New module to use hmmalign from HMMER to align sequences (#470)

* Ignore vim tmp files

* Added hmmalign module, not yet tests

* Test output

* Replaced functions.nf for hmmalign with upstream

* Update software/hmmer/hmmalign/main.nf

Co-authored-by: Harshil Patel <drpatelh@users.noreply.github.com>

* Update software/hmmer/hmmalign/main.nf

Co-authored-by: Harshil Patel <drpatelh@users.noreply.github.com>

* Update software/hmmer/hmmalign/meta.yml

Co-authored-by: Harshil Patel <drpatelh@users.noreply.github.com>

* Update tests/software/hmmer/hmmalign/main.nf

Co-authored-by: Harshil Patel <drpatelh@users.noreply.github.com>

* Update tests/software/hmmer/hmmalign/main.nf

Co-authored-by: Harshil Patel <drpatelh@users.noreply.github.com>

* Update tests/software/hmmer/hmmalign/test.yml

Co-authored-by: Harshil Patel <drpatelh@users.noreply.github.com>

* Update tests/config/pytest_software.yml

Co-authored-by: Harshil Patel <drpatelh@users.noreply.github.com>

* Update software/hmmer/hmmalign/main.nf

Co-authored-by: Harshil Patel <drpatelh@users.noreply.github.com>

Co-authored-by: Harshil Patel <drpatelh@users.noreply.github.com>

.gitignore

@@ -5,3 +5,5 @@ test_output/
 output/
 .DS_Store
 *.code-workspace
+.screenrc
+.*.sw?

software/hmmer/hmmalign/functions.nf

@@ -0,0 +1,70 @@
+/*
+ * -----------------------------------------------------
+ *  Utility functions used in nf-core DSL2 module files
+ * -----------------------------------------------------
+ */
+
+/*
+ * Extract name of software tool from process name using $task.process
+ */
+def getSoftwareName(task_process) {
+    return task_process.tokenize(':')[-1].tokenize('_')[0].toLowerCase()
+}
+
+/*
+ * Function to initialise default values and to generate a Groovy Map of available options for nf-core modules
+ */
+def initOptions(Map args) {
+    def Map options = [:]
+    options.args            = args.args ?: ''
+    options.args2           = args.args2 ?: ''
+    options.args3           = args.args3 ?: ''
+    options.publish_by_meta = args.publish_by_meta ?: []
+    options.publish_dir     = args.publish_dir ?: ''
+    options.publish_files   = args.publish_files
+    options.suffix          = args.suffix ?: ''
+    return options
+}
+
+/*
+ * Tidy up and join elements of a list to return a path string
+ */
+def getPathFromList(path_list) {
+    def paths = path_list.findAll { item -> !item?.trim().isEmpty() }      // Remove empty entries
+    paths     = paths.collect { it.trim().replaceAll("^[/]+|[/]+\$", "") } // Trim whitespace and trailing slashes
+    return paths.join('/')
+}
+
+/*
+ * Function to save/publish module results
+ */
+def saveFiles(Map args) {
+    if (!args.filename.endsWith('.version.txt')) {
+        def ioptions  = initOptions(args.options)
+        def path_list = [ ioptions.publish_dir ?: args.publish_dir ]
+        if (ioptions.publish_by_meta) {
+            def key_list = ioptions.publish_by_meta instanceof List ? ioptions.publish_by_meta : args.publish_by_meta
+            for (key in key_list) {
+                if (args.meta && key instanceof String) {
+                    def path = key
+                    if (args.meta.containsKey(key)) {
+                        path = args.meta[key] instanceof Boolean ? "${key}_${args.meta[key]}".toString() : args.meta[key]
+                    }
+                    path = path instanceof String ? path : ''
+                    path_list.add(path)
+                }
+            }
+        }
+        if (ioptions.publish_files instanceof Map) {
+            for (ext in ioptions.publish_files) {
+                if (args.filename.endsWith(ext.key)) {
+                    def ext_list = path_list.collect()
+                    ext_list.add(ext.value)
+                    return "${getPathFromList(ext_list)}/$args.filename"
+                }
+            }
+        } else if (ioptions.publish_files == null) {
+            return "${getPathFromList(path_list)}/$args.filename"
+        }
+    }
+}

