furthere splitting up add & build

modules/nf-core/metabuli/add/main.nf

@@ -9,9 +9,8 @@ process METABULI_ADD {
 
  input:
  tuple val(meta), path(fasta)
- path taxonomy_names, stageAs: 'taxonomy/names.dmp'
- path taxonomy_nodes, stageAs: 'taxonomy/nodes.dmp'
- path accession2taxid, stageAs: 'taxonomy/*'
+ path accession2taxid
+ path db
 
  output:
  tuple val(meta), path("${prefix}"), emit: db
@@ -25,33 +24,31 @@ process METABULI_ADD {
  def prefix = task.ext.prefix ?: "${meta.id}"
 
  """
- samtools \\
- sort \\
- $args \\
- -@ $task.cpus \\
- -o ${prefix}.bam \\
- -T $prefix \\
- $bam
+ mkdir -p $prefix
+ mv $db/* $prefix
+
+ ls $fasta > fasta.txt
+ metabuli add-to-library \\
+ fasta.txt \\
+ $accession2taxid \\
+ $prefix \\
+ $args
 
  cat <<-END_VERSIONS > versions.yml
  "${task.process}":
- metabuli: \$(samtools --version |& sed '1!d ; s/samtools //')
+ metabuli: \$(metabuli version)
  END_VERSIONS
  """
 
  stub:
  def args = task.ext.args ?: ''
  def prefix = task.ext.prefix ?: "${meta.id}"
- // TODO nf-core: A stub section should mimic the execution of the original module as best as possible
- // Have a look at the following examples:
- // Simple example: https://github.com/nf-core/modules/blob/818474a292b4860ae8ff88e149fbcda68814114d/modules/nf-core/bcftools/annotate/main.nf#L47-L63
- // Complex example: https://github.com/nf-core/modules/blob/818474a292b4860ae8ff88e149fbcda68814114d/modules/nf-core/bedtools/split/main.nf#L38-L54
  """
- touch ${prefix}.bam
+ mkdir -p $prefix
 
  cat <<-END_VERSIONS > versions.yml
  "${task.process}":
- metabuli: \$(samtools --version |& sed '1!d ; s/samtools //')
+ metabuli: \$(metabuli version)
  END_VERSIONS
  """
 }

modules/nf-core/metabuli/add/meta.yml

@@ -1,57 +1,54 @@
----
-# yaml-language-server: $schema=https://raw.githubusercontent.com/nf-core/modules/master/modules/meta-schema.json
 name: "metabuli_add"
-## TODO nf-core: Add a description of the module and list keywords
-description: write your description here
+description: Add fasta sequences to a database needed to use the metabuli classification tool
 keywords:
- - sort
- - example
- - genomics
+ - metabuli
+ - metagenomics
+ - profiling
+ - taxonomy
+ - database
 tools:
  - "metabuli":
- ## TODO nf-core: Add a description and other details for the software below
  description: "Metabuli: specific and sensitive metagenomic classification via joint analysis of DNA and amino acid"
- homepage: "None"
- documentation: "None"
- tool_dev_url: "None"
- doi: ""
- licence: ['GPL v3']
+ homepage: "https://github.com/steineggerlab/Metabuli"
+ documentation: "https://github.com/steineggerlab/Metabuli#readme"
+ tool_dev_url: "https://github.com/steineggerlab/Metabuli"
+ doi: "10.1101/2023.05.31.543018"
+ licence: "['GPL v3']"
 
-## TODO nf-core: Add a description of all of the variables used as input
 input:
- # Only when we have meta
  - meta:
  type: map
  description: |
  Groovy Map containing sample information
- e.g. `[ id:'sample1', single_end:false ]`
-
- ## TODO nf-core: Delete / customise this example input
- - bam:
+ e.g. [ id:'test', single_end:false ]
+ - fasta:
  type: file
- description: Sorted BAM/CRAM/SAM file
- pattern: "*.{bam,cram,sam}"
+ description: Genome files that serve as entries in the database
+ pattern: "*.{fa,fasta,fna}"
+ - accession2taxid:
+ type: file
+ description: |
+ Accession number to taxid file.
+ A four column tsv with the following header:
+ accession, accession.revision, taxid, gi.
+ - db:
+ type: directory
+ description: |
+ Output folder name for the database.
+ If the taxonomy-path optional parameter is not set to a directory
+ containing names.dmp and nodes.dmp, this directory needs
+ to contain a folder named taxonomy containing those two files.
 
-## TODO nf-core: Add a description of all of the variables used as output
 output:
- #Only when we have meta
- - meta:
- type: map
- description: |
- Groovy Map containing sample information
- e.g. `[ id:'sample1', single_end:false ]`
-
  - versions:
  type: file
  description: File containing software versions
  pattern: "versions.yml"
- ## TODO nf-core: Delete / customise this example output
- - bam:
- type: file
- description: Sorted BAM/CRAM/SAM file
- pattern: "*.{bam,cram,sam}"
+ - db:
+ type: directory
+ description: Compressed metabuli database
+ pattern: "${prefix}/"
 
 authors:
- - "@Joon-Klaps"
-maintainers:
+ - "@TheOafidian"
  - "@Joon-Klaps"

modules/nf-core/metabuli/build/main.nf

@@ -9,8 +9,6 @@ process METABULI_BUILD {
  'biocontainers/metabuli:1.0.5--pl5321h6a68c12_1' }"
 
  input:
- tuple val(meta),path(genomes)
- path(acc2taxid)
  path(db)
 
  output:
@@ -22,16 +20,7 @@ process METABULI_BUILD {
 
  script:
  def args = task.ext.args ?: ''
- def args_lib = task.ext.args_lib ?: ''
- // def skip_lib = params.skip_lib ?: false
  """
- ls $genomes > fastas.txt
- metabuli \\
- add-to-library \\
- fastas.txt \\
- $acc2taxid \\
- $db
- $args_lib
 
  ls $db/library/* > lib.txt
  metabuli \\
@@ -42,10 +31,6 @@ process METABULI_BUILD {
  $acc2taxid \\
  $args
 
- rm -r $db/library
- tar -czf metabuli_db.tar.gz $db
- rm -r $db
-
  cat <<-END_VERSIONS > versions.yml
  "${task.process}":
  metabuli: \$(metabuli | grep Version | sed 's/^metabuli Version: //';))