Skip to content

Commit 2867f84

Browse files
guanqiaofengguanqiaofeng
committed
cleanup code, cleanup step running correctly. Need to 1. make sure PREP_REF_TRANS runs when needed 2. handle PREP_REF_TRANS in cleanup 3. add output redirectory setting
1 parent 79844ec commit 2867f84

File tree

3 files changed

+14
-117
lines changed

3 files changed

+14
-117
lines changed

‎modules/icgc-argo-workflows/checkinput/main.nf

+4-4
Original file line numberDiff line numberDiff line change
@@ -18,7 +18,7 @@ process CHECKINPUT {
1818
when:
1919
task.ext.when == null || task.ext.when
2020

21-
script:
21+
script:
2222
"""
2323
case '$workflow_name' in
2424
'Pre Alignment QC')
@@ -32,12 +32,12 @@ process CHECKINPUT {
3232
$samplesheet \\
3333
samplesheet.valid.csv
3434
;;
35-
'DNA Alignment')
35+
'DNA Seq Alignment')
3636
dnaaln.py \\
3737
$samplesheet \\
3838
samplesheet.valid.csv
3939
;;
40-
'RNA Alignment')
40+
'RNA Seq Alignment')
4141
rnaaln.py \\
4242
$samplesheet \\
4343
samplesheet.valid.csv
@@ -58,4 +58,4 @@ process CHECKINPUT {
5858
python: \$(python --version | sed 's/Python //g')
5959
END_VERSIONS
6060
"""
61-
}
61+
}

‎subworkflows/local/gen_transcript_ref/main.nf

-1
Original file line numberDiff line numberDiff line change
@@ -27,7 +27,6 @@ workflow PREP_REF_TRANS {
2727
ch_versions = ch_versions.mix(SAMTOOLS_FAIDX.out.versions)
2828

2929
trans_ref = GFFREAD.out.gffread_fasta.mix(SAMTOOLS_FAIDX.out.fai)
30-
trans_ref.subscribe { println("PREP_TRAN_REF: ${it}") }
3130

