[MODIF] add pairtools nf-core#162

nservant · Jun 15, 2023 · a4a546e · a4a546e
1 parent 8d40b36
commit a4a546e
Show file tree

Hide file tree

Showing 5 changed files with 29 additions and 9 deletions.
diff --git a/bin/digest_genome.py b/bin/digest_genome.py
@@ -113,6 +113,7 @@ def replaceN(cs):
             "specified."
         ),
     )
+    parser.add_argument("--extra", default=False, action='store_false', help="Add extra BED columns")
     parser.add_argument("-o", "--out", default=None)
     args = parser.parse_args()
 
@@ -193,8 +194,10 @@ def replaceN(cs):
                 # allow to remove cases where the enzyme cut at
                 # the first position of the chromosome
                 if end > begin:
-                    frag_id += 1
-                    frag_name = "HIC_{}_{}".format(str(chrom_name), int(frag_id))
-                    outfile.write(
-                        "{}\t{}\t{}\t{}\t0\t+\n".format(str(chrom_name), int(begin), int(end), str(frag_name))
-                    )
+                    if args.extra:
+                        frag_id += 1
+                        frag_name = "HIC_{}_{}".format(str(chrom_name), int(frag_id))
+                        outfile.write("{}\t{}\t{}\t{}\t0\t+\n".format(str(chrom_name), int(begin), int(end), str(frag_name)))
+                    else:
+                        outfile.write("{}\t{}\t{}\n".format(str(chrom_name), int(begin), int(end)))
+
diff --git a/conf/modules.config b/conf/modules.config
@@ -39,6 +39,7 @@ process {
             mode: 'copy',
             enabled: params.save_reference
         ]
+        ext.args = params.processing == "hicpro" ? '--extra' : ''
     }
 
     //*******************************************
@@ -182,8 +183,15 @@ process {
     }
 
     withName: 'PAIRTOOLS_PARSE' {
-        ext.args = { "--min-mapq 40 --walks-policy 5unique --max-inter-align-gap 30 --output-stats ${meta.id}_parse.stats --add-columns mapq --drop-sam --drop-seq" } 
+        ext.args = { [
+            '--add-columns mapq',
+            params.save_interaction_bam ? '' : '--drop-sam --drop-seq',
+            "--walks-policy 5unique --output-stats ${meta.id}_parse.stats" 
+        ].join(' ').trim() }
+    }
 
+    withName: 'PAIRTOOLS_RESTRICT' {
+        ext.prefix = { "${meta.id}_restrict" }
     }
 
     withName: 'PAIRTOOLS_DEDUP' {

diff --git a/modules/local/hicpro/get_restriction_fragments.nf b/modules/local/hicpro/get_restriction_fragments.nf
@@ -16,8 +16,10 @@ process GET_RESTRICTION_FRAGMENTS {
     path("versions.yml"), emit: versions
 
     script:
+    def args = task.ext.args ?: ''
+    def prefix = task.ext.prefix ?: "restriction_fragments"
     """
-    digest_genome.py -r ${res_site} -o restriction_fragments.bed ${fasta}
+    digest_genome.py ${args} -r ${res_site} -o ${prefix}.bed ${fasta}
 
     cat <<-END_VERSIONS > versions.yml
     "${task.process}":

diff --git a/subworkflows/local/pairtools.nf b/subworkflows/local/pairtools.nf
@@ -31,6 +31,7 @@ workflow PAIRTOOLS {
   take:
   reads // [meta, read1, read2]
   index // [meta2, path]
+  frag
   chrsize // path
 
   main:
@@ -39,16 +40,21 @@ workflow PAIRTOOLS {
   BWA_MEM(
     reads,
     index,
-    Channel.value("view")
+    Channel.value("false")
   )
 
   PAIRTOOLS_PARSE(
     BWA_MEM.out.bam,
     chrsize
   )
 
+  PAIRTOOLS_RESTRICT(
+    PAIRTOOLS_PARSE.out.pairsam,
+    frag.map{it->it[1]}
+  )
+
   PAIRTOOLS_SORT(
-    PAIRTOOLS_PARSE.out.pairsam
+    PAIRTOOLS_RESTRICT.out.restrict
   )
 
   ch_valid_pairs = PAIRTOOLS_SORT.out.sorted.map{ it -> removeChunks(it)}.groupTuple()

diff --git a/workflows/hic.nf b/workflows/hic.nf
@@ -193,6 +193,7 @@ workflow HIC {
     PAIRTOOLS(
       INPUT_CHECK.out.reads,
       PREPARE_GENOME.out.index,
+      PREPARE_GENOME.out.res_frag,
       PREPARE_GENOME.out.chromosome_size
     )
     ch_versions = ch_versions.mix(PAIRTOOLS.out.versions)