Skip to content

Commit

Permalink
Update: Adds a step block to start directly on JaBbA
Browse files Browse the repository at this point in the history
  • Loading branch information
@tanubrata
tanubrata committed Nov 16, 2023
1 parent 86b25f5 commit b571820
Show file tree
Hide file tree
Showing 4 changed files with 144 additions and 34 deletions.
81 changes: 79 additions & 2 deletions assets/schema_input.json
View file
Original file line number Diff line number Diff line change
Expand Up @@ -163,11 +163,11 @@
"exists": true
},
"cov": {
"errorMessage": "COV file cannot contain spaces and must have extension '.rds'",
"errorMessage": "COV file cannot contain spaces and must have extension '.rds' or '.txt'",
"anyOf": [
{
"type": "string",
"pattern": "^\\S+\\.rds$"
"pattern": "^\\S+\\.(rds|txt)$"
},
{
"type": "string",
Expand All @@ -184,6 +184,14 @@
"type": "string",
"pattern": "^\\S+\\.txt$"
},
{
"type": "string",
"pattern": "^NA$"
},
{
"type": "string",
"pattern": "^/dev/null$"
},
{
"type": "string",
"maxLength": 0
Expand All @@ -207,6 +215,75 @@
"format": "file-path",
"exists": true
},
"vcf2": {
"errorMessage": "VCF file for reads 1 cannot contain spaces and must have extension '.vcf' or '.vcf.gz'",
"anyOf": [
{
"type": "string",
"pattern": "^\\S+\\.vcf(\\.gz)?$"
},
{
"type": "string",
"pattern": "^NA$"
},
{
"type": "string",
"pattern": "^/dev/null$"
},
{
"type": "string",
"maxLength": 0
}
],
"format": "file-path",
"exists": true
},
"seg": {
"errorMessage": "SEG file cannot contain spaces and must have extension '.rds'",
"anyOf": [
{
"type": "string",
"pattern": "^\\S+\\.rds$"
},
{
"type": "string",
"pattern": "^NA$"
},
{
"type": "string",
"pattern": "^/dev/null$"
},
{
"type": "string",
"maxLength": 0
}
],
"format": "file-path",
"exists": true
},
"nseg": {
"errorMessage": "NSEG file cannot contain spaces and must have extension '.rds'",
"anyOf": [
{
"type": "string",
"pattern": "^\\S+\\.rds$"
},
{
"type": "string",
"pattern": "^NA$"
},
{
"type": "string",
"pattern": "^/dev/null$"
},
{
"type": "string",
"maxLength": 0
}
],
"format": "file-path",
"exists": true
},
"variantcaller": {
"type": "string"
}
Expand Down
26 changes: 15 additions & 11 deletions modules/local/jabba/main.nf
View file
Original file line number Diff line number Diff line change
Expand Up @@ -3,17 +3,17 @@ process JABBA {
label 'process_high'

container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
'docker://mskilab/jabba:latest':
'/gpfs/commons/home/tdey/lab/singularity_files/nextflow_singularity_cache/mskilab-jabba_cplex-latest.img':
'mskilab/jabba:latest' }"

