Merge pull request #196 from apeltzer/dev

Fix remaining issues with indices for non-fasta endings

Author: apeltzer

CHANGELOG.md

@@ -18,7 +18,8 @@ and this project adheres to [Semantic Versioning](http://semver.org/spec/v2.0.0.
 * [#176](https://github.com/nf-core/eager/pull/176) - Increase runtime for DamageProfiler on [large reference genomes](https://github.com/nf-core/eager/issues/173)
 * [#172](https://github.com/nf-core/eager/pull/152) - DamageProfiler errors [won't crash entire pipeline anymore](https://github.com/nf-core/eager/issues/171)
 * [#174](https://github.com/nf-core/eager/pull/190) - Publish DeDup files [properly](https://github.com/nf-core/eager/issues/183)
-* TBF - Fix reference [issues](https://github.com/nf-core/eager/issues/150)
+* [#196](https://github.com/nf-core/eager/pull/190) - Fix reference [issues](https://github.com/nf-core/eager/issues/150)
+* [#196](https://github.com/nf-core/eager/pull/190) - Fix issues with PE data being mapped incompletely
 
 ### `Dependencies`
 

main.nf

@@ -245,9 +245,10 @@ if("${params.fasta}".endsWith(".gz")){
         file zipped_fasta
 
         output:
-        file "*.fasta" into fasta_for_indexing
+        file "*.{fa,fn,fna,fasta}" into fasta_for_indexing
 
         script:
+        rm_zip = zipped_fasta - '.gz'
         """
         pigz -f -d -p ${task.cpus} $zipped_fasta
         """
@@ -486,13 +487,12 @@ process makeFastaIndex {
     file where_are_my_files
 
     output:
-    file "${base}.fasta.fai" into ch_fasta_faidx_index
+    file "*.fai" into ch_fasta_faidx_index
     file "where_are_my_files.txt"
 
     script:
-    base = "${fasta.baseName}"
     """
-    samtools faidx "${base}.fasta"
+    samtools faidx $fasta
     """
 }
 
@@ -516,16 +516,12 @@ process makeSeqDict {
     file where_are_my_files
 
     output:
-    file "seq_dict/*.dict" into ch_seq_dict
+    file "*.dict" into ch_seq_dict
     file "where_are_my_files.txt"
 
     script:
-    base = "${fasta.baseName}.fasta"
     """
-    mkdir -p seq_dict
-    mv $fasta "seq_dict/${base}"
-    cd seq_dict
-    picard -Xmx${task.memory.toMega()}M -Xms${task.memory.toMega()}M CreateSequenceDictionary R=$base O="${fasta.baseName}.dict"
+    picard -Xmx${task.memory.toMega()}M -Xms${task.memory.toMega()}M CreateSequenceDictionary R=$fasta O="${fasta.baseName}.dict"
     """
 }
 
@@ -679,7 +675,7 @@ process adapter_removal {
 * STEP 2.1 - FastQC after clipping/merging (if applied!)
 */
 process fastqc_after_clipping {
-    tag "${prefix}"
+    tag "${name}"
     publishDir "${params.outdir}/FastQC/after_clipping", mode: 'copy',
         saveAs: {filename -> filename.indexOf(".zip") > 0 ? "zips/$filename" : "$filename"}
 
@@ -692,7 +688,6 @@ process fastqc_after_clipping {
     file "*_fastqc.{zip,html}" optional true into ch_fastqc_after_clipping
 
     script:
-    prefix = reads[0].toString().tokenize('.')[0]
     """
     fastqc -q $reads
     """
@@ -703,7 +698,7 @@ Step 3: Mapping with BWA, SAM to BAM, Sort BAM
 */
 
 process bwa {
-    tag "$prefix"
+    tag "${name}"
     publishDir "${params.outdir}/mapping/bwa", mode: 'copy'
 
     when: !params.circularmapper && !params.bwamem
@@ -723,8 +718,8 @@ process bwa {
     fasta = "${index}/${bwa_base}"
 
     //PE data without merging, PE data without any AR applied
-    if (!params.singleEnd && (params.skip_collapse || params.skip_adapterremoval)){
-    prefix = reads[0].toString().tokenize('.')[0]
+    if (!params.singleEnd && (params.skip_collapse || params.skip_adapterremoval || params.skip_trim)){
+    prefix = "${reads[0].baseName}"
     """
     bwa aln -t ${task.cpus} $fasta ${reads[0]} -n ${params.bwaalnn} -l ${params.bwaalnl} -k ${params.bwaalnk} -f ${prefix}.r1.sai
     bwa aln -t ${task.cpus} $fasta ${reads[1]} -n ${params.bwaalnn} -l ${params.bwaalnl} -k ${params.bwaalnk} -f ${prefix}.r2.sai
@@ -733,7 +728,7 @@ process bwa {
     """
     } else {
     //PE collapsed, or SE data 
-    prefix = reads[0].toString().tokenize('.')[0]
+    prefix = "${reads}.baseName}"
     """
     bwa aln -t ${task.cpus} $fasta $reads -n ${params.bwaalnn} -l ${params.bwaalnl} -k ${params.bwaalnk} -f ${prefix}.sai
     bwa samse -r "@RG\\tID:ILLUMINA-${prefix}\\tSM:${prefix}\\tPL:illumina" $fasta ${prefix}.sai $reads | samtools sort -@ ${task.cpus} -O bam - > "${prefix}".sorted.bam