Skip to content

IRIS pipeline updates #30

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

Open
shguturu wants to merge 5 commits into
base: dev
Choose a base branch
from
Open

IRIS pipeline updates #30

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
5 commits
Select commit Hold shift + click to select a range
9713e38
update IRIS paths for v1 and v2 config files
shguturu Oct 25, 2025
85b044b
update queue to cmobic_cpu
shguturu Oct 28, 2025
2f358bf
clinical bam mirror path update
shguturu Nov 4, 2025
ce1c1f7
update GBCMS IRIS path
shguturu Nov 4, 2025
7ca98f4
update iris paths, increase conda env memory, and set biometrics version
shguturu Nov 21, 2025
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
28 changes: 14 additions & 14 deletions conf/iris_accessv1.config
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -5,16 +5,16 @@ executor {
}

process {
scratch = '/scratch/bergerm1/'
queue = 'cpu'
scratch = '/scratch/bergerm1/guturus1'
queue = 'cmobic_cpu'

withLabel: genotype_variants {
cpus = 8
memory = '8 GB'
memory = '16 GB'
}
withLabel: biometrics_extract {
cpus = 8
memory = '8 GB'
memory = '16 GB'
}
}

Expand All @@ -26,29 +26,29 @@ params {
// Regex Patterns
clinical_access_sample_regex_pattern = ".*-XS.*-standard.*"
clinical_impact_sample_regex_pattern = ".*(-IM|-IH).*"
fasta_ref = "/data1/core006/access/production/resources/reference/current/Homo_sapiens_assembly19.fasta"
fasta_ref = "/data1/core006/access/production/resources/reference/versions/hg19/Homo_sapiens_assembly19.fasta"
biometrics = [
bed : "/data1/core006/access/production/resources/msk-access/v1.0/regions_of_interest/versions/v1.0/MSK-ACCESS-v1_0-probe-B.sorted_chrY.bed",
vcf : "/data1/core006/access/resources/msk-access/v1.0/regions_of_interest/versions/v1.0/MSK-ACCESS-v1_0-TilingaAndFpSNPs.vcf"
vcf : "/data1/core006/access/production/resources/msk-access/v1.0/regions_of_interest/versions/v1.0/MSK-ACCESS-v1_0-TilingaAndFpSNPs.vcf"
]
base_dirs = [
research_access : [
data_dir: "/data1/core006/access/production/data",
bam_dir_template: "/data1/core006/access/production/data/bams/{cmo_patient_id}/{sample_id}/current"
],
clinical_access : [
bam_dir_template : "/data1/share001/access_12_245/{anon_id_fl}/{anon_id_sl}",
variant_dir : "/data1/core006/access/production/resources/cbioportal/current/msk_solid_heme",
bam_dir_template : "/data1/share001/share/access_12_245/{anon_id_fl}/{anon_id_sl}",
variant_dir : "/data1/core006/access/production/resources/cbioportal/versions/msk-impact/msk_solid_heme",
],
clinical_impact : [
bam_dir_template : "/data1/share001/irb12_245/{anon_id_fl}/{anon_id_sl}",
variant_dir : "/data1/core006/access/production/resources/cbioportal/current/msk_solid_heme",
bam_dir_template : "/data1/share001/share/impact_12_245/{anon_id_fl}/{anon_id_sl}",
variant_dir : "/data1/core006/access/production/resources/cbioportal/versions/msk-impact/msk_solid_heme",
facets_dir: "/data1/core006/ccs/shared/resources/impact/facets/all/"
]
]
// File paths
hotspot_list = "/data1/core006/access/production/resources/msk-access/v1.0/regions_of_interest/versions/v1.0/hotspot-list-union-v1-v2_with_TERT.txt"
ch_list = "/data1/core006/access/production/resources/dmp_signedout_CH/current/signedout_CH.txt"
ch_list = "/data1/core006/access/production/resources/dmp_signedout_CH/versions/10Feb2020/signedout_CH.txt"

file_paths = [
research_access : [
Expand All @@ -66,7 +66,7 @@ params {
]
],
clinical_access : [
key_file : "/data1/share001/request/ACCESS-12-245/key.txt",
key_file : "/data1/share001/dmp/request/ACCESS-12-245/key.txt",
bam_file_template : [
simplex : "${params.base_dirs.clinical_access.bam_dir_template}/{anon_id}-simplex.bam",
duplex : "${params.base_dirs.clinical_access.bam_dir_template}/{anon_id}-duplex.bam",
Expand All @@ -77,11 +77,11 @@ params {
mutations : "${params.base_dirs.clinical_access.variant_dir}/data_mutations_extended.txt",
cna : "${params.base_dirs.clinical_access.variant_dir}/data_CNA.txt",
sv : "${params.base_dirs.clinical_access.variant_dir}/data_sv.txt",
msi : "/data1/core006/access/production/resources/dmp_msi_admie_scores/current/all_admie_results_from_database.csv"
msi : "/data1/core006/access/production/resources/dmp_msi_admie_scores/versions/08Aug2023/all_admie_results_from_database.csv"
]
],
clinical_impact : [
key_file : "/data1/share001/request/12-245/key.txt",
key_file : "/data1/share001/dmp/request/12-245/key.txt",
bam_file_template : [
standard : "${params.base_dirs.clinical_impact.bam_dir_template}/{anon_id}.bam"
],
Expand Down
32 changes: 16 additions & 16 deletions conf/iris_accessv2.config
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -5,16 +5,16 @@ executor {
}