input:
tuple val(meta), path(cov_rds)
tuple val(meta), path(junction)
tuple val(meta), val(ploidy)
tuple val(meta), path(het_pileups_wgs)
tuple val(meta), path(cbs_seg_rds, stageAs: "cbs_seg.rds")
tuple val(meta), path(cbs_nseg_rds, stageAs: "cbs_nseg.rds")
tuple val(meta), path(j_supp)
tuple val(meta), val(het_pileups_wgs)
tuple val(meta), val(cbs_seg_rds)
tuple val(meta), val(cbs_nseg_rds)
tuple val(meta), val(j_supp)
val(blacklist_junctions) // this is declared as val to allow for "NULL" default value, but is treated like a path
val(geno)
val(indel)
Expand All @@ -35,7 +35,6 @@ process JABBA {
val(linear)
val(tilim)
val(epgap)
val(name)
val(fix_thres)
val(lp)
val(ism)
Expand Down Expand Up @@ -64,6 +63,11 @@ process JABBA {
def allin_switch = allin == "TRUE" ? "--allin" : ""
def linear_switch = linear == "TRUE" ? "--linear" : ""
def verbose_switch = verbose == "TRUE" ? "--verbose" : ""
def cbs_seg_rds = cbs_seg_rds == '/dev/null' || cbs_seg_rds == 'NA' || cbs_seg_rds == 'NULL' ? "" : "--seg ${cbs_seg_rds}"
def cbs_nseg_rds = cbs_nseg_rds == '/dev/null' || cbs_nseg_rds == 'NA' || cbs_nseg_rds == 'NULL' ? "" : "--nseg ${cbs_nseg_rds}"
def het_pileups_wgs = het_pileups_wgs == '/dev/null' || het_pileups_wgs == 'NA' || het_pileups_wgs == 'NULL' ? "" : "--hets ${het_pileups_wgs}"
def j_supp = j_supp == '/dev/null' || j_supp == 'NA' || j_supp == 'NULL' ? "" : "--j.supp ${j_supp}"


def VERSION = '1.1'
"""
Expand Down Expand Up @@ -96,7 +100,7 @@ process JABBA {
export cmd="Rscript \$jba $junction $cov_rds \\
--blacklist.junctions $blacklist_junctions \\
$geno_switch \\
--j.supp $j_supp \\
$j_supp \\
--indel $indel \\
--tfield $tfield \\
--iterate $iter \\
Expand All @@ -107,11 +111,11 @@ process JABBA {
$strict_switch \\
$allin_switch \\
--field $field \\
--seg $cbs_seg_rds \\
$cbs_seg_rds \\
--maxna $maxna \\
--blacklist.coverage $blacklist_coverage \\
--nseg $cbs_nseg_rds \\
--hets $het_pileups_wgs \\
$cbs_nseg_rds \\
$het_pileups_wgs \\
--ploidy $ploidy \\
--purity $purity \\
--ppmethod $pp_method \\
Expand All @@ -120,7 +124,7 @@ process JABBA {
$linear_switch \\
--tilim $tilim \\
--epgap $epgap \\
--name $name \\
--name ${meta.patient} \\
--cores $task.cpus \\
--fix.thres $fix_thres \\
--lp $lp \\
Expand Down
6 changes: 2 additions & 4 deletions subworkflows/local/jabba/main.nf
View file
Original file line number Diff line number Diff line change
Expand Up @@ -35,7 +35,6 @@ workflow COV_JUNC_JABBA {
linear_jabba
tilim_jabba
epgap_jabba
name_jabba
fix_thres_jabba
lp_jabba
ism_jabba
Expand All @@ -59,9 +58,8 @@ workflow COV_JUNC_JABBA {
iter_jabba, rescue_window_jabba, rescue_all_jabba, nudgebalanced_jabba,
edgenudge_jabba, strict_jabba, allin_jabba, field_jabba, maxna_jabba,
blacklist_coverage_jabba, purity_jabba, pp_method_jabba, cnsignif_jabba,
slack_jabba, linear_jabba, tilim_jabba, epgap_jabba, name_jabba,
fix_thres_jabba, lp_jabba, ism_jabba, filter_loose_jabba, gurobi_jabba,
verbose_jabba)
slack_jabba, linear_jabba, tilim_jabba, epgap_jabba, fix_thres_jabba, lp_jabba,
ism_jabba, filter_loose_jabba, gurobi_jabba, verbose_jabba)

jabba_rds = JABBA.out.jabba_rds
jabba_gg = JABBA.out.jabba_gg
Expand Down
65 changes: 48 additions & 17 deletions workflows/nfjabba.nf
View file
Original file line number Diff line number Diff line change
Expand Up @@ -91,9 +91,9 @@ if (params.input) {
}

