* Specify more guidelines on input channels

* Linting

* Updates based on code review

* Update README.md

* Fix broken sentence

* Start work, continue once on non-mobile internet

* finished and working on conda

* Update modules/amps/main.nf

Co-authored-by: Jose Espinosa-Carrasco <kadomu@gmail.com>

* Apply suggestions from code review

Co-authored-by: Jose Espinosa-Carrasco <kadomu@gmail.com>

Co-authored-by: Jose Espinosa-Carrasco <kadomu@gmail.com>
This commit is contained in:
James A. Fellows Yates 2021-09-30 12:54:16 +02:00 committed by GitHub
parent 216dc8c984
commit 01cc326c23
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
6 changed files with 238 additions and 0 deletions

78
modules/amps/functions.nf Normal file
View file

@ -0,0 +1,78 @@
//
// 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()
}
//
// Extract name of module from process name using $task.process
//
def getProcessName(task_process) {
return task_process.tokenize(':')[-1]
}
//
// Function to initialise default values and to generate a Groovy Map of available options for nf-core modules
//
def initOptions(Map args) {
def Map options = [:]
options.args = args.args ?: ''
options.args2 = args.args2 ?: ''
options.args3 = args.args3 ?: ''
options.publish_by_meta = args.publish_by_meta ?: []
options.publish_dir = args.publish_dir ?: ''
options.publish_files = args.publish_files
options.suffix = args.suffix ?: ''
return options
}
//
// Tidy up and join elements of a list to return a path string
//
def getPathFromList(path_list) {
def paths = path_list.findAll { item -> !item?.trim().isEmpty() } // Remove empty entries
paths = paths.collect { it.trim().replaceAll("^[/]+|[/]+\$", "") } // Trim whitespace and trailing slashes
return paths.join('/')
}
//
// Function to save/publish module results
//
def saveFiles(Map args) {
def ioptions = initOptions(args.options)
def path_list = [ ioptions.publish_dir ?: args.publish_dir ]
// Do not publish versions.yml unless running from pytest workflow
if (args.filename.equals('versions.yml') && !System.getenv("NF_CORE_MODULES_TEST")) {
return null
}
if (ioptions.publish_by_meta) {
def key_list = ioptions.publish_by_meta instanceof List ? ioptions.publish_by_meta : args.publish_by_meta
for (key in key_list) {
if (args.meta && key instanceof String) {
def path = key
if (args.meta.containsKey(key)) {
path = args.meta[key] instanceof Boolean ? "${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"
}
}

47
modules/amps/main.nf Normal file
View file

@ -0,0 +1,47 @@
// Import generic module functions
include { initOptions; saveFiles; getSoftwareName; getProcessName } from './functions'
params.options = [:]
options = initOptions(params.options)
process AMPS {
label 'process_low'
publishDir "${params.outdir}",
mode: params.publish_dir_mode,
saveAs: { filename -> saveFiles(filename:filename, options:params.options, publish_dir:getSoftwareName(task.process), meta:[:], publish_by_meta:[]) }
conda (params.enable_conda ? "bioconda::hops=0.35" : null)
if (workflow.containerEngine == 'singularity' && !params.singularity_pull_docker_container) {
container "https://depot.galaxyproject.org/singularity/hops:0.35--hdfd78af_1"
} else {
container "quay.io/biocontainers/hops:0.35--hdfd78af_1"
}
input:
path maltextract_results
path taxon_list
val filter
output:
path "results/heatmap_overview_Wevid.json" , emit: json
path "results/heatmap_overview_Wevid.pdf" , emit: summary_pdf
path "results/heatmap_overview_Wevid.tsv" , emit: tsv
path "results/pdf_candidate_profiles/" , emit: candidate_pdfs
path "versions.yml" , emit: version
script:
"""
postprocessing.AMPS.r \\
-r $maltextract_results \\
-n $taxon_list \\
-m $filter \\
-t $task.cpus \\
-j \\
$options.args
cat <<-END_VERSIONS > versions.yml
${getProcessName(task.process)}:
amps: \$(echo \$(hops --version 2>&1) | sed 's/HOPS version//')
END_VERSIONS
"""
}