process {
scratch = '/scratch/bergerm1/'
queue = 'cpu'
scratch = '/scratch/bergerm1/guturus1'
queue = 'cmobic_cpu'

withLabel: genotype_variants {
cpus = 8
memory = '8 GB'
}
withLabel: biometrics_extract {
cpus = 8
memory = '8 GB'
memory = '16 GB'
}
}

Expand All @@ -26,31 +26,31 @@ params {
// Regex Patterns
clinical_access_sample_regex_pattern = ".*-XS.*-standard.*"
clinical_impact_sample_regex_pattern = ".*(-IM|-IH).*"
fasta_ref = "/data1/core006/access/production/resources/reference/current/Homo_sapiens_assembly19.fasta"
fasta_ref = "/data1/core006/access/production/resources/reference/versions/hg19/Homo_sapiens_assembly19.fasta"
biometrics = [
// bed : "/data1/core006/access/production/resources/msk-access/v1.0/regions_of_interest/versions/v1.0/MSK-ACCESS-v1_0-probe-B.sorted_chrY.bed", // v1 bed
bed : "/data1/core006/access/production/resources/msk-access/v2.0/regions_of_interest/versions/v1.0/MSK-ACCESS-v2_probes_Y_only.bed", // v2 bed
vcf : "/data1/core006/access/production/resources/msk-access/v1.0/regions_of_interest/versions/v1.0/MSK-ACCESS-v1_0-TilingaAndFpSNPs.vcf" // using v1 file because there are many more SNPs in v2 which makes biometrics extremely slow //
// vcf : "/data1/core006/access/production/resources/msk-access/v2.0/regions_of_interest/versions/v1.0/MSK-ACCESS-v2_0-TilingaAndFpSNPs.vcf" // v2 SNPs file
bed : "/data1/core006/access/production/resources/msk-access/v2.0/regions_of_interest/versions/v1.0/MSK-ACCESS-v2_probes_Y_only.bed",
// using v1 bed
vcf : "/data1/core006/access/production/resources/msk-access/v1.0/regions_of_interest/versions/v1.0/MSK-ACCESS-v1_0-TilingaAndFpSNPs.vcf"
//vcf : "/data1/core006/access/production/resources/msk-access/v2.0/regions_of_interest/versions/v1.0/MSK-ACCESS-v2_0-TilingaAndFpSNPs.vcf"
]
base_dirs = [
research_access : [
data_dir: "/data1/core006/access/production/data",
bam_dir_template: "/data1/core006/access/production/data/bams/{cmo_patient_id}/{sample_id}/current"
],
clinical_access : [
bam_dir_template : "/data1/share001/access_12_245/{anon_id_fl}/{anon_id_sl}",
variant_dir : "/data1/core006/access/production/resources/cbioportal/current/msk_solid_heme",
bam_dir_template : "/data1/share001/share/access_12_245/{anon_id_fl}/{anon_id_sl}",
variant_dir : "/data1/core006/access/production/resources/cbioportal/versions/msk-impact/msk_solid_heme",
],
clinical_impact : [
bam_dir_template : "/data1/share001/irb12_245/{anon_id_fl}/{anon_id_sl}",
variant_dir : "/data1/core006/access/production/resources/cbioportal/current/msk_solid_heme",
bam_dir_template : "/data1/share001/share/impact_12_245/{anon_id_fl}/{anon_id_sl}",
variant_dir : "/data1/core006/access/production/resources/cbioportal/versions/msk-impact/msk_solid_heme",
facets_dir: "/data1/core006/ccs/shared/resources/impact/facets/all/"
]
]
// File paths
hotspot_list = "/data1/core006/access/production/resources/msk-access/v2.0/regions_of_interest/versions/v1.0/hotspot-list-union-v1-v2_with_TERT.txt"
ch_list = "/data1/core006/access/production/resources/dmp_signedout_CH/current/signedout_CH.txt"
ch_list = "/data1/core006/access/production/resources/dmp_signedout_CH/versions/10Feb2020/signedout_CH.txt"

