Path object updates and other fixes

conf/modules.config

@@ -104,7 +104,7 @@ process {
     }
 
     withName: 'GAWK_RENAME_IDS' {
-        ext.args2 = "'{ gsub(/\\./, \"0\"); print}'"
+        ext.args2  = "'{ gsub(/\\./, \"0\"); print}'"
         ext.prefix = { "${meta.id}_renamed" }
         ext.suffix = 'bed'
     }

modules/local/extract/ancestral/main.nf

@@ -38,7 +38,7 @@ process EXTRACT_ANCESTRAL {
     def prefix  = task.ext.prefix   ?: "${meta.id}"
     """
     touch ${prefix}_buscopainter_complete_location.tsv
-    touch ${prefox}_buscopainter_duplicated_location.tsv
+    touch ${prefix}_buscopainter_duplicated_location.tsv
     touch ${prefix}_summary.tsv
 
     cat <<-END_VERSIONS > versions.yml

subworkflows/local/ancestral_gene/main.nf

@@ -10,40 +10,29 @@ include { UCSC_BEDTOBIGBED   } from '../../../modules/nf-core/ucsc/bedtobigbed/m
 
 workflow ANCESTRAL_GENE {
     take:
-    busco_dir            // Channel: tuple [val(meta),/path/to/busco/output/dir]
+    busco_full_table     // Channel: tuple [val(meta),/path/to/busco/output/**/fulltable.tsv ]
     dot_genome           // Channel: tuple [val(meta), [ datafile ]]
     buscogene_as         // Channel: val(dot_as location)
     ancestral_table      // Channel: val(ancestral_table location)
 
     main:
     ch_versions             = Channel.empty()
 
-    ch_grab                 = GrabFiles(busco_dir)
-
     //
     // MODULE: EXTRACTS ANCESTRALLY LINKED BUSCO GENES FROM FULL TABLE
     //
     EXTRACT_ANCESTRAL(
-        ch_grab,
+        busco_full_table,
         ancestral_table
     )
     ch_versions             = ch_versions.mix(EXTRACT_ANCESTRAL.out.versions)
 
-    //
-    // LOGIC: STRIP OUT METADATA
-    //
-    ch_grab
-        .map { meta, fulltable
-                -> fulltable
-            }
-        .set { assignanc_input }
-
     //
     // MODULE: ASSIGN EXTRACTED GENES TO ANCESTRAL GROUPS
     //
     ASSIGN_ANCESTRAL(
         EXTRACT_ANCESTRAL.out.comp_location,
-        assignanc_input
+        busco_full_table.map { _meta, fulltable -> fulltable }
     )
     ch_versions             = ch_versions.mix(EXTRACT_ANCESTRAL.out.versions)
 
@@ -70,17 +59,3 @@ workflow ANCESTRAL_GENE {
     ch_ancestral_bigbed     = UCSC_BEDTOBIGBED.out.bigbed
     versions                = ch_versions
 }
-process GrabFiles {
-    label 'process_tiny'
-
-    tag "${meta.id}"
-    executor 'local'
-
-    input:
-    tuple val(meta), path("in")
-
-    output:
-    tuple val(meta), path("in/*/*/full_table.tsv")
-
-    "true"
-}

subworkflows/local/busco_annotation/main.nf

@@ -30,30 +30,26 @@ workflow BUSCO_ANNOTATION {
     main:
     ch_versions                 = Channel.empty()
 
-    // COMMENT: Set BUSCO mode to 'genome'
-    ch_busco_mode         = Channel.of( "genome" )
-
-
     //
     // MODULE: RUN BUSCO TO OBTAIN FULL_TABLE.CSV
     //         EMITS FULL_TABLE.CSV
     //
     BUSCO_BUSCO (
         reference_tuple,
-        ch_busco_mode,
+        "genome",
         lineageinfo,
         lineagespath,
         []
     )
-    ch_versions                 = ch_versions.mix(BUSCO_BUSCO.out.versions.first())
-    ch_grab                     = GrabFiles(BUSCO_BUSCO.out.busco_dir)
+    ch_versions          = ch_versions.mix(BUSCO_BUSCO.out.versions.first())
+    ch_busco_full_table  = BUSCO_BUSCO.out.busco_dir.map { meta, dir -> tuple(meta, files(dir.resolve("*/*/full_table.tsv"), checkIfExists: true)) }
 
