8000 add test data in igenomes by maxulysse · Pull Request #1489 · nf-core/sarek · GitHub
[go: up one dir, main page]
More Web Proxy on the site http://driver.im/
Skip to content

add test data in igenomes #1489

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 communit 8000 y.

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
merged 14 commits into from
Apr 30, 2024
Merged

add test data in igenomes #1489

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
14 commits
Select commit Hold shift + click to select a range
956529f
add test data in igenomes
maxulysse Apr 29, 2024
2a37636
remove test_cache profile
maxulysse Apr 29, 2024
a9706df
fix order
maxulysse Apr 29, 2024
cc6c66d
update CHANGELOG
maxulysse Apr 29, 2024
8b5d74d
fai -> fasta_fai
maxulysse Apr 29, 2024
87cd62c
fix ngscheckmate bed usage
maxulysse Apr 29, 2024
70ef51c
update and fix tests
maxulysse Apr 29, 2024
67fb4cd
typo
maxulysse Apr 29, 2024
3f55321
Apply suggestions from code review
maxulysse Apr 29, 2024
45f116a
fix included task
maxulysse Apr 29, 2024
714ff6e
git pushMerge branch 'igemomes_tests' of github.com:maxulysse/nf-core…
maxulysse Apr 29, 2024
936d80f
fix profile
maxulysse Apr 29, 2024
f614fdc
no dbsnp_vqsr
maxulysse Apr 29, 2024
c7b428b
fix ALL tests
maxulysse Apr 29, 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
4 changes: 4 additions & 0 deletions .github/workflows/ci.yml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -256,6 +256,10 @@ jobs:
- tags: "tabix/tabix"
- tags: "tiddit/sv"
- tags: "untar"
- tags: "pipeline_sarek"
include:
- tags: "pipeline_sarek"
profile: "test,docker"
env:
NXF_ANSI_LOG: false
TEST_DATA_BASE: "${{ github.workspace }}/test-datasets"
Expand Down
4 changes: 4 additions & 0 deletions CHANGELOG.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -9,6 +9,8 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0

### Added

- [#1489](https://github.com/nf-core/sarek/pull/1489) - Added a `testdata.nf-core.sarek` key in `conf/igenomes.config` for small reference

### Changed

- [#1477](https://github.com/nf-core/sarek/pull/1477) - Back to dev
Expand All @@ -23,6 +25,8 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0

### Removed

- [#1489](https://github.com/nf-core/sarek/pull/1489) - Remove `test_cache` profile

### Dependencies

| Dependency | Old version | New version |
Expand Down
20 changes: 20 additions & 0 deletions conf/igenomes.config
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -320,5 +320,25 @@ params {
fasta = "${params.igenomes_base}/Sus_scrofa/UCSC/susScr3/Sequence/WholeGenomeFasta/genome.fa"
readme = "${params.igenomes_base}/Sus_scrofa/UCSC/susScr3/Annotation/README.txt"
}
'testdata.nf-core.sarek' {
dbsnp = "${params.igenomes_base}/genomics/homo_sapiens/genome/vcf/dbsnp_146.hg38.vcf.gz"
dbsnp_tbi = "${params.igenomes_base}/genomics/homo_sapiens/genome/vcf/dbsnp_146.hg38.vcf.gz.tbi"
dbsnp_vqsr = '--resource:dbsnp,known=false,training=true,truth=false,prior=2.0 dbsnp_146.hg38.vcf.gz'
dict = "${params.igenomes_base}/genomics/homo_sapiens/genome/genome.dict"
fasta = "${params.igenomes_base}/genomics/homo_sapiens/genome/genome.fasta"
fasta_fai = "${params.igenomes_base}/genomics/homo_sapiens/genome/genome.fasta.fai"
germline_resource = "${params.igenomes_base}/genomics/homo_sapiens/genome/vcf/gnomAD.r2.1.1.vcf.gz"
germline_resource_tbi = "${params.igenomes_base}/genomics/homo_sapiens/genome/vcf/gnomAD.r2.1.1.vcf.gz.tbi"
intervals = "${params.igenomes_base}/genomics/homo_sapiens/genome/genome.interval_list"
known_indels = "${params.igenomes_base}/genomics/homo_sapiens/genome/vcf/mills_and_1000G.indels.vcf.gz"
known_indels_tbi = "${params.igenomes_base}/genomics/homo_sapiens/genome/vcf/mills_and_1000G.indels.vcf.gz.tbi"
known_indels_vqsr = '--resource:mills,known=false,training=true,truth=true,prior=10.0 mills_and_1000G.indels.vcf.gz'
ngscheckmate_bed = "${params.igenomes_base}/genomics/homo_sapiens/genome/chr21/germlineresources/SNP_GRCh38_hg38_wChr.bed"
snpeff_db = '105'
snpeff_genome = 'WBcel235'
vep_cache_version = '110'
vep_genome = 'WBcel235'
vep_species = 'caenorhabditis_elegans'
}
}
}
27 changes: 8 additions & 19 deletions conf/test.config
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -18,30 +18,22 @@ params {
max_memory = '6.5GB'
max_time = '8.h'

