vep.txt.gz",
         ref_id_mapping=config["ref_id_mapping"],
         hotspots="{sample}/snv-indels/{sample}.hotspot.vcf",
-        scr=srcdir("scripts/filter_vep.py"),
+        scr=workflow.source_path("scripts/filter_vep.py"),
         blacklist=config.get("blacklist", []),
     params:
         vep_consequences=config["vep_include_consequence"],
@@ -413,7 +413,7 @@ rule json_output:
         insert_stats="{sample}/snv-indels/{sample}.insert_stats",
         exon_cov_stats="{sample}/snv-indels/{sample}.exon_cov_stats.json",
         vep_stats="{sample}/snv-indels/{sample}.vep_stats.txt",
-        src=srcdir("scripts/json-output.py"),
+        src=workflow.source_path("scripts/json-output.py"),
     output:
         "{sample}/snv-indels/snv-indels-output.json",
     log:
@@ -436,7 +436,7 @@ rule json_output:
 rule multiqc:
     input:
         stats=module_output.multiqc_files,
-        config=srcdir("../../cfg/multiqc.yml"),
+        config=workflow.source_path("../../cfg/multiqc.yml"),
     params:
         filelist="multiqc_filelist.txt",
         depth=2,

diff --git a/test/test_utilities.yml b/test/test_utilities.yml
@@ -39,9 +39,7 @@
   command: >
     snakemake -n
     --snakefile utilities/deps/Snakefile
-    --reason
-    --printshellcmds
-    --verbose
+    --workflow-profile test
   stdout:
     contains:
       - rule create_call_region
diff --git a/utilities/deps/Snakefile b/utilities/deps/Snakefile
@@ -104,7 +104,7 @@ rule rewrite_gtf:
     """ Add the 'chr' prefix to the chromosome names """
     input:
         gtf=rules.download_gtf.output,
-        rewrite=srcdir("scripts/rewrite-gtf.py"),
+        rewrite=workflow.source_path("scripts/rewrite-gtf.py"),
     output:
         gtf=gtf_renamed,
     singularity:
@@ -171,7 +171,7 @@ rule create_refflat:
 rule rewrite_refflat:
     input:
         gtf=rules.create_refflat.output,
-        scr=srcdir("scripts/rewrite-refflat.py"),
+        scr=workflow.source_path("scripts/rewrite-refflat.py"),
     output:
         "ucsc_gencode.refFlat",
     singularity:
@@ -184,7 +184,7 @@ rule rewrite_refflat:
 
 rule create_id_mappings:
     input:
-        srcdir("small-files/id_mappings.tsv"),
+        workflow.source_path("small-files/id_mappings.tsv"),
     output:
         "id_mappings.tsv",
     singularity:
@@ -197,7 +197,7 @@ rule create_id_mappings:
 
 rule create_blacklist:
     input:
-        srcdir("small-files/blacklist.txt"),
+        workflow.source_path("small-files/blacklist.txt"),
     output:
         "blacklist.txt",
     singularity:
@@ -210,7 +210,7 @@ rule create_blacklist:
 
 rule create_call_region:
     input:
-        srcdir("small-files/call_regions.bed"),
+        workflow.source_path("small-files/call_regions.bed"),
     output:
         "call_regions.bed",
     singularity:
@@ -252,7 +252,7 @@ rule create_rRNA_refflat:
 
 rule genome_hotspots:
     input:
-        srcdir("small-files/hotspots_genome.bed"),
+        workflow.source_path("small-files/hotspots_genome.bed"),
     output:
         "hotspots_genome.bed",
     singularity:
@@ -266,7 +266,7 @@ rule genome_hotspots:
 rule create_report_genes:
     input:
         folder="arriba",
-        genes=srcdir("small-files/report_genes.txt"),
+        genes=workflow.source_path("small-files/report_genes.txt"),
     output:
         "arriba/report_genes.txt",
     singularity:
@@ -307,7 +307,7 @@ rule unpack_vep_cache:
 rule copy_itd:
     """All the needed files are in small-files/itd, so we just copy them"""
     input:
-        fasta=srcdir("small-files/itd/itd_genes.fa"),
+        fasta=workflow.source_path("small-files/itd/itd_genes.fa"),
     output:
         itd=directory("itd"),
     singularity: