using gawk to center bed start and end based on peack position and size value, needs testing

Author: alessiovignoli

bin/center_around_peak.sh

@@ -0,0 +1,32 @@
+BEGIN {
+    # Read chromosome sizes into an array
+    while ((getline < chrom_size_file) > 0) {
+        chrom_sizes[$1] = $2;
+    }
+}
+# Print header lines as they are
+/^#/ { print; next; }
+{
+    mid = $4;                  # extract peak piosition
+    left = int(N/2);           # Floor division for left padding
+    right = N - left - 1;      # Ensures total length is exactly N
+
+    # the new start and end values
+    start = mid - left;
+    end = 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];
+    }
+
+    # Print updated start, end, and ALL remaining columns
+    printf "%s\t%d\t%d", $1, start, end;
+    for (i=4; i<=NF; i++) {
+        printf "\t%s", $i;
+    }
+    print "";  # Newline
+}

conf/modules.config

@@ -32,6 +32,14 @@ process {
         ext.prefix = { "${meta.id}.background_aliens" }
     }
 
+    withName: "CENTER_AROUND_PEAK" {
+        publishDir = [
+            enabled: false
+        ]
+        ext.args = { "-v N=${meta.size} -v chrom_size_file=${meta.genome_file}" }
+        ext.prefix = { "${meta.id}_centered" }
+    }
+
     withName: "SPLIT_DATA_CONFIG" {
         publishDir = [
             path: { "${params.outdir}/configs" },

modules.json

@@ -14,6 +14,11 @@
                         "branch": "master",
                         "git_sha": "81880787133db07d9b4c1febd152c090eb8325dc",
                         "installed_by": ["modules"]
+                    },
+                    "gawk": {
+                        "branch": "master",
+                        "git_sha": "81880787133db07d9b4c1febd152c090eb8325dc",
+                        "installed_by": ["modules"]
                     }
                 }
             },