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.

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

update filenames #60

Merged
merged 13 commits into from
Mar 23, 2024
13 changes: 12 additions & 1 deletion module/depth_to_bed.nf
Original file line number Diff line number Diff line change
@@ -1,3 +1,4 @@
include { generate_standard_filename } from '../external/pipeline-Nextflow-module/modules/common/generate_standardized_filename/main.nf'
/*
* Module/process description here
*
Expand Down Expand Up @@ -32,12 +33,22 @@ process convert_depth_to_bed {
path ".command.*"

script:

output_filename = generate_standard_filename(
"SAMtools-${params.samtools_version}",
params.dataset_id,
params.sample_id,
[
'additional_information': "${tag}-depth-per-base.bed"
]
)

"""
set -euo pipefail

cat ${input_tsv} | \
awk 'BEGIN {OFS="\t"} {chr = \$1; start=\$2-1; stop=\$2; depth=\$3; print chr,start,stop,depth}' \
| sort -k1,1 -k2,2n \
> ${params.sample_id}.${tag}_depth-per-base.bed
> ${output_filename}
"""
}
38 changes: 34 additions & 4 deletions module/filter_off_target_depth.nf
Original file line number Diff line number Diff line change
@@ -1,4 +1,4 @@

include { generate_standard_filename } from '../external/pipeline-Nextflow-module/modules/common/generate_standardized_filename/main.nf'
/*
* Filter for sites with read depth above a minimum threshold.
* Important for excluding near-target regions from off-target calculations.
Expand Down Expand Up @@ -28,14 +28,24 @@ process run_depth_filter {
path ".command.*"

script:

output_filename = generate_standard_filename(
"SAMtools-${params.samtools_version}",
params.dataset_id,
params.sample_id,
[
'additional_information': "depth-filtered.bed"
]
)

"""
set -euo pipefail

awk \
-v min_depth="${params.min_read_depth}" \
'\$4 >= min_depth' \
${input} \
> ${params.sample_id}.depth-filtered.bed
> ${output_filename}
"""
}

Expand Down Expand Up @@ -73,6 +83,16 @@ process run_slop_BEDtools {
path ".command.*"

script:

output_filename = generate_standard_filename(
"BEDtools-${params.bedtools_version}",
params.dataset_id,
params.sample_id,
[
'additional_information': "${tag}_slop-${slop}.bed"
]
)

"""
set -euo pipefail

Expand All @@ -81,7 +101,7 @@ process run_slop_BEDtools {
-i ${target_bed} \
-g ${genome_sizes} \
-b ${slop} \
> ${params.sample_id}.${tag}_slop-${slop}.bed
> ${output_filename}
"""
}

Expand Down Expand Up @@ -113,6 +133,16 @@ process run_intersect_BEDtools {
path ".command.*"

script:

output_filename = generate_standard_filename(
"BEDtools-${params.bedtools_version}",
params.dataset_id,
params.sample_id,
[
'additional_information': "off-target-dbSNP_depth-per-base.bed"
]
)

"""
set -euo pipefail

Expand All @@ -121,6 +151,6 @@ process run_intersect_BEDtools {
-a ${off_target_bed} \
-b ${target_bed} \
-v \
> ${params.sample_id}.off-target-dbSNP_depth-per-base.bed
> ${output_filename}
"""
}
11 changes: 10 additions & 1 deletion module/get_depth_samtools.nf
Original file line number Diff line number Diff line change
@@ -1,3 +1,4 @@
include { generate_standard_filename } from '../external/pipeline-Nextflow-module/modules/common/generate_standardized_filename/main.nf'
/*
* Module/process description here
*
Expand Down Expand Up @@ -28,6 +29,14 @@ process run_depth_SAMtools {
path ".command.*"

script:
output_filename = generate_standard_filename(
"SAMtools-${params.samtools_version}",
params.dataset_id,
params.sample_id,
[
'additional_information': "${tag}-depth-per-base.tsv"
]
)
"""
set -euo pipefail

Expand All @@ -38,7 +47,7 @@ process run_depth_SAMtools {
-aa \
--min-BQ ${params.min_base_quality} \
--min-MQ ${params.min_mapping_quality} \
-o ${params.sample_id}.${tag}.depth_per_base.tsv \
-o ${output_filename} \
${params.samtools_depth_extra_args}
"""
}
13 changes: 12 additions & 1 deletion module/merge_bedfiles_bedtools.nf
Original file line number Diff line number Diff line change
@@ -1,3 +1,4 @@
include { generate_standard_filename } from '../external/pipeline-Nextflow-module/modules/common/generate_standardized_filename/main.nf'
/*
* Module/process description here
*
Expand Down Expand Up @@ -26,13 +27,23 @@ process merge_bedfiles_BEDtools {
path ".command.*"

script:

output_filename = generate_standard_filename(
"BEDtools-${params.bedtools_version}",
params.dataset_id,
params.sample_id,
[
'additional_information': "target-with-enriched-off-target-intervals.bed"
]
)

"""
set -euo pipefail

cat ${target_bed} ${off_target_bed} | \
sort -k1,1 -k2,2n | \
awk '{OFS = "\t"}{print \$1, \$2, \$3}' | \
bedtools merge \
> ${params.sample_id}.target_with_enriched_off-target_intervals.bed
> ${output_filename}
"""
}
13 changes: 12 additions & 1 deletion module/merge_intervals_bedtools.nf
Original file line number Diff line number Diff line change
@@ -1,3 +1,4 @@
include { generate_standard_filename } from '../external/pipeline-Nextflow-module/modules/common/generate_standardized_filename/main.nf'
/*
* Module/process description here
*
Expand Down Expand Up @@ -25,6 +26,16 @@ process run_merge_BEDtools {
path ".command.*"

script:

output_filename = generate_standard_filename(
"BEDtools-${params.bedtools_version}",
params.dataset_id,
params.sample_id,
[
'additional_information': "collapsed-coverage.bed"
]
)

