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

New module ctat splicing #587

Merged
merged 23 commits into from
Dec 20, 2024
Merged

New module ctat splicing #587

Show file tree
Hide file tree
Changes from 4 commits
Commits
Show all changes
23 commits
Select commit Hold shift + click to select a range
dbb45c9
fix test config resources
nvnieuwk Dec 17, 2024
4245c54
add ctatsplicing module
nvnieuwk Dec 17, 2024
f025945
implement ctatsplicing
nvnieuwk Dec 17, 2024
3268a45
fix pre-commit
nvnieuwk Dec 17, 2024
a84033b
Update nextflow.config
nvnieuwk Dec 17, 2024
4247b12
update changelog
nvnieuwk Dec 17, 2024
af80d58
Merge branch 'new-module-ctat-splicing' of github.com:nf-core/rnafusi…
nvnieuwk Dec 17, 2024
0db19d9
make ctatsplicing possible with arriba input
nvnieuwk Dec 17, 2024
350de1b
add some views to debug the full run
nvnieuwk Dec 19, 2024
b8bae77
try to fix issue with arriba output
nvnieuwk Dec 19, 2024
0006394
remove views
nvnieuwk Dec 19, 2024
05e0e61
remove breaking ifEmpties
nvnieuwk Dec 19, 2024
62fdf33
remove def
nvnieuwk Dec 19, 2024
8155168
redo star changes
nvnieuwk Dec 19, 2024
e386c81
use bam from starfusion
nvnieuwk Dec 19, 2024
62ee76f
create junctions with arriba for ctatsplicing
nvnieuwk Dec 19, 2024
19d1cc1
do not create an index in ctat splicing
nvnieuwk Dec 19, 2024
9dc352f
readd indexing to ctat & sort arriba bam
nvnieuwk Dec 20, 2024
45e4879
Merge branch 'dev' into new-module-ctat-splicing
nvnieuwk Dec 20, 2024
9ea1f3b
remove ctatsplicing check from starfusion
nvnieuwk Dec 20, 2024
1c98fc7
clarify changelog
nvnieuwk Dec 20, 2024
74d4534
update docs
nvnieuwk Dec 20, 2024
a209fea
prettyyy
nvnieuwk Dec 20, 2024
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
12 changes: 12 additions & 0 deletions conf/modules.config
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -49,6 +49,18 @@ process {
]
}

withName: 'CTATSPLICING_STARTOCANCERINTRONS' {
ext.args = {[
bam ? "--vis" : "",
"--sample_name ${meta.id}",
].join(" ")}
publishDir = [
path: { "${params.outdir}/ctatsplicing" },
mode: params.publish_dir_mode,
saveAs: { filename -> filename.equals('versions.yml') ? null : filename }
]
}

withName: 'ENSEMBL_DOWNLOAD' {
publishDir = [
path: { "${params.genomes_base}/ensembl" },
Expand Down
9 changes: 9 additions & 0 deletions conf/test.config
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -17,3 +17,12 @@ params {
// Input data
input = 'https://raw.githubusercontent.com/nf-core/test-datasets/rnafusion/testdata/human/samplesheet_valid.csv'
}

// Limit and standardize resources for github actions and reproducibility
process {
resourceLimits = [
cpus: 4,
memory: '15.GB',
time: '1.h'
]
}
9 changes: 9 additions & 0 deletions conf/test_build.config
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -22,3 +22,12 @@ params {

skip_salmon_index = true
}

// Limit and standardize resources for github actions and reproducibility
process {
resourceLimits = [
cpus: 4,
memory: '15.GB',
time: '1.h'
]
}
9 changes: 9 additions & 0 deletions conf/test_cosmic.config
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -20,3 +20,12 @@ params {
cosmic_username = secrets.COSMIC_USERNAME
cosmic_passwd = secrets.COSMIC_PASSWD
}