3231
emit:
3332
trans_ref = trans_ref

‎workflows/rnaaln.nf

+10-112
Original file line numberDiff line numberDiff line change
@@ -11,21 +11,14 @@ include { STAR_ALIGN } from '../modules/local/star/align/main'
1111
include { MERGE_DUP as MERG_DUP_S } from '../subworkflows/icgc-argo-workflows/merge_dup/main'
1212
include { MERGE_DUP as MERG_DUP_ST } from '../subworkflows/icgc-argo-workflows/merge_dup/main'
1313
include { MERGE_DUP as MERG_DUP_H } from '../subworkflows/icgc-argo-workflows/merge_dup/main'
14-
// include { PAYLOAD_ALIGNMENT as PAYLOAD_ALIGNMENT_S } from '../modules/local/payload/rnaseqalignment/main'
15-
// include { PAYLOAD_ALIGNMENT as PAYLOAD_ALIGNMENT_ST } from '../modules/local/payload/rnaseqalignment/main'
16-
// include { PAYLOAD_ALIGNMENT as PAYLOAD_ALIGNMENT_H } from '../modules/local/payload/rnaseqalignment/main'
17-
1814
include { PAYLOAD_ALIGNMENT as PAYLOAD_ALIGNMENT_S } from '../modules/icgc-argo-workflows/payload/alignment/main'
1915
include { PAYLOAD_ALIGNMENT as PAYLOAD_ALIGNMENT_ST } from '../modules/icgc-argo-workflows/payload/alignment/main'
2016
include { PAYLOAD_ALIGNMENT as PAYLOAD_ALIGNMENT_H } from '../modules/icgc-argo-workflows/payload/alignment/main'
21-
2217
include { SONG_SCORE_UPLOAD as UPLOAD_ALIGNMENT_S } from '../subworkflows/icgc-argo-workflows/song_score_upload/main'
2318
include { SONG_SCORE_UPLOAD as UPLOAD_ALIGNMENT_ST } from '../subworkflows/icgc-argo-workflows/song_score_upload/main'
2419
include { SONG_SCORE_UPLOAD as UPLOAD_ALIGNMENT_H } from '../subworkflows/icgc-argo-workflows/song_score_upload/main'
2520
include { MERGE_SPLICE_JUNCTION as MERGE_SPLICE_JUNCTION_S } from '../modules/local/merge_splice_junction/main.nf'
2621
include { MERGE_SPLICE_JUNCTION as MERGE_SPLICE_JUNCTION_H } from '../modules/local/merge_splice_junction/main.nf'
27-
// include { PAYLOAD_SPLICE_JUNCTION as PAYLOAD_SPLICE_JUNCTION_S } from '../modules/local/payload/novel_splice/main'
28-
// include { PAYLOAD_SPLICE_JUNCTION as PAYLOAD_SPLICE_JUNCTION_H } from '../modules/local/payload/novel_splice/main'
2922
include { PAYLOAD_SPLICE_JUNCTION as PAYLOAD_SPLICE_JUNCTION_S } from '../modules/icgc-argo-workflows/payload/splicejunction/main'
3023
include { PAYLOAD_SPLICE_JUNCTION as PAYLOAD_SPLICE_JUNCTION_H } from '../modules/icgc-argo-workflows/payload/splicejunction/main'
3124
include { SONG_SCORE_UPLOAD as UPLOAD_NOVEL_SPLICE_S } from '../subworkflows/icgc-argo-workflows/song_score_upload/main'
@@ -36,8 +29,6 @@ include { SAMTOOLS_STATS as SAMTOOLS_STATS_S } from '../modules/nf-core/samtools
3629
include { SAMTOOLS_STATS as SAMTOOLS_STATS_H } from '../modules/nf-core/samtools/stats/main'
3730
include { MULTIQC as MULTIQC_S } from '../modules/nf-core/multiqc/main'
3831
include { MULTIQC as MULTIQC_H } from '../modules/nf-core/multiqc/main'
39-
// include { PREP_METRICS as PREP_METRICS_S } from '../modules/local/prep/rnametrics/main'
40-
// include { PREP_METRICS as PREP_METRICS_H } from '../modules/local/prep/rnametrics/main'
4132
include { PREP_METRICS as PREP_METRICS_S } from '../modules/icgc-argo-workflows/prep/metrics/main'
4233
include { PREP_METRICS as PREP_METRICS_H } from '../modules/icgc-argo-workflows/prep/metrics/main'
4334
include { PAYLOAD_QCMETRICS as PAYLOAD_QCMETRICS_S} from '../modules/icgc-argo-workflows/payload/qcmetrics/main'
@@ -69,18 +60,17 @@ workflow RNAALN {
6960
)
7061

7162
ch_versions = ch_versions.mix(STAGE_INPUT.out.versions)
72-
// STAGE_INPUT.out.meta_files.subscribe { println("Meta Files Output: ${it}") }
7363

7464
// Prepare reference file [meta fasta] [meta, fai]
7565
ch_ref = Channel.fromPath(params.reference_fasta)
7666
.map{ path -> [ [id: 'fasta'], path ] }
7767
.mix( Channel.fromPath(params.reference_fai)
7868
.map{ path -> [ [id: 'fai'], path ] } )
7969

80-
// ch_ref_trans = Channel.fromPath(params.reference_trans_fasta)
81-
// .map{ path -> [ [id: 'fasta'], path ] }
82-
// .mix( Channel.fromPath(params.reference_trans_fai)
83-
// .map{ path -> [ [id: 'fai'], path ] } )
70+
ch_ref_trans = Channel.fromPath(params.reference_trans_fasta)
71+
.map{ path -> [ [id: 'fasta'], path ] }
72+
.mix( Channel.fromPath(params.reference_trans_fai)
73+
.map{ path -> [ [id: 'fai'], path ] } )
8474