"""
set -euo pipefail

Expand All @@ -33,6 +44,6 @@ process run_merge_BEDtools {
-i ${input_depth_bed} \
-c 4 \
-o ${params.merge_operation} \
> ${params.sample_id}.collapsed_coverage.bed
> ${output_filename}
"""
}
27 changes: 25 additions & 2 deletions module/run_HS_metrics.nf
Original file line number Diff line number Diff line change
@@ -1,3 +1,4 @@
include { generate_standard_filename } from '../external/pipeline-Nextflow-module/modules/common/generate_standardized_filename/main.nf'
/*
* Module/process description here
*
Expand Down Expand Up @@ -34,14 +35,26 @@ process run_BedToIntervalList_picard {
path ".command.*"

script:

output_filename_base = generate_standard_filename(
"Picard-${params.picard_version}",
params.dataset_id,
params.sample_id,
[
'additional_information': "${tag}"
]
)

output_filename = "${output_filename_base}.interval_list"

"""
set -euo pipefail

java \"-Xmx${(task.memory - params.gatk_command_mem_diff).getMega()}m\" \
-jar /usr/local/share/picard-slim-${params.picard_version}-0/picard.jar \
BedToIntervalList \
--INPUT $input_bed \
--OUTPUT ${params.sample_id}.${tag}.interval_list \
--OUTPUT ${output_filename} \
--SEQUENCE_DICTIONARY $reference_dict \
--SORT false
"""
Expand Down Expand Up @@ -70,6 +83,16 @@ process run_CollectHsMetrics_picard {
path ".command.*"

script:

output_filename = generate_standard_filename(
"Picard-${params.picard_version}",
params.dataset_id,
params.sample_id,
[
'additional_information': "HsMetrics.txt"
]
)

"""
set -euo pipefail

Expand All @@ -79,7 +102,7 @@ process run_CollectHsMetrics_picard {
--BAIT_INTERVALS $bait_interval_list \
--INPUT $input_bam \
--TARGET_INTERVALS $target_interval_list \
--OUTPUT ${params.sample_id}.HsMetrics.txt \
--OUTPUT ${output_filename} \
--COVERAGE_CAP ${params.coverage_cap} \
${params.picard_CollectHsMetrics_extra_args} \
--NEAR_DISTANCE ${params.near_distance} \
Expand Down
15 changes: 3 additions & 12 deletions nftest.yml
Original file line number Diff line number Diff line change
Expand Up @@ -12,21 +12,12 @@ cases:
skip: false
verbose: true
asserts:
- actual: calculate-targeted-coverage-*/TWGSAMIN000001-T002-S02-F/SAMtools-*/output/TWGSAMIN000001-T002-S02-F.collapsed_coverage.bed
- actual: calculate-targeted-coverage-*/TWGSAMIN000001-T002-S02-F/SAMtools-*/output/BEDtools-*_TWGSAMIN000001_TWGSAMIN000001-T002-S02-F_collapsed-coverage.bed
expect: /hot/software/pipeline/pipeline-calculate-targeted-coverage/Nextflow/development/output/TWGSAMIN000001-T002-S02-F.collapsed_coverage.bed
method: md5
- actual: calculate-targeted-coverage-*/TWGSAMIN000001-T002-S02-F/SAMtools-*/output/TWGSAMIN000001-T002-S02-F.collapsed_coverage.bed.sha512
expect: /hot/software/pipeline/pipeline-calculate-targeted-coverage/Nextflow/development/output/TWGSAMIN000001-T002-S02-F.collapsed_coverage.bed.sha512
method: md5
- actual: calculate-targeted-coverage-*/TWGSAMIN000001-T002-S02-F/SAMtools-*/output/TWGSAMIN000001-T002-S02-F.off-target-dbSNP_depth-per-base.bed
- actual: calculate-targeted-coverage-*/TWGSAMIN000001-T002-S02-F/SAMtools-*/output/BEDtools-*_TWGSAMIN000001_TWGSAMIN000001-T002-S02-F_off-target-dbSNP-depth-per-base.bed
expect: /hot/software/pipeline/pipeline-calculate-targeted-coverage/Nextflow/development/output/TWGSAMIN000001-T002-S02-F.off-target-dbSNP_depth-per-base.bed
method: md5
- actual: calculate-targeted-coverage-*/TWGSAMIN000001-T002-S02-F/SAMtools-*/output/TWGSAMIN000001-T002-S02-F.off-target-dbSNP_depth-per-base.bed.sha512
expect: /hot/software/pipeline/pipeline-calculate-targeted-coverage/Nextflow/development/output/TWGSAMIN000001-T002-S02-F.off-target-dbSNP_depth-per-base.bed.sha512
method: md5
- actual: calculate-targeted-coverage-*/TWGSAMIN000001-T002-S02-F/SAMtools-*/output/TWGSAMIN000001-T002-S02-F.target_with_enriched_off-target_intervals.bed
- actual: calculate-targeted-coverage-*/TWGSAMIN000001-T002-S02-F/SAMtools-*/output/BEDtools-*_TWGSAMIN000001_TWGSAMIN000001-T002-S02-F_target-with-enriched-off-target-intervals.bed
expect: /hot/software/pipeline/pipeline-calculate-targeted-coverage/Nextflow/development/output/TWGSAMIN000001-T002-S02-F.target_with_enriched_off-target_intervals.bed
method: md5
- actual: calculate-targeted-coverage-*/TWGSAMIN000001-T002-S02-F/SAMtools-*/output/TWGSAMIN000001-T002-S02-F.target_with_enriched_off-target_intervals.bed.sha512
expect: /hot/software/pipeline/pipeline-calculate-targeted-coverage/Nextflow/development/output/TWGSAMIN000001-T002-S02-F.target_with_enriched_off-target_intervals.bed.sha512
method: md5
2 changes: 1 addition & 1 deletion test/configtest-F16.json
Original file line number Diff line number Diff line change
@@ -1,450 +1,450 @@
{
"nextflow_version": "23.10.0",
"config": [
"test/nftest.config"
],
"params_file": "test/single.yaml",
"cpus": 16,
"memory_gb": 31,
"nf_params": {
"output_dir": "/tmp/nf-config-test-outputs"

