Fix output channels allow BLAST table customisation

modules/diamond/blastp/main.nf

@@ -11,10 +11,17 @@ process DIAMOND_BLASTP {
     tuple val(meta), path(fasta)
     path db
     val outext
+    val blast_columns
 
     output:
-    tuple val(meta), path('*.{blast,xml,txt,daa,sam,tsv,paf}'), emit: output
+    tuple val(meta), path('*.{blast}'), optional: true, emit: blast
-    path "versions.yml"           , emit: versions
+    tuple val(meta), path('*.{xml}')  , optional: true, emit: xml
+    tuple val(meta), path('*.{txt}')  , optional: true, emit: txt
+    tuple val(meta), path('*.{daa}')  , optional: true, emit: daa
+    tuple val(meta), path('*.{sam}')  , optional: true, emit: sam
+    tuple val(meta), path('*.{tsv}')  , optional: true, emit: tsv
+    tuple val(meta), path('*.{paf}')  , optional: true, emit: paf
+    path "versions.yml"               , emit: versions
 
     when:
     task.ext.when == null || task.ext.when
@@ -22,6 +29,7 @@ process DIAMOND_BLASTP {
     script:
     def args = task.ext.args ?: ''
     def prefix = task.ext.prefix ?: "${meta.id}"
+    def columns = blast_columns ? "${blast_columns}" : ''
     switch ( outext ) {
         case "blast": outfmt = 0; break
         case "xml": outfmt = 5; break
@@ -39,7 +47,7 @@ process DIAMOND_BLASTP {
         --threads $task.cpus \\
         --db \$DB \\
         --query $fasta \\
-        --outfmt ${outfmt} \\
+        --outfmt ${outfmt} ${columns} \\
         $args \\
         --out ${prefix}.${outext}
 

modules/diamond/blastp/meta.yml

@@ -36,12 +36,42 @@ input:
         `txt` corresponds to to BLAST tabular format. `tsv` corresponds to
         taxonomic classification format.
       pattern: "blast|xml|txt|daa|sam|tsv|paf"
+  - blast_columns:
+      type: string
+      description: |
+        Optional space separated list of DIAMOND tabular BLAST output keywords
+        used for in conjunction with the 'txt' outext option (--outfmt 6). See
+        DIAMOND documnetation for more information.
 
 output:
-  - txt:
+  - blast:
       type: file
       description: File containing blastp hits
-      pattern: "*.{blastp.txt}"
+      pattern: "*.{blast}"
+  - xml:
+      type: file
+      description: File containing blastp hits
+      pattern: "*.{xml}"
+  - txt:
+      type: file
+      description: File containing hits in tabular BLAST format.
+      pattern: "*.{txt}"
+  - daa:
+      type: file
+      description: File containing hits DAA format
+      pattern: "*.{daa}"
+  - sam:
+      type: file
+      description: File containing aligned reads in SAM format
+      pattern: "*.{sam}"
+  - tsv:
+      type: file
+      description: Tab separated file containing taxonomic classification of hits
+      pattern: "*.{tsv}"
+  - paf:
+      type: file
+      description: File containing aligned reads in pairwise mapping format format
+      pattern: "*.{paf}"
   - versions:
       type: file
       description: File containing software versions

modules/diamond/blastx/main.nf

@@ -11,10 +11,17 @@ process DIAMOND_BLASTX {
     tuple val(meta), path(fasta)
     path db
     val outext
+    val blast_columns
 
     output:
-    tuple val(meta), path('*.{blast,xml,txt,daa,sam,tsv,paf}'), emit: output
+    tuple val(meta), path('*.{blast}'), optional: true, emit: blast
-    path "versions.yml"           , emit: versions
+    tuple val(meta), path('*.{xml}')  , optional: true, emit: xml
+    tuple val(meta), path('*.{txt}')  , optional: true, emit: txt
+    tuple val(meta), path('*.{daa}')  , optional: true, emit: daa
+    tuple val(meta), path('*.{sam}')  , optional: true, emit: sam
+    tuple val(meta), path('*.{tsv}')  , optional: true, emit: tsv
+    tuple val(meta), path('*.{paf}')  , optional: true, emit: paf
+    path "versions.yml"                               , emit: versions
 
