Add local module dshbio/fastatoparquet

Author: heuermh

conf/base.config

@@ -62,4 +62,7 @@ process {
     withName: SEQKIT_STATS {
         ext.args = ' ' // turn off --all default argument
     }
+    withName: DSHBIO_FASTATOPARQUET {
+        ext.args = '--alphabet protein'
+    }
 }

modules/local/dshbio/fastatoparquet/environment.yml

@@ -0,0 +1,7 @@
+---
+# yaml-language-server: $schema=https://raw.githubusercontent.com/nf-core/modules/master/modules/environment-schema.json
+channels:
+  - conda-forge
+  - bioconda
+dependencies:
+  - bioconda::dsh-bio=3.0

modules/local/dshbio/fastatoparquet/main.nf

@@ -0,0 +1,47 @@
+process DSHBIO_FASTATOPARQUET {
+    tag "${meta.id}"
+    label 'process_medium'
+
+    conda "${moduleDir}/environment.yml"
+    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
+        'https://depot.galaxyproject.org/singularity/dsh-bio:3.0--hdfd78af_0' :
+        'biocontainers/dsh-bio:3.0--hdfd78af_0' }"
+
+    input:
+    tuple val(meta), path(fasta)
+
+    output:
+    tuple val(meta), path("*.sequences.parquet"), emit: parquet
+    path "versions.yml"                         , emit: versions
+
+    when:
+    task.ext.when == null || task.ext.when
+
+    script:
+    def args = task.ext.args ?: ''
+    def prefix = task.ext.prefix ?: "${meta.id}"
+    """
+    dsh-bio \\
+        fasta-to-parquet3 \\
+        $args \\
+        -i $fasta \\
+        -o ${prefix}.sequences.parquet
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        dshbio: \$(dsh-bio --version 2>&1 | grep -o 'dsh-bio-tools .*' | cut -f2 -d ' ')
+    END_VERSIONS
+    """
+
+    stub:
+    def args = task.ext.args ?: ''
+    def prefix = task.ext.prefix ?: "${meta.id}"
+    """
+    mkdir -p ${prefix}.sequences.parquet
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        dshbio: \$(dsh-bio --version 2>&1 | grep -o 'dsh-bio-tools .*' | cut -f2 -d ' ')
+    END_VERSIONS
+    """
+}

modules/local/dshbio/fastatoparquet/meta.yml

@@ -0,0 +1,52 @@
+---
+# yaml-language-server: $schema=https://raw.githubusercontent.com/nf-core/modules/master/modules/meta-schema.json
+name: "dshbio_fastatoparquet"
+description: Convert DNA or protein sequences in FASTA format to Parquet format
+keywords:
+  - fasta
+  - parquet
+  - sequence
+tools:
+  - dshbio:
+      description: |
+        Reads, features, variants, assemblies, alignments, genomic range trees, pangenome
+        graphs, and a bunch of random command line tools for bioinformatics. LGPL version 3
+        or later.
+      homepage: https://github.com/heuermh/dishevelled-bio
+      documentation: https://github.com/heuermh/dishevelled-bio
+      doi: "10.5281/zenodo.15027131"
+      licence: ["LGPL-3.0-or-later"]
+
+input:
+  - - meta:
+        type: map
+        description: |
+          Groovy Map containing sample information
+          e.g. [ id:'test', single_end:false ]
+    - fasta:
+        type: file
+        description: DNA or protein sequences in compressed FASTA format
+        pattern: "*.fasta.{gz|zst|bgz|bgzf|bzip2}"
+
+output:
+  - parquet:
+      - meta:
+          type: map
+          description: |
+            Groovy Map containing sample information
+            e.g. [ id:'test', single_end:false ]
+      - "*.sequences.parquet":
+          type: directory
+          description: |
+            Directory of DNA or protein sequences in Parquet format with zstd compression
+          pattern: "*.sequences.parquet"
+  - versions:
+      - versions.yml:
+          type: file
+          description: File containing software versions
+          pattern: "versions.yml"
+
+authors:
+  - "@heuermh"
+maintainers:
+  - "@heuermh"

workflows/proteinannotator.nf

@@ -3,6 +3,7 @@
     IMPORT MODULES / SUBWORKFLOWS / FUNCTIONS
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
 */
+include { DSHBIO_FASTATOPARQUET  } from '../modules/local/dshbio/fastatoparquet/main'
 include { MULTIQC                } from '../modules/nf-core/multiqc/main'
 include { SEQKIT_STATS           } from '../modules/nf-core/seqkit/stats/main'
 include { paramsSummaryMap       } from 'plugin/nf-schema'
@@ -34,6 +35,10 @@ workflow PROTEINANNOTATOR {
     SEQKIT_STATS(ch_samplesheet)
     ch_versions = ch_versions.mix(SEQKIT_STATS.out.versions)
 
+    // todo: move this to stats on input fasta subworkflow
+    DSHBIO_FASTATOPARQUET(ch_samplesheet)
+    ch_versions = ch_versions.mix(DSHBIO_FASTATOPARQUET.out.versions)
+
     //
     // Collate and save software versions
     //