Skip to content
Closed
Show file tree
Hide file tree
Changes from all commits
Commits
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
44 changes: 44 additions & 0 deletions .github/workflows/main.yml
Original file line number Diff line number Diff line change
@@ -0,0 +1,44 @@
name: Nextflow Lint and Auto-fix

on:
pull_request:
push:
branches:
- main

jobs:
lint:
name: Run Nextflow lint and commit fixes
runs-on: ubuntu-latest

steps:
# Checkout the repo, full history needed to push
- name: Checkout repository
uses: actions/checkout@v4
with:
fetch-depth: 0
ref: ${{ github.head_ref || github.ref_name }}

# Setup Nextflow
- name: Setup Nextflow
uses: nf-core/setup-nextflow@v2.0.0
with:
version: latest-stable

# Run Nextflow lint
- name: Run Nextflow lint
run: nextflow lint -format -harshil-alignment *

# Commit and push changes if any
- name: Commit and push lint auto-fixes
run: |
if [[ -n "$(git status --porcelain)" ]]; then
echo "Lint made changes, committing..."
git config user.name "github-actions[bot]"
git config user.email "github-actions[bot]@users.noreply.github.com"
git add -A
git commit -m "chore: apply Nextflow lint auto-fixes"
git push origin HEAD
else
echo "No changes to commit"
fi
113 changes: 56 additions & 57 deletions conf/base.config
Original file line number Diff line number Diff line change
Expand Up @@ -10,23 +10,23 @@

process {

resourceLimits = [ cpus: params.max_cpus, memory: params.max_memory, time: params.max_time ]
resourceLimits = [cpus: params.max_cpus, memory: params.max_memory, time: params.max_time]

// TODO nf-core: Check the defaults for all processes
cpus = { 1 }
memory = { 6.GB * task.attempt }
time = { 15.min * task.attempt }
cpus = { 1 }
memory = { 6.GB * task.attempt }
time = { 15.min * task.attempt }



errorStrategy = { task.exitStatus in ((130..145) + 104) ? 'retry' : 'finish' }
maxRetries = 3
maxErrors = '-1'
errorStrategy = { task.exitStatus in ((130..145) + 104) ? 'retry' : 'finish' }
maxRetries = 3
maxErrors = '-1'

withLabel:error_ignore {
withLabel: error_ignore {
errorStrategy = 'ignore'
}
withLabel:error_retry {
withLabel: error_retry {
errorStrategy = 'retry'
maxRetries = 2
}
Expand All @@ -37,85 +37,84 @@ process {
// These labels are used and recognised by default in DSL2 files hosted on nf-core/modules.
// If possible, it would be nice to keep the same label naming convention when
// adding in your local modules too.
withLabel:process_single {
cpus = { 1 }
withLabel: process_single {
cpus = { 1 }
}
withLabel:process_low {
cpus = { 2 * task.attempt }
memory = { 12.GB * task.attempt }
withLabel: process_low {
cpus = { 2 * task.attempt }
memory = { 12.GB * task.attempt }
}
withLabel:process_medium {
cpus = { 6 * task.attempt }
memory = { 36.GB * task.attempt }
withLabel: process_medium {
cpus = { 6 * task.attempt }
memory = { 36.GB * task.attempt }
}
withLabel:process_high {
cpus = { 12 * task.attempt }
memory = { 72.GB * task.attempt }
time = { 16.h * task.attempt }
withLabel: process_high {
cpus = { 12 * task.attempt }
memory = { 72.GB * task.attempt }
time = { 16.h * task.attempt }
}


withLabel:process_low_memory {
memory = { 4.GB * task.attempt }
withLabel: process_low_memory {
memory = { 4.GB * task.attempt }
}
withLabel:memory_medium {
memory = { 8.GB * task.attempt }
withLabel: memory_medium {
memory = { 8.GB * task.attempt }
}
withLabel:process_medium_high_memory {
memory = { 36.GB * task.attempt }
withLabel: process_medium_high_memory {
memory = { 36.GB * task.attempt }
}
withLabel:process_high_memory {
memory = { 200.GB * task.attempt }
withLabel: process_high_memory {
memory = { 200.GB * task.attempt }
}



withLabel:time_minimal {
time = { 15.m * task.attempt }
withLabel: time_minimal {
time = { 15.m * task.attempt }
}
withLabel:time_low {
time = { 4.h * task.attempt }
withLabel: time_low {
time = { 4.h * task.attempt }
}
withLabel:time_medium {
time = { 8.h * task.attempt }
withLabel: time_medium {
time = { 8.h * task.attempt }
}
withLabel:process_long {
time = { 20.h * task.attempt }
withLabel: process_long {
time = { 20.h * task.attempt }
}