input_sample = ch_from_samplesheet
.map{ meta, fastq_1, fastq_2, table, cram, crai, bam, bai, cov, hets, vcf, variantcaller ->
.map{ meta, fastq_1, fastq_2, table, cram, crai, bam, bai, cov, hets, vcf, vcf2, seg, nseg, variantcaller ->
// generate patient_sample key to group lanes together
[ meta.patient + meta.sample, [meta, fastq_1, fastq_2, table, cram, crai, bam, bai, cov, hets, vcf, variantcaller] ]
[ meta.patient + meta.sample, [meta, fastq_1, fastq_2, table, cram, crai, bam, bai, cov, hets, vcf, vcf2, seg, nseg, variantcaller] ]
}
.tap{ ch_with_patient_sample } // save the channel
.groupTuple() //group by patient_sample to get all lanes
Expand All @@ -104,7 +104,7 @@ input_sample = ch_from_samplesheet
.combine(ch_with_patient_sample, by: 0) // for each entry add numLanes
.map { patient_sample, num_lanes, ch_items ->

(meta, fastq_1, fastq_2, table, cram, crai, bam, bai, cov, hets, vcf, variantcaller) = ch_items
(meta, fastq_1, fastq_2, table, cram, crai, bam, bai, cov, hets, vcf, vcf2, seg, nseg, variantcaller) = ch_items
if (meta.lane && fastq_2) {
meta = meta + [id: "${meta.sample}-${meta.lane}".toString()]
def CN = params.seq_center ? "CN:${params.seq_center}\\t" : ''
Expand Down Expand Up @@ -172,6 +172,14 @@ input_sample = ch_from_samplesheet
error("Samplesheet contains bam files but step is `$params.step`. Please check your samplesheet or adjust the step parameter.")
}
// hetpileups
} else if (cov && hets && vcf && vcf2 && seg && nseg) {
meta = meta + [id: meta.sample, data_type: ['cov', 'vcf', 'hets', 'seg']]

if (params.step == 'jabba') return [ meta - meta.subMap('lane'), cov, hets, vcf, vcf2, seg, nseg ]
else {
error("Samplesheet contains cov .rds and vcf files but step is `$params.step`. Please check your samplesheet or adjust the step parameter.")
}
// dryclean
} else if (cov && hets) {
meta = meta + [id: meta.sample, data_type: ['cov', 'hets']]

Expand All @@ -180,14 +188,6 @@ input_sample = ch_from_samplesheet
error("Samplesheet contains cov .rds and hets .txt files but step is `$params.step`. Please check your samplesheet or adjust the step parameter.")
}
// jabba
} else if (cov && vcf) {
meta = meta + [id: meta.sample, data_type: ['vcf', 'cov']]

if (params.step == 'jabba') return [ meta - meta.subMap('lane'), vcf, cov]
else {
error("Samplesheet contains cov .rds and vcf files but step is `$params.step`. Please check your samplesheet or adjust the step parameter.")
}
// dryclean
} else if (cov) {
meta = meta + [id: meta.sample, data_type: 'cov']

Expand Down Expand Up @@ -327,7 +327,7 @@ allin_jabba = params.allin_jabba ?: Channel.empty()
field_jabba = params.field_jabba ?: Channel.empty()
maxna_jabba = params.maxna_jabba ?: Channel.empty()
purity_jabba = params.purity_jabba ?: Channel.empty()
//ploidy_jabba = params.ploidy_jabba ?: Channel.empty()
ploidy_jab = params.ploidy_jabba ?: Channel.empty()
pp_method_jabba = params.pp_method_jabba ?: Channel.empty()
cnsignif_jabba = params.cnsignif_jabba ?: Channel.empty()
slack_jabba = params.slack_jabba ?: Channel.empty()
Expand Down Expand Up @@ -456,9 +456,9 @@ include { COV_DRYCLEAN as NORMAL_DRYCLEAN } from '../subworkflows/l
//ASCAT
include { COV_ASCAT } from '../subworkflows/local/cov_ascat/main'