software/hmmer/hmmalign/main.nf

@@ -0,0 +1,42 @@
+// Import generic module functions
+include { initOptions; saveFiles; getSoftwareName } from './functions'
+
+params.options = [:]
+options        = initOptions(params.options)
+
+process HMMER_HMMALIGN {
+    tag "$meta.id"
+    label 'process_medium'
+    publishDir "${params.outdir}",
+        mode: params.publish_dir_mode,
+        saveAs: { filename -> saveFiles(filename:filename, options:params.options, publish_dir:getSoftwareName(task.process), meta:meta, publish_by_meta:['id']) }
+
+    conda (params.enable_conda ? "bioconda::hmmer=3.3.2" : null)
+    if (workflow.containerEngine == 'singularity' && !params.singularity_pull_docker_container) {
+        container "https://depot.galaxyproject.org/singularity/hmmer:3.3.2--h1b792b2_1"
+    } else {
+        container "quay.io/biocontainers/hmmer:3.3.2--h1b792b2_1"
+    }
+
+    input:
+    tuple val(meta), path(fasta)
+    path hmm
+
+    output:
+    tuple val(meta), path("*.sthlm.gz"), emit: sthlm
+    path "*.version.txt"               , emit: version
+
+    script:
+    def software = getSoftwareName(task.process)
+    def prefix   = options.suffix ? "${meta.id}${options.suffix}" : "${meta.id}"
+    def fastacmd = fasta.getExtension() == 'gz' ? "gunzip -c $fasta" : "cat $fasta"
+    """
+    $fastacmd | \\
+        hmmalign \\
+        $options.args \\
+        $hmm \\
+        - | gzip -c > ${meta.id}.sthlm.gz
+
+    echo \$(hmmalign -h | grep -o '^# HMMER [0-9.]*') | sed 's/^# HMMER *//' > ${software}.version.txt
+    """
+}

software/hmmer/hmmalign/meta.yml

@@ -0,0 +1,45 @@
+name: hmmer_hmmalign
+description: hmmalign from the HMMER suite aligns a number of sequences to an HMM profile
+keywords:
+  - alignment
+tools:
+  - hmmer:
+      description: Biosequence analysis using profile hidden Markov models
+      homepage: http://hmmer.org/
+      documentation: http://hmmer.org/documentation.html
+      tool_dev_url: None
+      doi: "http://dx.doi.org/10.1371/journal.pcbi.1002195"
+      licence: ['BSD']
+
+input:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test' ]
+  - fasta:
+      type: file
+      description: Amino acid or nucleotide fasta file, gzipped or not
+      pattern: "*.{fna,fna.gz,faa,faa.gz,fasta,fasta.gz,fa,fa.gz}"
+  - hmm:
+      type: file
+      description: HMM file
+      pattern: "*.hmm"
+
+output:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test', single_end:false ]
+  - version:
+      type: file
+      description: File containing software version
+      pattern: "*.{version.txt}"
+  - sthlm:
+      type: file
+      description: Multiple alignment in gzipped Stockholm format
+      pattern: "*.sthlm.gz"
+
+authors:
+  - "@erikrikarddaniel"

tests/config/pytest_software.yml

@@ -297,6 +297,10 @@ hisat2/extractsplicesites:
   - software/hisat2/extractsplicesites/**
   - tests/software/hisat2/extractsplicesites/**
 
+hmmer/hmmalign:
+  - software/hmmer/hmmalign/**
+  - tests/software/hmmer/hmmalign/**
+
 homer/annotatepeaks:
   - software/homer/annotatepeaks/**
   - tests/software/homer/annotatepeaks/**

tests/software/hmmer/hmmalign/main.nf

@@ -0,0 +1,17 @@
+#!/usr/bin/env nextflow
+
+nextflow.enable.dsl = 2
+
+include { HMMER_HMMALIGN } from '../../../../software/hmmer/hmmalign/main.nf' addParams( options: [:] )
+
+workflow test_hmmer_hmmalign {
+
+    input = [
+        [ id:'test' ], // meta map
+        file('https://raw.githubusercontent.com/erikrikarddaniel/test-datasets/modules/data/delete_me/e_coli_k12_16s.fna')      // Change to params.test_data syntax after the data is included in tests/config/test_data.config
+    ]
+
+    hmm   = file('https://raw.githubusercontent.com/erikrikarddaniel/test-datasets/modules/data/delete_me/bac.16S_rRNA.hmm')
+
+    HMMER_HMMALIGN ( input, hmm )
+}

tests/software/hmmer/hmmalign/test.yml

@@ -0,0 +1,8 @@
+- name: hmmer hmmalign test_hmmer_hmmalign
+  command: nextflow run tests/software/hmmer/hmmalign -entry test_hmmer_hmmalign -c tests/config/nextflow.config
+  tags:
+    - hmmer
+    - hmmer/hmmalign
+  files:
+    - path: output/hmmer/test.sthlm.gz
+      md5sum: ddaa8b96291edf4e1a929a224329161b