Bump seqwish/induce to v0.7.6 (#2083)

* Update seqwish to version 0.7.2

* seqwish can work with a comma-separated list of PAFs

* level with nf-core/modules master branch

* update seqwish/induce to v0.7.6

* add pangenome test data

* test seqwish/induce v0.7.6 with pangenomics test data

* we already have pointed to the pangenomics test data sets

* update paths to test data

* add path to bgzipped fa, gzi, fai

* remove one tab

* remove one tab

* actually execute the 2nd test

* try to fix versions.yml

* pangenomic tests can be run in their own subworkflow

* maybe the csv input is the problem

* remove space as suggested by Rike

* csv input was not the problem

* update test.yml

* typo

* enable pangenome tests

* add md5sum for pangenomic test

* Update tests/modules/seqwish/induce/test.yml

Co-authored-by: Gisela Gabernet <gisela.gabernet@gmail.com>

* PAF input is a list of files

* beautify comment

Co-authored-by: Michael L Heuer <heuermh@acm.org>
Co-authored-by: Gisela Gabernet <gisela.gabernet@gmail.com>
Co-authored-by: Simon Pearce <24893913+SPPearce@users.noreply.github.com>

modules/seqwish/induce/main.nf

@@ -2,11 +2,11 @@ process SEQWISH_INDUCE {
     tag "$meta.id"
     label 'process_medium'
 
-    // WARN: Version information not provided by tool on CLI. Please update version string below when bumping container versions.
+    conda (params.enable_conda ? 'bioconda::seqwish=0.7.6' : null)
-    conda (params.enable_conda ? 'bioconda::seqwish=0.7.2' : null)
+
     container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
-        'https://depot.galaxyproject.org/singularity/seqwish:0.7.2--h2e03b76_0' :
+        'https://depot.galaxyproject.org/singularity/seqwish:0.7.6--h5b5514e_1' :
-        'quay.io/biocontainers/seqwish:0.7.2--h2e03b76_0' }"
+        'quay.io/biocontainers/seqwish:0.7.6--h5b5514e_1' }"
 
     input:
     tuple val(meta), path(paf), path(fasta)
@@ -21,18 +21,23 @@ process SEQWISH_INDUCE {
     script:
     def args = task.ext.args ?: ''
     def prefix = task.ext.prefix ?: "${meta.id}"
-    def VERSION = '0.7.2' // WARN: Version information not provided by tool on CLI. Please update this string when bumping container versions.
+    def input = paf.join(',') // this ensures that we can actually input a
+        // comma-separated list of PAF files as required by
+        // https://github.com/nf-core/pangenome. If one wants to use this,
+        // ensure that you put a ".collect()" behind your channel.
+        // See https://github.com/nf-core/pangenome/blob/34149c6cdc19bce3a7b99f97c769d8986a8d429b/main.nf#L543
+        // for an example.
     """
     seqwish \\
         --threads $task.cpus \\
-        --paf-alns=$paf \\
+        --paf-alns=$input \\
         --seqs=$fasta \\
         --gfa=${prefix}.gfa \\
         $args
 
     cat <<-END_VERSIONS > versions.yml
     "${task.process}":
-        seqwish: $VERSION
+        seqwish: \$(echo \$(seqwish --version 2>&1) | cut -f 1 -d '-' | cut -f 2 -d 'v')
     END_VERSIONS
     """
 }

modules/seqwish/induce/meta.yml

@@ -21,9 +21,9 @@ input:
         Groovy Map containing sample information
         e.g. [ id:'test', single_end:false ]
   - paf:
-      type: file
+      type: list
-      description: PAF file of alignments
+      description: comma-separated PAF file(s) of alignments, single entry allowed
-      pattern: "*.{paf,paf.gz}"
+      pattern: "[*.{paf,paf.gz},*.{paf,paf.gz},...]"
   - fasta:
       type: file
       description: FASTA file used to generate alignments

tests/config/test_data.config

@@ -194,7 +194,9 @@ params {
             }
             'pangenome' {
                 pangenome_fa                                   = "${test_data_dir}/pangenomics/homo_sapiens/pangenome.fa"
-                pangenome_fa_gz                                = "${test_data_dir}/pangenomics/homo_sapiens/pangenome.fa.gz"
+                pangenome_fa_bgzip                             = "${test_data_dir}/pangenomics/homo_sapiens/pangenome.fa.gz"
+                pangenome_fa_bgzip_fai                         = "${test_data_dir}/pangenomics/homo_sapiens/pangenome.fa.gz.fai"
+                pangenome_fa_bgzip_gzi                         = "${test_data_dir}/pangenomics/homo_sapiens/pangenome.fa.gz.gzi"
                 pangenome_paf                                  = "${test_data_dir}/pangenomics/homo_sapiens/pangenome.paf"
                 pangenome_paf_gz                               = "${test_data_dir}/pangenomics/homo_sapiens/pangenome.paf.gz"
                 pangenome_seqwish_gfa                          = "${test_data_dir}/pangenomics/homo_sapiens/pangenome.seqwish.gfa"

tests/modules/seqwish/induce/main.nf

@@ -4,7 +4,7 @@ nextflow.enable.dsl = 2
 
 include { SEQWISH_INDUCE } from '../../../../modules/seqwish/induce/main.nf'
 
-workflow test_seqwish_induce {
+workflow test_seqwish_induce_transcriptome {
     input = [ [ id:'test' ], // meta map
               [ file(params.test_data['sarscov2']['genome']['transcriptome_paf'], checkIfExists: true)],
               [ file(params.test_data['sarscov2']['genome']['transcriptome_fasta'], checkIfExists: true) ]
@@ -12,3 +12,12 @@ workflow test_seqwish_induce {
 
     SEQWISH_INDUCE ( input )
 }
+
+workflow test_seqwish_induce_pangenome {
+    input = [ [ id:'test' ], // meta map
+            [ file(params.test_data['homo_sapiens']['pangenome']['pangenome_paf'], checkIfExists: true)],
+            [ file(params.test_data['homo_sapiens']['pangenome']['pangenome_fa'], checkIfExists: true) ]
+        ]
+
+    SEQWISH_INDUCE ( input )
+}

tests/modules/seqwish/induce/test.yml

@@ -1,8 +1,17 @@
-- name: seqwish induce
+- name: seqwish induce transcriptome
-  command: nextflow run ./tests/modules/seqwish/induce -entry test_seqwish_induce -c ./tests/config/nextflow.config -c ./tests/modules/seqwish/induce/nextflow.config
+  command: nextflow run ./tests/modules/seqwish/induce -entry test_seqwish_induce_transcriptome -c ./tests/config/nextflow.config -c ./tests/modules/seqwish/induce/nextflow.config
   tags:
     - seqwish
     - seqwish/induce
   files:
     - path: output/seqwish/test.gfa
       md5sum: 216a02d3aca322a457c31a62c628548e
+
+- name: seqwish induce pangenome
+  command: nextflow run ./tests/modules/seqwish/induce -entry test_seqwish_induce_pangenome -c ./tests/config/nextflow.config -c ./tests/modules/seqwish/induce/nextflow.config
+  tags:
+    - seqwish
+    - seqwish/induce
+  files:
+    - path: output/seqwish/test.gfa
+      md5sum: a73e998dc13a75d86d4685b12625d784