Updating channels and assignments, removing unused channels

sanger-tol · Nov 21, 2023 · 41eefc4 · 41eefc4
1 parent 14b35e6
commit 41eefc4
Show file tree

Hide file tree

Showing 8 changed files with 108 additions and 86 deletions.
diff --git a/subworkflows/local/busco_annotation.nf b/subworkflows/local/busco_annotation.nf
@@ -23,7 +23,6 @@ workflow BUSCO_ANNOTATION {
     take:
     dot_genome           // channel: [val(meta), [ datafile ]]
     reference_tuple      // channel: [val(meta), [ datafile ]]
-    assembly_classT      // channel: val(class)
     lineageinfo          // channel: val(lineage_db)
     lineagespath         // channel: val(/path/to/buscoDB)
     buscogene_as         // channel: val(dot_as location)

diff --git a/subworkflows/local/gene_alignment.nf b/subworkflows/local/gene_alignment.nf
@@ -19,7 +19,6 @@ workflow GENE_ALIGNMENT {
     reference_tuple     // Channel [ val(meta), path(file) ]
     reference_index     // Channel [ val(meta), path(file) ]
     max_scaff_size      // Channel val(size of largest scaffold in bp)
-    assembly_classT     // Channel val(clade_id)
     alignment_datadir   // Channel val(geneset_dir)
     alignment_genesets  // Channel val(geneset_id)
     alignment_common    // Channel val(common_name) // Not yet in use
@@ -46,10 +45,10 @@ workflow GENE_ALIGNMENT {
     //
     ch_data
         .combine( alignment_datadir )
-        .combine( assembly_classT )
+        .combine( reference_tuple )
         .map {
-            ch_org, data_dir, classT ->
-                file("${data_dir}${classT}/csv_data/${ch_org}-data.csv")
+            ch_org, data_dir, meta, ref ->
+                file("${data_dir}${meta.class}/csv_data/${ch_org}-data.csv")
         }
         .splitCsv( header: true, sep:',')
         .map( row ->

diff --git a/subworkflows/local/generate_genome.nf b/subworkflows/local/generate_genome.nf
@@ -9,29 +9,17 @@ include { GET_LARGEST_SCAFF     } from '../../modules/local/get_largest_scaff'
 
 workflow GENERATE_GENOME {
     take:
-    assembly_id     // Channel val(assembly_id)
-    reference_file  // Channel path(file)
+    reference_ch    // tuple( [id: name] , file)
 
     main:
     ch_versions     = Channel.empty()
 
-    //
-    // LOGIC: GENERATES A REFERENCE DATA TUPLE
-    //
-    reference_file
-        .combine( assembly_id )
-        .map { file, sample_id ->
-            tuple ([id: sample_id],
-                    file)
-        }
-        .set { to_chromsize }
-
     //
     // MODULE: GENERATE INDEX OF REFERENCE
     //          EMITS REFERENCE INDEX FILE MODIFIED FOR SCAFF SIZES
     //
     CUSTOM_GETCHROMSIZES (
-        to_chromsize,
+        reference_ch,
         "temp.genome"
     )
     ch_versions     = ch_versions.mix(  CUSTOM_GETCHROMSIZES.out.versions )
@@ -56,6 +44,5 @@ workflow GENERATE_GENOME {
     max_scaff_size  = GET_LARGEST_SCAFF.out.scaff_size.toInteger()
     dot_genome      = GNU_SORT.out.sorted
     ref_index       = CUSTOM_GETCHROMSIZES.out.fai
-    reference_tuple = to_chromsize
     versions        = ch_versions.ifEmpty(null)
 }
diff --git a/subworkflows/local/insilico_digest.nf b/subworkflows/local/insilico_digest.nf
@@ -14,7 +14,6 @@ include { UCSC_BEDTOBIGBED              } from '../../modules/nf-core/ucsc/bedto
 
 workflow INSILICO_DIGEST {
     take:
-    myid            // Channel val(sample_id)
     sizefile        // Channel [ val(meta), path(my.genome_file) ]
     sample          // Channel [ val(meta), path(reference_file) ]
     ch_enzyme       // Channel val( "bspq1","bsss1","DLE1" )

diff --git a/subworkflows/local/kmer.nf b/subworkflows/local/kmer.nf
@@ -16,8 +16,8 @@ include { MERQURYFK_MERQURYFK } from '../../modules/nf-core/merquryfk/merquryfk/
 