8575
// HISAT2 //
8676
if (params.tools.split(',').contains('hisat2_aln')){
@@ -107,8 +97,6 @@ workflow RNAALN {
10797
)
10898
ch_versions = ch_versions.mix(MERG_DUP_H.out.versions)
10999

110-
// MERG_DUP_H.out.cram_alignment_index.map { meta, cram, crai -> [meta, cram] }.subscribe{ println("MERGE dup no crai: ${it}") }
111-
112100
// Combine channels to determine upload status and payload creation
113101
MERG_DUP_H.out.cram_alignment_index
114102
.combine(STAGE_INPUT.out.upRdpc)
@@ -145,8 +133,6 @@ workflow RNAALN {
145133
.mix(HISAT2_ALIGN.out.versions)
146134
.mix(MERG_DUP_H.out.versions)
147135
.collectFile(name: 'collated_versions.yml')
148-
// params.genome_build,
149-
// params.genome_annotation
150136
)
151137
ch_versions = ch_versions.mix(PAYLOAD_ALIGNMENT_H.out.versions)
152138

@@ -253,6 +239,7 @@ workflow RNAALN {
253239
Channel.fromPath(params.reference_fasta).map{ it -> [ [ id:'fasta' ], it ] }
254240
)
255241
ch_versions = ch_versions.mix(SAMTOOLS_STATS_H.out.versions)
242+
256243
// Picard
257244
PICARD_COLLECTRNASEQMETRICS_H(
258245
MERG_DUP_H.out.cram_alignment_index,
@@ -262,16 +249,8 @@ workflow RNAALN {
262249
Channel.fromPath(params.rrna_intervals)
263250
)
264251

265-
// PICARD_COLLECTRNASEQMETRICS_H(
266-
// MERG_DUP_H.out.cram_alignment_index.map { meta, cram, crai -> [meta, cram] },
267-
// Channel.fromPath(params.ref_flat),
268-
// Channel.fromPath(params.reference_fasta),
269-
// Channel.fromPath(params.rrna_intervals)
270-
// )
271252
ch_versions = ch_versions.mix(PICARD_COLLECTRNASEQMETRICS_H.out.versions)
272253

273-
// PICARD_COLLECTRNASEQMETRICS_H.out.metrics.subscribe { println("Picard metrics - HISAT2: ${it}") }
274-
275254
// MultiQC
276255
ch_reports = (
277256
Channel.empty()
@@ -296,17 +275,6 @@ workflow RNAALN {
296275
)
297276
ch_versions = ch_versions.mix(MULTIQC_H.out.versions)
298277

299-
// MULTIQC_H.out.report.subscribe { println("MultiQC report - HISAT2: ${it}") }
300-
// MULTIQC_H.out.data.subscribe { println("MultiQC data - HISAT2: ${it}") }
301-
302-
// PICARD_COLLECTRNASEQMETRICS_H.out.metrics (meta, path)
303-
// MULTIQC_H.out.picard_multi
304-
// MULTIQC_H.out.hisat2_multi
305-
306-
// PICARD_COLLECTRNASEQMETRICS_H.out.metrics.subscribe { println("Picard output: ${it}") }
307-
// MULTIQC_H.out.picard_multi.subscribe { println("MultiQC picard output: ${it}") }
308-
// MULTIQC_H.out.hisat2_multi.subscribe { println("MultiQC hisat2 output: ${it}") }
309-
310278
// metrics preparation
311279
PICARD_COLLECTRNASEQMETRICS_H.out.metrics
312280
.combine(MULTIQC_H.out.data)
@@ -329,24 +297,11 @@ workflow RNAALN {
329297
}
330298
.set{ch_h_prep_metrics}
331299

332-
// ch_h_prep_metrics.subscribe { println("prep metrics input: ${it}") }
333-
// ch_h_prep_metrics.subscribe { println("Multiqc_FILES input: ${it}") }
334-
335300
PREP_METRICS_H(
336301
ch_h_prep_metrics,
337302
[]
338303
)
339304