Check warning on line 10 in test/configtest-F16.json

View workflow job for this annotation

GitHub Actions / tests / run (test/configtest-F16.json)

< "nextflow_version": "23.10.0", < "config": [ < "test/nftest.config" < ], < "params_file": "test/single.yaml", < "cpus": 16, < "memory_gb": 31, < "nf_params": { < "output_dir": "/tmp/nf-config-test-outputs" --- > "nextflow_version": "23.10.0", > "config": [ > "test/nftest.config" > ], > "params_file": "test/single.yaml", > "cpus": 16, > "memory_gb": 31, > "nf_params": { > "output_dir": "/tmp/nf-config-test-outputs" > }, > "envvars": { > "SLURM_JOB_ID": "4674821" > }, > "mocks": { > "check_path": "" > }, > "dated_fields": [ > "params.log_output_dir", > "report.file", > "timeline.file", > "trace.file", > "params.date" > ], > "expected_result": { > "docker": { > "all_group_ids": "$(for i in `id --real --groups`; do echo -n \"--group-add=$i \"; done)", > "enabled": true, > "runOptions": "-u $(id -u):$(id -g) $(for i in `id --real --groups`; do echo -n \"--group-add=$i \"; done)", > "uid_and_gid": "-u $(id -u):$(id -g)"
},
"envvars": {
"SLURM_JOB_ID": "4674821"

Check warning on line 13 in test/configtest-F16.json

View workflow job for this annotation

GitHub Actions / tests / run (test/configtest-F16.json)

< "envvars": { < "SLURM_JOB_ID": "4674821" --- > "manifest": { > "author": "Nicole Zeltser", > "description": "Nextflow pipeline for calculating read-depth related statistics for targeted sequencing experiments", > "name": "calculate-targeted-coverage", > "version": "1.0.0-rc.2"
},
"mocks": {
"check_path": ""

Check warning on line 16 in test/configtest-F16.json

View workflow job for this annotation

GitHub Actions / tests / run (test/configtest-F16.json)