 workflow KMER {
     take:
-    reference_tuple     // Channel [ val(meta), path(file) ]
-    reads_path          // Channel: [ val(meta), val( str ) ]
+    reference_tuple     // Channel: [ val( meta ), path( file ) ]
+    reads_path          // Channel: [ val( meta ), val( str ) ]
 
     main:
     ch_versions                 = Channel.empty()
@@ -52,31 +52,31 @@ workflow KMER {
     //
     CAT_CAT.out.file_out
         .map{ meta, reads ->
-            reads.getName().endsWith('gz') ? [meta, reads.getParent().toString() + '/' + reads.getBaseName().toString() + '.fa.gz'] : [meta, reads.getParent().toString() + '/' + reads.getBaseName().toString() + '.fa']
+                reads.getName().endsWith('gz') ? [meta, reads.getParent().toString() + '/' + reads.getBaseName().toString() + '.fa.gz'] : [meta, reads.getParent().toString() + '/' + reads.getBaseName().toString() + '.fa']
             }
         .set{ ch_reads_merged }
 
     //
     // LOGIC: PREPARE FASTK INPUT
     //
     CAT_CAT.out.file_out
-        .join(ch_reads_merged)
+        .join( ch_reads_merged )
         .map{ meta, reads_old, reads_new ->
-            reads_old.renameTo(reads_new);
+            reads_old.renameTo( reads_new );
         }
 
     //
     // MODULE: COUNT KMERS
     //
     FASTK_FASTK( ch_reads_merged )
-    ch_versions = ch_versions.mix(FASTK_FASTK.out.versions.first())
+    ch_versions = ch_versions.mix( FASTK_FASTK.out.versions.first() )
 
     //
     // LOGIC: PREPARE MERQURYFK INPUT
     //
     FASTK_FASTK.out.hist
-        .combine(FASTK_FASTK.out.ktab)
-        .combine(reference_tuple)
+        .combine( FASTK_FASTK.out.ktab )
+        .combine( reference_tuple )
         .map{ meta_hist, hist, meta_ktab, ktab, meta_ref, primary ->
             tuple( meta_hist, hist, ktab, primary, [])
         }
@@ -86,7 +86,7 @@ workflow KMER {
     // MODULE: USE KMER HISTOGRAM TO PRODUCE SPECTRA
     //
     MERQURYFK_MERQURYFK ( ch_merq )
-    ch_versions = ch_versions.mix(MERQURYFK_MERQURYFK.out.versions.first())
+    ch_versions = ch_versions.mix( MERQURYFK_MERQURYFK.out.versions.first() )
 
     emit:
     merquryk_completeness     = MERQURYFK_MERQURYFK.out.stats  // meta, stats

diff --git a/subworkflows/local/longread_coverage.nf b/subworkflows/local/longread_coverage.nf
@@ -39,7 +39,7 @@ workflow LONGREAD_COVERAGE {
     MINIMAP2_INDEX(
         reference_tuple
     )
-    ch_versions = ch_versions.mix( MINIMAP2_INDEX.out.versions )
+    ch_versions             = ch_versions.mix( MINIMAP2_INDEX.out.versions )
 
     //
     // LOGIC: PREPARE GET_READS_FROM_DIRECTORY INPUT
@@ -58,7 +58,7 @@ workflow LONGREAD_COVERAGE {
     //
     // MODULE: GETS PACBIO READ PATHS FROM READS_PATH
     //
-    ch_grabbed_read_paths       = GrabFiles( get_reads_input )
+    ch_grabbed_read_paths   = GrabFiles( get_reads_input )
 
     //
     // LOGIC: PACBIO READS FILES TO CHANNEL
@@ -126,8 +126,8 @@ workflow LONGREAD_COVERAGE {
         small.bool_cigar_paf,
         small.bool_cigar_bam
     )
-    ch_versions = ch_versions.mix(MINIMAP2_ALIGN.out.versions)
-    ch_align_bams = MINIMAP2_ALIGN.out.bam
+    ch_versions             = ch_versions.mix( MINIMAP2_ALIGN.out.versions )
+    ch_align_bams           = MINIMAP2_ALIGN.out.bam
 