340-
// PREP_METRICS_H.out.metrics_json.subscribe { println("prep metrics output: ${it}") }
341-
342-
// ch_h_prep_metrics.subscribe { println("prep metrics: ${it}") }
343-
// PREP_METRICS_H.out.metrics_json.subscribe { println("prep metrics out json: ${it}") }
344-
// MULTIQC_H.out.data.subscribe { println("multiQC: ${it}") }
345-
346-
// TAR(ch_h_prep_metrics)
347-
348-
// TAR.out.stats.subscribe { println("TAR: ${it}") }
349-
350305
PICARD_COLLECTRNASEQMETRICS_H.out.metrics
351306
.combine(MULTIQC_H.out.picard_multi)
352307
.combine(MULTIQC_H.out.hisat2_multi)
@@ -408,8 +363,6 @@ workflow RNAALN {
408363
.collect()
409364
.set{hisat2_qc_cleanup}
410365

411-
// ch_h_qcmetrics_payload.subscribe { println("prep payload input: ${it}") }
412-
413366
PAYLOAD_QCMETRICS_H( // [val(meta) path(json), [path(picard_multiQC), path(hisat2_multiQC)], path(multiQC)]
414367
ch_h_qcmetrics_payload,
415368
Channel.empty()
@@ -422,11 +375,11 @@ workflow RNAALN {
422375
)
423376
ch_versions = ch_versions.mix(PAYLOAD_QCMETRICS_H.out.versions)
424377

425-
// PAYLOAD_QCMETRICS_H.out.payload_files.subscribe { println("Generated Payload: ${it}") }
426-
427378
// upload - qc metrics
428379
UPLOAD_QC_H(PAYLOAD_QCMETRICS_H.out.payload_files) // [val(meta), path("*.payload.json"), [path(CRAM),path(CRAI)]
429380
ch_versions = ch_versions.mix(UPLOAD_QC_H.out.versions)
381+
382+
hisat2OutFlag_ch = UPLOAD_ALIGNMENT_H.out.analysis_id.concat(UPLOAD_NOVEL_SPLICE_H.out.analysis_id, UPLOAD_QC_H.out.analysis_id).collect()
430383
}
431384

432385
// STAR //
@@ -496,7 +449,6 @@ workflow RNAALN {
496449
// Upload files - alignment
497450
UPLOAD_ALIGNMENT_S(PAYLOAD_ALIGNMENT_S.out.payload_files) // [val(meta), path("*.payload.json"), [path(CRAM),path(CRAI)]
498451
ch_versions = ch_versions.mix(UPLOAD_ALIGNMENT_S.out.versions)
499-
// UPLOAD_ALIGNMENT_S.out.analysis_id.subscribe { println("Upload Analysis Id: ${it}") }
500452

501453
if (!binding.hasVariable('ch_ref_trans') || !ch_ref_trans) {
502454
// Prepare transcript fasta and fai
@@ -556,8 +508,6 @@ workflow RNAALN {
556508
// Upload files - alignment
557509
UPLOAD_ALIGNMENT_ST(PAYLOAD_ALIGNMENT_ST.out.payload_files) // [val(meta), path("*.payload.json"), [path(CRAM),path(CRAI)]
558510
ch_versions = ch_versions.mix(UPLOAD_ALIGNMENT_ST.out.versions)
559-
// UPLOAD_ALIGNMENT_ST.out.analysis_id.subscribe { println("Upload Analysis Id STAR ST: ${it}") }
560-
561511