// Base directory for nf-core/modules test data
modules_testdata_base_path = 's3://ngi-igenomes/testdata/nf-core/modules'

// Input data
input = "${projectDir}/tests/csv/3.0/fastq_single.csv"

// No AWS iGenomes
genome = null
igenomes_ignore = true
// small genome on igenomes
igenomes_base = 's3://ngi-igenomes/testdata/nf-core/modules'
genome = 'testdata.nf-core.sarek'

// Small reference genome
bcftools_annotations = "https://raw.githubusercontent.com/nf-core/test-datasets/modules/data/genomics/sarscov2/illumina/vcf/test2.vcf.gz"
bcftools_annotations_tbi = "https://raw.githubusercontent.com/nf-core/test-datasets/modules/data/genomics/sarscov2/illumina/vcf/test2.vcf.gz.tbi"
bcftools_annotations = "${params.modules_testdata_base_path}/genomics/sarscov2/illumina/vcf/test2.vcf.gz"
bcftools_annotations_tbi = "${params.modules_testdata_base_path}/genomics/sarscov2/illumina/vcf/test2.vcf.gz.tbi"
bcftools_header_lines = "${projectDir}/tests/config/bcfann_test_header.txt"
dbsnp = "https://raw.githubusercontent.com/nf-core/test-datasets/modules/data/genomics/homo_sapiens/genome/vcf/dbsnp_146.hg38.vcf.gz"
fasta = "https://raw.githubusercontent.com/nf-core/test-datasets/modules/data/genomics/homo_sapiens/genome/genome.fasta"
germline_resource = "https://raw.githubusercontent.com/nf-core/test-datasets/modules/data/genomics/homo_sapiens/genome/vcf/gnomAD.r2.1.1.vcf.gz"
intervals = "https://raw.githubusercontent.com/nf-core/test-datasets/modules/data/genomics/homo_sapiens/genome/genome.interval_list"
known_indels = "https://raw.githubusercontent.com/nf-core/test-datasets/modules/data/genomics/homo_sapiens/genome/vcf/mills_and_1000G.indels.vcf.gz"
ngscheckmate_bed = "https://raw.githubusercontent.com/nf-core/test-datasets/modules/data/genomics/homo_sapiens/genome/chr21/germlineresources/SNP_GRCh38_hg38_wChr.bed"
snpeff_cache = null
snpeff_db = '105'
snpeff_genome = 'WBcel235'
vep_cache = null
vep_cache_version = '110'
vep_genome = 'WBcel235'
vep_species = 'caenorhabditis_elegans'

// Sentieon
sentieon_dnascope_model = "s3://ngi-igenomes/igenomes/Homo_sapiens/GATK/GRCh38/Annotation/Sentieon/SentieonDNAscopeModel1.1.model"
Expand All @@ -52,9 +44,6 @@ params {

// Ignore params that will throw warning through params validation
validationSchemaIgnoreParams = 'genomes'

// Base directory for nf-core/modules test data
modules_testdata_base_path = 's3://ngi-igenomes/testdata/nf-core/modules/'
}

process {
Expand Down
133 changes: 0 additions & 133 deletions conf/test/cache.config
View file
Open in desktop

This file was deleted.

