Add ENTREZDIRECT/ESUMMARY (#1833)

* first commit * entrezdirect/esummary fixed version definition * resolved suggestion * updated main.nf * changed output definition * output: XML file * output definition: XML file * updated XML format in tests * updated test file * version: esummary instead of entrezdirect * output file pattern: *.esummary.xml * updated test file * updated versions * restored versions stdout * updated test file * changed xml_esummary pattern * changed entrezdirect to esummary version * updated test file * Update modules/entrezdirect/esummary/meta.yml changed output file pattern: "*.xml" Co-authored-by: James A. Fellows Yates <jfy133@gmail.com> * Update modules/entrezdirect/esummary/meta.yml updated keywords Co-authored-by: James A. Fellows Yates <jfy133@gmail.com> * Update modules/entrezdirect/esummary/main.nf Output file pattern: *.xml Co-authored-by: James A. Fellows Yates <jfy133@gmail.com> * Update modules/entrezdirect/esummary/main.nf Output file pattern: *.xml Co-authored-by: James A. Fellows Yates <jfy133@gmail.com> * Update modules/entrezdirect/esummary/main.nf database as separate input channel Co-authored-by: James A. Fellows Yates <jfy133@gmail.com> * removed blank spaces in input definition * database as separate channel * conditional script for stdin * updated input definition * entrez-direct version:16.2_1 * all input channels are separate * ignore stderr, catch xml stdout * removed blank lines * added ids file input * updated test * conditional script for input * removed bad definition of input file * updated test file * Update modules/entrezdirect/esummary/main.nf changed input definition: ui, uids_file Co-authored-by: James A. Fellows Yates <jfy133@gmail.com> * Update modules/entrezdirect/esummary/meta.yml added uids_file description Co-authored-by: James A. Fellows Yates <jfy133@gmail.com> * Update modules/entrezdirect/esummary/main.nf Co-authored-by: James A. Fellows Yates <jfy133@gmail.com> * input: uid or uids_file * updated input * added uids_file to input * input file as optional input * input file as optional input in each test * new conditional script * unpdated test file * single input definition * added error messages * updated test * removed cat from command output * Update modules/entrezdirect/esummary/main.nf added comment on use of grep in output Co-authored-by: James A. Fellows Yates <jfy133@gmail.com> * added comment * removed blank spaces * input file: empty list * input file: empty list * removed comment at wrong position * optional file defined as empty list * updated successful test * Apply suggestions from code review Accepted suggestions. Co-authored-by: Matthieu Muffato <mm49@sanger.ac.uk> * Update modules/entrezdirect/esummary/main.nf Fixed comment. Co-authored-by: Matthieu Muffato <mm49@sanger.ac.uk> * Update modules/entrezdirect/esummary/main.nf Updated grep in output file. Co-authored-by: Matthieu Muffato <mm49@sanger.ac.uk> * added tail -n+3 before output * updated successful test Co-authored-by: James A. Fellows Yates <jfy133@gmail.com> Co-authored-by: Matthieu Muffato <mm49@sanger.ac.uk>
2024-12-21 18:58:16 +00:00 · 2022-07-13 11:26:58 -06:00 · 2022-07-13 11:26:58 -06:00 · b4452a4881
commit b4452a4881
parent d8bef6057b
6 changed files with 184 additions and 0 deletions
--- a/modules/entrezdirect/esummary/main.nf
+++ b/modules/entrezdirect/esummary/main.nf
@ -0,0 +1,39 @@
+process ENTREZDIRECT_ESUMMARY {
+    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), val(uid), path(uids_file)
+    val database
+
+    output:
+    tuple val(meta), path("*.xml"), emit: xml_esummary
+    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 = uids_file ? "-input ${uids_file}" : "-id ${uid}"
+    if (!uid && !uids_file) error "No input. Valid input: an identifier or a .txt file with identifiers"
+    if (uid && uids_file) error "Only one input is required: a single identifier or a .txt file with identifiers"
+    // use of 'tail -n+3' is to ensure a clean XML file. Otherwise an irrelevant Perl compilation error ends up in the XML
+    """
+    esummary \\
+        $args \\
+        -db $database \\
+        $input | tail -n+3 > ${prefix}.xml
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        esummary: \$(esummary -version)
+    END_VERSIONS
+    """
+}
--- a/modules/entrezdirect/esummary/meta.yml
+++ b/modules/entrezdirect/esummary/meta.yml
@ -0,0 +1,57 @@
+name: "entrezdirect_esummary"
+description: Queries an NCBI database using Unique Identifier(s)
+keywords:
+  - public datasets
+  - ncbi
+  - entrez
+  - metadata
+  - query
+  - 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 ]
+  - database:
+      type: value
+      description: Value must be a valid Entrez database name ('assembly', etc).
