Fixing issue #280

CHANGELOG.md

@@ -7,6 +7,7 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ### `Added`
 
+- Substituted VCF_TO_CSV local module with GATK4/VARIANTSTOTABLE nf-core module [#280](https://github.com/nf-core/variantbenchmarking/issues/280)
 - RTGtools update to 3.13 [#261](https://github.com/nf-core/variantbenchmarking/issues/261)
 - Transforming local modules with bcftools and tabix to standard nf-core modules [#267](https://github.com/nf-core/variantbenchmarking/pull/267)
 - Replace local modules SORT_BED and REFORMAT_HEADER with nf-core ones. [#268](https://github.com/nf-core/variantbenchmarking/pull/268)

bin/merge_sompy_features.py

@@ -75,16 +75,16 @@ def get_sample_names(files):
                 sample_names.append(gt_column.replace('.GT', ''))
     return sample_names
 
-def write_merged_csv(merged_data, output_file, sample_names):
-    """Write merged dictionary to CSV."""
+def write_merged_file(merged_data, output_file, sample_names, delimiter):
+    """Write merged dictionary to file according to delimiter."""
     sorted_keys = sorted(merged_data.keys(), key=lambda x: (x[0], int(x[1])))
 
     fixed_fields = ["CHROM", "POS", "REF", "ALT", "FILTER"]
     dynamic_fields = sorted([f"{sample}_GT" for sample in sample_names])
     fieldnames = fixed_fields + dynamic_fields
 
     with open(output_file, 'w', newline='') as f:
-        writer = csv.DictWriter(f, fieldnames=fieldnames, restval='./.')
+        writer = csv.DictWriter(f, fieldnames=fieldnames, restval='./.', delimiter = delimiter)
         writer.writeheader()
         for key in sorted_keys:
             writer.writerow({field: merged_data[key].get(field, "./.") for field in fieldnames})
@@ -94,7 +94,7 @@ def main():
         description="Merge CSVs by CHROM, POS, and handle dynamic GT columns."
     )
     parser.add_argument("files", nargs='+', help="Input CSV files (e.g. *_TP.csv)")
-    parser.add_argument("--output", required=True, help="Output merged CSV file")
+    parser.add_argument("--output", required=True, help="Output merged TSV file")
     args = parser.parse_args()
 
     all_dicts = []
@@ -106,7 +106,7 @@ def main():
         all_dicts.append(sample_dict)
 
     merged = merge_dicts_by_key(all_dicts, all_sample_names)
-    write_merged_csv(merged, args.output, all_sample_names)
+    write_merged_file(merged, args.output, all_sample_names, delimiter = "\t")
     print(f"Merged CSV written to {args.output}")
 
 if __name__ == "__main__":

bin/plot_upset.py

@@ -28,7 +28,7 @@ def parse_file(file_path, category_name):
         return {}
 
     try:
-        df = pd.read_csv(file_path, sep=',')
+        df = pd.read_csv(file_path, sep='\t')
     except pd.errors.EmptyDataError:
         print(f"Warning: File {file_path} is empty.")
         return {}

conf/modules.config

@@ -676,13 +676,18 @@ process {
         ]
     }
 
+    withName: BCFTOOLS_SORT_COMPARE{
+        ext.prefix = { vcf.baseName - ".vcf" + ".sort"}
+        publishDir = [
+            enabled: false
+        ]
+    }
 
-    withName: VCF_TO_CSV {
-        ext.prefix = {"${meta.id}.${meta.tag}"}
+        withName: "BCFTOOLS_REHEADER_COMPARE" {
+        ext.args2  = {"--output-type z" }
+        ext.prefix = { vcf.baseName - ".vcf" + ".reheader"}
         publishDir = [
-            path: {"${params.outdir}/${params.variant_type}/summary/comparisons/${meta.id}"},
-            pattern: "*{.csv}",
-            mode: params.publish_dir_mode
+            enabled: false
         ]
     }
 

modules.json

@@ -15,6 +15,11 @@
                         "git_sha": "6383d8fe58f9498eecd5aa303e71a4a932d1e9f6",
                         "installed_by": ["modules"]
                     },
+                    "bcftools/index": {
+                        "branch": "master",
+                        "git_sha": "6383d8fe58f9498eecd5aa303e71a4a932d1e9f6",
+                        "installed_by": ["modules"]
+                    },
                     "bcftools/merge": {
                         "branch": "master",
                         "git_sha": "6383d8fe58f9498eecd5aa303e71a4a932d1e9f6",
@@ -66,6 +71,11 @@
                         "installed_by": ["modules"],
                         "patch": "modules/nf-core/gatk4/concordance/gatk4-concordance.diff"
                     },
+                    "gatk4/variantstotable": {
+                        "branch": "master",
+                        "git_sha": "52b7843bd92ccf833cc12e71cd84aeccf2583852",
+                        "installed_by": ["modules"]
+                    },
                     "gawk": {
                         "branch": "master",
                         "git_sha": "76b1f53edcf72798d8515c82f4728ad44b3dd902",

modules/local/custom/merge_sompy_features/main.nf

@@ -11,7 +11,7 @@ process MERGE_SOMPY_FEATURES {
     tuple val(meta), path(csvs)
 
     output:
-    tuple val(meta), path("*.csv")   , emit: output
+    tuple val(meta), path("*.tsv")   , emit: output
     path "versions.yml"              , emit: versions
 
     when:
@@ -22,7 +22,7 @@ process MERGE_SOMPY_FEATURES {
     def prefix = task.ext.prefix ?: "${meta.id}"
 
     """
-    merge_sompy_features.py $csvs --output ${prefix}.${meta.tag}.csv
+    merge_sompy_features.py $csvs --output ${prefix}.${meta.tag}.tsv
 
     cat <<-END_VERSIONS > versions.yml
     "${task.process}":
@@ -32,7 +32,7 @@ process MERGE_SOMPY_FEATURES {
     stub:
     def prefix = task.ext.prefix ?: "${meta.id}"
     """
-    touch ${prefix}.${meta.tag}.summary.csv
+    touch ${prefix}.${meta.tag}.summary.tsv
 
     cat <<-END_VERSIONS > versions.yml
     "${task.process}":

modules/local/custom/plot_upset/main.nf

@@ -21,10 +21,10 @@ process PLOT_UPSET {
     def prefix = task.ext.prefix ?: "${meta.id}"
     """
     plot_upset.py \\
-        --fp ${meta.id}.FP.csv \\
-        --fn ${meta.id}.FN.csv \\
-        --tp-base ${meta.id}.TP_base.csv \\
-        --tp-comp ${meta.id}.TP_comp.csv \\
+        --fp ${meta.id}.FP.tsv \\
+        --fn ${meta.id}.FN.tsv \\
+        --tp-base ${meta.id}.TP_base.tsv \\
+        --tp-comp ${meta.id}.TP_comp.tsv \\
         --output ${prefix} \\
         --title "Upset plot for ${meta.id}"