2 changes: 1 addition & 1 deletion conf/test/targeted.config
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -10,7 +10,7 @@
*/

params {
intervals = params.test_data['homo_sapiens']['genome']['genome_multi_interval_bed']
intervals = "${params.modules_testdata_base_path}/genomics/homo_sapiens/genome/genome.multi_intervals.bed"
nucleotides_per_second = 20
tools = null
wes = true
Expand Down
17 changes: 12 additions & 5 deletions conf/test/tools.config
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -11,11 +11,18 @@

params {
input = "${projectDir}/tests/csv/3.0/recalibrated.csv"
dbsnp = params.test_data['homo_sapiens']['genome']['dbsnp_138_hg38_21_vcf_gz']
fasta = params.test_data['homo_sapiens']['genome']['genome_21_fasta']
germline_resource = params.test_data['homo_sapiens']['genome']['gnomad_r2_1_1_21_vcf_gz']
intervals = params.test_data['homo_sapiens']['genome']['genome_21_multi_interval_bed']
pon = params.test_data['homo_sapiens']['genome']['mills_and_1000g_indels_21_vcf_gz']
genome = null
igenomes_ignore = true
dbsnp = "${params.modules_testdata_base_path}/genomics/homo_sapiens/genome/chr21/germlineresources/dbsnp_138.hg38.vcf.gz"
dbsnp_tbi = "${params.modules_testdata_base_path}/genomics/homo_sapiens/genome/chr21/germlineresources/dbsnp_138.hg38.vcf.gz.tbi"
fasta_fai = "${params.modules_testdata_base_path}/genomics/homo_sapiens/genome/chr21/sequence/genome.fasta.fai"
fasta = "${params.modules_testdata_base_path}/genomics/homo_sapiens/genome/chr21/sequence/genome.fasta"
germline_resource = "${params.modules_testdata_base_path}/genomics/homo_sapiens/genome/chr21/germlineresources/gnomAD.r2.1.1.vcf.gz"
germline_resource_tbi = "${params.modules_testdata_base_path}/genomics/homo_sapiens/genome/chr21/germlineresources/gnomAD.r2.1.1.vcf.gz.tbi"
intervals = "${params.modules_testdata_base_path}/genomics/homo_sapiens/genome/chr21/sequence/multi_intervals.bed"
pon = "${params.modules_testdata_base_path}/genomics/homo_sapiens/genome/chr21/germlineresources/mills_and_1000G.indels.hg38.vcf.gz"
pon_tbi = "${params.modules_testdata_base_path}/genomics/homo_sapiens/genome/chr21/germlineresources/mills_and_1000G.indels.hg38.vcf.gz.tbi"
ngscheckmate_bed = "${params.modules_testdata_base_path}/genomics/homo_sapiens/genome/chr21/germlineresources/SNP_GRCh38_hg38_wChr.bed"
nucleotides_per_second = 20
step = 'variant_calling'
tools = null
Expand Down
17 changes: 12 additions & 5 deletions conf/test/tools_germline.config
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -11,13 +11,20 @@