include { COV_CBS as CBS } from '../subworkflows/local/cov_cbs/main'
include { COV_CBS as CBS } from '../subworkflows/local/cov_cbs/main'

include { COV_JUNC_JABBA as JABBA } from '../subworkflows/local/jabba/main'
include { COV_JUNC_JABBA as JABBA } from '../subworkflows/local/jabba/main'
/*
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
RUN MAIN WORKFLOW
Expand Down Expand Up @@ -1189,15 +1189,46 @@ workflow NFJABBA {

if (params.step in ['alignment', 'markduplicates', 'prepare_recalibration', 'recalibrate', 'sv_calling', 'fragcounter', 'hetpileups', 'dryclean', 'jabba']) {

if (params.step == 'jabba') {
input_jabba = input_sample
.map{ meta, cov, hets, vcf, vcf2, seg, nseg -> [ meta + [data_type: ['cov','hets','vcf','seg']], cov, hets, vcf, vcf2, seg, nseg ] }

input_cov_jabba = input_jabba
.map{ meta, cov, hets, vcf, vcf2, seg, nseg -> [ meta, cov ] }

input_hets_jabba = input_jabba
.map{ meta, cov, hets, vcf, vcf2, seg, nseg -> [ meta, hets ] }

input_vcf_jabba = input_jabba
.map{ meta, cov, hets, vcf, vcf2, seg, nseg -> [ meta, vcf ] }

input_vcf2_jabba = input_jabba
.map{ meta, cov, hets, vcf, vcf2, seg, nseg -> [ meta, vcf2 ] }

input_seg_jabba = input_jabba
.map{ meta, cov, hets, vcf, vcf2, seg, nseg -> [ meta, seg ] }

input_nseg_jabba = input_jabba
.map{ meta, cov, hets, vcf, vcf2, seg, nseg -> [ meta, nseg ] }

tumor_dryclean_cov = Channel.empty().mix(input_cov_jabba)
sites_from_het_pileups_wgs = Channel.empty().mix(input_hets_jabba)
vcf_from_sv_calling = Channel.empty().mix(input_vcf_jabba)
unfiltered_som_sv = Channel.empty().mix(input_vcf2_jabba)
cbs_seg_rds = Channel.empty().mix(input_seg_jabba)
cbs_nseg_rds = Channel.empty().mix(input_nseg_jabba)
}

if (params.tools && params.tools.split(',').contains('jabba')) {
//ploidy_jabba = "NA"
if (params.tools && params.tools.split(',').contains('ascat')) {
ploidy_jabba = ploidy
} else {
ploidy_jabba = input_sample.map{ meta -> [ meta, ploidy_jabba ] }
ploidy_jabba = input_sample.map{ tuple -> [ tuple[0], ploidy_jab ] }
}

//name_jabba = input_sample .map{ meta -> meta.id }
name_jabba = 'tumor'
//name_jabba = 'tumor'

JABBA(tumor_dryclean_cov, vcf_from_sv_calling, ploidy_jabba,
sites_from_het_pileups_wgs, cbs_seg_rds, cbs_nseg_rds,
Expand All @@ -1207,7 +1238,7 @@ workflow NFJABBA {
strict_jabba, allin_jabba, field_jabba, maxna_jabba,
blacklist_coverage_jabba, purity_jabba, pp_method_jabba,
cnsignif_jabba, slack_jabba, linear_jabba, tilim_jabba,
epgap_jabba, name_jabba, fix_thres_jabba, lp_jabba,
epgap_jabba, fix_thres_jabba, lp_jabba,
ism_jabba, filter_loose_jabba, gurobi_jabba,
verbose_jabba)

Expand Down

0 comments on commit b571820

Please sign in to comment.