< "mocks": { < "check_path": "" --- > "params": { > "bait_bed": "", > "bait_interval_list": "", > "bedr_version": "1.1.0", > "bedtools_version": "2.29.2", > "blcds_registered_dataset": false, > "collect_metrics": true, > "coverage_cap": "3000", > "dataset_id": "TWGSAMIN000001", > "dataset_registry_prefix": "/hot/data", > "date": "19970704T165655Z", > "dbSNP_slop": "150", > "docker_container_registry": "ghcr.io/uclahs-cds", > "docker_image_bedops": "ghcr.io/uclahs-cds/bedr:1.1.0", > "docker_image_bedtools": "ghcr.io/uclahs-cds/bedtools:2.29.2", > "docker_image_picard": "ghcr.io/uclahs-cds/picard:3.0.0", > "docker_image_samtools": "ghcr.io/uclahs-cds/samtools:1.16.1", > "docker_image_validate": "ghcr.io/uclahs-cds/pipeval:4.0.0-rc.2", > "gatk_command_mem_diff": "2 GB", > "genome_sizes": "/hot/ref/reference/GRCh38-BI-20160721/Homo_sapiens_assembly38.fasta.fai", > "input": { > "bam": "/hot/resource/SMC-HET/tumours/A-mini/bams/n1/output/S2.T-n1.bam" > }, > "log_output_dir": "/tmp/nf-config-test-outputs/calculate-targeted-coverage-1.0.0-rc.2/TWGSAMIN000001-T002-S02-F/log-calculate-targeted-coverage-1.0.0-rc.2-19970704T165655Z", > "max_cpus": "16", > "max_memory": "31 GB", > "merge_operation": "collapse", > "min_base_quality": "20", > "min_cpus": "1", > "min_mapping_quality": "20", > "min_memory": "1 MB", > "min_read_depth": "30", > "near_distance": "250", > "off_target_depth": true, > "off_target_slop": "500", > "output_dir": "/tmp/nf-config-test-outputs", > "output_dir_base": "/tmp/nf-config-test-outputs/calculate-targeted-coverage-1.0.0-rc.2/TWGSAMIN000001-T002-S02-F", > "output_enriched_target_file": true, > "patient": "null", > "picard_CollectHsMetrics_extra_args": "", > "picard_version": "3.0.0", > "pipeval_version": "4.0.0-rc.2", > "reference_dbSNP": "/hot/ref/database/dbSNP-155/thinned/GRCh38/dbSNP-155_thinned_hg38.vcf.gz", > "reference_dict": "/hot/ref/reference/GRCh38-BI-20160721/Homo_sapiens_assembly38.dict", > "sample": "null", > "sample_id": "TWGSAMIN000001-T002-S02-F", > "samtools_depth_extra_args": "", > "samtools_version": "1.16.1", > "save_all_dbSNP": false, > "save_intermediate_files": false, > "save_interval_list": false, > "save_raw_target_bed": false, > "target_bed": "/hot/software/pipeline/pipeline-calculate-targeted-coverage/Nextflow/development/input/GRch38-small.bed", > "target_depth": true, > "target_interval_list": "", > "ucla_cds": true, > "work_dir": "/scratch/4674821", > "workflow_output_dir": "/tmp/nf-config-test-outputs/calculate-targeted-coverage-1.0.0-rc.2/TWGSAMIN000001-T002-S02-F/SAMtools-1.16.1"
},
"dated_fields": [
"params.log_output_dir",
"report.file",
"timeline.file",
"trace.file",
"params.date"
],
"expected_result": {
"docker": {
"all_group_ids": "$(for i in `id --real --groups`; do echo -n \"--group-add=$i \"; done)",
"enabled": true,
"runOptions": "-u $(id -u):$(id -g) $(for i in `id --real --groups`; do echo -n \"--group-add=$i \"; done)",
"uid_and_gid": "-u $(id -u):$(id -g)"
},
"manifest": {
"author": "Nicole Zeltser",
"description": "Nextflow pipeline for calculating read-depth related statistics for targeted sequencing experiments",
"name": "calculate-targeted-coverage",
"version": "1.0.0-rc.2"
},
"params": {
"bait_bed": "",
"bait_interval_list": "",
"bedr_version": "1.1.0",
"bedtools_version": "2.29.2",
"blcds_registered_dataset": false,
"collect_metrics": true,
"coverage_cap": "3000",
"dataset_id": "TWGSAMIN000001-T002-S02-F",
"dataset_id": "TWGSAMIN000001",
"dataset_registry_prefix": "/hot/data",
"date": "19970704T165655Z",
"dbSNP_slop": "150",
"docker_container_registry": "ghcr.io/uclahs-cds",
"docker_image_bedops": "ghcr.io/uclahs-cds/bedr:1.1.0",
"docker_image_bedtools": "ghcr.io/uclahs-cds/bedtools:2.29.2",
"docker_image_picard": "ghcr.io/uclahs-cds/picard:3.0.0",
"docker_image_samtools": "ghcr.io/uclahs-cds/samtools:1.16.1",
"docker_image_validate": "ghcr.io/uclahs-cds/pipeval:4.0.0-rc.2",
"gatk_command_mem_diff": "2 GB",
"genome_sizes": "/hot/ref/reference/GRCh38-BI-20160721/Homo_sapiens_assembly38.fasta.fai",
"input": {
"bam": "/hot/resource/SMC-HET/tumours/A-mini/bams/n1/output/S2.T-n1.bam"
},
"log_output_dir": "/tmp/nf-config-test-outputs/calculate-targeted-coverage-1.0.0-rc.2/TWGSAMIN000001-T002-S02-F/log-calculate-targeted-coverage-1.0.0-rc.2-19970704T165655Z",
"max_cpus": "16",
"max_memory": "31 GB",
"merge_operation": "collapse",
"min_base_quality": "20",
"min_cpus": "1",
"min_mapping_quality": "20",
"min_memory": "1 MB",
"min_read_depth": "30",
"near_distance": "250",
"off_target_depth": true,
"off_target_slop": "500",
"output_dir": "/tmp/nf-config-test-outputs",
"output_dir_base": "/tmp/nf-config-test-outputs/calculate-targeted-coverage-1.0.0-rc.2/TWGSAMIN000001-T002-S02-F",
"output_enriched_target_file": true,
"patient": "null",
"picard_CollectHsMetrics_extra_args": "",
"picard_version": "3.0.0",
"pipeval_version": "4.0.0-rc.2",
"reference_dbSNP": "/hot/ref/database/dbSNP-155/thinned/GRCh38/dbSNP-155_thinned_hg38.vcf.gz",
"reference_dict": "/hot/ref/reference/GRCh38-BI-20160721/Homo_sapiens_assembly38.dict",
"sample": "null",
"sample_id": "TWGSAMIN000001-T002-S02-F",
"samtools_depth_extra_args": "",
"samtools_version": "1.16.1",
"save_all_dbSNP": false,
"save_intermediate_files": false,
"save_interval_list": false,
"save_raw_target_bed": false,
"target_bed": "/hot/software/pipeline/pipeline-calculate-targeted-coverage/Nextflow/development/input/GRch38-small.bed",
"target_depth": true,
"target_interval_list": "",
"ucla_cds": true,
"work_dir": "/scratch/4674821",
"workflow_output_dir": "/tmp/nf-config-test-outputs/calculate-targeted-coverage-1.0.0-rc.2/TWGSAMIN000001-T002-S02-F/SAMtools-1.16.1"
},
"params_schema": {
"bait_bed": {
"allow_empty": true,
"help": "Target intervals to process for DNA panel/targeted sequencing samples; leave empty for WGS",
"required": true,
"type": "String"
},
"bait_interval_list": {
"allow_empty": true,
"help": "Target intervals to process for DNA panel/targeted sequencing samples; leave empty for WGS",
"required": true,
"type": "String"
},
"collect_metrics": {
"default": true,
"help": "Whether to run picard CollectHsMetrics",
"required": true,
"type": "Bool"
},
"dataset_id": {
"help": "Dataset ID",
"required": true,
"type": "String"
},
"genome_sizes": {
"help": "Absolute path to table of chromosome lengths, can be fasta index",
"mode": "r",
"required": true,
"type": "Path"
},
"input": {
"elements": {
"bam": {
"help": "Input BAM for coverage analysis",
"mode": "r",
"required": true,
"type": "Path"
}
},
"help": "Input samples",
"required": true,
"type": "InputNamespace"
},
"off_target_depth": {
"default": true,
"help": "Whether to calculate depth at off-target dbSNP loci",
"required": true,
"type": "Bool"
},
"output_dir": {
"help": "Absolute path to output directory",
"mode": "w",
"required": true,
"type": "Path"
},
"output_enriched_target_file": {
"default": true,
"help": "Whether or not to output a new target file containing high-coverage off-target dbSNP loci",
"required": true,
"type": "Bool"
},
"picard_CollectHsMetrics_extra_args": {
"allow_empty": true,
"help": "Extra arguments for CollectHsMetrics",
"required": true,
"type": "String"
},
"reference_dbSNP": {
"help": "Absolute path to thinned dbSNP VCF",
"mode": "r",
"required": true,
"type": "Path"
},
"reference_dict": {
"help": "Absolute path to reference genome dictionary",
"mode": "r",
"required": true,
"type": "Path"
},
"sample_id": {
"help": "Sample ID",
"required": true,
"type": "String"
},
"samtools_depth_extra_args": {
"allow_empty": true,
"help": "Extra arguments for samtools depth",
"required": true,
"type": "String"
},
"save_intermediate_files": {
"default": false,
"help": "Whether to save intermediate files",
"required": true,
"type": "Bool"
},
"save_interval_list": {
"default": false,
"help": "Whether to save a copy of the interval list generated for picard CollectHsMetrics",
"required": true,
"type": "Bool"
},
"target_bed": {
"allow_empty": true,
"help": "Target intervals to process for DNA panel/targeted sequencing samples; leave empty for WGS",
"required": true,
"type": "String"

