Skip to content

Update test profile #692

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

Merged
maxulysse merged 6 commits into from
Sep 1, 2022
Merged

Update test profile #692

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
6 commits
Select commit Hold shift + click to select a range
8d649bd
tools=strelka by default in profile test + code polish
maxulysse Jul 27, 2022
7517a62
update CHANGELOG
maxulysse Jul 27, 2022
1c129ee
Merge remote-tracking branch 'upstream/dev' into dev_test_profile
maxulysse Aug 24, 2022
3d05d78
fix md5checsum
maxulysse Sep 1, 2022
6592068
fix typo
maxulysse Sep 1, 2022
af01590
regenerate output
maxulysse Sep 1, 2022
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
5 changes: 3 additions & 2 deletions CHANGELOG.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -14,9 +14,10 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
### Changed

- [#679](https://github.com/nf-core/sarek/pull/679) - Back to `dev`
- [#685](https://github.com/nf-core/sarek/pull/685) - Updating the nf-core modules used by Sarek.
- [#685](https://github.com/nf-core/sarek/pull/685) - Updating the nf-core modules used by Sarek
- [#691](https://github.com/nf-core/sarek/pull/691) - To run the same pytest as before locally, use `PROFILE=docker`
- [#696](https://github.com/nf-core/sarek/pull/696) - Adding check of md5-sums in CI-tests.
- [#692](https://github.com/nf-core/sarek/pull/692) - Use `params.tools=strelka` in profile `test`
- [#696](https://github.com/nf-core/sarek/pull/696) - Adding check of md5-sums in CI-tests

### Fixed

Expand Down
201 changes: 110 additions & 91 deletions conf/test.config
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -38,163 +38,182 @@ params {
snpeff_db = 'WBcel235.105'
snpeff_genome = 'WBcel235'
snpeff_version = '5.1'
split_fastq = 0
vep_cache_version = 106
vep_genome = 'WBcel235'
vep_species = 'caenorhabditis_elegans'
vep_version = '106.1'

// default params
split_fastq = 0 // no FASTQ splitting
tools = 'strelka' // Variant calling with Strelka

// Ignore params that will throw warning through params validation
schema_ignore_params = 'genomes,test_data,snpeff_version,vep_version'
}

profiles {
annotation {
params.input = "${projectDir}/tests/csv/3.0/vcf_single.csv"
params.step = 'annotate'
params.input = "${projectDir}/tests/csv/3.0/vcf_single.csv"
params.step = 'annotate'
params.tools = null // vep, snpeff and/or merge should be specified on the command line
}
no_intervals {
params.intervals = null
params.no_intervals = true
params.intervals = null
params.no_intervals = true
params.tools = null
}
pair {
params.input = "${projectDir}/tests/csv/3.0/fastq_pair.csv"
params.input = "${projectDir}/tests/csv/3.0/fastq_pair.csv"
params.tools = null
}
markduplicates_bam {
params.input = "${projectDir}/tests/csv/3.0/mapped_single_bam.csv"
params.step = 'markduplicates'
params.input = "${projectDir}/tests/csv/3.0/mapped_single_bam.csv"
params.step = 'markduplicates'
params.tools = null
}
markduplicates_cram {
params.input = "${projectDir}/tests/csv/3.0/mapped_single_cram.csv"
params.step = 'markduplicates'
params.input = "${projectDir}/tests/csv/3.0/mapped_single_cram.csv"
params.step = 'markduplicates'
params.tools = null
}
prepare_recalibration_bam {
params.input = "${projectDir}/tests/csv/3.0/mapped_single_bam.csv"
params.step = 'prepare_recalibration'
params.input = "${projectDir}/tests/csv/3.0/mapped_single_bam.csv"
params.step = 'prepare_recalibration'
params.tools = null
}
prepare_recalibration_cram {
params.input = "${projectDir}/tests/csv/3.0/mapped_single_cram.csv"
params.step = 'prepare_recalibration'
params.input = "${projectDir}/tests/csv/3.0/mapped_single_cram.csv"
params.step = 'prepare_recalibration'
params.tools = null
}
recalibrate_bam {
params.input = "${projectDir}/tests/csv/3.0/prepare_recalibration_single_bam.csv"
params.step = 'recalibrate'
params.input = "${projectDir}/tests/csv/3.0/prepare_recalibration_single_bam.csv"
params.step = 'recalibrate'
params.tools = null
}
recalibrate_cram {
params.input = "${projectDir}/tests/csv/3.0/prepare_recalibration_single_cram.csv"
params.step = 'recalibrate'
params.input = "${projectDir}/tests/csv/3.0/prepare_recalibration_single_cram.csv"
params.step = 'recalibrate'
params.tools = null
}
save_bam_mapped {
params.save_bam_mapped = true
params.save_bam_mapped = true
params.tools = null
}
skip_bqsr {
params.skip_tools = "baserecalibrator"
params.skip_tools = "baserecalibrator"
params.tools = null
}
skip_markduplicates {
params.skip_tools = "markduplicates"
params.skip_tools = "markduplicates"
params.tools = null
}
split_fastq {
params.split_fastq = 150000
params.save_split_fastqs = true
params.save_split_fastqs = true
params.split_fastq = 150000
params.tools = null
}
targeted {
params.intervals = params.test_data['homo_sapiens']['genome']['genome_multi_interval_bed']
params.wes = true
params.nucleotides_per_second = 20
params.intervals = params.test_data['homo_sapiens']['genome']['genome_multi_interval_bed']
params.nucleotides_per_second = 20
params.tools = null
params.wes = true
}
tools {
params.input = "${projectDir}/tests/csv/3.0/recalibrated.csv"
params.dbsnp = params.test_data['homo_sapiens']['genome']['dbsnp_138_hg38_21_vcf_gz']
params.fasta = params.test_data['homo_sapiens']['genome']['genome_21_fasta']
params.germline_resource = params.test_data['homo_sapiens']['genome']['gnomad_r2_1_1_21_vcf_gz']
params.intervals = params.test_data['homo_sapiens']['genome']['genome_21_multi_interval_bed']
params.pon = params.test_data['homo_sapiens']['genome']['mills_and_1000g_indels_21_vcf_gz']
params.step = 'variant_calling'
params.wes = true

