Add module: goat/taxonsearch (#1866)

* first commit

* single taxon input

* added .tsv output

* input: single taxon or file with taxon identifiers

* updated input and output

* removed wrong tool description

* added tests

* ext.args = '-l -b'

* fixed wrong input names

* updated test file

* Update modules/goat/taxonsearch/main.nf

simple version output

Co-authored-by: Matthieu Muffato <mm49@sanger.ac.uk>

* removed 'NO_FILE' from input definition

* added ! in if statement

* optional input: empty list

* successful updated test

* added test with file

* remove blank spaces in include {}

* added test with taxa file

Co-authored-by: Matthieu Muffato <mm49@sanger.ac.uk>

modules/goat/taxonsearch/main.nf

@@ -0,0 +1,36 @@
+process GOAT_TAXONSEARCH {
+    tag "$meta.id"
+    label 'process_low'
+
+    conda (params.enable_conda ? "bioconda::goat=0.2.0" : null)
+    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
+        'https://depot.galaxyproject.org/singularity/goat:0.2.0--h92d785c_0':
+        'quay.io/biocontainers/goat:0.2.0--h92d785c_0' }"
+
+    input:
+    tuple val(meta), val(taxon), path(taxa_file)
+
+    output:
+    tuple val(meta), path("*.tsv"), emit: taxonsearch
+    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}"
+    input = taxa_file ? "-f ${taxa_file}" : "-t ${taxon}"
+    if (!taxon && !taxa_file) error "No input. Valid input: single taxon identifier or a .txt file with identifiers"
+    if (taxon && taxa_file ) error "Only one input is required: a single taxon identifier or a .txt file with identifiers"
+    """
+    goat-cli taxon search \\
+        $args \\
+        $input > ${prefix}.tsv
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        goat: \$(goat-cli --version | cut -d' ' -f2)
+    END_VERSIONS
+    """
+}

modules/goat/taxonsearch/meta.yml

@@ -0,0 +1,51 @@
+name: "goat_taxonsearch"
+description: Query metadata for any taxon across the tree of life.
+keywords:
+  - public datasets
+  - ncbi
+  - genomes on a tree
+tools:
+  - goat:
+      description: |
+        goat-cli is a command line interface to query the
+        Genomes on a Tree Open API.
+      homepage: https://github.com/genomehubs/goat-cli
+      documentation: https://github.com/genomehubs/goat-cli/wiki
+      tool_dev_url: https://genomehubs.github.io/goat-cli/goat_cli/
+      doi: "None"
+      licence: ["MIT"]
+
+input:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test']
+  - taxon:
+      type: val
+      description: |
+        The taxon to search. An NCBI taxon ID, or the name of a taxon at any rank.
+  - taxa_file:
+      type: file
+      description: |
+        A file of NCBI taxonomy ID's (tips) and/or binomial names. Each line
+        should contain a single entry.File size is limited to 500 entries.
+      pattern: "*.txt"
+
+output:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test', single_end:false ]
+  - versions:
+      type: file
+      description: File containing software versions
+      pattern: "versions.yml"
+  - taxonsearch:
+      type: file
+      description: TSV file containing search results.
+      pattern: "*.tsv"
+
+authors:
+  - "@alxndrdiaz"

tests/config/pytest_modules.yml

@@ -1015,6 +1015,10 @@ glnexus:
   - modules/glnexus/**
   - tests/modules/glnexus/**
 
+goat/taxonsearch:
+  - modules/goat/taxonsearch/**
+  - tests/modules/goat/taxonsearch/**
+
 graphmap2/align:
   - modules/graphmap2/align/**
   - tests/modules/graphmap2/align/**

tests/modules/goat/taxonsearch/main.nf

@@ -0,0 +1,44 @@
+#!/usr/bin/env nextflow
+
+nextflow.enable.dsl = 2
+
+include { GOAT_TAXONSEARCH } from '../../../../modules/goat/taxonsearch/main.nf'
+
+//
+// Test with genus name (Canis)
+//
+workflow test_goat_taxonsearch_genus_name {
+
+    input = [
+      [ id:'test_genus_name' ], // meta map
+      taxon = 'Canis',
+      []
+  ]
+    GOAT_TAXONSEARCH ( input )
+}
+
+//
+// Test with genus (Drosophila, fruit flies) using NCBI taxonomy ID
+//
+workflow test_goat_taxonsearch_genus_id {
+
+    input = [
+      [ id:'test_genus_id' ], // meta map
+      taxon = '7215',
+      []
+  ]
+    GOAT_TAXONSEARCH ( input )
+}
+
+//
+// Test with multiple species from a taxa file
+//
+workflow test_goat_taxonsearch_species {
+
+    input = [
+      [ id:'test_species' ], // meta map
+      taxon = '',
+      file('https://raw.githubusercontent.com/nf-core/test-datasets/modules/data/delete_me/goat_taxonsearch/taxonomy_ids.txt', checkIfExists: true)
+  ]
+    GOAT_TAXONSEARCH ( input )
+}

tests/modules/goat/taxonsearch/nextflow.config

@@ -0,0 +1,8 @@
+process {
+
+    publishDir = { "${params.outdir}/${task.process.tokenize(':')[-1].tokenize('_')[0].toLowerCase()}" }
+
+    withName: GOAT_TAXONSEARCH {
+         ext.args = '-l -b'
+     }
+}

tests/modules/goat/taxonsearch/test.yml

@@ -0,0 +1,26 @@
+- name: goat taxonsearch test_goat_taxonsearch_genus_name
+  command: nextflow run ./tests/modules/goat/taxonsearch -entry test_goat_taxonsearch_genus_name -c ./tests/config/nextflow.config  -c ./tests/modules/goat/taxonsearch/nextflow.config
+  tags:
+    - goat
+    - goat/taxonsearch
+  files:
+    - path: output/goat/test_genus_name.tsv
+      md5sum: e3de63a2bc2e16038aabeb325452bd16
+
+- name: goat taxonsearch test_goat_taxonsearch_genus_id
+  command: nextflow run ./tests/modules/goat/taxonsearch -entry test_goat_taxonsearch_genus_id -c ./tests/config/nextflow.config  -c ./tests/modules/goat/taxonsearch/nextflow.config
+  tags:
+    - goat
+    - goat/taxonsearch
+  files:
+    - path: output/goat/test_genus_id.tsv
+      md5sum: 2cc41abbbc21b4b66f4d5126cfbba2bc
+
+- name: goat taxonsearch test_goat_taxonsearch_species
+  command: nextflow run ./tests/modules/goat/taxonsearch -entry test_goat_taxonsearch_species -c ./tests/config/nextflow.config  -c ./tests/modules/goat/taxonsearch/nextflow.config
+  tags:
+    - goat
+    - goat/taxonsearch
+  files:
+    - path: output/goat/test_species.tsv
+      md5sum: 7f5b36414820bd3ce2bfda06d98e479c