Update isoseq3/cluster (#856)

* 📦 NEW: Add isoseq3/cluster module

* 🐛FIX: Fix reports channel and add .pbi to it

* 🐛FIX: Fix report channel definition

* 👌IMPROVE: Move .pbi file into reports channel

* 👌IMPROVE: remove --use_qvs option from command line

* 👌 IMPROVE: Add in addParams removed options from command line

* 👌 IMPROVE: Add some pacbio test files

* 🐛 FIX: Add Pacbio index to test_data.config

* 👌 IMPROVE: Re add 10000 data test

* 👌 IMPROVE: Add some pbindex

* 🐛 FIX: Add pbi extension to files

* 👌 IMPROVE: The module accept one channel (primers moved into the first channel)

* 📦 NEW: Add galgal6 chr30 test data

* 📦 NEW: Add bamtools module

* 👌 IMPROVE: Ignore test data

* 👌 IMPROVE: Update to last templates version

* 👌 IMPROVE: Update to last templates version

* 👌 IMPROVE: add singletons parameter and improve outputs

* 🐛 FIX: Update test with last module model

* 👌 IMPROVE: Add test tag

* 👌 IMPROVE: Update module to last template version

* 👌 IMPROVE: Update module to last template version

* 👌 IMPROVE: Update test data config

* 👌 IMPROVE: Remove pbi from input files

* 👌 IMPROVE: Remove unused index

* 👌 IMPROVE: Final version of test datasets config

* 👌 IMPROVE: Final version of test datasets config

* 👌 IMPROVE: Remove useless index + Fix Typos

* 👌 IMPROVE: Remove useless index + Fix Typos

* 👌 IMPROVE: Fill contains args

* 📦 NEW: Add isoseq3/cluster module

* 🐛FIX: Fix reports channel and add .pbi to it

* 🐛FIX: Fix report channel definition

* 👌IMPROVE: Move .pbi file into reports channel

* 👌IMPROVE: remove --use_qvs option from command line

* 👌 IMPROVE: Add in addParams removed options from command line

* 👌 IMPROVE: Add some pacbio test files

* 🐛 FIX: Add Pacbio index to test_data.config

* 👌 IMPROVE: Re add 10000 data test

* 👌 IMPROVE: Add some pbindex

* 🐛 FIX: Add pbi extension to files

* 👌 IMPROVE: The module accept one channel (primers moved into the first channel)

* 👌 IMPROVE: Update to last templates version

* 👌 IMPROVE: add singletons parameter and improve outputs

* 🐛 FIX: Update test with last module model

* 👌 IMPROVE: Add test tag

* 👌 IMPROVE: Update test data config

* 👌 IMPROVE: Remove pbi from input files

* 👌 IMPROVE: Remove unused index

* 👌 IMPROVE: Final version of test datasets config

* 👌 IMPROVE: Remove useless index + Fix Typos

* 👌 IMPROVE: Fill contains args

* 👌 IMPROVE: Add some pacbio test files

* 🐛 FIX: Add Pacbio index to test_data.config

* 👌 IMPROVE: Re add 10000 data test

* 👌 IMPROVE: Add some pbindex

* 🐛 FIX: Add pbi extension to files

* 📦 NEW: Add galgal6 chr30 test data

* 📦 NEW: Add bamtools module

* 👌 IMPROVE: Ignore test data

* 👌 IMPROVE: Update to last templates version

* 👌 IMPROVE: Update module to last template version

* 👌 IMPROVE: Update module to last template version

* 👌 IMPROVE: Final version of test datasets config

* 👌 IMPROVE: Remove useless index + Fix Typos

* 👌 IMPROVE: Update code to new versions capture + better output channels

* 👌 IMPROVE: Update with new versions.yml file

* 🐛 FIX: Update meta.yml + correct typos

* 👌 IMPROVE: Clean output file names + correct typo

* 🐛 FIX: Remove bamtools/split module from isoseq3/cluster

* 🐛 FIX: Update output filename pattern

input filename and output filename were the same

* 👌 IMPROVE: Update meta.yml
This commit is contained in:
Sébastien Guizard 2021-10-14 11:07:53 +01:00 committed by GitHub
parent c912117972
commit 1cf207a5b6
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
3 changed files with 50 additions and 49 deletions

View file

@ -22,19 +22,20 @@ process ISOSEQ3_CLUSTER {
tuple val(meta), path(bam)
output:
tuple val(meta), path("*.bam") , emit: bam
tuple val(meta), path("*.bam.pbi") , emit: pbi
tuple val(meta), path("*.cluster") , emit: cluster
tuple val(meta), path("*.cluster_report.csv"), emit: cluster_report
tuple val(meta), path("*.transcriptset.xml") , emit: transcriptset
tuple val(meta), path("*.hq.bam") , emit: hq_bam
tuple val(meta), path("*.hq.bam.pbi") , emit: hq_pbi
tuple val(meta), path("*.lq.bam") , emit: lq_bam
tuple val(meta), path("*.lq.bam.pbi") , emit: lq_pbi
tuple val(meta), path("*.transcripts.bam") , emit: bam
tuple val(meta), path("*.transcripts.bam.pbi") , emit: pbi
tuple val(meta), path("*.transcripts.cluster") , emit: cluster
tuple val(meta), path("*.transcripts.cluster_report.csv"), emit: cluster_report
tuple val(meta), path("*.transcripts.transcriptset.xml") , emit: transcriptset
path "versions.yml" , emit: versions
tuple val(meta), path("*.singletons.bam") , optional: true, emit: singletons_bam
tuple val(meta), path("*.singletons.bam.pbi"), optional: true, emit: singletons_pbi
tuple val(meta), path("*.transcripts.hq.bam") , optional: true, emit: hq_bam
tuple val(meta), path("*.transcripts.hq.bam.pbi") , optional: true, emit: hq_pbi
tuple val(meta), path("*.transcripts.lq.bam") , optional: true, emit: lq_bam
tuple val(meta), path("*.transcripts.lq.bam.pbi") , optional: true, emit: lq_pbi
tuple val(meta), path("*.transcripts.singletons.bam") , optional: true, emit: singletons_bam
tuple val(meta), path("*.transcripts.singletons.bam.pbi"), optional: true, emit: singletons_pbi
script:
def prefix = options.suffix ? "${meta.id}${options.suffix}" : "${meta.id}"
@ -42,7 +43,7 @@ process ISOSEQ3_CLUSTER {
isoseq3 \\
cluster \\
$bam \\
${prefix}.bam \\
${prefix}.transcripts.bam \\
$options.args
cat <<-END_VERSIONS > versions.yml

