Add cd-hit module

modules/nf-core/cdhit/cdhit/main.nf

@@ -0,0 +1,36 @@
+process CDHIT_CDHIT {
+    tag "$meta.id"
+    label 'process_medium'
+
+    conda (params.enable_conda ? "bioconda::cd-hit=4.8.1" : null)
+    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
+        'https://depot.galaxyproject.org/singularity/cd-hit%3A4.8.1--h5b5514e_7':
+        'quay.io/biocontainers/cd-hit:4.8.1--h5b5514e_7' }"
+
+    input:
+    tuple val(meta), path(sequences)
+
+    output:
+    tuple val(meta), path("*.fasta")    ,emit: fasta
+    tuple val(meta), path("*.clstr")    ,emit: clusters
+    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}"
+    """
+    cd-hit \\
+        -i $sequences \\
+        -o ${prefix}.fasta \\
+        -M $task.memory.mega \\
+        -T $task.cpus
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        cdhit: \$(echo \$(cd-hit -h|head -n 1 2>&1) | sed 's/====== CD-HIT version //;s/ (built on .*) ======//' )
+    END_VERSIONS
+    """
+}

modules/nf-core/cdhit/cdhit/meta.yml

@@ -0,0 +1,49 @@
+name: "cdhit"
+description: Cluster protein sequences using sequence similarity
+keywords:
+  - cluster
+  - protein
+  - alignment
+  - fasta
+tools:
+  - "cdhit":
+      description: "Clusters and compares protein or nucleotide sequences"
+      homepage: "https://sites.google.com/view/cd-hit/home"
+      documentation: "https://github.com/weizhongli/cdhit/wiki"
+      tool_dev_url: "https://github.com/weizhongli/cdhit"
+      doi: "10.1093/bioinformatics/btl158"
+      licence: "['GPL v2']"
+
+input:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test', single_end:false ]
+  - sequences:
+      type: file
+      description: fasta file of sequences to be clustered
+      pattern: "*.{fa,fasta}"
+
+output:
+  #Only when we have meta
+  - 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"
+  - fasta:
+      type: file
+      description: fasta file of the representative sequences for each cluster
+      pattern: "*.{fasta}"
+  - clusters:
+      type: file
+      description: List of clusters
+      pattern: "*.{clstr}"
+
+authors:
+  - "@timslittle"

tests/config/pytest_modules.yml

@@ -529,6 +529,10 @@ cat/fastq:
   - modules/nf-core/cat/fastq/**
   - tests/modules/nf-core/cat/fastq/**
 
+cdhit:
+  - modules/nf-core/cdhit/cdhit/**
+  - tests/modules/nf-core/cdhit/cdhit/**
+
 cellranger/count:
   - modules/nf-core/cellranger/count/**
   - tests/modules/nf-core/cellranger/count/**

tests/modules/nf-core/cdhit/cdhit/main.nf

@@ -0,0 +1,15 @@
+#!/usr/bin/env nextflow
+
+nextflow.enable.dsl = 2
+
+include { CDHIT } from '../../../../../modules/nf-core/cdhit/cdhit/main.nf'
+
+workflow test_cdhit {
+
+    input = [
+        [ id:'test', single_end:false ], // meta map
+        file(params.test_data['proteomics']['database']['yeast_ups'], checkIfExists: true)
+    ]
+
+    CDHIT ( input )
+}

tests/modules/nf-core/cdhit/cdhit/nextflow.config

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

tests/modules/nf-core/cdhit/cdhit/test.yml

@@ -0,0 +1,11 @@
+- name: cdhit cdhit test_cdhit
+  command: nextflow run ./tests/modules/nf-core/cdhit/cdhit -entry test_cdhit -c ./tests/config/nextflow.config -c ./tests/modules/nf-core/cdhit/cdhit/nextflow.config
+  tags:
+    - cdhit
+    - cdhit/cdhit
+  files:
+    - path: output/cdhit/test.fasta
+      md5sum: 0d4dda84911f7ffa3237c82391160c45
+    - path: output/cdhit/test.fasta.clstr
+      md5sum: 07b5af3b377f05c6970e6f3d2bb75ef2
+    - path: output/cdhit/versions.yml