Disable BWAMEM2 index when no short reads data

subworkflows/local/prepare_genome.nf

@@ -12,7 +12,6 @@ workflow PREPARE_GENOME {
     take:
     fasta    // channel: [ meta, /path/to/fasta ]
 
-
     main:
     ch_versions = Channel.empty()
 
@@ -33,24 +32,27 @@ workflow PREPARE_GENOME {
     UNMASK ( ch_fasta )
     ch_versions = ch_versions.mix ( UNMASK.out.versions )
 
-
     // Generate BWA index
-    if ( params.bwamem2_index ) {
-        Channel.fromPath ( params.bwamem2_index )
-        | combine ( ch_fasta )
-        | map { bwa, meta, fa -> [ meta, bwa ] }
-        | set { ch_bwamem }
-
-        if ( params.bwamem2_index.endsWith('.tar.gz') ) {
-            ch_bwamem2_index = UNTAR ( ch_bwamem ).untar
-            ch_versions      = ch_versions.mix ( UNTAR.out.versions )
+    if ( checkShortReads(params.input) ) {
+        if ( params.bwamem2_index ) {
+            Channel.fromPath ( params.bwamem2_index )
+            | combine ( ch_fasta )
+            | map { bwa, meta, fa -> [ meta, bwa ] }
+            | set { ch_bwamem }
+
+            if ( params.bwamem2_index.endsWith('.tar.gz') ) {
+                ch_bwamem2_index = UNTAR ( ch_bwamem ).untar
+                ch_versions      = ch_versions.mix ( UNTAR.out.versions.first() )
+            } else {
+                ch_bwamem2_index = ch_bwamem
+            }
+
         } else {
-            ch_bwamem2_index = ch_bwamem
+            ch_bwamem2_index = BWAMEM2_INDEX ( UNMASK.out.fasta ).index
+            ch_versions      = ch_versions.mix ( BWAMEM2_INDEX.out.versions.first() )
         }
-
     } else {
-        ch_bwamem2_index = BWAMEM2_INDEX ( UNMASK.out.fasta ).index
-        ch_versions      = ch_versions.mix ( BWAMEM2_INDEX.out.versions )
+        ch_bwamem2_index = Channel.empty()
     }
 
 
@@ -59,3 +61,24 @@ workflow PREPARE_GENOME {
     bwaidx   = ch_bwamem2_index.first()    // channel: [ meta, /path/to/bwamem2/index_dir/ ]
     versions = ch_versions                 // channel: [ versions.yml ]
 }
+
+def checkShortReads(filePath, columnToCheck="datatype") {
+    // Define the target values to check
+    def valuesToCheck = ['illumina', 'hic']
+    // Read the CSV file
+    def csvLines = new File(filePath).readLines()
+    // Extract the header and find the index of the column
+    def header = csvLines[0].split(',')
+    def columnIndex = header.findIndexOf { it == columnToCheck }
+    // Check if the column index was found
+    if (columnIndex == -1) {
+        println "Column '${columnToCheck}' not found in the CSV header."
+        return false
+    }
+    // Check for the values in the specified column and return true if found
+    def containsValues = csvLines[1..-1].any { line ->
+        def columns = line.split(',')
+        valuesToCheck.contains(columns[columnIndex].toLowerCase())
+    }
+    return containsValues
+}

workflows/readmapping.nf

@@ -76,10 +76,6 @@ workflow READMAPPING {
 
     ch_versions = ch_versions.mix ( INPUT_CHECK.out.versions )
 
-
-    //
-    // SUBWORKFLOW: Uncompress and prepare reference genome files
-    //
     ch_fasta
     | map { [ [ id: it.baseName ], it ] }
     | set { ch_genome }