Check warning on line 203 in test/configtest-F16.json

View workflow job for this annotation

GitHub Actions / tests / run (test/configtest-F16.json)

< "dated_fields": [ < "params.log_output_dir", < "report.file", < "timeline.file", < "trace.file", < "params.date" < ], < "expected_result": { < "docker": { < "all_group_ids": "$(for i in `id --real --groups`; do echo -n \"--group-add=$i \"; done)", < "enabled": true, < "runOptions": "-u $(id -u):$(id -g) $(for i in `id --real --groups`; do echo -n \"--group-add=$i \"; done)", < "uid_and_gid": "-u $(id -u):$(id -g)" < }, < "manifest": { < "author": "Nicole Zeltser", < "description": "Nextflow pipeline for calculating read-depth related statistics for targeted sequencing experiments", < "name": "calculate-targeted-coverage", < "version": "1.0.0-rc.2" < }, < "params": { < "bait_bed": "", < "bait_interval_list": "", < "bedr_version": "1.1.0", < "bedtools_version": "2.29.2", < "blcds_registered_dataset": false, < "collect_metrics": true, < "coverage_cap": "3000", < "dataset_id": "TWGSAMIN000001", < "dataset_registry_prefix": "/hot/data", < "date": "19970704T165655Z", < "dbSNP_slop": "150", < "docker_container_registry": "ghcr.io/uclahs-cds", < "docker_image_bedops": "ghcr.io/uclahs-cds/bedr:1.1.0", < "docker_image_bedtools": "ghcr.io/uclahs-cds/bedtools:2.29.2", < "docker_image_picard": "ghcr.io/uclahs-cds/picard:3.0.0", < "docker_image_samtools": "ghcr.io/uclahs-cds/samtools:1.16.1", < "docker_image_validate": "ghcr.io/uclahs-cds/pipeval:4.0.0-rc.2", < "gatk_command_mem_diff": "2 GB", < "genome_sizes": "/hot/ref/reference/GRCh38-BI-20160721/Homo_sapiens_assembly38.fasta.fai", < "input": { < "bam": "/hot/resource/SMC-HET/tumours/A-mini/bams/n1/output/S2.T-n1.bam" < }, < "log_output_dir": "/tmp/nf-config-test-outputs/calculate-targeted-coverage-1.0.0-rc.2/TWGSAMIN000001-T002-S02-F/log-calculate-targeted-coverage-1.0.0-rc.2-19970704T165655Z", < "max_cpus": "16", < "max_memory": "31 GB", < "merge_operation": "collapse", < "min_base_quality": "20", < "min_cpus": "1", < "min_mapping_quality": "20", < "min_memory": "1 MB", < "min_read_depth": "30", < "near_distance": "250", < "off_target_depth": true, < "off_target_slop": "500", < "output_dir": "/tmp/nf-config-test-outputs", < "output_dir_base": "/tmp/nf-config-test-outputs/calculate-targeted-coverage-1.0.0-rc.2/TWGSAMIN000001-T002-S02-F", < "output_enriched_target_file": true, < "patient": "null", < "picard_CollectHsMetrics_extra_args": "", < "picard_version": "3.0.0", < "pipeval_version": "4.0.0-rc.2", < "reference_dbSNP": "/hot/ref/database/dbSNP-155/thinned/GRCh38/dbSNP-155_thinned_hg38.vcf.gz", < "reference_dict": "/hot/ref/reference/GRCh38-BI-20160721/Homo_sapiens_assembly38.dict", < "sample": "null", < "sample_id": "TWGSAMIN000001-T002-S02-F", < "samtools_depth_extra_args": "", < "samtools_version": "1.16.1", < "save_all_dbSNP": false, < "save_intermediate_files": false, < "save_interval_list": false, < "save_raw_target_bed": false, < "target_bed": "/hot/software/pipeline/pipeline-calculate-targeted-coverage/Nextflow/development/input/GRch38-small.bed", < "target_depth": true, < "target_interval_list": "", < "ucla_cds": true, < "work_dir": "/scratch/4674821", < "workflow_output_dir": "/tmp/nf-config-test-outputs/calculate-targeted-coverage-1.0.0-rc.2/TWGSAMIN000001-T002-S02-F/SAMtools-1.16.1" < }, < "params_schema": { < "bait_bed": { < "allow_empty": true, < "help": "Target intervals to process for DNA panel/targeted sequencing samples; leave empty for WGS", < "required": true, < "type": "String" < },
},
"target_depth": {
"default": false,
"help": "Whether or not to output a new target file containing high-coverage off-target dbSNP loci",
"required": true,
"type": "Bool"

