new (fixed) module: entrezdirect/xtract (#1926)

* first commit: module files

* last version main.nf

* modules/entrezdirect/xtract/meta.yml

* updated file

* updated test

* Update modules/entrezdirect/xtract/main.nf

changed name of output file

Co-authored-by: James A. Fellows Yates <jfy133@gmail.com>

* Update modules/entrezdirect/xtract/meta.yml

Co-authored-by: James A. Fellows Yates <jfy133@gmail.com>

* Update tests/modules/entrezdirect/xtract/main.nf

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

* Update tests/modules/entrezdirect/xtract/main.nf

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

* updated test, removed esummary input file

Co-authored-by: James A. Fellows Yates <jfy133@gmail.com>
Co-authored-by: Matthieu Muffato <mm49@sanger.ac.uk>

modules/entrezdirect/xtract/main.nf

@@ -0,0 +1,39 @@
+process ENTREZDIRECT_XTRACT {
+    tag "$meta.id"
+    label 'process_low'
+
+    conda (params.enable_conda ? "bioconda::entrez-direct=16.2" : null)
+    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
+    'https://depot.galaxyproject.org/singularity/entrez-direct:16.2--he881be0_1':
+    'quay.io/biocontainers/entrez-direct:16.2--he881be0_1' }"
+
+    input:
+    tuple val(meta), path(xml_input)
+    val pattern
+    val element
+    val sep
+
+    output:
+    tuple val(meta), path("*.txt"), emit: txt
+    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}"
+    """
+    cat $xml_input | xtract \\
+        -pattern $pattern \\
+        -tab $sep \\
+        -element $element \\
+        $args \\
+        > ${prefix}.txt
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        xtract: \$(xtract -version)
+    END_VERSIONS
+    """
+}

modules/entrezdirect/xtract/meta.yml

@@ -0,0 +1,59 @@
+name: "entrezdirect_xtract"
+description: Queries an NCBI database using an UID
+keywords:
+  - public datasets
+  - entrez
+  - search
+  - ncbi
+  - database
+tools:
+  - entrezdirect:
+      description: |
+        Entrez Direct (EDirect) is a method for accessing the NCBI's set of
+        interconnected databases (publication, sequence, structure, gene,
+        variation, expression, etc.) from a UNIX terminal window. Functions
+        take search terms from command line arguments. Individual operations
+        are combined to build multi-step queries. Record retrieval and
+        formatting normally complete the process.
+      homepage: https://www.ncbi.nlm.nih.gov/books/NBK179288/
+      documentation: https://www.ncbi.nlm.nih.gov/books/NBK25501/
+      tool_dev_url: https://www.ncbi.nlm.nih.gov/books/NBK25498/
+      doi: 10.1016/S0076-6879(96)66012-1
+      licence: ["PUBLIC DOMAIN"]
+
+input:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test', single_end:false ]
+  - xml_input:
+      type: file
+      description: XML text file containing query results from database.
+  - pattern:
+      type: value
+      description: String in xml_input that encloses element to search.
+  - element:
+      type: value
+      description: Space-delimited strings that will be converted to columns.
+  - sep:
+      type: value
+      description: Separator/delimiter between columns (for instance "," or "\t").
+
+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"
+  - xtract_table:
+      type: file
+      description: TXT file containing columns searched from element.
+      pattern: "*.txt"
+
+authors:
+  - "@alxndrdiaz"

tests/config/pytest_modules.yml

@@ -695,6 +695,10 @@ entrezdirect/esummary:
   - modules/entrezdirect/esummary/**
   - tests/modules/entrezdirect/esummary/**
 
+entrezdirect/xtract:
+  - modules/entrezdirect/xtract/**
+  - tests/modules/entrezdirect/xtract/**
+
 expansionhunter:
   - modules/expansionhunter/**
   - tests/modules/expansionhunter/**

tests/modules/entrezdirect/xtract/main.nf

@@ -0,0 +1,46 @@
+#!/usr/bin/env nextflow
+
+nextflow.enable.dsl = 2
+
+include { ENTREZDIRECT_ESUMMARY } from '../../../../modules/entrezdirect/esummary/main.nf'
+include { ENTREZDIRECT_XTRACT   } from '../../../../modules/entrezdirect/xtract/main.nf'
+
+//
+// Test with Assembly database
+//
+workflow test_entrezdirect_xtract_assembly {
+
+    input = [
+        [ id:'test_assembly' ], // meta map
+        uid = '191021',
+        []
+    ]
+    database = 'assembly'
+
+    pattern_in = 'DocumentSummary'
+    element_in = 'SpeciesName BioprojectAccn FtpPath_GenBank'
+    delim = ","
+
+    ENTREZDIRECT_ESUMMARY ( input, database )
+    ENTREZDIRECT_XTRACT ( ENTREZDIRECT_ESUMMARY.out.xml, pattern_in, element_in, delim )
+}
+
+//
+// Test with Genome database
+//
+workflow test_entrezdirect_xtract_genome {
+
+    input = [
+        [ id:'test_genome' ], // meta map
+        uid = '768',
+        []
+    ]
+    database = 'genome'
+
+    pattern_in = 'DocumentSummary'
+    element_in = 'TaxId Organism_Name Project_Accession Assembly_Accession'
+    delim = ","
+
+    ENTREZDIRECT_ESUMMARY ( input, database )
+    ENTREZDIRECT_XTRACT ( ENTREZDIRECT_ESUMMARY.out.xml, pattern_in, element_in, delim )
+}

tests/modules/entrezdirect/xtract/nextflow.config

@@ -0,0 +1,5 @@
+process {
+
+    publishDir = { "${params.outdir}/${task.process.tokenize(':')[-1].tokenize('_')[0].toLowerCase()}" }
+    
+}

tests/modules/entrezdirect/xtract/test.yml

@@ -0,0 +1,17 @@
+- name: entrezdirect xtract test_entrezdirect_xtract_assembly
+  command: nextflow run ./tests/modules/entrezdirect/xtract -entry test_entrezdirect_xtract_assembly -c ./tests/config/nextflow.config  -c ./tests/modules/entrezdirect/xtract/nextflow.config
+  tags:
+    - entrezdirect/xtract
+    - entrezdirect
+  files:
+    - path: output/entrezdirect/test_assembly.xml
+      md5sum: 32f81147eea61df5814e87c2df1092a9
+
+- name: entrezdirect xtract test_entrezdirect_xtract_genome
+  command: nextflow run ./tests/modules/entrezdirect/xtract -entry test_entrezdirect_xtract_genome -c ./tests/config/nextflow.config  -c ./tests/modules/entrezdirect/xtract/nextflow.config
+  tags:
+    - entrezdirect/xtract
+    - entrezdirect
+  files:
+    - path: output/entrezdirect/test_genome.xml
+      md5sum: af6242f231bdc147d6197edfd0954585