     when:
     task.ext.when == null || task.ext.when
@@ -22,6 +29,7 @@ process DIAMOND_BLASTX {
     script:
     def args = task.ext.args ?: ''
     def prefix = task.ext.prefix ?: "${meta.id}"
+    def columns = blast_columns ? "${blast_columns}" : ''
     switch ( outext ) {
         case "blast": outfmt = 0; break
         case "xml": outfmt = 5; break
@@ -39,7 +47,7 @@ process DIAMOND_BLASTX {
         --threads $task.cpus \\
         --db \$DB \\
         --query $fasta \\
-        --outfmt ${outfmt} \\
+        --outfmt ${outfmt} ${columns} \\
         $args \\
         --out ${prefix}.${outext}
 

modules/diamond/blastx/meta.yml

@@ -38,10 +38,34 @@ input:
       pattern: "blast|xml|txt|daa|sam|tsv|paf"
 
 output:
+  - blast:
+      type: file
+      description: File containing blastp hits
+      pattern: "*.{blast}"
+  - xml:
+      type: file
+      description: File containing blastp hits
+      pattern: "*.{xml}"
   - txt:
       type: file
-      description: File containing blastx hits
+      description: File containing hits in tabular BLAST format.
-      pattern: "*.{blastx.txt}"
+      pattern: "*.{txt}"
+  - daa:
+      type: file
+      description: File containing hits DAA format
+      pattern: "*.{daa}"
+  - sam:
+      type: file
+      description: File containing aligned reads in SAM format
+      pattern: "*.{sam}"
+  - tsv:
+      type: file
+      description: Tab separated file containing taxonomic classification of hits
+      pattern: "*.{tsv}"
+  - paf:
+      type: file
+      description: File containing aligned reads in pairwise mapping format format
+      pattern: "*.{paf}"
   - versions:
       type: file
       description: File containing software versions

tests/modules/diamond/blastp/main.nf

@@ -10,9 +10,10 @@ workflow test_diamond_blastp {
     db = [ file(params.test_data['sarscov2']['genome']['proteome_fasta'], checkIfExists: true) ]
     fasta = [ file(params.test_data['sarscov2']['genome']['proteome_fasta'], checkIfExists: true) ]
     outext = 'txt'
+    blast_columns = 'qseqid qlen'
 
     DIAMOND_MAKEDB ( db )
-    DIAMOND_BLASTP ( [ [id:'test'], fasta ], DIAMOND_MAKEDB.out.db, outext )
+    DIAMOND_BLASTP ( [ [id:'test'], fasta ], DIAMOND_MAKEDB.out.db, outext, blast_columns )
 }
 
 workflow test_diamond_blastp_daa {
@@ -20,7 +21,8 @@ workflow test_diamond_blastp_daa {
     db = [ file(params.test_data['sarscov2']['genome']['proteome_fasta'], checkIfExists: true) ]
     fasta = [ file(params.test_data['sarscov2']['genome']['proteome_fasta'], checkIfExists: true) ]
     outext = 'daa'
+    blast_columns = []
 
     DIAMOND_MAKEDB ( db )
-    DIAMOND_BLASTP ( [ [id:'test'], fasta ], DIAMOND_MAKEDB.out.db, outext )
+    DIAMOND_BLASTP ( [ [id:'test'], fasta ], DIAMOND_MAKEDB.out.db, outext, blast_columns )
 }

tests/modules/diamond/blastx/main.nf

@@ -10,9 +10,10 @@ workflow test_diamond_blastx {
     db = [ file(params.test_data['sarscov2']['genome']['proteome_fasta'], checkIfExists: true) ]
     fasta = [ file(params.test_data['sarscov2']['genome']['transcriptome_fasta'], checkIfExists: true) ]
     outext = 'txt'
+    blast_columns = 'qseqid qlen'
 
     DIAMOND_MAKEDB ( db )
-    DIAMOND_BLASTX ( [ [id:'test'], fasta ], DIAMOND_MAKEDB.out.db, outext )
+    DIAMOND_BLASTX ( [ [id:'test'], fasta ], DIAMOND_MAKEDB.out.db, outext, blast_columns )
 }
 
 workflow test_diamond_blastx_daa {
@@ -20,7 +21,8 @@ workflow test_diamond_blastx_daa {
     db = [ file(params.test_data['sarscov2']['genome']['proteome_fasta'], checkIfExists: true) ]
     fasta = [ file(params.test_data['sarscov2']['genome']['transcriptome_fasta'], checkIfExists: true) ]
     outext = 'daa'
+    blast_columns = []
 
     DIAMOND_MAKEDB ( db )
-    DIAMOND_BLASTX ( [ [id:'test'], fasta ], DIAMOND_MAKEDB.out.db, outext )
+    DIAMOND_BLASTX ( [ [id:'test'], fasta ], DIAMOND_MAKEDB.out.db, outext, blast_columns )
 }