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

FEAT: Use annotation-cache and update VEP to v110 #1122

Merged
merged 24 commits into from
Aug 17, 2023
Merged

FEAT: Use annotation-cache and update VEP to v110 #1122

Show file tree
Hide file tree
Changes from 21 commits
Commits
Show all changes
24 commits
Select commit Hold shift + click to select a range
34a59bb
use s3://annotation-cache
maxulysse Jun 20, 2023
690922e
sort list
maxulysse Jun 20, 2023
6ce0619
sort list
maxulysse Jun 20, 2023
971c850
add error message
maxulysse Jun 20, 2023
2fc8a85
update config files
maxulysse Jun 20, 2023
7462df1
remove container with built-in cache
maxulysse Jun 20, 2023
ef5efe2
update tests
maxulysse Jun 20, 2023
be19c48
remove snpeff_version and vep_version
maxulysse Jun 21, 2023
e9c73e0
rework meta.id key for VEP download
maxulysse Jun 21, 2023
7183f33
add use_annotation_cache_keys
maxulysse Jun 21, 2023
7f506f2
it's a params
maxulysse Jun 21, 2023
28f76e1
no need for /
maxulysse Jun 21, 2023
1aef254
update vep cache version
maxulysse Jun 22, 2023
afd0df5
Merge branch 'dev' of github.com:nf-core/sarek into annotation_cache
maxulysse Jul 6, 2023
0078a67
Merge branch 'dev' into annotation_cache
maxulysse Jul 9, 2023
a86340f
Merge branch 'dev' into annotation_cache
maxulysse Jul 13, 2023
e78b35a
Merge branch 'dev' into annotation_cache
maxulysse Jul 21, 2023
ef4e2ea
Update nextflow.config
maxulysse Jul 21, 2023
1fe7b55
update modules
maxulysse Jul 25, 2023
aa69d6b
fix meta maps
maxulysse Jul 26, 2023
2e77a5c
fix syntac
maxulysse Aug 16, 2023
29c323e
Merge branch 'dev' into annotation_cache
maxulysse Aug 17, 2023
cd72227
Apply suggestions from code review
maxulysse Aug 17, 2023
6ef8a46
update CHANGELOG
maxulysse Aug 17, 2023
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
40 changes: 8 additions & 32 deletions conf/igenomes.config
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -37,11 +37,9 @@ params {
mappability = "${params.igenomes_base}/Homo_sapiens/GATK/GRCh37/Annotation/Control-FREEC/out100m2_hg19.gem"
snpeff_db = 87
snpeff_genome = 'GRCh37'
snpeff_version = '5.1'
vep_cache_version = 108
vep_cache_version = 110
vep_genome = 'GRCh37'
vep_species = 'homo_sapiens'
vep_version = '108.2'
}
'GATK.GRCh38' {
ascat_alleles = "${params.igenomes_base}/Homo_sapiens/GATK/GRCh38/Annotation/ASCAT/G1000_alleles_hg38.zip"
Expand Down Expand Up @@ -74,34 +72,28 @@ params {
pon_tbi = "${params.igenomes_base}/Homo_sapiens/GATK/GRCh38/Annotation/GATKBundle/1000g_pon.hg38.vcf.gz.tbi"
snpeff_db = 105
snpeff_genome = 'GRCh38'
snpeff_version = '5.1'
vep_cache_version = 108
vep_cache_version = 110
vep_genome = 'GRCh38'
vep_species = 'homo_sapiens'
vep_version = '108.2'
}
'Ensembl.GRCh37' {
bwa = "${params.igenomes_base}/Homo_sapiens/Ensembl/GRCh37/Sequence/BWAIndex/version0.6.0/"
fasta = "${params.igenomes_base}/Homo_sapiens/Ensembl/GRCh37/Sequence/WholeGenomeFasta/genome.fa"
readme = "${params.igenomes_base}/Homo_sapiens/Ensembl/GRCh37/Annotation/README.txt"