Check warning on line 209 in test/configtest-F16.json

View workflow job for this annotation

GitHub Actions / tests / run (test/configtest-F16.json)

< "target_depth": { < "default": false, < "help": "Whether or not to output a new target file containing high-coverage off-target dbSNP loci", < "required": true, < "type": "Bool" --- > "help": "Input samples", > "required": true, > "type": "InputNamespace" > }, > "off_target_depth": { > "default": true, > "help": "Whether to calculate depth at off-target dbSNP loci", > "required": true, > "type": "Bool" > }, > "output_dir": { > "help": "Absolute path to output directory", > "mode": "w", > "required": true, > "type": "Path" > }, > "output_enriched_target_file": { > "default": true, > "help": "Whether or not to output a new target file containing high-coverage off-target dbSNP loci", > "required": true, > "type": "Bool" > }, > "picard_CollectHsMetrics_extra_args": { > "allow_empty": true, > "help": "Extra arguments for CollectHsMetrics", > "required": true, > "type": "String" > }, > "reference_dbSNP": { > "help": "Absolute path to thinned dbSNP VCF", > "mode": "r", > "required": true, > "type": "Path" > }, > "reference_dict": { > "help": "Absolute path to reference genome dictionary", > "mode": "r", > "required": true, > "type": "Path" > }, > "sample_id": { > "help": "Sample ID", > "required": true, > "type": "String" > }, > "samtools_depth_extra_args": { > "allow_empty": true, > "help": "Extra arguments for samtools depth", > "required": true, > "type": "String" > }, > "save_intermediate_files": { > "default": false, > "help": "Whether to save intermediate files", > "required": true, > "type": "Bool" > }, > "save_interval_list": { > "default": false, > "help": "Whether to save a copy of the interval list generated for picard CollectHsMetrics", > "required": true, > "type": "Bool" > }, > "target_bed": { > "allow_empty": true, > "help": "Target intervals to process for DNA panel/targeted sequencing samples; leave empty for WGS", > "required": true, > "type": "String" > }, > "target_depth": { > "default": false, > "help": "Whether or not to output a new target file containing high-coverage off-target dbSNP loci", > "required": true, > "type": "Bool" > }, > "target_interval_list": { > "allow_empty": true, > "help": "Target intervals to process for DNA panel/targeted sequencing samples; leave empty for WGS", > "required": true, > "type": "String" > } > }, > "process": { > "cache": true, > "containerOptions": { > "1": "--cpu-shares 1024 --cpus $task.cpus", > "2": "--cpu-shares 1024 --cpus $task.cpus", > "3": "--cpu-shares 1024 --cpus $task.cpus", > "closure": "--cpu-shares 1024 --cpus $task.cpus" > }, > "cpus": { > "1": "1", > "2": "2", > "3": "3", > "closure": "closure()" > }, > "echo": true, > "errorStrategy": { > "1": "finish", > "2": "finish", > "3": "finish", > "closure": "finish" > }, > "executor": "local", > "maxRetries": "1", > "memory": "31 GB", > "withLabel:process_high": { > "cpus": { > "1": "12", > "2": "16", > "3": "16", > "closure": "closure()"
},
"target_interval_list": {
"allow_empty": true,
"help": "Target intervals to process for DNA panel/targeted sequencing samples; leave empty for WGS",
"required": true,
"type": "String"

Check warning on line 215 in test/configtest-F16.json

View workflow job for this annotation

GitHub Actions / tests / run (test/configtest-F16.json)

< "target_interval_list": { < "allow_empty": true, < "help": "Target intervals to process for DNA panel/targeted sequencing samples; leave empty for WGS", < "required": true, < "type": "String" --- > "memory": { > "1": "31 GB", > "2": "31 GB", > "3": "31 GB", > "closure": "closure()"
}
},
"process": {
"cache": true,
"containerOptions": {
"1": "--cpu-shares 1024 --cpus $task.cpus",
"2": "--cpu-shares 1024 --cpus $task.cpus",
"3": "--cpu-shares 1024 --cpus $task.cpus",
"closure": "--cpu-shares 1024 --cpus $task.cpus"
},

Check warning on line 225 in test/configtest-F16.json

View workflow job for this annotation

GitHub Actions / tests / run (test/configtest-F16.json)

< "process": { < "cache": true, < "containerOptions": { < "1": "--cpu-shares 1024 --cpus $task.cpus", < "2": "--cpu-shares 1024 --cpus $task.cpus", < "3": "--cpu-shares 1024 --cpus $task.cpus", < "closure": "--cpu-shares 1024 --cpus $task.cpus" < }, --- > "withLabel:process_low": {
"cpus": {
"1": "1",
"2": "2",
"3": "3",

Check warning on line 229 in test/configtest-F16.json

View workflow job for this annotation

GitHub Actions / tests / run (test/configtest-F16.json)