params.input = "${projectDir}/tests/csv/3.0/recalibrated.csv"
params.dbsnp = params.test_data['homo_sapiens']['genome']['dbsnp_138_hg38_21_vcf_gz']
params.fasta = params.test_data['homo_sapiens']['genome']['genome_21_fasta']
params.germline_resource = params.test_data['homo_sapiens']['genome']['gnomad_r2_1_1_21_vcf_gz']
params.intervals = params.test_data['homo_sapiens']['genome']['genome_21_multi_interval_bed']
params.pon = params.test_data['homo_sapiens']['genome']['mills_and_1000g_indels_21_vcf_gz']
params.nucleotides_per_second = 20
params.step = 'variant_calling'
params.tools = null
params.wes = true
}
tools_germline {
params.input = "${projectDir}/tests/csv/3.0/recalibrated_germline.csv"
params.dbsnp = params.test_data['homo_sapiens']['genome']['dbsnp_138_hg38_21_vcf_gz']
params.known_indels = params.test_data['homo_sapiens']['genome']['mills_and_1000g_indels_21_vcf_gz']
params.fasta = params.test_data['homo_sapiens']['genome']['genome_21_fasta']
params.intervals = params.test_data['homo_sapiens']['genome']['genome_21_multi_interval_bed']
params.step = 'variant_calling'
params.wes = true

params.input = "${projectDir}/tests/csv/3.0/recalibrated_germline.csv"
params.dbsnp = params.test_data['homo_sapiens']['genome']['dbsnp_138_hg38_21_vcf_gz']
params.fasta = params.test_data['homo_sapiens']['genome']['genome_21_fasta']
params.intervals = params.test_data['homo_sapiens']['genome']['genome_21_multi_interval_bed']
params.known_indels = params.test_data['homo_sapiens']['genome']['mills_and_1000g_indels_21_vcf_gz']
params.nucleotides_per_second = 20
params.step = 'variant_calling'
params.tools = null
params.wes = true
}
tools_tumoronly {
params.input = "${projectDir}/tests/csv/3.0/recalibrated_tumoronly.csv"
params.dbsnp = params.test_data['homo_sapiens']['genome']['dbsnp_138_hg38_21_vcf_gz']
params.fasta = params.test_data['homo_sapiens']['genome']['genome_21_fasta']
params.germline_resource = params.test_data['homo_sapiens']['genome']['gnomad_r2_1_1_21_vcf_gz']
params.intervals = params.test_data['homo_sapiens']['genome']['genome_21_multi_interval_bed']
params.pon = params.test_data['homo_sapiens']['genome']['mills_and_1000g_indels_21_vcf_gz']
params.step = 'variant_calling'
params.wes = true

params.input = "${projectDir}/tests/csv/3.0/recalibrated_tumoronly.csv"
params.dbsnp = params.test_data['homo_sapiens']['genome']['dbsnp_138_hg38_21_vcf_gz']
params.fasta = params.test_data['homo_sapiens']['genome']['genome_21_fasta']
params.germline_resource = params.test_data['homo_sapiens']['genome']['gnomad_r2_1_1_21_vcf_gz']
params.intervals = params.test_data['homo_sapiens']['genome']['genome_21_multi_interval_bed']
params.pon = params.test_data['homo_sapiens']['genome']['mills_and_1000g_indels_21_vcf_gz']
params.nucleotides_per_second = 20
params.step = 'variant_calling'
params.tools = null
params.wes = true
}
tools_somatic {
params.input = "${projectDir}/tests/csv/3.0/recalibrated_somatic.csv"
params.chr_dir = params.test_data['homo_sapiens']['genome']['genome_21_chromosomes_dir']
params.dbsnp = params.test_data['homo_sapiens']['genome']['dbsnp_138_hg38_21_vcf_gz']
params.fasta = params.test_data['homo_sapiens']['genome']['genome_21_fasta']
params.germline_resource = params.test_data['homo_sapiens']['genome']['gnomad_r2_1_1_21_vcf_gz']
params.intervals = params.test_data['homo_sapiens']['genome']['genome_21_multi_interval_bed']
params.pon = params.test_data['homo_sapiens']['genome']['mills_and_1000g_indels_21_vcf_gz']
params.step = 'variant_calling'
params.wes = true