withLabel:cpu_single_fixed {
cpus = { 1 }
withLabel: cpu_single_fixed {
cpus = { 1 }
}
withLabel:cpu_single {
cpus = { 1 * task.attempt }
withLabel: cpu_single {
cpus = { 1 * task.attempt }
}
withLabel:process_low_fixed_cpus {
cpus = { 2 }
withLabel: process_low_fixed_cpus {
cpus = { 2 }
}
withLabel:cpu_low {
cpus = { 2 * task.attempt }
withLabel: cpu_low {
cpus = { 2 * task.attempt }
}
withLabel:cpu_lowmed {
cpus = { 4 * task.attempt }
withLabel: cpu_lowmed {
cpus = { 4 * task.attempt }
}
withLabel:cpu_medium {
cpus = { 8 * task.attempt }
withLabel: cpu_medium {
cpus = { 8 * task.attempt }
}
withLabel:cpu_medium_high {
cpus = { 12 }
withLabel: cpu_medium_high {
cpus = { 12 }
}
withLabel:cpu_high {
cpus = { 30 * task.attempt }
withLabel: cpu_high {
cpus = { 30 * task.attempt }
}
withLabel:cpu_veryhigh {
cpus = { 50 * task.attempt }
withLabel: cpu_veryhigh {
cpus = { 50 * task.attempt }
}


withName:CUSTOM_DUMPSOFTWAREVERSIONS {
withName: CUSTOM_DUMPSOFTWAREVERSIONS {
cache = false
}

}
30 changes: 14 additions & 16 deletions conf/general_files_BBG.config
Original file line number Diff line number Diff line change
@@ -1,30 +1,28 @@
// This configuration file is used to define the general parameters for the pipeline when ran in BBGCluster
params {

vep_cache = "/workspace/datasets/vep"
vep_cache = "/workspace/datasets/vep"

// Fasta references
fasta = '/workspace/datasets/genomes/GRCh38/clean_n_fixed_genome/GCA_000001405.15_GRCh38_no_alt_analysis_set.masked.fna'
fasta = '/workspace/datasets/genomes/GRCh38/clean_n_fixed_genome/GCA_000001405.15_GRCh38_no_alt_analysis_set.masked.fna'

wgs_trinuc_counts = "assets/trinucleotide_counts/trinuc_counts.homo_sapiens.tsv"
wgs_trinuc_counts = "assets/trinucleotide_counts/trinuc_counts.homo_sapiens.tsv"

cosmic_ref_signatures = "/workspace/datasets/transfer/ferriol_deepcsa/COSMIC_v3.4_SBS_GRCh38.txt"
wgs_trinuc_counts = "/workspace/datasets/transfer/ferriol_deepcsa/trinucleotide_counts/trinuc_counts.homo_sapiens.tsv"
cadd_scores = "/workspace/datasets/CADD/v1.7/hg38/whole_genome_SNVs.tsv.gz"
cadd_scores_ind = "/workspace/datasets/CADD/v1.7/hg38/whole_genome_SNVs.tsv.gz.tbi"
cosmic_ref_signatures = "/workspace/datasets/transfer/ferriol_deepcsa/COSMIC_v3.4_SBS_GRCh38.txt"
wgs_trinuc_counts = "/workspace/datasets/transfer/ferriol_deepcsa/trinucleotide_counts/trinuc_counts.homo_sapiens.tsv"
cadd_scores = "/workspace/datasets/CADD/v1.7/hg38/whole_genome_SNVs.tsv.gz"
cadd_scores_ind = "/workspace/datasets/CADD/v1.7/hg38/whole_genome_SNVs.tsv.gz.tbi"

dnds_ref_transcripts = "/workspace/projects/prominent/analysis/dNdScv/data/reference_files/RefCDS_human_latest_intogen.rda"
dnds_covariates = "/workspace/projects/prominent/analysis/dNdScv/data/reference_files/covariates_hg19_hg38_epigenome_pcawg.rda"
dnds_ref_transcripts = "/workspace/projects/prominent/analysis/dNdScv/data/reference_files/RefCDS_human_latest_intogen.rda"
dnds_covariates = "/workspace/projects/prominent/analysis/dNdScv/data/reference_files/covariates_hg19_hg38_epigenome_pcawg.rda"