< "1": "1", < "2": "2", < "3": "3", --- > "1": "2", > "2": "4", > "3": "6",
"closure": "closure()"
},
"echo": true,
"errorStrategy": {
"1": "finish",
"2": "finish",
"3": "finish",
"closure": "finish"
},
"executor": "local",
"maxRetries": "1",
"memory": "31 GB",
"withLabel:process_high": {
"cpus": {
"1": "12",
"2": "16",
"3": "16",
"closure": "closure()"
},
"memory": {
"1": "31 GB",
"2": "31 GB",
"3": "31 GB",
"closure": "closure()"
}
},
"withLabel:process_low": {
"cpus": {
"1": "2",
"2": "4",
"3": "6",
"closure": "closure()"
},
"memory": {
"1": "3 GB",
"2": "6 GB",
"3": "9 GB",
"closure": "closure()"
}
},
"withLabel:process_medium": {
"cpus": {
"1": "6",
"2": "12",
"3": "16",
"closure": "closure()"
},
"memory": {
"1": "31 GB",
"2": "31 GB",
"3": "31 GB",
"closure": "closure()"
}
},
"withName:convert_depth_to_bed": {
"cpus": "1",
"memory": "1 GB"
},
"withName:merge_bedfiles_BEDtools": {
"cpus": "1",
"memory": "1 GB"
},
"withName:run_BedToIntervalList_picard": {
"cpus": "1",
"memory": "3 GB"
},
"withName:run_CollectHsMetrics_picard": {
"cpus": "1",
"memory": "25 GB"
},
"withName:run_depth_SAMtools": {
"cpus": "1",
"memory": "1 GB"
},
"withName:run_depth_filter": {
"cpus": "1",
"memory": "1 GB"
},
"withName:run_intersect_BEDtools": {
"cpus": "1",
"memory": "1 GB"
},
"withName:run_merge_BEDtools": {
"cpus": "1",
"memory": "1 GB"
},
"withName:run_slop_BEDtools": {
"cpus": "1",
"memory": "1 GB"

Check warning on line 318 in test/configtest-F16.json

View workflow job for this annotation

GitHub Actions / tests / run (test/configtest-F16.json)

< "echo": true, < "errorStrategy": { < "1": "finish", < "2": "finish", < "3": "finish", < "closure": "finish" < }, < "executor": "local", < "maxRetries": "1", < "memory": "31 GB", < "withLabel:process_high": { < "cpus": { < "1": "12", < "2": "16", < "3": "16", < "closure": "closure()" < }, < "memory": { < "1": "31 GB", < "2": "31 GB", < "3": "31 GB", < "closure": "closure()" < } < }, < "withLabel:process_low": { < "cpus": { < "1": "2", < "2": "4", < "3": "6", < "closure": "closure()" < }, < "memory": { < "1": "3 GB", < "2": "6 GB", < "3": "9 GB", < "closure": "closure()" < } < }, < "withLabel:process_medium": { < "cpus": { < "1": "6", < "2": "12", < "3": "16", < "closure": "closure()" < }, < "memory": { < "1": "31 GB", < "2": "31 GB", < "3": "31 GB", < "closure": "closure()" < } < }, < "withName:convert_depth_to_bed": { < "cpus": "1", < "memory": "1 GB" < }, < "withName:merge_bedfiles_BEDtools": { < "cpus": "1", < "memory": "1 GB" < }, < "withName:run_BedToIntervalList_picard": { < "cpus": "1", < "memory": "3 GB" < }, < "withName:run_CollectHsMetrics_picard": { < "cpus": "1", < "memory": "25 GB" < }, < "withName:run_depth_SAMtools": { < "cpus": "1", < "memory": "1 GB" < }, < "withName:run_depth_filter": { < "cpus": "1", < "memory": "1 GB" < }, < "withName:run_intersect_BEDtools": { < "cpus": "1", < "memory": "1 GB" < }, < "withName:run_merge_BEDtools": { < "cpus": "1", < "memory": "1 GB" < }, < "withName:run_slop_BEDtools": { < "cpus": "1", < "memory": "1 GB" --- > "memory": { > "1": "3 GB", > "2": "6 GB", > "3": "9 GB", > "closure": "closure()"
}
},
"report": {
"enabled": true,
"file": "/tmp/nf-config-test-outputs/calculate-targeted-coverage-1.0.0-rc.2/TWGSAMIN000001-T002-S02-F/log-calculate-targeted-coverage-1.0.0-rc.2-19970704T165655Z/nextflow-log/report.html"
},
"timeline": {
"enabled": true,
"file": "/tmp/nf-config-test-outputs/calculate-targeted-coverage-1.0.0-rc.2/TWGSAMIN000001-T002-S02-F/log-calculate-targeted-coverage-1.0.0-rc.2-19970704T165655Z/nextflow-log/timeline.html"
},
"trace": {
"enabled": true,
"file": "/tmp/nf-config-test-outputs/calculate-targeted-coverage-1.0.0-rc.2/TWGSAMIN000001-T002-S02-F/log-calculate-targeted-coverage-1.0.0-rc.2-19970704T165655Z/nextflow-log/trace.txt"
},
"tz": "sun.util.calendar.ZoneInfo[id=\"UTC\",offset=0,dstSavings=0,useDaylight=false,transitions=0,lastRule=null]",
"workDir": "/scratch/4674821",
"yaml": {
"bait_bed": {
"allow_empty": true,
"help": "Target intervals to process for DNA panel/targeted sequencing samples; leave empty for WGS",
"required": true,
"type": "String"
},
"bait_interval_list": {
"allow_empty": true,
"help": "Target intervals to process for DNA panel/targeted sequencing samples; leave empty for WGS",
"required": true,
"type": "String"
},
"collect_metrics": {
"default": true,
"help": "Whether to run picard CollectHsMetrics",
"required": true,
"type": "Bool"
},
"dataset_id": {
"help": "Dataset ID",
"required": true,
"type": "String"
},
"genome_sizes": {
"help": "Absolute path to table of chromosome lengths, can be fasta index",
"mode": "r",
"required": true,
"type": "Path"
},
"input": {
"elements": {
"bam": {
"help": "Input BAM for coverage analysis",
"mode": "r",
"required": true,
"type": "Path"
}
},
"help": "Input samples",
"required": true,
"type": "InputNamespace"
},
"off_target_depth": {
"default": true,
"help": "Whether to calculate depth at off-target dbSNP loci",
"required": true,
"type": "Bool"
},
"output_dir": {
"help": "Absolute path to output directory",
"mode": "w",
"required": true,
"type": "Path"
},
"output_enriched_target_file": {
"default": true,
"help": "Whether or not to output a new target file containing high-coverage off-target dbSNP loci",
"required": true,
"type": "Bool"
},
"picard_CollectHsMetrics_extra_args": {
"allow_empty": true,
"help": "Extra arguments for CollectHsMetrics",
"required": true,
"type": "String"
},
"reference_dbSNP": {
"help": "Absolute path to thinned dbSNP VCF",
"mode": "r",
"required": true,
"type": "Path"
},
"reference_dict": {
"help": "Absolute path to reference genome dictionary",
"mode": "r",
"required": true,
"type": "Path"
},
"sample_id": {
"help": "Sample ID",
"required": true,
"type": "String"
},
"samtools_depth_extra_args": {
"allow_empty": true,
"help": "Extra arguments for samtools depth",
"required": true,
"type": "String"
},
"save_intermediate_files": {
"default": false,
"help": "Whether to save intermediate files",
"required": true,
"type": "Bool"
},
"save_interval_list": {
"default": false,
"help": "Whether to save a copy of the interval list generated for picard CollectHsMetrics",
"required": true,
"type": "Bool"
},
"target_bed": {
"allow_empty": true,
"help": "Target intervals to process for DNA panel/targeted sequencing samples; leave empty for WGS",
"required": true,
"type": "String"
},
"target_depth": {
"default": false,
"help": "Whether or not to output a new target file containing high-coverage off-target dbSNP loci",
"required": true,
"type": "Bool"