// Limit and standardize resources for github actions and reproducibility
process {
resourceLimits = [
cpus: 4,
memory: '15.GB',
time: '1.h'
]
}
71 changes: 71 additions & 0 deletions modules/local/ctatsplicing/startocancerintrons/main.nf
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,71 @@
process CTATSPLICING_STARTOCANCERINTRONS {
tag "$meta.id"
label 'process_single'

container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
'https://data.broadinstitute.org/Trinity/CTAT_SINGULARITY/CTAT-SPLICING/ctat_splicing.v0.0.2.simg' :
'docker.io/trinityctat/ctat_splicing:0.0.2' }"

input:
tuple val(meta), path(split_junction), path(junction), path(bam), path(bai)
tuple val(meta2), path(genome_lib)

output:
tuple val(meta), path("*.cancer_intron_reads.sorted.bam") , emit: cancer_introns_sorted_bam
tuple val(meta), path("*.cancer_intron_reads.sorted.bam.bai") , emit: cancer_introns_sorted_bai
tuple val(meta), path("*.gene_reads.sorted.sifted.bam") , emit: gene_reads_sorted_bam
tuple val(meta), path("*.gene_reads.sorted.sifted.bam.bai") , emit: gene_reads_sorted_bai
tuple val(meta), path("*.cancer.introns") , emit: cancer_introns
tuple val(meta), path("*.cancer.introns.prelim") , emit: cancer_introns_prelim
tuple val(meta), path("*${prefix}.introns") , emit: introns
tuple val(meta), path("*.introns.for_IGV.bed") , emit: introns_igv_bed, optional: true
tuple val(meta), path("*.ctat-splicing.igv.html") , emit: igv_html, optional: true
tuple val(meta), path("*.igv.tracks") , emit: igv_tracks, optional: true
tuple val(meta), path("*.chckpts") , emit: chckpts
path "versions.yml" , emit: versions

script:
def args = task.ext.args ?: ''
prefix = task.ext.prefix ?: "${meta.id}"
rannick marked this conversation as resolved.
Show resolved Hide resolved
def bam_arg = bam ? "--bam_file ${bam}" : ""
def VERSION = '0.0.2' // WARN: Version information not provided by tool on CLI. Please update this string when bumping container versions.
def create_index = bam && !bai ? "samtools index ${bam}" : ""
rannick marked this conversation as resolved.
Show resolved Hide resolved
"""
${create_index}
/usr/local/src/CTAT-SPLICING/STAR_to_cancer_introns.py \\
--SJ_tab_file ${split_junction} \\
--chimJ_file ${junction} \\
${bam_arg} \\
--output_prefix ${prefix} \\
--ctat_genome_lib ${genome_lib} \\
${args}

cat <<-END_VERSIONS > versions.yml
"${task.process}":
ctat-splicing: $VERSION
END_VERSIONS
"""

stub:
def args = task.ext.args ?: ''
prefix = task.ext.prefix ?: "${meta.id}"
rannick marked this conversation as resolved.
Show resolved Hide resolved
def VERSION = '0.0.2' // WARN: Version information not provided by tool on CLI. Please update this string when bumping container versions.
def create_igv_files = args.contains("--vis") ? "touch ${prefix}.introns.for_IGV.bed && touch ${prefix}.ctat-splicing.igv.html && touch ${prefix}.igv.tracks" : ""
"""
${create_igv_files}
touch ${prefix}.cancer_intron_reads.sorted.bam
touch ${prefix}.cancer_intron_reads.sorted.bam.bai
touch ${prefix}.gene_reads.sorted.sifted.bam
touch ${prefix}.gene_reads.sorted.sifted.bam.bai
touch ${prefix}.cancer.introns
touch ${prefix}.cancer.introns.prelim
touch ${prefix}.introns
touch ${prefix}.chckpts


cat <<-END_VERSIONS > versions.yml
"${task.process}":
ctat-splicing: $VERSION
END_VERSIONS
"""
}
69 changes: 69 additions & 0 deletions modules/local/ctatsplicing/startocancerintrons/tests/main.nf.test
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,69 @@
nextflow_process {

name "Test Process CTATSPLICING_STARTOCANCERINTRONS"
script "../main.nf"
process "CTATSPLICING_STARTOCANCERINTRONS"
options "-stub"

test("test without BAM") {

when {
params {
outdir = "tests/results"
}
process {
"""
input[0] = [
[id:"test"],
file("test.SJ.out.tab"),
file("test.Chimeric.out.junctions"),
[],
[]
]
input[1] = [
[id:"reference"],
file("ctat_genome_lib")
]
"""
}
}

then {
assertAll(
{ assert process.success },
{ assert snapshot(process.out.findAll { key, value -> !key.isNumber() }).match() }
)
}
}

test("test with BAM") {

when {
params {
outdir = "tests/results"
}
process {
"""
input[0] = [
[id:"test"],
file("test.SJ.out.tab"),
file("test.Chimeric.out.junctions"),
file("test.Aligned.sortedByCoord.out.bam"),
[]
]
input[1] = [
[id:"reference"],
file("ctat_genome_lib")
]
"""
}
}

