Skip to content

Commit

Permalink
Fix ch_dbsnp channel (#39)
Browse files Browse the repository at this point in the history
* fix typo for bwaIndex in params.genomes[params.genome]
* add more logs for reference Files
* fix params.dbsnpIndex
* remove bwaIndex from smallGRCh37
* fix ch_dbsnp
* update CHANGELOG
  • Loading branch information
maxulysse authored Sep 27, 2019
1 parent dc6cf30 commit 64d9c10
Show file tree
Hide file tree
Showing 3 changed files with 26 additions and 17 deletions.
1 change: 1 addition & 0 deletions CHANGELOG.md
Original file line number Diff line number Diff line change
Expand Up @@ -125,6 +125,7 @@ Initial release of `nf-core/sarek`, created with the [nf-core](http://nf-co.re/)
- [#31](https://github.com/nf-core/sarek/pull/31) - Fix rcolorbrewer version according to nf-core lint
- [#33](https://github.com/nf-core/sarek/pull/33) - Fix MD Linting
- [#38](https://github.com/nf-core/sarek/pull/38) - Avoid collision in MultiQC
- [#39](https://github.com/nf-core/sarek/pull/39) - Fix `ch_dbsnp` channel

### `Deprecated`

Expand Down
1 change: 0 additions & 1 deletion conf/genomes.config
Original file line number Diff line number Diff line change
Expand Up @@ -50,7 +50,6 @@ params {
'smallGRCh37' {
acLoci = "${params.genomes_base}/1000G_phase3_20130502_SNP_maf0.3.small.loci"
acLociGC = "${params.genomes_base}/1000G_phase3_20130502_SNP_maf0.3.small.loci.gc"
bwaIndex = "${params.genomes_base}/human_g1k_v37_decoy.small.fasta.{amb,ann,bwt,pac,sa}"
dbsnp = "${params.genomes_base}/dbsnp_138.b37.small.vcf.gz"
fasta = "${params.genomes_base}/human_g1k_v37_decoy.small.fasta"
germlineResource = "${params.genomes_base}/dbsnp_138.b37.small.vcf.gz"
Expand Down
41 changes: 25 additions & 16 deletions main.nf
Original file line number Diff line number Diff line change
Expand Up @@ -144,7 +144,7 @@ params.fasta = params.genome && !('annotate' in step) ? params.genomes[params.ge
// The rest can be sorted
params.acLoci = params.genome && 'ascat' in tools ? params.genomes[params.genome].acLoci ?: null : null
params.acLociGC = params.genome && 'ascat' in tools ? params.genomes[params.genome].acLociGC ?: null : null
params.bwaIndex = params.genome && params.fasta && 'mapping' in step ? params.genomes[params.genome].bwa ?: null : null
params.bwaIndex = params.genome && params.fasta && 'mapping' in step ? params.genomes[params.genome].bwaIndex ?: null : null
params.chrDir = params.genome && 'controlfreec' in tools ? params.genomes[params.genome].chrDir ?: null : null
params.chrLength = params.genome && 'controlfreec' in tools ? params.genomes[params.genome].chrLength ?: null : null
params.dbsnp = params.genome && ('mapping' in step || 'controlfreec' in tools || 'haplotypecaller' in tools || 'mutect2' in tools) ? params.genomes[params.genome].dbsnp ?: null : null
Expand Down Expand Up @@ -238,10 +238,10 @@ ch_fastaFai = params.fastaFai && !('annotate' in step) ? Channel.value(file(para
ch_germlineResource = params.germlineResource && 'mutect2' in tools ? Channel.value(file(params.germlineResource)) : "null"
ch_intervals = params.intervals && !('annotate' in step) ? Channel.value(file(params.intervals)) : "null"