     //
     // MODULE: ALIGN READS TO REFERENCE WHEN REFERENCE >5GB PER SCAFFOLD
@@ -139,7 +139,7 @@ workflow LONGREAD_COVERAGE {
         large.bool_cigar_paf,
         large.bool_cigar_bam
     )
-    ch_versions = ch_versions.mix(MINIMAP2_ALIGN_SPLIT.out.versions)
+    ch_versions             = ch_versions.mix( MINIMAP2_ALIGN_SPLIT.out.versions )
 
     //
     // LOGIC: COLLECT OUTPUTTED BAM FILES FROM BOTH PROCESSES
@@ -172,15 +172,15 @@ workflow LONGREAD_COVERAGE {
         reference_tuple,
         [[],[]]
     )
-    ch_versions = ch_versions.mix(SAMTOOLS_MERGE.out.versions)
+    ch_versions             = ch_versions.mix( SAMTOOLS_MERGE.out.versions )
 
     //
     // MODULE: SORT THE MERGED BAM BEFORE CONVERSION
     //
     SAMTOOLS_SORT (
         SAMTOOLS_MERGE.out.bam
     )
-    ch_versions = ch_versions.mix( SAMTOOLS_MERGE.out.versions )
+    ch_versions             = ch_versions.mix( SAMTOOLS_MERGE.out.versions )
 
     //
     // LOGIC: PREPARING MERGE INPUT WITH REFERENCE GENOME AND REFERENCE INDEX
@@ -209,15 +209,15 @@ workflow LONGREAD_COVERAGE {
         view_input.ref_input,
         []
     )
-    ch_versions = ch_versions.mix(SAMTOOLS_VIEW.out.versions)
+    ch_versions             = ch_versions.mix( SAMTOOLS_VIEW.out.versions )
 
     //
     // MODULE: BAM TO PRIMARY BED
     //
     BEDTOOLS_BAMTOBED(
         SAMTOOLS_VIEW.out.bam
     )
-    ch_versions = ch_versions.mix(BEDTOOLS_BAMTOBED.out.versions)
+    ch_versions             = ch_versions.mix( BEDTOOLS_BAMTOBED.out.versions )
 
     //
     // LOGIC: PREPARING Genome2Cov INPUT
@@ -244,48 +244,48 @@ workflow LONGREAD_COVERAGE {
         genomecov_input.dot_genome,
         genomecov_input.file_suffix
     )
-    ch_versions = ch_versions.mix(BEDTOOLS_GENOMECOV.out.versions)
+    ch_versions             = ch_versions.mix( BEDTOOLS_GENOMECOV.out.versions )
 
     //
     // MODULE: SORT THE PRIMARY BED FILE
     //
     GNU_SORT(
         BEDTOOLS_GENOMECOV.out.genomecov
     )
-    ch_versions = ch_versions.mix(GNU_SORT.out.versions)
+    ch_versions             = ch_versions.mix( GNU_SORT.out.versions )
 
     //
     // MODULE: get_minmax_punches
     //
     GETMINMAXPUNCHES(
         GNU_SORT.out.sorted
     )
-    ch_versions = ch_versions.mix(GETMINMAXPUNCHES.out.versions)
+    ch_versions         = ch_versions.mix( GETMINMAXPUNCHES.out.versions)
 
     //
     // MODULE: get_minmax_punches
     //
     BEDTOOLS_MERGE_MAX(
         GETMINMAXPUNCHES.out.max
     )
-    ch_versions = ch_versions.mix(BEDTOOLS_MERGE_MAX.out.versions)
+    ch_versions             = ch_versions.mix( BEDTOOLS_MERGE_MAX.out.versions )
 
     //
     // MODULE: get_minmax_punches
     //
     BEDTOOLS_MERGE_MIN(
         GETMINMAXPUNCHES.out.min
     )
-    ch_versions = ch_versions.mix(BEDTOOLS_MERGE_MIN.out.versions)
+    ch_versions             = ch_versions.mix( BEDTOOLS_MERGE_MIN.out.versions )
 
     //
     // MODULE: GENERATE DEPTHGRAPH
     //
     GRAPHOVERALLCOVERAGE(
         GNU_SORT.out.sorted
     )
-    ch_versions = ch_versions.mix(GRAPHOVERALLCOVERAGE.out.versions)
-    ch_depthgraph = GRAPHOVERALLCOVERAGE.out.part
+    ch_versions             = ch_versions.mix( GRAPHOVERALLCOVERAGE.out.versions )
+    ch_depthgraph           = GRAPHOVERALLCOVERAGE.out.part
 