then {
assertAll(
{ assert process.success },
{ assert snapshot(process.out.findAll { key, value -> !key.isNumber() }).match() }
)
}
}
}
191 changes: 191 additions & 0 deletions modules/local/ctatsplicing/startocancerintrons/tests/main.nf.test.snap
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,191 @@
{
"test without BAM": {
"content": [
{
"cancer_introns": [
[
{
"id": "test"
},
"test.cancer.introns:md5,d41d8cd98f00b204e9800998ecf8427e"
]
],
"cancer_introns_prelim": [
[
{
"id": "test"
},
"test.cancer.introns.prelim:md5,d41d8cd98f00b204e9800998ecf8427e"
]
],
"cancer_introns_sorted_bai": [
[
{
"id": "test"
},
"test.cancer_intron_reads.sorted.bam.bai:md5,d41d8cd98f00b204e9800998ecf8427e"
]
],
"cancer_introns_sorted_bam": [
[
{
"id": "test"
},
"test.cancer_intron_reads.sorted.bam:md5,d41d8cd98f00b204e9800998ecf8427e"
]
],
"chckpts": [
[
{
"id": "test"
},
"test.chckpts:md5,d41d8cd98f00b204e9800998ecf8427e"
]
],
"gene_reads_sorted_bai": [
[
{
"id": "test"
},
"test.gene_reads.sorted.sifted.bam.bai:md5,d41d8cd98f00b204e9800998ecf8427e"
]
],
"gene_reads_sorted_bam": [
[
{
"id": "test"
},
"test.gene_reads.sorted.sifted.bam:md5,d41d8cd98f00b204e9800998ecf8427e"
]
],
"igv_html": [

],
"igv_tracks": [

],
"introns": [
[
{
"id": "test"
},
"test.introns:md5,d41d8cd98f00b204e9800998ecf8427e"
]
],
"introns_igv_bed": [

],
"versions": [
"versions.yml:md5,fcf861a15f9951342a874b6bc476a37e"
]
}
],
"meta": {
"nf-test": "0.9.1",
"nextflow": "24.10.1"
},
"timestamp": "2024-12-17T13:35:13.723215847"
},
"test with BAM": {
"content": [
{
"cancer_introns": [
[
{
"id": "test"
},
"test.cancer.introns:md5,d41d8cd98f00b204e9800998ecf8427e"
]
],
"cancer_introns_prelim": [
[
{
"id": "test"
},
"test.cancer.introns.prelim:md5,d41d8cd98f00b204e9800998ecf8427e"
]
],
"cancer_introns_sorted_bai": [
[
{
"id": "test"
},
"test.cancer_intron_reads.sorted.bam.bai:md5,d41d8cd98f00b204e9800998ecf8427e"
]
],
"cancer_introns_sorted_bam": [
[
{
"id": "test"
},
"test.cancer_intron_reads.sorted.bam:md5,d41d8cd98f00b204e9800998ecf8427e"
]
],
"chckpts": [
[
{
"id": "test"
},
"test.chckpts:md5,d41d8cd98f00b204e9800998ecf8427e"
]
],
"gene_reads_sorted_bai": [
[
{
"id": "test"
},
"test.gene_reads.sorted.sifted.bam.bai:md5,d41d8cd98f00b204e9800998ecf8427e"
]
],
"gene_reads_sorted_bam": [
[
{
"id": "test"
},
"test.gene_reads.sorted.sifted.bam:md5,d41d8cd98f00b204e9800998ecf8427e"
]
],
"igv_html": [
[
{
"id": "test"
},
"test.ctat-splicing.igv.html:md5,d41d8cd98f00b204e9800998ecf8427e"
]
],
"igv_tracks": [
[
{
"id": "test"
},
"test.igv.tracks:md5,d41d8cd98f00b204e9800998ecf8427e"
]
],
"introns": [
[
{
"id": "test"
},
"test.introns:md5,d41d8cd98f00b204e9800998ecf8427e"
]
],
"introns_igv_bed": [
[
{
"id": "test"
},
"test.introns.for_IGV.bed:md5,d41d8cd98f00b204e9800998ecf8427e"
]
],
"versions": [
"versions.yml:md5,fcf861a15f9951342a874b6bc476a37e"
]
}
],
"meta": {
"nf-test": "0.9.1",
"nextflow": "24.10.1"
},
"timestamp": "2024-12-17T13:33:27.36677449"
}
}
Loading
Loading