562512
// Collect Splice Junctions
563513
STAR_ALIGN.out.spl_junc_tab.flatten().buffer( size: 2 )
@@ -657,13 +607,7 @@ workflow RNAALN {
657607
Channel.fromPath(params.reference_fasta).map{ it -> [ [ id:'fasta' ], it ] }
658608
)
659609
ch_versions = ch_versions.mix(SAMTOOLS_STATS_S.out.versions)
660-
// Picard
661-
// PICARD_COLLECTRNASEQMETRICS_S(
662-
// MERG_DUP_S.out.bam_post_dup,
663-
// Channel.fromPath(params.ref_flat),
664-
// Channel.fromPath(params.reference_fasta),
665-
// Channel.fromPath(params.rrna_intervals)
666-
// )
610+
667611
PICARD_COLLECTRNASEQMETRICS_S(
668612
MERG_DUP_S.out.cram_alignment_index,
669613
Channel.fromPath(params.ref_flat),
@@ -673,9 +617,6 @@ workflow RNAALN {
673617
)
674618
ch_versions = ch_versions.mix(PICARD_COLLECTRNASEQMETRICS_S.out.versions)
675619

676-
// PICARD_COLLECTRNASEQMETRICS_S.out.metrics.subscribe { println("Picard output - STAR: ${it}") }
677-
678-
679620
// MultiQC
680621
ch_reports_s = (
681622
Channel.empty()
@@ -704,9 +645,6 @@ workflow RNAALN {
704645
)
705646
ch_versions = ch_versions.mix(MULTIQC_S.out.versions)
706647

707-
// MULTIQC_S.out.report.subscribe { println("MultiQC report - STAR: ${it}") }
708-
// MULTIQC_S.out.data.subscribe { println("MultiQC data - STAR: ${it}") }
709-
710648
// Prepare Metrics
711649
PICARD_COLLECTRNASEQMETRICS_S.out.metrics
712650
.combine(MULTIQC_S.out.data)
@@ -729,15 +667,11 @@ workflow RNAALN {
729667
}
730668
.set{ch_s_prep_metrics}
731669

732-
// ch_s_prep_metrics.subscribe { println("prep metrics input: ${it}") }
733-
734670
PREP_METRICS_S(
735671
ch_s_prep_metrics,
736672
[]
737673
)
738674

739-
// PREP_METRICS_S.out.metrics_json.subscribe { println("prep metrics output: ${it}") }
740-
741675
PICARD_COLLECTRNASEQMETRICS_S.out.metrics
742676
.combine(MULTIQC_S.out.picard_multi)
743677
.combine(MULTIQC_S.out.star_multi)
@@ -791,14 +725,6 @@ workflow RNAALN {
791725
}
792726
.set{ch_s_qcmetrics_payload}
793727

794-
// Channel.empty()
795-
// .mix(SAMTOOLS_STATS_S.out.stats.map{meta,files -> files}.collect())
796-
// .mix(PICARD_COLLECTRNASEQMETRICS_S.out.metrics.map{meta,file -> file}.collect())
797-
// .mix(MULTIQC_S.out.data.collect())
798-
// .mix(PREP_METRICS_S.out.metrics_json.map{meta,file -> file}.collect())
799-
// .collect()
800-
// .set{star_qc_cleanup}
801-
802728
Channel.empty()
803729
.mix(SAMTOOLS_STATS_S.out.stats.map{meta,files -> files}.collect())
804730
.mix(PICARD_COLLECTRNASEQMETRICS_S.out.metrics.map{meta,file -> file}.collect())
@@ -807,8 +733,6 @@ workflow RNAALN {
807733
.collect()
808734
.set{star_qc_cleanup}
809735

810-
// ch_s_qcmetrics_payload.subscribe { println("prep payload input: ${it}") }
811-
812736
PAYLOAD_QCMETRICS_S( // [val(meta) path(json), [path(picard_multiQC), path(hisat2_multiQC)], path(multiQC)]
813737
ch_s_qcmetrics_payload,
814738
Channel.empty()
@@ -821,35 +745,10 @@ workflow RNAALN {
821745
)
822746
ch_versions = ch_versions.mix(PAYLOAD_QCMETRICS_S.out.versions)
823747