snpeff_db = 87
snpeff_genome = 'GRCh37'
snpeff_version = '5.1'
vep_cache_version = 108
vep_cache_version = 110
vep_genome = 'GRCh37'
vep_species = 'homo_sapiens'
vep_version = '108.2'
}
'NCBI.GRCh38' {
bwa = "${params.igenomes_base}/Homo_sapiens/NCBI/GRCh38/Sequence/BWAIndex/version0.6.0/"
fasta = "${params.igenomes_base}/Homo_sapiens/NCBI/GRCh38/Sequence/WholeGenomeFasta/genome.fa"
snpeff_db = 105
snpeff_genome = 'GRCh38'
snpeff_version = '5.1'
vep_cache_version = 108
vep_cache_version = 110
vep_genome = 'GRCh38'
vep_species = 'homo_sapiens'
vep_version = '108.2'
}
'CHM13' {
fasta = "${params.igenomes_base}/Homo_sapiens/UCSC/CHM13/Sequence/WholeGenomeFasta/genome.fa"
Expand All @@ -123,11 +115,9 @@ params {
readme = "${params.igenomes_base}/Mus_musculus/Ensembl/GRCm38/Annotation/README.txt"
snpeff_db = 99
snpeff_genome = 'GRCm38'
snpeff_version = '5.1'
vep_cache_version = 102
vep_genome = 'GRCm38'
vep_species = 'mus_musculus'
vep_version = '108.2'
}
'TAIR10' {
bwa = "${params.igenomes_base}/Arabidopsis_thaliana/Ensembl/TAIR10/Sequence/BWAIndex/version0.6.0/"
Expand All @@ -145,34 +135,28 @@ params {
readme = "${params.igenomes_base}/Bos_taurus/Ensembl/UMD3.1/Annotation/README.txt"
snpeff_db = 75
snpeff_genome = 'UMD3.1'
snpeff_version = '5.1'
vep_cache_version = 94
vep_genome = 'UMD3.1'
vep_species = 'bos_taurus'
vep_version = '108.2'
}
'WBcel235' {
bwa = "${params.igenomes_base}/Caenorhabditis_elegans/Ensembl/WBcel235/Sequence/BWAIndex/version0.6.0/"
fasta = "${params.igenomes_base}/Caenorhabditis_elegans/Ensembl/WBcel235/Sequence/WholeGenomeFasta/genome.fa"
snpeff_db = 105
snpeff_genome = 'WBcel235'
snpeff_version = '5.1'
vep_cache_version = 108
vep_cache_version = 110
vep_genome = 'WBcel235'
vep_species = 'caenorhabditis_elegans'
vep_version = '108.2'
}
'CanFam3.1' {
bwa = "${params.igenomes_base}/Canis_familiaris/Ensembl/CanFam3.1/Sequence/BWAIndex/version0.6.0/"
fasta = "${params.igenomes_base}/Canis_familiaris/Ensembl/CanFam3.1/Sequence/WholeGenomeFasta/genome.fa"
readme = "${params.igenomes_base}/Canis_familiaris/Ensembl/CanFam3.1/Annotation/README.txt"
snpeff_db = 99
snpeff_genome = 'CanFam3.1'
snpeff_version = '5.1'
vep_cache_version = 104
vep_genome = 'CanFam3.1'
vep_species = 'canis_lupus_familiaris'
vep_version = '108.2'
}
'GRCz10' {
bwa = "${params.igenomes_base}/Danio_rerio/Ensembl/GRCz10/Sequence/BWAIndex/version0.6.0/"
Expand Down Expand Up @@ -228,11 +212,9 @@ params {
fasta = "${params.igenomes_base}/Saccharomyces_cerevisiae/Ensembl/R64-1-1/Sequence/WholeGenomeFasta/genome.fa"
snpeff_db = 105
snpeff_genome = 'R64-1-1'
snpeff_version = '5.1'
vep_cache_version = 108
vep_cache_version = 110
vep_genome = 'R64-1-1'
vep_species = 'saccharomyces_cerevisiae'
vep_version = '108.2'
}
'EF2' {
bwa = "${params.igenomes_base}/Schizosaccharomyces_pombe/Ensembl/EF2/Sequence/BWAIndex/version0.6.0/"
Expand All @@ -258,35 +240,29 @@ params {