// oncodrive3d
datasets3d = "/workspace/nobackup/scratch/oncodrive3d/datasets_240506"
annotations3d = "/workspace/nobackup/scratch/oncodrive3d/annotations_240506"
domains_file = "/workspace/projects/prominent/dev/internal_development/domains/o3d_pfam_parsed.tsv"


datasets3d = "/workspace/nobackup/scratch/oncodrive3d/datasets_240506"
annotations3d = "/workspace/nobackup/scratch/oncodrive3d/annotations_240506"
domains_file = "/workspace/projects/prominent/dev/internal_development/domains/o3d_pfam_parsed.tsv"
}


// Define the cacheDir for the singularity images
singularity.cacheDir = '/workspace/datasets/pipelines/nextflow_containers'
singularity.libraryDir = '/workspace/datasets/pipelines/nextflow_containers'
singularity.cacheDir = '/workspace/datasets/pipelines/nextflow_containers'
singularity.libraryDir = '/workspace/datasets/pipelines/nextflow_containers'
26 changes: 12 additions & 14 deletions conf/general_files_IRB.config
Original file line number Diff line number Diff line change
@@ -1,27 +1,25 @@
// This configuration file is used to define the general parameters for the pipeline when ran in IRBCluster
params {

vep_cache = "/data/bbg/datasets/vep"
vep_cache = "/data/bbg/datasets/vep"

// Fasta references
fasta = '/data/bbg/datasets/genomes/GRCh38/clean_n_fixed_genome/GCA_000001405.15_GRCh38_no_alt_analysis_set.masked.fna'
fasta = '/data/bbg/datasets/genomes/GRCh38/clean_n_fixed_genome/GCA_000001405.15_GRCh38_no_alt_analysis_set.masked.fna'

wgs_trinuc_counts = "assets/trinucleotide_counts/trinuc_counts.homo_sapiens.tsv"
wgs_trinuc_counts = "assets/trinucleotide_counts/trinuc_counts.homo_sapiens.tsv"

cosmic_ref_signatures = "/data/bbg/datasets/transfer/ferriol_deepcsa/COSMIC_v3.4_SBS_GRCh38.txt"
wgs_trinuc_counts = "/data/bbg/datasets/transfer/ferriol_deepcsa/trinucleotide_counts/trinuc_counts.homo_sapiens.tsv"
cadd_scores = "/data/bbg/datasets/CADD/v1.7/hg38/whole_genome_SNVs.tsv.gz"
cadd_scores_ind = "/data/bbg/datasets/CADD/v1.7/hg38/whole_genome_SNVs.tsv.gz.tbi"
cosmic_ref_signatures = "/data/bbg/datasets/transfer/ferriol_deepcsa/COSMIC_v3.4_SBS_GRCh38.txt"
wgs_trinuc_counts = "/data/bbg/datasets/transfer/ferriol_deepcsa/trinucleotide_counts/trinuc_counts.homo_sapiens.tsv"
cadd_scores = "/data/bbg/datasets/CADD/v1.7/hg38/whole_genome_SNVs.tsv.gz"
cadd_scores_ind = "/data/bbg/datasets/CADD/v1.7/hg38/whole_genome_SNVs.tsv.gz.tbi"

dnds_ref_transcripts = "/data/bbg/projects/prominent/analysis/dNdScv/data/reference_files/RefCDS_human_latest_intogen.rda"
dnds_covariates = "/data/bbg/projects/prominent/analysis/dNdScv/data/reference_files/covariates_hg19_hg38_epigenome_pcawg.rda"
dnds_ref_transcripts = "/data/bbg/projects/prominent/analysis/dNdScv/data/reference_files/RefCDS_human_latest_intogen.rda"
dnds_covariates = "/data/bbg/projects/prominent/analysis/dNdScv/data/reference_files/covariates_hg19_hg38_epigenome_pcawg.rda"

// oncodrive3d
datasets3d = "/data/bbg/nobackup/scratch/oncodrive3d/datasets_240506"
annotations3d = "/data/bbg/nobackup/scratch/oncodrive3d/annotations_240506"
domains_file = "/data/bbg/projects/prominent/dev/internal_development/domains/o3d_pfam_parsed.tsv"


datasets3d = "/data/bbg/nobackup/scratch/oncodrive3d/datasets_240506"
annotations3d = "/data/bbg/nobackup/scratch/oncodrive3d/annotations_240506"
domains_file = "/data/bbg/projects/prominent/dev/internal_development/domains/o3d_pfam_parsed.tsv"
}


