Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

all intervals stuff in out of main.nf #247

Merged
merged 9 commits into from
Jul 17, 2020
Merged

all intervals stuff in out of main.nf #247

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
9 commits
Select commit Hold shift + click to select a range
87df112
update Nextflow version to 20.06.0-edge
maxulysse Jul 16, 2020
5d53898
skip_qc is back + collect() too as it was actually useful
maxulysse Jul 16, 2020
1756f81
fix bwa-mem2 version
maxulysse Jul 16, 2020
be8b3d2
remove unused params(params) and addParams(params)
maxulysse Jul 16, 2020
f683c50
center headers
maxulysse Jul 16, 2020
5d8fc2b
all intervals stuff in out of main.nf
maxulysse Jul 16, 2020
b8df2dd
restore multiple channels for bedintervals
maxulysse Jul 16, 2020
1e15297
code polishing
maxulysse Jul 16, 2020
cfb2ffd
further polishing
maxulysse Jul 16, 2020
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 1 addition & 1 deletion README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2,7 +2,7 @@

> **An open-source analysis pipeline to detect germline or somatic variants from whole genome or targeted sequencing**

[![Nextflow](https://img.shields.io/badge/nextflow-%E2%89%A520.04.1-brightgreen.svg)](https://www.nextflow.io/)
[![Nextflow](https://img.shields.io/badge/nextflow-%E2%89%A520.06.0--edge-brightgreen.svg)](https://www.nextflow.io/)
[![nf-core](https://img.shields.io/badge/nf--core-pipeline-brightgreen.svg)](https://nf-co.re/)
[![DOI](https://zenodo.org/badge/184289291.svg)](https://zenodo.org/badge/latestdoi/184289291)

Expand Down
2 changes: 1 addition & 1 deletion bin/scrape_software_versions.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -7,7 +7,7 @@
'AlleleCount': ['v_allelecount.txt', r"(\S+)"],
'ASCAT': ['v_ascat.txt', r"Version: (\S+)"],
'bcftools': ['v_bcftools.txt', r"bcftools (\S+)"],
'BWAMEM2': ['v_bwamem2.txt', r"Version: (\S+)"],
'BWA-MEM2': ['v_bwamem2.txt', r"(\S+)"],
'CNVkit': ['v_cnvkit.txt', r"(\S+)"],
'Control-FREEC': ['v_controlfreec.txt', r"Control-FREEC\s(\S+)"],
'FastQC': ['v_fastqc.txt', r"FastQC v(\S+)"],
Expand Down
69 changes: 27 additions & 42 deletions main.nf
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -38,6 +38,7 @@ if (params.help) {
include {
check_parameter_existence;
check_parameter_list;
define_skip_qc_list;
define_step_list;
define_tool_list;
extract_bam;
Expand Down Expand Up @@ -86,9 +87,9 @@ tools = params.tools ? params.tools.split(',').collect{it.trim().toLowerCase().r
if (step == 'controlfreec') tools = ['controlfreec']
if (!check_parameter_list(tools, tool_list)) exit 1, 'Unknown tool(s), see --help for more information'

// skip_qc_list = define_skip_qc_list()
// skip_qc = params.skip_qc ? params.skip_qc == 'all' ? skip_qc_list : params.skip_qc.split(',').collect{it.trim().toLowerCase().replaceAll('-', '').replaceAll('_', '')} : []
// if (!check_parameter_list(skip_qc, skip_qc_list)) exit 1, 'Unknown QC tool(s), see --help for more information'
skip_qc_list = define_skip_qc_list()
skip_qc = params.skip_qc ? params.skip_qc == 'all' ? skip_qc_list : params.skip_qc.split(',').collect{it.trim().toLowerCase().replaceAll('-', '').replaceAll('_', '')} : []
if (!check_parameter_list(skip_qc, skip_qc_list)) exit 1, 'Unknown QC tool(s), see --help for more information'

// anno_list = define_anno_list()
// annotate_tools = params.annotate_tools ? params.annotate_tools.split(',').collect{it.trim().toLowerCase().replaceAll('-', '')} : []
Expand Down Expand Up @@ -248,23 +249,31 @@ if (params.sentieon) log.warn "[nf-core/sarek] Sentieon will be used, only works

/*
================================================================================
INCLUDE LOCAL PIPELINE MODULES
INCLUDE LOCAL PIPELINE MODULES
================================================================================
*/

include { BWAMEM2_MEM } from './modules/local/bwamem2_mem.nf' addParams(params)
include { GET_SOFTWARE_VERSIONS } from './modules/local/get_software_versions' params(params)
include { OUTPUT_DOCUMENTATION } from './modules/local/output_documentation' params(params)
include { TRIM_GALORE } from './modules/local/trim_galore.nf' addParams(params)
include { BWAMEM2_MEM } from './modules/local/bwamem2_mem.nf'
include { GET_SOFTWARE_VERSIONS } from './modules/local/get_software_versions'
include { OUTPUT_DOCUMENTATION } from './modules/local/output_documentation'
include { TRIM_GALORE } from './modules/local/trim_galore.nf'