66
modules/amps/meta.yml Normal file
View file

@ -0,0 +1,66 @@
name: amps
description: Post-processing script of the MaltExtract component of the HOPS package
keywords:
- malt
- MaltExtract
- HOPS
- amps
- alignment
- metagenomics
- ancient DNA
- aDNA
- palaeogenomics
- archaeogenomics
- microbiome
- authentication
- damage
- edit distance
- post Post-processing
- visualisation
tools:
- amps:
description: Post-processing script of the MaltExtract tool for ancient metagenomics
homepage: "https://github.com/rhuebler/HOPS"
documentation: "https://github.com/keyfm/amps"
tool_dev_url: "https://github.com/keyfm/amps"
doi: "10.1186/s13059-019-1903-0"
licence: ['GPL >=3']
input:
- maltextract_results:
type: directory
description: MaltExtract output directory
pattern: "results/"
- taxon_list:
type: file
description: List of target taxa to evaluate used in MaltExtract
pattern: "*.txt"
- filter:
type: string
description: The filter mode used in MaltExtract
pattern: "def_anc|default|scan|ancient|crawl"
output:
- version:
type: file
description: File containing software version
pattern: "versions.yml"
- json:
type: file
description: Candidate summary heatmap in MultiQC compatible JSON format
pattern: "heatmap_overview_Wevid.json"
- summary_pdf:
type: file
description: Candidate summary heatmap in PDF format
pattern: "heatmap_overview_Wevid.pdf"
- tsv:
type: file
description: Candidate summary heatmap in TSV format
pattern: "heatmap_overview_Wevid.tsv"
- candidate_pdfs:
type: directory
description: Directory of per sample output PDFs organised by reference
pattern: "pdf_candidate_profiles/"
authors:
- "@jfy133"

View file

@ -14,6 +14,10 @@ allelecounter:
- modules/allelecounter/**
- tests/modules/allelecounter/**
amps:
- modules/amps/**
- tests/modules/amps/**
arriba:
- modules/arriba/**
- tests/modules/arriba/**

View file

@ -0,0 +1,32 @@
#!/usr/bin/env nextflow
nextflow.enable.dsl = 2
include { UNZIP as UNZIP_MALT } from '../../../modules/unzip/main.nf' addParams( options: [:] )
include { UNZIP as UNZIP_MALTEXTRACT } from '../../../modules/unzip/main.nf' addParams( options: [:] )
include { MALT_BUILD } from '../../../modules/malt/build/main.nf' addParams( options: [:] )
include { MALT_RUN } from '../../../modules/malt/run/main.nf' addParams( options: [:] )
include { MALTEXTRACT } from '../../../modules/maltextract/main.nf' addParams( options: [args: "-f def_anc"] )
include { AMPS } from '../../../modules/amps/main.nf' addParams( options: [:] )
workflow test_amps {
fastas = file(params.test_data['sarscov2']['genome']['genome_fasta'], checkIfExists: true)
gff = []
seq_type = "DNA"
map_db = file("https://software-ab.informatik.uni-tuebingen.de/download/megan6/megan-nucl-Jan2021.db.zip", checkIfExists: true)
input = file(params.test_data['sarscov2']['illumina']['test_1_fastq_gz'], checkIfExists: true)
mode = "BlastN"
taxon_list = file(params.test_data['sarscov2']['genome']['taxon_list_txt'], checkIfExists: true)
ncbi_dir = file(params.test_data['sarscov2']['genome']['ncbi_taxmap_zip'], checkIfExists: true)
filter = "def_anc"
UNZIP_MALT ( map_db )
UNZIP_MALTEXTRACT ( ncbi_dir )
MALT_BUILD ( fastas, seq_type, gff, UNZIP_MALT.out.unzipped_archive )
MALT_RUN ( input, mode, MALT_BUILD.out.index )
MALTEXTRACT ( MALT_RUN.out.rma6, taxon_list, UNZIP_MALTEXTRACT.out.unzipped_archive)
AMPS ( MALTEXTRACT.out.results, taxon_list, filter )
}

View file

@ -0,0 +1,11 @@
- name: amps
command: nextflow run ./tests/modules/amps -entry test_amps -c tests/config/nextflow.config
tags:
- amps
files:
- path: output/amps/results/heatmap_overview_Wevid.json
md5sum: 82f484d02a9e3d0cc3d5bcdcc2965e44
- path: output/amps/results/heatmap_overview_Wevid.pdf
- path: output/amps/results/heatmap_overview_Wevid.tsv
md5sum: 1a7d565a37ef4d6054f7ade63fbadc2f
- path: output/amps/results/pdf_candidate_profiles/Severe_acute_respiratory_syndrome_coronavirus_2/stp1_test_1.rma6_Severe_acute_respiratory_syndrome_coronavirus_2_summary.pdf