Expand Down
3 changes: 1 addition & 2 deletions conf/local.config
Original file line number Diff line number Diff line change
Expand Up @@ -10,6 +10,5 @@
----------------------------------------------------------------------------------------
*/

process.resourceLimits = [ cpus: 16, memory: 70.GB, time: 6.h ]
process.resourceLimits = [cpus: 16, memory: 70.GB, time: 6.h]
process.errorStrategy = 'finish'

46 changes: 23 additions & 23 deletions conf/mice.config
Original file line number Diff line number Diff line change
Expand Up @@ -3,37 +3,38 @@ params {
config_profile_description = 'Running deepCSA for mice data'

// Input data
input = '/data/bbg/nobackup2/prominent/ucsf_mice/deepUMIcaller/deepCSA_input.med.csv'
input = '/data/bbg/nobackup2/prominent/ucsf_mice/deepUMIcaller/deepCSA_input.med.csv'

// Fasta references
fasta = '/data/bbg/datasets/genomes/mm39/GCA_000001635.9_genome/GCA_000001635.9_GRCm39_genomic.fna'
fasta = '/data/bbg/datasets/genomes/mm39/GCA_000001635.9_genome/GCA_000001635.9_GRCm39_genomic.fna'

features_table = "/data/bbg/nobackup2/prominent/ucsf_mice/2024-10-17_clinical_features_summary.tsv"
features_table_separator = 'tab'
features_table_dict = ['"unique_identifier" : "sample"',
'"groups_of_interest" : [ ["DMBA"], ["TPA"], ["treatment"], ["sex"], ["timepoint"], ["timepoint", "treatment"], ["timepoint", "TPA"], ["timepoint", "DMBA"] ]'
].join(',\t').trim()
features_table = "/data/bbg/nobackup2/prominent/ucsf_mice/2024-10-17_clinical_features_summary.tsv"
features_table_separator = 'tab'
features_table_dict = [
'"unique_identifier" : "sample"',
'"groups_of_interest" : [ ["DMBA"], ["TPA"], ["treatment"], ["sex"], ["timepoint"], ["timepoint", "treatment"], ["timepoint", "TPA"], ["timepoint", "DMBA"] ]',
].join(',\t').trim()

use_custom_minimum_depth = 30
use_custom_minimum_depth = 30


wgs_trinuc_counts = "$projectDir/assets/trinucleotide_counts/trinuc_counts.mus_musculus.mm39.tsv"
wgs_trinuc_counts = "${projectDir}/assets/trinucleotide_counts/trinuc_counts.mus_musculus.mm39.tsv"

vep_genome = "GRCm39"
vep_cache_version = 111
vep_out_format = "tab"
vep_params = "--no_stats --cache --offline --symbol --protein --canonical"
vep_species = "mus_musculus"
vep_cache = "/data/bbg/datasets/vep/mus_musculus/111_GRCm39"
vep_genome = "GRCm39"
vep_cache_version = 111
vep_out_format = "tab"
vep_params = "--no_stats --cache --offline --symbol --protein --canonical"
vep_species = "mus_musculus"
vep_cache = "/data/bbg/datasets/vep/mus_musculus/111_GRCm39"


// oncodrive3d
datasets3d = "/data/bbg/nobackup/scratch/oncodrive3d/datasets_mouse"
// annotations3d = "/workspace/nobackup/scratch/oncodrive3d/annotations_240506"

omega_withingene = false
omega_subgenic_bedfile = "/data/bbg/datasets/transfer/ferriol_deepcsa/mouse_skin_panel.hotspots.bed4.bed"
hotspot_expansion = 15
omega_withingene = false
omega_subgenic_bedfile = "/data/bbg/datasets/transfer/ferriol_deepcsa/mouse_skin_panel.hotspots.bed4.bed"
hotspot_expansion = 15


oncodrivefml = false
Expand All @@ -50,8 +51,8 @@ params {


signatures = true
mutationdensity = true
mutated_cells_vaf = false
mutationdensity = true
mutated_cells_vaf = false

indels = false

Expand All @@ -75,12 +76,11 @@ params {
mutation_depth_threshold = 40

repetitive_variant_thres = 5

}


process {
withLabel:process_high_memory {
memory = { 15.GB * task.attempt }
withLabel: process_high_memory {
memory = { 15.GB * task.attempt }
}
}
6 changes: 3 additions & 3 deletions conf/modes/basic.config
Original file line number Diff line number Diff line change
@@ -1,5 +1,5 @@
params {
plot_depths = true
signatures = true
profileall = true
plot_depths = true
signatures = true
profileall = true
}
Loading