 
     //
     // MODULE: EXTRACT THE BUSCO GENES FOUND IN REFERENCE
     //
     GAWK_EXTRACT_BUSCOGENE (
-        ch_grab,
+        ch_busco_full_table,
         file("${projectDir}/bin/get_busco_gene.awk"),
         false
     )
@@ -92,33 +88,22 @@ workflow BUSCO_ANNOTATION {
     ch_versions                 = ch_versions.mix( UCSC_BEDTOBIGBED.out.versions )
 
     //
-    // LOGIC: AGGREGATE DATA AND SORT BRANCH ON CLASS
+    // SUBWORKFLOW: RUN ANCESTRAL BUSCO ID (ONLY AVAILABLE FOR LEPIDOPTERA)
+    // LOGIC: AGGREGATE DATA AND FILTER ON CLASS
     //
     lineageinfo
-        .combine(BUSCO_BUSCO.out.busco_dir)
+        .combine(ch_busco_full_table)
         .combine(ancestral_table)
-        .branch {
-            lep:     it[0].split('_')[0] == "lepidoptera"
-            general: it[0].split('_')[0] != "lepidoptera"
+        .filter { lineage, _meta, _btable, _atable ->
+            lineage.split('_')[0] == "lepidoptera"
         }
-        .set{ ch_busco_data }
-
-    //
-    // LOGIC: BUILD NEW INPUT CHANNEL FOR ANCESTRAL ID
-    //
-    ch_busco_data
-            .lep
-            .multiMap { lineage, meta, busco_dir, ancestral_table ->
-                busco_dir:    tuple( meta, busco_dir )
-                atable:       ancestral_table
-            }
-            .set{ ch_busco_lep_data }
-
-    //
-    // SUBWORKFLOW: RUN ANCESTRAL BUSCO ID (ONLY AVAILABLE FOR LEPIDOPTERA)
-    //
+        .multiMap { _lineage, meta, busco_full_table, ancestral_table_ ->
+            busco_table: tuple( meta, busco_full_table )
+            atable:      ancestral_table_
+        }
+        .set{ ch_busco_lep_data }
     ANCESTRAL_GENE (
-        ch_busco_lep_data.busco_dir,
+        ch_busco_lep_data.busco_table,
         dot_genome,
         buscogene_as,
         ch_busco_lep_data.atable
@@ -131,17 +116,3 @@ workflow BUSCO_ANNOTATION {
     versions                    = ch_versions
 
 }
-process GrabFiles {
-    label 'process_tiny'
-
-    tag "${meta.id}"
-    executor 'local'
-
-    input:
-    tuple val(meta), path("in")
-
-    output:
-    tuple val(meta), path("in/*/*/full_table.tsv")
-
-    "true"
-}

subworkflows/local/gene_alignment/main.nf

@@ -18,7 +18,7 @@ workflow GENE_ALIGNMENT {
     dot_genome          // Channel: [ val(meta), path(file) ]
     reference_tuple     // Channel: [ val(meta), path(file) ]
     reference_index     // Channel: [ val(meta), path(file) ]
-    alignment_genesets  // Channel: val(geneset_id)
+    alignment_genesets  // Channel: [ path(geneset_csv) ]
     intron_size         // Channel: val(50k)
     as_files            // Channel: [ val(meta), path(file) ]
 
@@ -37,7 +37,7 @@ workflow GENE_ALIGNMENT {
     //          LIST IS MERGED WITH DATA_DIRECTORY AND ORGANISM_CLASS
     //
     ch_data             = alignment_genesets
-                            .splitCsv()
+                            // .splitCsv()
                             .flatten()
 
