new (fixed) module: entrezdirect/esearch (#1927)

* added module files

* latest version

* latest version

* latest version

* latest version

* updated test, failing

* added comment on why to use tail -n+3

* same as latest test

* moved args to the end of script

* updated test

* double quotes for esearch input

* removed tail -n+3, stderr is redirected by nextflow

* changed single to double quotes

* Update modules/entrezdirect/esearch/main.nf

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

* Update modules/entrezdirect/esearch/meta.yml

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

* Update meta.yml

removed default from database parameter

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

modules/entrezdirect/esearch/main.nf

@@ -0,0 +1,35 @@
+process ENTREZDIRECT_ESEARCH {
+    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(term)
+    val database
+
+    output:
+    tuple val(meta), path("*.xml") , emit: xml
+    path "versions.yml"            , emit: versions
+
+    when:
+    task.ext.when == null || task.ext.when
+
+    script:
+    def prefix = task.ext.prefix ?: "${meta.id}"
+    def args = task.ext.args ?: ''
+    """
+    esearch \\
+        -db $database \\
+        -query $term \\
+        $args > ${prefix}.xml
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        esearch: \$(esearch -version)
+    END_VERSIONS
+    """
+}

modules/entrezdirect/esearch/meta.yml

@@ -0,0 +1,55 @@
+name: "entrezdirect_esearch"
+description: Searches a term in a public NCBI database
+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' ]
+  - database:
+      type: value
+      description: Value must be a valid Entrez database name.
+  - term:
+      type: value
+      description: |
+        Entrez text query. All special characters must be URL encoded.
+        Spaces may be replaced by '+' signs.
+
+output:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test' ]
+  - versions:
+      type: file
+      description: File containing software versions
+      pattern: "versions.yml"
+  - result_xml:
+      type: file
+      description: Query result text in XML format
+      pattern: "*.xml"
+
+authors:
+  - "@alxndrdiaz"

tests/config/pytest_modules.yml

@@ -691,6 +691,10 @@ ensemblvep:
   - modules/ensemblvep/**
   - tests/modules/ensemblvep/**
 
+entrezdirect/esearch:
+  - modules/entrezdirect/esearch/**
+  - tests/modules/entrezdirect/esearch/**
+
 entrezdirect/esummary:
   - modules/entrezdirect/esummary/**
   - tests/modules/entrezdirect/esummary/**

tests/modules/entrezdirect/esearch/main.nf

@@ -0,0 +1,46 @@
+#!/usr/bin/env nextflow
+
+nextflow.enable.dsl = 2
+
+include { ENTREZDIRECT_ESEARCH as ENTREZDIRECT_ESEARCHP  } from "../../../../modules/entrezdirect/esearch/main.nf"
+include { ENTREZDIRECT_ESEARCH                           } from "../../../../modules/entrezdirect/esearch/main.nf"
+
+//
+// Test with PubMed database, using date range and spell check,
+// see nextflow.config file for optional definition(ext.args)
+//
+workflow test_entrezdirect_esearch_pubmed {
+    input = [
+        [ id:'test_pubmed' ], // meta map
+        term = "selective serotonin reuptake inhibitor"
+    ]
+    database = "pubmed"
+
+    ENTREZDIRECT_ESEARCHP ( input, database )
+}
+
+//
+// Test with Genome database and species; no date range, no spell check
+//
+workflow test_entrezdirect_esearch_genome {
+    input = [
+        [ id:'test_genome' ], // meta map,
+        term = "Danio+rerio"
+    ]
+    database = "genome"
+
+    ENTREZDIRECT_ESEARCH ( input, database  )
+}
+
+//
+// Test with Assembly database and GenBank accession; no date range, no spell check
+//
+workflow test_entrezdirect_esearch_assembly {
+    input = [
+        [ id:'test_assembly' ], // meta map
+        term = "GCA_000001635.9"
+    ]
+    database = "assembly"
+
+    ENTREZDIRECT_ESEARCH ( input, database )
+}

tests/modules/entrezdirect/esearch/nextflow.config

@@ -0,0 +1,8 @@
+process {
+
+    publishDir = { "${params.outdir}/${task.process.tokenize(":")[-1].tokenize("_")[0].toLowerCase()}" }
+
+    withName: ENTREZDIRECT_ESEARCHP {
+        ext.args = '-sort pub+date -datetype pdat -mindate 2021/06/20 -maxdate 2022/06/20 -spell'
+    }
+}

tests/modules/entrezdirect/esearch/test.yml

@@ -0,0 +1,47 @@
+- name: entrezdirect esearch test_entrezdirect_esearch_pubmed
+  command: nextflow run ./tests/modules/entrezdirect/esearch -entry test_entrezdirect_esearch_pubmed -c ./tests/config/nextflow.config  -c ./tests/modules/entrezdirect/esearch/nextflow.config
+  tags:
+    - entrezdirect/esearch
+    - entrezdirect
+  files:
+    - path: output/entrezdirect/test_pubmed.xml
+      contains:
+        - "<ENTREZ_DIRECT>"
+        - "<Db>pubmed</Db>"
+        - "<WebEnv>"
+        - "<QueryKey>"
+        - "<Step>"
+        - "<Count>"
+        - "</ENTREZ_DIRECT>"
+
+- name: entrezdirect esearch test_entrezdirect_esearch_genome
+  command: nextflow run ./tests/modules/entrezdirect/esearch -entry test_entrezdirect_esearch_genome -c ./tests/config/nextflow.config  -c ./tests/modules/entrezdirect/esearch/nextflow.config
+  tags:
+    - entrezdirect/esearch
+    - entrezdirect
+  files:
+    - path: output/entrezdirect/test_genome.xml
+      contains:
+        - "<ENTREZ_DIRECT>"
+        - "<Db>genome</Db>"
+        - "<WebEnv>"
+        - "<QueryKey>"
+        - "<Count>"
+        - "<Step>"
+        - "</ENTREZ_DIRECT>"
+
+- name: entrezdirect esearch test_entrezdirect_esearch_assembly
+  command: nextflow run ./tests/modules/entrezdirect/esearch -entry test_entrezdirect_esearch_assembly -c ./tests/config/nextflow.config  -c ./tests/modules/entrezdirect/esearch/nextflow.config
+  tags:
+    - entrezdirect/esearch
+    - entrezdirect
+  files:
+    - path: output/entrezdirect/test_assembly.xml
+      contains:
+        - "<ENTREZ_DIRECT>"
+        - "<Db>assembly</Db>"
+        - "<WebEnv>"
+        - "<QueryKey>"
+        - "<Count>"
+        - "<Step>"
+        - "</ENTREZ_DIRECT>"