824-
// PAYLOAD_QCMETRICS_S.out.payload_files.subscribe { println("Generated Payload: ${it}") }
825-
826748
// upload - qc metrics
827749
UPLOAD_QC_S(PAYLOAD_QCMETRICS_S.out.payload_files) // [val(meta), path("*.payload.json"), [path(CRAM),path(CRAI)]
828750
ch_versions = ch_versions.mix(UPLOAD_QC_S.out.versions)
829751
}
830-
// cleanup
831-
// CLEAN_ALN_H(
832-
// hisat2_qc_cleanup.unique().collect(),
833-
// UPLOAD_QC_H.out.analysis_id // what is it
834-
// )
835-
836-
// CLEAN_ALN_S(
837-
// star_qc_cleanup.unique().collect(),
838-
// UPLOAD_QC_S.out.analysis_id
839-
// )
840-
// hisat2 trouble shoot
841-
// STAGE_INPUT.out.meta_analysis.subscribe { println("STAGE_INPUT meta_analysis: ${it}") }
842-
// STAGE_INPUT.out.meta_files.subscribe{ println("STAGE_INPUT meta_files: ${it}") }
843-
// HISAT2_ALIGN.out.bam.subscribe{ println("HISAT2_ALIGN bam: ${it}") }
844-
// MERG_DUP_H.out.tmp_files.subscribe{ println("MERG_DUP_H tmp_files: ${it}") }
845-
// MERG_DUP_H.out.cram_alignment_index.subscribe{ println("MERG_DUP_H cram_alignment_index: ${it}") }
846-
// MERGE_SPLICE_JUNCTION_H.out.all_novel_splice.subscribe{ println("MERGE_SPLICE_JUNCTION_H all_novel_splice: ${it}") }
847-
// hisat2_qc_cleanup.subscribe{ println("hisat2_qc_cleanup: ${it}") }
848-
// PAYLOAD_ALIGNMENT_H.out.payload_files.subscribe{ println("PAYLOAD_ALIGNMENT_H payload_files: ${it}") }
849-
// PAYLOAD_SPLICE_JUNCTION_H.out.payload_files.subscribe{ println("PAYLOAD_SPLICE_JUNCTION_H payload_files: ${it}") }
850-
// PAYLOAD_QCMETRICS_H.out.payload_files.subscribe{ println("PAYLOAD_QCMETRICS_H payload_files: ${it}") }
851-
// MERG_DUP_S.out.tmp_files.subscribe{ println("MERG_DUP_S tmp_files: ${it}") }
852-
// MERG_DUP_ST.out.tmp_files.subscribe{ println("MERG_DUP_ST tmp_files: ${it}") }
853752

854753
if (params.tools.split(',').contains('cleanup')){
855754
if (params.samplesheet) {
@@ -860,6 +759,7 @@ workflow RNAALN {
860759
ch_cleanup_H=Channel.empty()
861760
.mix(STAGE_INPUT.out.meta_analysis.map{meta,metadata -> metadata}.collect())
862761
.mix(STAGE_INPUT.out.meta_files.map{meta,files -> files}.flatten().collect())
762+
ch_cleanup_S=Channel.empty()
863763
} else if (params.tools.split(',').contains('hisat2_aln')) {
864764
ch_cleanup_H=Channel.empty()
865765
.mix(STAGE_INPUT.out.meta_analysis.map{meta,metadata -> metadata}.collect())
@@ -921,7 +821,7 @@ workflow RNAALN {
921821

922822
CLEAN_ALN_H(
923823
ch_cleanup_H.unique().collect(),
924-
UPLOAD_QC_H.out.analysis_id
824+
hisat2OutFlag_ch
925825
)
926826
} else {
927827
CLEAN_ALN_H(
@@ -940,8 +840,6 @@ workflow RNAALN {
940840
versions = ch_versions // channel: [ path(versions.yml) ]
941841
}
942842

943-
// .mix(HISAT2_ALIGN.out.bam.map{meta,file -> file}.flatten().collect())
944-
945843
/*
946844
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
947845
THE END

0 commit comments

Comments
 (0)