fasta = "${params.igenomes_base}/Homo_sapiens/UCSC/hg38/Sequence/WholeGenomeFasta/genome.fa"
snpeff_db = 105
snpeff_genome = 'GRCh38'
snpeff_version = '5.1'
vep_cache_version = 108
vep_cache_version = 110
vep_genome = 'GRCh38'
vep_species = 'homo_sapiens'
vep_version = '108.2'
}
'hg19' {
bwa = "${params.igenomes_base}/Homo_sapiens/UCSC/hg19/Sequence/BWAIndex/version0.6.0/"
fasta = "${params.igenomes_base}/Homo_sapiens/UCSC/hg19/Sequence/WholeGenomeFasta/genome.fa"
readme = "${params.igenomes_base}/Homo_sapiens/UCSC/hg19/Annotation/README.txt"
snpeff_db = 87
snpeff_genome = 'GRCh37'
snpeff_version = '5.1'
vep_cache_version = 108
vep_cache_version = 110
vep_genome = 'GRCh37'
vep_species = 'homo_sapiens'
vep_version = '108.2'
}
'mm10' {
bwa = "${params.igenomes_base}/Mus_musculus/UCSC/mm10/Sequence/BWAIndex/version0.6.0/"
fasta = "${params.igenomes_base}/Mus_musculus/UCSC/mm10/Sequence/WholeGenomeFasta/genome.fa"
readme = "${params.igenomes_base}/Mus_musculus/UCSC/mm10/Annotation/README.txt"
snpeff_db = 99
snpeff_genome = 'GRCm38'
snpeff_version = '5.1'
maxulysse marked this conversation as resolved.
Show resolved Hide resolved
vep_cache_version = 102
vep_genome = 'GRCm38'
vep_species = 'mus_musculus'
vep_version = '108.2'
}
'bosTau8' {
bwa = "${params.igenomes_base}/Bos_taurus/UCSC/bosTau8/Sequence/BWAIndex/version0.6.0/"
Expand Down
2 changes: 0 additions & 2 deletions conf/modules/annotate.config
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -20,7 +20,6 @@ process {
withName: 'SNPEFF_SNPEFF' {
ext.prefix = { vcf.baseName - ".vcf" + "_snpEff" }
ext.args = '-nodownload -canon -v'
if (!params.snpeff_cache && !params.download_cache) container = { params.snpeff_genome ? "docker.io/nfcore/snpeff:${params.snpeff_version}.${params.snpeff_genome}" : "docker.io/nfcore/snpeff:${params.snpeff_version}.${params.genome}" }
publishDir = [
[
mode: params.publish_dir_mode,
Expand All @@ -46,7 +45,6 @@ process {
].join(' ').trim() }
// If just VEP: <vcf prefix>_VEP.ann.vcf
ext.prefix = { vcf.baseName - ".vcf" + "_VEP.ann" }
if (!params.vep_cache && !params.download_cache) container = { params.vep_genome ? "docker.io/nfcore/vep:${params.vep_version}.${params.vep_genome}" : "docker.io/nfcore/vep:${params.vep_version}.${params.genome}" }
publishDir = [
[
mode: params.publish_dir_mode,
Expand Down
8 changes: 4 additions & 4 deletions conf/test.config
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -29,20 +29,20 @@ params {
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"
snpeff_cache = null
FriederikeHanssen marked this conversation as resolved.
Show resolved Hide resolved
snpeff_db = 105
snpeff_genome = 'WBcel235'
snpeff_version = '5.1'
vep_cache_version = 106
vep_cache = null
vep_cache_version = 108
maxulysse marked this conversation as resolved.
Show resolved Hide resolved
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
validationSchemaIgnoreParams = 'genomes,snpeff_version,vep_version'
validationSchemaIgnoreParams = 'genomes'
}

