When running GSAlign use whole-genome vs whole-genome

MazdaX · Dec 7, 2020 · 8d92d5d · 8d92d5d
1 parent 5e2b02f
commit 8d92d5d
Show file tree

Hide file tree

Showing 2 changed files with 18 additions and 4 deletions.
diff --git a/modules/processes/preprocess.nf b/modules/processes/preprocess.nf
@@ -201,6 +201,15 @@ process splittgt {
         mkdir ./SPLIT_tgt && chmod a+rw ./SPLIT_tgt
         faSplit size -oneFile -lift=target.lift -extra=500 ${target} 4500 SPLIT_tgt/tmp
         """
+    else if ( params.aligner == 'gsalign' )
+        """
+        myvalue=`faSize -tab ${target} | awk '\$1=="maxSize" {print \$2}'`
+        if [ -z \$myvalue ]; then
+            myvalue=`faSize -tab ${target} | awk '\$1=="baseCount" {print \$2}'`
+        fi
+        mkdir ./SPLIT_tgt && chmod a+rw ./SPLIT_tgt
+        faSplit size -oneFile -lift=source.lift ${target} \$myvalue SPLIT_tgt/tgt
+        """
     else
         """
         mkdir SPLIT_tgt && chmod a+rw SPLIT_tgt

diff --git a/modules/subworkflows/preprocess.nf b/modules/subworkflows/preprocess.nf
@@ -25,19 +25,24 @@ workflow PREPROC {
         splitsrc(ch_source)
         src_lift = splitsrc.out.src_lift_ch
         if ( params.aligner == 'blat' || params.aligner == 'gsalign' || params.aligner == 'last' ){
-            ch_fragm_out = splitsrc.out.srcsplit_ch
+            ch_fragm_src_out = splitsrc.out.srcsplit_ch
         } else {
             groupsrc(splitsrc.out.srcsplit_ch)
-            ch_fragm_out = groupsrc.out.srcclst_ch
+            ch_fragm_src_out = groupsrc.out.srcclst_ch
         }
 
         // split and group target
         splittgt(ch_target)
         tgt_lift = splittgt.out.tgt_lift_ch
-        grouptgt(splittgt.out.tgtsplit_ch)
+        if ( params.aligner == 'blat' || params.aligner == 'gsalign' || params.aligner == 'last' ){
+            ch_fragm_tgt_out = splittgt.out.tgtsplit_ch
+        } else {
+            grouptgt(splittgt.out.tgtsplit_ch)
+            ch_fragm_tgt_out = grouptgt.out.tgtclst_ch
+        }
 
         // prepare pairs
-        pairs( ch_fragm_out, grouptgt.out.tgtclst_ch )
+        pairs( ch_fragm_src_out, ch_fragm_tgt_out )
         pairs.out.pairspath
             .splitCsv(header: ['srcname', 'srcfile', 'tgtname', 'tgtfile'])
             .map{ row-> tuple(row.srcname, row.srcfile, row.tgtname, row.tgtfile) }