/*
================================================================================
INCLUDE LOCAL PIPELINE SUBWORKFLOWS
================================================================================
*/

include { BUILD_INDICES } from './modules/subworkflows/build_indices'

/*
================================================================================
INCLUDE nf-core PIPELINE MODULES
================================================================================
*/

include { FASTQC } from './modules/nf-core/fastqc' params(params)
include { MULTIQC } from './modules/nf-core/multiqc' params(params)
include { FASTQC } from './modules/nf-core/fastqc'
include { MULTIQC } from './modules/nf-core/multiqc'

// PREPARING CHANNELS FOR PREPROCESSING AND QC

Expand Down Expand Up @@ -313,8 +322,6 @@ include { MULTIQC } from './modules/nf-core/multiqc' params(params)
================================================================================
*/

include { BUILD_INDICES } from './modules/subworkflows/build_indices' addParams(params)

workflow {

BUILD_INDICES(
Expand All @@ -331,39 +338,17 @@ workflow {
dict = params.dict ?: BUILD_INDICES.out.dict
fai = params.fasta_fai ? params.fasta_fai : BUILD_INDICES.out.fai
germline_resource_tbi = params.germline_resource ? params.germline_resource_index ?: BUILD_INDICES.out.germline_resource_tbi : Channel.empty()
intervals_bed = params.no_intervals ? Channel.empty() : BUILD_INDICES.out.intervals_bed
known_indels_tbi = params.known_indels ? params.known_indels_index ?: BUILD_INDICES.out.known_indels_tbi : Channel.empty()
// known_indels_tbi = params.known_indels ? params.known_indels_index ?: BUILD_INDICES.out.known_indels_tbi.collect() : Channel.empty()
intervals_bed = BUILD_INDICES.out.intervals_bed
known_indels_tbi = params.known_indels ? params.known_indels_index ?: BUILD_INDICES.out.known_indels_tbi.collect() : Channel.empty()
pon_tbi = params.pon ? params.pon_index ?: BUILD_INDICES.out.pon_tbi : Channel.empty()

// PREPROCESSING

// BED INTERVAL CHANNEL TRANSFORMING
intervals_bed.flatten()
.map { intervalFile ->
def duration = 0.0
for (line in intervalFile.readLines()) {
final fields = line.split('\t')
if (fields.size() >= 5) duration += fields[4].toFloat()
else {
start = fields[1].toInteger()
end = fields[2].toInteger()
duration += (end - start) / params.nucleotides_per_second
}
}
[ duration, intervalFile]
}.toSortedList({ a, b -> b[0] <=> a[0] })
.flatten().collate(2)
.map{duration, intervalFile -> intervalFile}
intervals_bed.dump(tag:'bedintervals')

if (params.no_intervals && step != 'annotate') {
file("${params.outdir}/no_intervals.bed").text = "no_intervals\n"
intervals_bed = Channel.from(file("${params.outdir}/no_intervals.bed"))
}

// if(!('fastqc' in skip_qc))
FASTQC(input_sample)
if(!('fastqc' in skip_qc))
result_fastqc = FASTQC(input_sample)
else
result_fastqc = Channel.empty()

if (params.trim_fastq) {
TRIM_GALORE(input_sample)
Expand All @@ -382,11 +367,11 @@ workflow {
GET_SOFTWARE_VERSIONS()

MULTIQC(
FASTQC.out.ifEmpty([]),
result_fastqc.collect().ifEmpty([]),
multiqc_config,
multiqc_custom_config.ifEmpty([]),
GET_SOFTWARE_VERSIONS.out.yml,
result_trim_galore.ifEmpty([]),
result_trim_galore.collect().ifEmpty([]),
workflow_summary)
}

Expand Down
26 changes: 23 additions & 3 deletions modules/subworkflows/build_indices.nf
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -65,13 +65,33 @@ workflow BUILD_INDICES{
else
result_pon_tbi = Channel.empty()

if (!('annotate' in step) && !('controlfreec' in step))
if (params.no_intervals) {
file("${params.outdir}/no_intervals.bed").text = "no_intervals\n"
result_intervals = Channel.from(file("${params.outdir}/no_intervals.bed"))
} else if (!('annotate' in step) && !('controlfreec' in step))
if (!params.intervals)
result_intervals = CREATE_INTERVALS_BED(BUILD_INTERVALS(SAMTOOLS_FAIDX.out))
else
result_intervals = CREATE_INTERVALS_BED(params.intervals)
else
result_intervals = Channel.empty()

if (!params.no_intervals) {
result_intervals = result_intervals.flatten()
.map { intervalFile ->
def duration = 0.0
for (line in intervalFile.readLines()) {
final fields = line.split('\t')
if (fields.size() >= 5) duration += fields[4].toFloat()
else {
start = fields[1].toInteger()
end = fields[2].toInteger()
duration += (end - start) / params.nucleotides_per_second
}
}
[duration, intervalFile]
}.toSortedList({ a, b -> b[0] <=> a[0] })
.flatten().collate(2)
.map{duration, intervalFile -> intervalFile}
}

emit:
bwa = result_bwa
Expand Down