View file

@ -35,47 +35,47 @@ output:
- bam:
type: file
description: BAM file of clustered consensus
pattern: "*.bam"
pattern: "*.transcripts.bam"
- pbi:
type: file
description: Pacbio Index of consensus reads generated by clustering
pattern: "*.pbi"
pattern: "*.transcripts.bam.pbi"
- cluster:
type: file
description: A two columns (from, to) file describing original read name to new read name
pattern: "*.cluster"
pattern: "*.transcripts.cluster"
- cluster_report:
type: file
description: A table files clusters (transcripts) members (read)
pattern: "*.cluster_report.csv"
pattern: "*.transcripts.cluster_report.csv"
- transcriptset:
type: file
description: A metadata xml file which contains full paths to data files
pattern: "*.clustered.transcriptset.xml"
pattern: "*.transcripts.transcriptset.xml"
- hq_bam:
type: file
description: High quality reads
pattern: "*.hq.bam"
description: High quality reads (when --use-qvs is set)
pattern: "*.transcripts.hq.bam"
- hq_pbi:
type: file
description: Pacbio index of high quality reads
pattern: "*.hq.bam.pbi"
description: Pacbio index of high quality reads (when --use-qvs is set)
pattern: "*.transcripts.hq.bam.pbi"
- lq_bam:
type: file
description: Low quality reads
pattern: "*.lq.bam"
description: Low quality reads (when --use-qvs is set)
pattern: "*.transcripts.lq.bam"
- lq_pbi:
type: file
description: Pacbio index of low quality reads
pattern: "*.lq.bam.pbi"
description: Pacbio index of low quality reads (when --use-qvs is set)
pattern: "*.transcripts.lq.bam.pbi"
- singletons_bam:
type: file
description: Unclustered reads
pattern: "*.singletons.bam"
description: Unclustered reads (when --singletons is set)
pattern: "*.transcripts.singletons.bam"
- singletons_pbi:
type: file
description: Pacbio index of unclustered reads
pattern: "*.singletons.bam.pbi"
description: Pacbio index of unclustered reads (when --singletons is set)
pattern: "*.transcripts.singletons.bam.pbi"
authors:
- "@sguizard"

View file

@ -4,25 +4,25 @@
- isoseq3
- isoseq3/cluster
files:
- path: output/isoseq3/test.bam
md5sum: ca8277f4d8fe1bba68ba266c42b46dd1
- path: output/isoseq3/test.bam.pbi
md5sum: cbc06657b4543faba7ff886b3b12b862
- path: output/isoseq3/test.cluster
- path: output/isoseq3/test.transcripts.bam
md5sum: eb36697688099c757ef4196f54ad7d7a
- path: output/isoseq3/test.transcripts.bam.pbi
md5sum: db70cee03421822e9b8f9fb6b228f461
- path: output/isoseq3/test.transcripts.cluster
md5sum: d5059d856763fc5591332980bfc0d57b
- path: output/isoseq3/test.cluster_report.csv
- path: output/isoseq3/test.transcripts.cluster_report.csv
md5sum: 342d97dc10aedf80a45977edcb491c62
- path: output/isoseq3/test.hq.bam
md5sum: e93ea85776c35c246364d954032c2ea9
- path: output/isoseq3/test.hq.bam.pbi
md5sum: 5a8ea7668e8f8e173478b28cbb6ab515
- path: output/isoseq3/test.lq.bam
md5sum: 4ea0e4f4a6cc689dcc275adcdf688fad
- path: output/isoseq3/test.lq.bam.pbi
md5sum: f5edc24711b2c8d6474d60cb69022af0
- path: output/isoseq3/test.singletons.bam
md5sum: 73d131920bd42e1fc5fca2e6cb71f4b2
- path: output/isoseq3/test.singletons.bam.pbi
md5sum: 73980863be4b5bda2846325c737f0b5e
- path: output/isoseq3/test.transcriptset.xml
- path: output/isoseq3/test.transcripts.hq.bam
md5sum: 4c5f4ffb429107c9c9578419e07d6987
- path: output/isoseq3/test.transcripts.hq.bam.pbi
md5sum: 39ac3e957c8d55b0ce3f425d63baa154
- path: output/isoseq3/test.transcripts.lq.bam
md5sum: 710ca4bc58ac039d76775460e1c822a0
- path: output/isoseq3/test.transcripts.lq.bam.pbi
md5sum: 9b32036553bf3dced3065e6d0f36aef9
- path: output/isoseq3/test.transcripts.singletons.bam
md5sum: 0288577406b9d1e7356de9b4d7c2bb7c
- path: output/isoseq3/test.transcripts.singletons.bam.pbi
md5sum: 8e0e0681179c0c36209b49fa60783841
- path: output/isoseq3/test.transcripts.transcriptset.xml
contains: [ 'PacBio.DataSet.TranscriptSet' ]