params.input = "${projectDir}/tests/csv/3.0/recalibrated_somatic.csv"
params.chr_dir = params.test_data['homo_sapiens']['genome']['genome_21_chromosomes_dir']
params.dbsnp = params.test_data['homo_sapiens']['genome']['dbsnp_138_hg38_21_vcf_gz']
params.fasta = params.test_data['homo_sapiens']['genome']['genome_21_fasta']
params.germline_resource = params.test_data['homo_sapiens']['genome']['gnomad_r2_1_1_21_vcf_gz']
params.intervals = params.test_data['homo_sapiens']['genome']['genome_21_multi_interval_bed']
params.pon = params.test_data['homo_sapiens']['genome']['mills_and_1000g_indels_21_vcf_gz']
params.nucleotides_per_second = 20
params.step = 'variant_calling'
params.tools = null
params.wes = true
}
// can only be tested locally due to too large cram files for GHA
// download corresponding input files (ascat_somatic.csv) from ftp://ftp.1000genomes.ebi.ac.uk/vol1/ftp/phase3/data/
// test works only without chromosome annotated loci files available at https://github.com/VanLoo-lab/ascat/tree/master/ReferenceFiles/WGS
tools_somatic_ascat{
params.input = "${baseDir}/tests/csv/3.0/ascat_somatic.csv"
params.chr_dir = params.test_data['homo_sapiens']['genome']['genome_21_chromosomes_dir']
params.ascat_loci = "/mnt/volume/repos/modules/test_ascat2/G1000_loci_hg19.zip"
params.ascat_chromosomes = 'c("21", "22")'
params.ascat_min_base_qual = 30
params.germline_resource = params.test_data['homo_sapiens']['genome']['gnomad_r2_1_1_21_vcf_gz']
params.intervals = params.test_data['homo_sapiens']['genome']['genome_21_multi_interval_bed']
params.step = 'variant_calling'
params.joint_germline = true
params.wes = false
params.tools = 'ascat'
params.igenomes_ignore = false
params.genome = 'GATK.GRCh37'

params.input = "${baseDir}/tests/csv/3.0/ascat_somatic.csv"
params.genome = 'GATK.GRCh37'
params.igenomes_ignore = false
params.ascat_chromosomes = 'c("21", "22")'
params.ascat_loci = "/mnt/volume/repos/modules/test_ascat2/G1000_loci_hg19.zip"
params.ascat_min_base_qual = 30
params.chr_dir = params.test_data['homo_sapiens']['genome']['genome_21_chromosomes_dir']
params.germline_resource = params.test_data['homo_sapiens']['genome']['gnomad_r2_1_1_21_vcf_gz']
params.intervals = params.test_data['homo_sapiens']['genome']['genome_21_multi_interval_bed']
params.joint_germline = true
params.step = 'variant_calling'
params.tools = 'ascat'
params.wes = false
}
trimming {
params.clip_r1 = 1
params.clip_r2 = 1
params.three_prime_clip_r1 = 1
params.three_prime_clip_r2 = 1
params.trim_fastq = true
params.clip_r1 = 1
params.clip_r2 = 1
params.three_prime_clip_r1 = 1
params.three_prime_clip_r2 = 1
params.tools = null
params.trim_fastq = true
}
umi {
params.input = "${projectDir}/tests/csv/3.0/fastq_umi.csv"
params.umi_read_structure = '+T 7M1S+T'
params.input = "${projectDir}/tests/csv/3.0/fastq_umi.csv"
params.tools = null
params.umi_read_structure = '+T 7M1S+T'
}
use_gatk_spark {
params.use_gatk_spark = 'baserecalibrator,markduplicates'
params.tools = null
params.use_gatk_spark = 'baserecalibrator,markduplicates'
}
variantcalling_channels {
params.input = "${projectDir}/tests/csv/3.0/recalibrated.csv"
params.fasta = params.test_data['homo_sapiens']['genome']['genome_21_fasta']
params.intervals = params.test_data['homo_sapiens']['genome']['genome_21_multi_interval_bed']
params.wes = true
params.step = 'variant_calling'

params.input = "${projectDir}/tests/csv/3.0/recalibrated.csv"
params.fasta = params.test_data['homo_sapiens']['genome']['genome_21_fasta']
params.intervals = params.test_data['homo_sapiens']['genome']['genome_21_multi_interval_bed']
params.nucleotides_per_second = 20
params.step = 'variant_calling'
params.tools = null
params.wes = true
}
alignment_to_fastq {
params.input = "${projectDir}/tests/csv/3.0/bam_for_remapping.csv"
params.input = "${projectDir}/tests/csv/3.0/bam_for_remapping.csv"
params.tools = null
}
}

Expand Down
Loading