     //
     // LOGIC: PREPARING FINDHALFCOVERAGE INPUT
@@ -308,7 +308,7 @@ workflow LONGREAD_COVERAGE {
         halfcov_input.genome_file,
         halfcov_input.depthgraph_file
     )
-    ch_versions = ch_versions.mix(FINDHALFCOVERAGE.out.versions)
+    ch_versions             = ch_versions.mix(FINDHALFCOVERAGE.out.versions)
 
     //
     // LOGIC: PREPARING NORMAL COVERAGE INPUT
@@ -329,15 +329,15 @@ workflow LONGREAD_COVERAGE {
         bed2bw_normal_input.ch_coverage_bed,
         bed2bw_normal_input.genome_file
     )
-    ch_versions = ch_versions.mix(BED2BW_NORMAL.out.versions)
+    ch_versions             = ch_versions.mix(BED2BW_NORMAL.out.versions)
 
     //
     // MODULE: CONVERT COVERAGE TO LOG2
     //
     LONGREADCOVERAGESCALELOG2(
         GNU_SORT.out.sorted
     )
-    ch_versions = ch_versions.mix(LONGREADCOVERAGESCALELOG2.out.versions)
+    ch_versions             = ch_versions.mix(LONGREADCOVERAGESCALELOG2.out.versions)
 
     //
     // LOGIC: PREPARING LOG2 COVERAGE INPUT
@@ -358,13 +358,11 @@ workflow LONGREAD_COVERAGE {
         bed2bw_log2_input.ch_coverage_bed,
         bed2bw_log2_input.genome_file
     )
-    ch_versions = ch_versions.mix(BED2BW_LOG2.out.versions)
+    ch_versions             = ch_versions.mix(BED2BW_LOG2.out.versions)
 
     //
     // LOGIC: GENERATE A SUMMARY TUPLE FOR OUTPUT
     //
-    ch_grabbed_read_paths.map{ it }
-
     ch_grabbed_read_paths
             .collect()
             .map { meta, fasta ->
@@ -376,13 +374,13 @@ workflow LONGREAD_COVERAGE {
             .set { ch_reporting_pacbio }
 
     emit:
-    ch_minbed       = BEDTOOLS_MERGE_MIN.out.bed
-    ch_halfbed      = FINDHALFCOVERAGE.out.bed
-    ch_maxbed       = BEDTOOLS_MERGE_MAX.out.bed
-    ch_reporting    = ch_reporting_pacbio.collect()
-    ch_covbw_nor    = BED2BW_NORMAL.out.bigwig
-    ch_covbw_log    = BED2BW_LOG2.out.bigwig
-    versions        = ch_versions
+    ch_minbed               = BEDTOOLS_MERGE_MIN.out.bed
+    ch_halfbed              = FINDHALFCOVERAGE.out.bed
+    ch_maxbed               = BEDTOOLS_MERGE_MAX.out.bed
+    ch_reporting            = ch_reporting_pacbio.collect()
+    ch_covbw_nor            = BED2BW_NORMAL.out.bigwig
+    ch_covbw_log            = BED2BW_LOG2.out.bigwig
+    versions                = ch_versions
 }
 
 process GrabFiles {

diff --git a/subworkflows/local/synteny.nf b/subworkflows/local/synteny.nf
@@ -10,7 +10,6 @@ workflow SYNTENY {
     take:
     reference_tuple     // Channel [ val(meta), path(file) ]
     synteny_path        // Channel val(meta)
-    assembly_classT     // Channel val(meta)
 
     main:
     ch_versions                 = Channel.empty()
@@ -19,9 +18,15 @@ workflow SYNTENY {
     // MODULE: SEARCHES PREDETERMINED PATH FOR SYNTENIC GENOME FILES BASED ON CLASS
     //         EMITS PATH LIST
     //
+    reference_ch
+        .map{meta, file ->
+            meta.class
+        }
+        .set { defined_class }
+
     GET_SYNTENY_GENOMES(
         synteny_path,
-        assembly_classT
+        defined_class
     )
     ch_versions                 = ch_versions.mix( GET_SYNTENY_GENOMES.out.versions )