params {
input = "${projectDir}/tests/csv/3.0/recalibrated_germline.csv"
dbsnp = params.test_data['homo_sapiens']['genome']['dbsnp_138_hg38_21_vcf_gz']
fasta = params.test_data['homo_sapiens']['genome']['genome_21_fasta']
intervals = params.test_data['homo_sapiens']['genome']['genome_21_multi_interval_bed']
known_indels = params.test_data['homo_sapiens']['genome']['mills_and_1000g_indels_21_vcf_gz']
genome = null
igenomes_ignore = true
dbsnp = "${params.modules_testdata_base_path}/genomics/homo_sapiens/genome/chr21/germlineresources/dbsnp_138.hg38.vcf.gz"
dbsnp_tbi = "${params.modules_testdata_base_path}/genomics/homo_sapiens/genome/chr21/germlineresources/dbsnp_138.hg38.vcf.gz.tbi"
fasta = "${params.modules_testdata_base_path}/genomics/homo_sapiens/genome/chr21/sequence/genome.fasta"
fasta_fai = "${params.modules_testdata_base_path}/genomics/homo_sapiens/genome/chr21/sequence/genome.fasta.fai"
intervals = "${params.modules_testdata_base_path}/genomics/homo_sapiens/genome/chr21/sequence/multi_intervals.bed"
known_indels = "${params.modules_testdata_base_path}/genomics/homo_sapiens/genome/chr21/germlineresources/mills_and_1000G.indels.hg38.vcf.gz"
known_indels_tbi = "${params.modules_testdata_base_path}/genomics/homo_sapiens/genome/chr21/germlineresources/mills_and_1000G.indels.hg38.vcf.gz.tbi"
known_indels_vqsr = "--resource:1000G,known=false,training=true,truth=true,prior=10.0 mills_and_1000G.indels.hg38.vcf.gz"
known_snps = params.test_data['homo_sapiens']['genome']['hapmap_3_3_hg38_21_vcf_gz']
known_snps = "${params.modules_testdata_base_path}/genomics/homo_sapiens/genome/chr21/germlineresources/hapmap_3.3.hg38.vcf.gz"
known_snps_tbi = "${params.modules_testdata_base_path}/genomics/homo_sapiens/genome/chr21/germlineresources/hapmap_3.3.hg38.vcf.gz.tbi"
known_snps_vqsr = "--resource:hapmap,known=false,training=true,truth=true,prior=10.0 hapmap_3.3.hg38.vcf.gz"
ngscheckmate_bed = "${params.modules_testdata_base_path}/genomics/homo_sapiens/genome/chr21/germlineresources/SNP_GRCh38_hg38_wChr.bed"
nucleotides_per_second = 20
step = 'variant_calling'
tools = null
Expand Down
19 changes: 13 additions & 6 deletions conf/test/tools_somatic.config
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -11,12 +11,19 @@

params {
input = "${projectDir}/tests/csv/3.0/recalibrated_somatic.csv"
chr_dir = params.test_data['homo_sapiens']['genome']['genome_21_chromosomes_dir']
dbsnp = params.test_data['homo_sapiens']['genome']['dbsnp_138_hg38_21_vcf_gz']
fasta = params.test_data['homo_sapiens']['genome']['genome_21_fasta']
germline_resource = params.test_data['homo_sapiens']['genome']['gnomad_r2_1_1_21_vcf_gz']
intervals = params.test_data['homo_sapiens']['genome']['genome_21_multi_interval_bed']
pon = params.test_data['homo_sapiens']['genome']['mills_and_1000g_indels_21_vcf_gz']
genome = null
igenomes_ignore = true
chr_dir = "${params.modules_testdata_base_path}/genomics/homo_sapiens/genome/chr21/sequence/chromosomes.tar.gz"
dbsnp = "${params.modules_testdata_base_path}/genomics/homo_sapiens/genome/chr21/germlineresources/dbsnp_138.hg38.vcf.gz"
dbsnp_tbi = "${params.modules_testdata_base_path}/genomics/homo_sapiens/genome/chr21/germlineresources/dbsnp_138.hg38.vcf.gz.tbi"
fasta = "${params.modules_testdata_base_path}/genomics/homo_sapiens/genome/chr21/sequence/genome.fasta"
fasta_fai = "${params.modules_testdata_base_path}/genomics/homo_sapiens/genome/chr21/sequence/genome.fasta.fai"
germline_resource = "${params.modules_testdata_base_path}/genomics/homo_sapiens/genome/chr21/germlineresources/gnomAD.r2.1.1.vcf.gz"
germline_resource_tbi = "${params.modules_testdata_base_path}/genomics/homo_sapiens/genome/chr21/germlineresources/gnomAD.r2.1.1.vcf.gz.tbi"
intervals = "${params.modules_testdata_base_path}/genomics/homo_sapiens/genome/chr21/sequence/multi_intervals.bed"
pon = "${params.modules_testdata_base_path}/genomics/homo_sapiens/genome/chr21/germlineresources/mills_and_1000G.indels.hg38.vcf.gz"
pon_tbi = "${params.modules_testdata_base_path}/genomics/homo_sapiens/genome/chr21/germlineresources/mills_and_1000G.indels.hg38.vcf.gz.tbi"
ngscheckmate_bed = "${params.modules_testdata_base_path}/genomics/homo_sapiens/genome/chr21/germlineresources/SNP_GRCh38_hg38_wChr.bed"
nucleotides_per_second = 20
step = 'variant_calling'
tools = null
Expand Down
Loading
0