Check warning on line 447 in test/configtest-F16.json

View workflow job for this annotation

GitHub Actions / tests / run (test/configtest-F16.json)

< "report": { < "enabled": true, < "file": "/tmp/nf-config-test-outputs/calculate-targeted-coverage-1.0.0-rc.2/TWGSAMIN000001-T002-S02-F/log-calculate-targeted-coverage-1.0.0-rc.2-19970704T165655Z/nextflow-log/report.html" < }, < "timeline": { < "enabled": true, < "file": "/tmp/nf-config-test-outputs/calculate-targeted-coverage-1.0.0-rc.2/TWGSAMIN000001-T002-S02-F/log-calculate-targeted-coverage-1.0.0-rc.2-19970704T165655Z/nextflow-log/timeline.html" < }, < "trace": { < "enabled": true, < "file": "/tmp/nf-config-test-outputs/calculate-targeted-coverage-1.0.0-rc.2/TWGSAMIN000001-T002-S02-F/log-calculate-targeted-coverage-1.0.0-rc.2-19970704T165655Z/nextflow-log/trace.txt" < }, < "tz": "sun.util.calendar.ZoneInfo[id=\"UTC\",offset=0,dstSavings=0,useDaylight=false,transitions=0,lastRule=null]", < "workDir": "/scratch/4674821", < "yaml": { < "bait_bed": { < "allow_empty": true, < "help": "Target intervals to process for DNA panel/targeted sequencing samples; leave empty for WGS", < "required": true, < "type": "String" < }, < "bait_interval_list": { < "allow_empty": true, < "help": "Target intervals to process for DNA panel/targeted sequencing samples; leave empty for WGS", < "required": true, < "type": "String" < }, < "collect_metrics": { < "default": true, < "help": "Whether to run picard CollectHsMetrics", < "required": true, < "type": "Bool" < }, < "dataset_id": { < "help": "Dataset ID", < "required": true, < "type": "String" < }, < "genome_sizes": { < "help": "Absolute path to table of chromosome lengths, can be fasta index", < "mode": "r", < "required": true, < "type": "Path" < }, < "input": { < "elements": { < "bam": { < "help": "Input BAM for coverage analysis", < "mode": "r", < "required": true, < "type": "Path" < } < }, < "help": "Input samples", < "required": true, < "type": "InputNamespace" < }, < "off_target_depth": { < "default": true, < "help": "Whether to calculate depth at off-target dbSNP loci", < "required": true, < "type": "Bool" < }, < "output_dir": { < "help": "Absolute path to output directory", < "mode": "w", < "required": true, < "type": "Path" < }, < "output_enriched_target_file": { < "default": true, < "help": "Whether or not to output a new target file containing high-coverage off-target dbSNP loci", < "required": true, < "type": "Bool" < }, < "picard_CollectHsMetrics_extra_args": { < "allow_empty": true, < "help": "Extra arguments for CollectHsMetrics", < "required": true, < "type": "String" < }, < "reference_dbSNP": { < "help": "Absolute path to thinned dbSNP VCF", < "mode": "r", < "required": true, < "type": "Path" < }, < "reference_dict": { < "help": "Absolute path to reference genome dictionary", < "mode": "r", < "required": true, < "type": "Path" < }, < "sample_id": { < "help": "Sample ID", < "required": true, < "type": "String" < }, < "samtools_depth_extra_args": { < "allow_empty": true, < "help": "Extra arguments for samtools depth", < "required": true, < "type": "String" < }, < "save_intermediate_files": { < "default": false, < "help": "Whether to save intermediate files", < "required": true, < "type": "B
},
"target_interval_list": {
"allow_empty": true,
Expand Down
2 changes: 1 addition & 1 deletion test/nftest.config
Original file line number Diff line number Diff line change
Expand Up @@ -9,7 +9,7 @@ includeConfig "${projectDir}/nextflow.config"
// Inputs/parameters of the pipeline
params {
// sample inputs
dataset_id = 'TWGSAMIN000001-T002-S02-F'
dataset_id = 'TWGSAMIN000001'
blcds_registered_dataset = false // if you want the output to be registered

// reference files
Expand Down
Loading