made example on how to call center_around_peack module and tested it

Author: alessiovignoli

bin/center_around_peak.sh

@@ -1,9 +1,7 @@
-BEGIN {
-    # Read chromosome sizes into an array
-    while ((getline < chrom_size_file) > 0) {
-        chrom_sizes[$1] = $2;
-    }
-}
+# First file (ex. chrom_sizes.txt): Load chromosome sizes into an array
+NR==FNR { chrom_sizes[$1] = $2; next; }
+
+# Second file (ex. input.bed): Process BED data
 # Print header lines as they are
 /^#/ { print; next; }
 {
@@ -13,18 +11,18 @@ BEGIN {
 
     # the new start and end values
     start = mid - left;
-    end = mid + right;
+    ends = mid + right;
 
     # Ensure start is not negative
     if (start < 0) start = 0;
 
     # Ensure end does not exceed chromosome size
-    if ($1 in chrom_sizes && end > chrom_sizes[$1]) {
-        end = chrom_sizes[$1];
+    if ($1 in chrom_sizes && ends > chrom_sizes[$1]) {
+        ends = chrom_sizes[$1];
     }
 
     # Print updated start, end, and ALL remaining columns
-    printf "%s\t%d\t%d", $1, start, end;
+    printf "%s\t%d\t%d", $1, start, ends;
     for (i=4; i<=NF; i++) {
         printf "\t%s", $i;
     }

conf/modules.config

@@ -36,8 +36,9 @@ process {
         publishDir = [
             enabled: false
         ]
-        ext.args = { "-v N=${meta.size} -v chrom_size_file=${meta.genome_file}" }
+        ext.args   = { "-v N=${meta.size}" }
         ext.prefix = { "${meta.id}_centered" }
+        ext.suffix = { "bed" }
     }
 
     withName: "SPLIT_DATA_CONFIG" {

subworkflows/local/preprocess_bedfile_to_fasta/main.nf

@@ -18,6 +18,8 @@ the dataset for stimulus with sequences as input and foreground/background
 */
 include { EXTRACT_DATA_CONTENT_BY_COLUMN_VALUES as EXTRACT_FOREGROUND        } from '../../../modules/local/extract_data_content_by_column_values'
 include { EXTRACT_DATA_CONTENT_BY_COLUMN_VALUES as EXTRACT_BACKGROUND_ALIENS } from '../../../modules/local/extract_data_content_by_column_values'
+include { GAWK as CENTER_AROUND_PEAK                                         } from '../../../modules/nf-core/gawk'
+
 
 workflow PREPROCESS_BEDFILE_TO_FASTA {
     take:
@@ -26,6 +28,19 @@ workflow PREPROCESS_BEDFILE_TO_FASTA {
 
     main:
 
+    // TODO the foolowing is just a proof of concept and how to example 
+    // on the usage of the GAWK nf-core module for modifying
+    // bed start and end values based on distance from peak (centering).
+    /*
+    ch_genome_size = channel.fromPath("/users/cn/avignoli/test/human.hg38.genome") // abs path so you can go and check if needed on cluster.
+    ch_input_bed = channel.fromPath("/users/cn/avignoli/test/input.bed")
+    ch_center_input = ch_genome_size.combine(ch_input_bed).map{
+        it -> [["id" : it[1].getBaseName(), "size" : 10], it]
+    } // TODO replace size with the appropriate params/variable containing the size to be used for centering
+    ch_awk_program = channel.fromPath('./bin/center_around_peak.sh')
+    CENTER_AROUND_PEAK(ch_center_input, ch_awk_program)
+    */
+
     // extract foreground
 
     ch_foreground_ids = ch_config