process {
Expand Down
8 changes: 4 additions & 4 deletions conf/test/cache.config
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -41,20 +41,20 @@ params {
germline_resource = params.test_data['homo_sapiens']['genome']['gnomad_r2_1_1_vcf_gz']
intervals = params.test_data['homo_sapiens']['genome']['genome_interval_list']
known_indels = params.test_data['homo_sapiens']['genome']['mills_and_1000g_indels_vcf_gz']
snpeff_cache = null
snpeff_db = 105
snpeff_genome = 'WBcel235'
snpeff_version = '5.1'
vep_cache_version = 106
vep_cache = null
vep_cache_version = 108
maxulysse marked this conversation as resolved.
Show resolved Hide resolved
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
validationSchemaIgnoreParams = 'genomes,test_data,snpeff_version,vep_version'
validationSchemaIgnoreParams = 'genomes,test_data'
}

process {
Expand Down
2 changes: 0 additions & 2 deletions main.nf
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -56,11 +56,9 @@ params.pon = WorkflowMain.getGenomeAttribute(params, 'pon')
params.pon_tbi = WorkflowMain.getGenomeAttribute(params, 'pon_tbi')
params.snpeff_db = WorkflowMain.getGenomeAttribute(params, 'snpeff_db')
params.snpeff_genome = WorkflowMain.getGenomeAttribute(params, 'snpeff_genome')
params.snpeff_version = WorkflowMain.getGenomeAttribute(params, 'snpeff_version')
params.vep_cache_version = WorkflowMain.getGenomeAttribute(params, 'vep_cache_version')
params.vep_genome = WorkflowMain.getGenomeAttribute(params, 'vep_genome')
params.vep_species = WorkflowMain.getGenomeAttribute(params, 'vep_species')
params.vep_version = WorkflowMain.getGenomeAttribute(params, 'vep_version')

/*
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
Expand Down
10 changes: 5 additions & 5 deletions modules.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -123,13 +123,13 @@
},
"ensemblvep/download": {
"branch": "master",
"git_sha": "911696ea0b62df80e900ef244d7867d177971f73",
"git_sha": "9f9e1fc31cb35876922070c0e601ae05abae5cae",
"installed_by": ["modules"]
},
"ensemblvep/vep": {
"branch": "master",
"git_sha": "911696ea0b62df80e900ef244d7867d177971f73",
"installed_by": ["vcf_annotate_ensemblvep", "modules"]
"git_sha": "9f9e1fc31cb35876922070c0e601ae05abae5cae",
"installed_by": ["modules", "vcf_annotate_ensemblvep"]
},
"fastp": {
"branch": "master",
Expand Down Expand Up @@ -403,12 +403,12 @@
},
"snpeff/download": {
"branch": "master",
"git_sha": "911696ea0b62df80e900ef244d7867d177971f73",
"git_sha": "4d584d5cf6ed5f7363a51cdb4b3eb25398e9e537",
"installed_by": ["modules"]
},
"snpeff/snpeff": {
"branch": "master",
"git_sha": "911696ea0b62df80e900ef244d7867d177971f73",
"git_sha": "4d584d5cf6ed5f7363a51cdb4b3eb25398e9e537",
"installed_by": ["vcf_annotate_snpeff", "modules"]
},
"strelka/germline": {
Expand Down
6 changes: 3 additions & 3 deletions modules/nf-core/ensemblvep/download/main.nf
View file
Open in desktop

Some generated files are not rendered by default. Learn more about how customized files appear on GitHub.

8 changes: 5 additions & 3 deletions modules/nf-core/ensemblvep/download/meta.yml
View file
Open in desktop

Some generated files are not rendered by default. Learn more about how customized files appear on GitHub.

6 changes: 3 additions & 3 deletions modules/nf-core/ensemblvep/vep/main.nf
View file
Open in desktop

Some generated files are not rendered by default. Learn more about how customized files appear on GitHub.

6 changes: 5 additions & 1 deletion modules/nf-core/snpeff/download/meta.yml
View file
Open in desktop

Some generated files are not rendered by default. Learn more about how customized files appear on GitHub.

2 changes: 1 addition & 1 deletion modules/nf-core/snpeff/snpeff/main.nf
View file
Open in desktop

Some generated files are not rendered by default. Learn more about how customized files appear on GitHub.

4 changes: 3 additions & 1 deletion modules/nf-core/snpeff/snpeff/meta.yml
View file
Open in desktop

Some generated files are not rendered by default. Learn more about how customized files appear on GitHub.

Loading