// knownIndels is currently a list of file, so transform it in a channel
// knownIndels is currently a list of file for smallGRCh37, so transform it in a channel
li_knownIndels = []
if (params.knownIndels && ('mapping' in step)) params.knownIndels.each { li_knownIndels.add(file(it)) }
ch_knownIndels = params.knownIndels ? Channel.value(li_knownIndels.collect()) : "null"
ch_knownIndels = params.knownIndels && params.genome == 'smallGRCh37' ? Channel.value(li_knownIndels.collect()) : params.knownIndels ? Channel.value(file(params.knownIndels)) : "null"

ch_snpEff_cache = params.snpEff_cache ? Channel.value(file(params.snpEff_cache)) : "null"
ch_snpeffDb = params.snpeffDb ? Channel.value(params.snpeffDb) : "null"
Expand Down Expand Up @@ -287,18 +287,25 @@ summary['Launch dir'] = workflow.launchDir
summary['Working dir'] = workflow.workDir
summary['Script dir'] = workflow.projectDir
summary['User'] = workflow.userName

if (params.acLoci) summary['acLoci'] = params.acLoci
if (params.acLociGC) summary['acLociGC'] = params.acLociGC
if (params.chrDir) summary['chrDir'] = params.chrDir
if (params.chrLength) summary['chrLength'] = params.chrLength
if (params.dbsnp) summary['dbsnp'] = params.dbsnp
if (params.fasta) summary['fasta'] = params.fasta
if (params.germlineResource) summary['germlineResource'] = params.germlineResource
if (params.intervals) summary['intervals'] = params.intervals
if (params.knownIndels) summary['knownIndels'] = params.knownIndels.join(', ')
if (params.snpeffDb) summary['snpeffDb'] = params.snpeffDb
if (params.vepCacheVersion) summary['vepCacheVersion'] = params.vepCacheVersion
summary['genome'] = params.genome

if (params.fasta) summary['fasta'] = params.fasta
if (params.fastaFai) summary['fastaFai'] = params.fastaFai
if (params.dict) summary['dict'] = params.dict
if (params.bwaIndex) summary['bwaIndex'] = params.bwaIndex
if (params.germlineResource) summary['germlineResource'] = params.germlineResource
if (params.germlineResourceIndex) summary['germlineResourceIndex'] = params.germlineResourceIndex
if (params.intervals) summary['intervals'] = params.intervals
if (params.acLoci) summary['acLoci'] = params.acLoci
if (params.acLociGC) summary['acLociGC'] = params.acLociGC
if (params.chrDir) summary['chrDir'] = params.chrDir
if (params.chrLength) summary['chrLength'] = params.chrLength
if (params.dbsnp) summary['dbsnp'] = params.dbsnp
if (params.dbsnpIndex) summary['dbsnpIndex'] = params.dbsnpIndex
if (params.knownIndels) summary['knownIndels'] = params.knownIndels
if (params.knownIndelsIndex) summary['knownIndelsIndex'] = params.knownIndelsIndex
if (params.snpeffDb) summary['snpeffDb'] = params.snpeffDb
if (params.vepCacheVersion) summary['vepCacheVersion'] = params.vepCacheVersion

if (workflow.profile == 'awsbatch') {
summary['AWS Region'] = params.awsregion
Expand Down Expand Up @@ -758,6 +765,8 @@ markDuplicatesReport = markDuplicatesReport.dump(tag:'MD Report')
(bamMD, bamMDToJoin) = duplicateMarkedBams.into(2)
bamBaseRecalibrator = bamMD.combine(intBaseRecalibrator)

bamBaseRecalibrator = bamBaseRecalibrator.dump(tag:'BAM FOR BASERECALIBRATOR')

// STEP 3: CREATING RECALIBRATION TABLES

process BaseRecalibrator {
Expand All @@ -770,8 +779,8 @@ process BaseRecalibrator {
set idPatient, idSample, file(bam), file(bai), file(intervalBed) from bamBaseRecalibrator
file(dbsnp) from ch_dbsnp
file(dbsnpIndex) from ch_dbsnpIndex
file(dict) from ch_dict
file(fasta) from ch_fasta
file(dict) from ch_dict
file(fastaFai) from ch_fastaFai
file(knownIndels) from ch_knownIndels
file(knownIndelsIndex) from ch_knownIndelsIndex
Expand Down

0 comments on commit 64d9c10

Please sign in to comment.