Cn_signatures_from_ichorcna

bin/reformat_ichorcna_seg.py

@@ -0,0 +1,46 @@
+#!/usr/bin/env python3
+
+import argparse
+import pandas as pd
+
+def main():
+    parser = argparse.ArgumentParser(description="Format ichorCNA .seg.txt file ")
+    parser.add_argument("-s", "--segmentation_file", required=True, help="Input ichorCNA .seg file")
+    parser.add_argument("-o", "--output", default=None, help="Output formatted .seg file")
+    args = parser.parse_args()
+
+    # Create file
+    df = pd.read_csv(args.segmentation_file, sep="\t", dtype=str)
+
+    # Check columns in .seg.txt file
+    required_cols = ["chrom", "start", "end", "logR_Copy_Number", "ID"]
+    missing = [c for c in required_cols if c not in df.columns]
+    if missing:
+        raise ValueError(f"There mandatory columns are missing {args.segmentation_file}: {missing}")
+
+    # Rename columns as required for CX signatures
+    df_out = (
+        df.loc[:, required_cols]
+          .rename(columns={
+              "chrom": "chromosome",
+              "logR_Copy_Number": "segVal",
+              "ID": "sample"
+          })
+    )
+
+    # Convert to numeric 
+    for col in ["start", "end", "segVal"]:
+        df_out[col] = pd.to_numeric(df_out[col], errors="coerce")
+
+    # Remove NAs
+    df_out = df_out.dropna(subset=["segVal"])
+
+    # Output file
+    out_file = args.output 
+
+    # Save formatted segmentation file
+    df_out.to_csv(out_file, sep="\t", index=False)
+
+
+if __name__ == "__main__":
+    main()

conf/modules.config

@@ -335,6 +335,15 @@ process {
         ext.when   = params.ichorcna_ploidy_aware_plot
     }
 
+    withName: FORMAT_ICHORCNA_SEG {
+        publishDir = [
+            path: { "${params.outdir}/ichorcna/formatted_segmentation_files" },
+            mode: params.publish_dir_mode,
+            saveAs: { filename -> filename.equals('versions.yml') ? null : filename },
+        ]
+        ext.when   = params.compute_signatures
+    }
+
     withName: CONCATENATE_QDNASEQ_PLOTS {
         publishDir = [
             path: { "${params.outdir}/cn_plots/qdnaseq/" },

modules/local/format_ichorcna_seg/main.nf

@@ -0,0 +1,23 @@
+process FORMAT_ICHORCNA_SEG {
+    tag "$meta.id"
+    container "quay.io/einar_rainhart/pandas-pandera:1.5.3"
+    label 'process_low'
+
+    input:
+    tuple val(meta), path(seg)
+
+    output:
+    path "${meta.id}_formatted.seg", emit: seg
+
+    script:
+    def VERSION = '0.0.1'
+
+    """
+    reformat_ichorcna_seg.py -s $seg --o ${meta.id}_formatted.seg
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        format_ichorcna: ${VERSION}
+    END_VERSIONS
+    """
+}

subworkflows/local/ichorcna/main.nf

@@ -4,6 +4,7 @@ include { HMMCOPY_READCOUNTER as HMMCOPY_READCOUNTER_ICHORCNA } from '../../../m
 include { CORRECT_LOGR_ICHORCNA                               } from '../../../modules/local/correct_logR_ichorcna/main'
 include { CONCATENATE_PDF as CONCATENATE_BIN_PLOTS            } from '../../../modules/local/concatenate_pdf/main'
 include { PLOT_ICHORCNA                                       } from '../../../modules/local/plot_ichorcna/main'
+include { FORMAT_ICHORCNA_SEG                                  } from '../../../modules/local/format_ichorcna_seg/main'
 
 workflow ICHORCNA {
     take:
@@ -76,11 +77,26 @@ workflow ICHORCNA {
     CONCATENATE_BIN_PLOTS(ICHORCNA_RUN.out.genome_plot.collect { _meta, plot -> plot })
     ch_versions = ch_versions.mix(CONCATENATE_BIN_PLOTS.out.versions)
 
+    // Create file for signature analysis
+
+    formatted_ichor = FORMAT_ICHORCNA_SEG(ICHORCNA_RUN.out.seg_txt)
+
+    signature_file_ichor = formatted_ichor  
+        .collectFile(
+            storeDir: "${params.outdir}/ichorcna/",
+            name: "all_segments_ichorcna_signatures.seg",
+            keepHeader: true,
+            skip: 1
+        )
+
+
+
     emit:
-    versions    = ch_versions
-    summary     = ch_reports
-    ch_segments = called_segments
-    ch_bins     = bins
-    gistic_file = corrected_gistic_file
-    genome_plot = genome_plot
+    versions       = ch_versions
+    summary        = ch_reports
+    ch_segments    = called_segments
+    ch_bins        = bins
+    gistic_file    = corrected_gistic_file
+    genome_plot    = genome_plot
+    signature_file = signature_file_ichor
 }

subworkflows/local/solid_biopsy/main.nf

@@ -157,6 +157,11 @@ workflow SOLID_BIOPSY {
         corrected_gistic_file = ICHORCNA.out.gistic_file
         ch_reports = ch_versions.mix(ICHORCNA.out.summary)
         ch_versions = ch_versions.mix(ICHORCNA.out.versions)
+
+        // FIXME: Compute signatures (duplication with ASCAT.sc)
+        CIN_SIGNATURE_QUANTIFICATION(ICHORCNA.out.signature_file)
+        ch_versions = ch_versions.mix(CIN_SIGNATURE_QUANTIFICATION.out.versions)
+        ch_reports = ch_reports.mix(CIN_SIGNATURE_QUANTIFICATION.out.sig_activity_plot)
     }
     else {
         error("Unknown CNV caller ${caller}")