     //
@@ -48,18 +48,19 @@ workflow GENE_ALIGNMENT {
     //          SUBWORKFLOW
     //
     ch_data
-        .map {
-            geneset_path ->
-                file(geneset_path)
-        }
+        // .map {
+        //     geneset_path ->
+        //         file(geneset_path)
+        // }
         .splitCsv( header: true, sep:',')
-        .map( row ->
-        tuple([ org:    row.org,
-                type:   row.type,
-                id:     row.data_file.split('/')[-1].split('.MOD.')[0]
-            ],
-            file(row.data_file)
-        ))
+        .map{ row ->
+            def data_file = file(row.data_file, checkIfExists: true)
+            tuple([ org:    row.org,
+                    type:   row.type,
+                    id:     data_file.name.split('.MOD.').first()
+                ],
+                data_file
+            )}
         .branch {
             pep: it[0].type  == 'pep'
             gen: it[0].type  == 'cdna'

subworkflows/local/hic_mapping/main.nf

@@ -170,10 +170,10 @@ workflow HIC_MAPPING {
     //
     PRETEXT_INGEST_SNDRD (
         PRETEXTMAP_STANDRD.out.pretext,
-        gap_file.map{it -> it[1]},
-        coverage_file.map{it -> it[1]},
-        telo_file.map{it -> it[1]},
-        repeat_density_file.map{it -> it[1]}
+        gap_file.map{ _meta, gapfile -> gapfile },
+        coverage_file.map{ _meta, covfile -> covfile },
+        telo_file.map{ _meta, telofile -> telofile },
+        repeat_density_file.map{ _meta, rdfile -> rdfile }
     )
     ch_versions         = ch_versions.mix( PRETEXT_INGEST_SNDRD.out.versions )
 
@@ -199,10 +199,10 @@ workflow HIC_MAPPING {
 
         PRETEXT_INGEST_HIRES (
             PRETEXTMAP_HIGHRES.out.pretext,
-            gap_file,
-            coverage_file,
-            telo_file,
-            repeat_density_file
+            gap_file.map{ _meta, gapfile -> gapfile },
+            coverage_file.map{ _meta, covfile -> covfile },
+            telo_file.map{ _meta, telofile -> telofile },
+            repeat_density_file.map{ _meta, rdfile -> rdfile }
         )
         ch_versions         = ch_versions.mix( PRETEXT_INGEST_HIRES.out.versions )
         hires_pretext       = PRETEXT_INGEST_HIRES.out.pretext

subworkflows/local/kmer/main.nf

@@ -35,7 +35,6 @@ workflow KMER {
         }
         .set { get_reads_input }
 
-
     //
     // MODULE: JOIN PACBIO READ
     //

subworkflows/local/synteny/main.nf

@@ -8,26 +8,26 @@ include { MINIMAP2_ALIGN        } from '../../../modules/nf-core/minimap2/align/
 workflow SYNTENY {
     take:
     reference_tuple             // Channel: tuple [ val(meta), path(file) ]
-    synteny_paths               // Channel: val(meta)
+    synteny_paths               // Channel: List [ path(file) ]
 
     main:
     ch_versions                 = Channel.empty()
 
     ch_data             = synteny_paths
-                            .splitCsv()
+                            // .splitCsv()
                             .flatten()
 
     //
     // LOGIC: PULL SYNTENIC GENOMES FROM DIRECTORY STRUCTURE
     //          AND PARSE INTO CHANNEL PER GENOME
     //
     ch_data
-        .map{synteny_path ->
-            file(synteny_path)
-        }
+        // .map{synteny_path ->
+        //     file(synteny_path)
+        // }
         .combine(reference_tuple)
         .multiMap{syntenic_ref, meta, ref ->
-            syntenic_tuple  : tuple([ id: syntenic_ref.toString().split('/')[-1].split(/\.fa(sta)?/)[0],
+            syntenic_tuple  : tuple([ id: syntenic_ref.baseName,
                                         class: meta.class,
                                         project_type: meta.project_type
                                     ],