+  - uid:
+      type: value
+      description: Unique Identifier (UID) of record in NCBI database. Cannot be used at the same time as uids_file
+  - uids_file:
+      type: file
+      description: Text file containing multiple UIDs. Cannot be used at the same time as uid.
+
+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"
+  - xml_esummary:
+      type: file
+      description: Query result in XML format
+      pattern: "*.xml"
+
+authors:
+  - "@alxndrdiaz"
--- a/tests/config/pytest_modules.yml
+++ b/tests/config/pytest_modules.yml
@ -679,6 +679,10 @@ ensemblvep:
  - modules/ensemblvep/**
  - tests/modules/ensemblvep/**

+entrezdirect/esummary:
+  - modules/entrezdirect/esummary/**
+  - tests/modules/entrezdirect/esummary/**
+
 expansionhunter:
  - modules/expansionhunter/**
  - tests/modules/expansionhunter/**
--- a/tests/modules/entrezdirect/esummary/main.nf
+++ b/tests/modules/entrezdirect/esummary/main.nf
@ -0,0 +1,53 @@
+#!/usr/bin/env nextflow
+
+nextflow.enable.dsl = 2
+
+include { ENTREZDIRECT_ESUMMARY } from '../../../../modules/entrezdirect/esummary/main.nf'
+
+//
+// Test with SRA database
+//
+workflow test_entrezdirect_esummary_sra {
+
+    input = [
+        [ id:'test_sra' ], // meta map
+        uid = '5135484',
+        []
+    ]
+
+    database = 'sra'
+
+    ENTREZDIRECT_ESUMMARY ( input, database )
+}
+
+//
+// Test with Genome database
+//
+workflow test_entrezdirect_esummary_genome {
+
+    input = [
+        [ id:'test_genome' ], // meta map
+        uid = '768',
+        []
+    ]
+
+    database = 'genome'
+
+    ENTREZDIRECT_ESUMMARY ( input, database )
+}
+
+//
+// Test with Assembly database
+//
+workflow test_entrezdirect_esummary_assembly {
+
+    input = [
+        [ id:'test_assembly' ], // meta map
+        uid = '191021',
+        []
+    ]
+
+    database = 'assembly'
+
+    ENTREZDIRECT_ESUMMARY ( input, database )
+}
--- a/tests/modules/entrezdirect/esummary/nextflow.config
+++ b/tests/modules/entrezdirect/esummary/nextflow.config
@ -0,0 +1,5 @@
+process {
+
+    publishDir = { "${params.outdir}/${task.process.tokenize(':')[-1].tokenize('_')[0].toLowerCase()}" }
+
+}
--- a/tests/modules/entrezdirect/esummary/test.yml
+++ b/tests/modules/entrezdirect/esummary/test.yml
@ -0,0 +1,26 @@
+- name: entrezdirect esummary test_entrezdirect_esummary_sra
+  command: nextflow run ./tests/modules/entrezdirect/esummary -entry test_entrezdirect_esummary_sra -c ./tests/config/nextflow.config  -c ./tests/modules/entrezdirect/esummary/nextflow.config
+  tags:
+    - entrezdirect
+    - entrezdirect/esummary
+  files:
+    - path: output/entrezdirect/test_sra.xml
+      md5sum: aeb7f5710a5447a8de89b9e6fc464606
+
+- name: entrezdirect esummary test_entrezdirect_esummary_genome
+  command: nextflow run ./tests/modules/entrezdirect/esummary -entry test_entrezdirect_esummary_genome -c ./tests/config/nextflow.config  -c ./tests/modules/entrezdirect/esummary/nextflow.config
+  tags:
+    - entrezdirect
+    - entrezdirect/esummary
+  files:
+    - path: output/entrezdirect/test_genome.xml
+      md5sum: 2abea497bcef9312105b23ed78b72f62
+
+- name: entrezdirect esummary test_entrezdirect_esummary_assembly
+  command: nextflow run ./tests/modules/entrezdirect/esummary -entry test_entrezdirect_esummary_assembly -c ./tests/config/nextflow.config  -c ./tests/modules/entrezdirect/esummary/nextflow.config
+  tags:
+    - entrezdirect
+    - entrezdirect/esummary
+  files:
+    - path: output/entrezdirect/test_assembly.xml
+      md5sum: b381959a000c1f3e8c18e7b35d7b2d0a