file_paths = [
research_access : [
Expand All @@ -68,7 +68,7 @@ params {
]
],
clinical_access : [
key_file : "/data1/share001/request/ACCESS-12-245/key.txt",
key_file : "/data1/share001/dmp/request/ACCESS-12-245/key.txt",
bam_file_template : [
simplex : "${params.base_dirs.clinical_access.bam_dir_template}/{anon_id}-simplex.bam",
duplex : "${params.base_dirs.clinical_access.bam_dir_template}/{anon_id}-duplex.bam",
Expand All @@ -79,11 +79,11 @@ params {
mutations : "${params.base_dirs.clinical_access.variant_dir}/data_mutations_extended.txt",
cna : "${params.base_dirs.clinical_access.variant_dir}/data_CNA.txt",
sv : "${params.base_dirs.clinical_access.variant_dir}/data_sv.txt",
msi : "/data1/core006/access/production/resources/dmp_msi_admie_scores/current/all_admie_results_from_database.csv"
msi : "/data1/core006/access/production/resources/dmp_msi_admie_scores/versions/08Aug2023/all_admie_results_from_database.csv"
]
],
clinical_impact : [
key_file : "/data1/share001/share/request/12-245/key.txt",
key_file : "/data1/share001/dmp/request/12-245/key.txt",
bam_file_template : [
standard : "${params.base_dirs.clinical_impact.bam_dir_template}/{anon_id}.bam"
],
Expand Down
2 changes: 1 addition & 1 deletion modules/local/BIOMETRICS/environment.yml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -9,4 +9,4 @@ dependencies:
- pandas
- importlib_metadata
- pyvcf3
- biometrics
- biometrics=0.2.15
28 changes: 10 additions & 18 deletions modules/local/INFER_SAMPLES/main.nf
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -21,23 +21,15 @@ process INFER_SAMPLES {

script:
"""
command="python3 ../../../bin/infer_samples.py \\
--id_mapping_file ${id_mapping_file} \\
--clinical_access_key_file ${clinical_access_key_file} \\
--clinical_impact_key_file ${clinical_impact_key_file} \\
--research_access_bam_dir_template '${research_access_bam_dir_template}' \\
--clinical_access_sample_regex_pattern '${clinical_access_sample_regex_pattern}' \\
--clinical_impact_sample_regex_pattern '${clinical_impact_sample_regex_pattern}'"

if [ -s "${keep_research_samples_file}" ]; then
command="\$command --keep_research_samples_file '${keep_research_samples_file}'"
fi

if [ -s "${exclude_samples_file}" ]; then
command="\$command --exclude_samples_file '${exclude_samples_file}'"
fi

echo \$command
eval \$command
python3 ${workflow.projectDir}/bin/infer_samples.py \
--id_mapping_file ${id_mapping_file} \
--clinical_access_key_file ${clinical_access_key_file} \
--clinical_impact_key_file ${clinical_impact_key_file} \
--research_access_bam_dir_template '${research_access_bam_dir_template}' \
--clinical_access_sample_regex_pattern '${clinical_access_sample_regex_pattern}' \
--clinical_impact_sample_regex_pattern '${clinical_impact_sample_regex_pattern}' \
${keep_research_samples_file ? "--keep_research_samples_file ${keep_research_samples_file}" : ""} \
${exclude_samples_file ? "--exclude_samples_file ${exclude_samples_file}" : ""}
"""

}
2 changes: 1 addition & 1 deletion modules/local/SNV_INDEL_GENOTYPE_VARIANTS/main.nf
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -29,7 +29,7 @@ process SNV_INDEL_GENOTYPE_VARIANTS {
-i ${genotyping_input} \\
-r ${fasta_ref} \\
--filter-duplicate 1 \\
-g /work/access/production/resources/tools/GetBaseCountsMultiSample/current/GetBaseCountsMultiSample \\
-g /data1/core006/access/production/resources/tools/GetBaseCountsMultiSample/versions/GetBaseCountsMultiSample-1.2.5 \\
-t ${task.cpus} \\

"""
Expand Down
11 changes: 6 additions & 5 deletions nextflow.config
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -10,14 +10,15 @@

// Global default params, used in configs
params {
input = "/juno/cmo/bergerlab/guturus1/testing_cohort/nf_inputs/v2/nf_v2_patients.csv"
keep_research_samples_file = "/juno/cmo/bergerlab/guturus1/testing_cohort/nf_inputs/v2/nf_v2_samples.csv"
// input = "/juno/cmo/bergerlab/arorak/repositories/clean_copy/access_data_analysis_nf/assets/test_accessv2_input.csv"
// keep_research_samples_file = "/juno/cmo/bergerlab/arorak/repositories/clean_copy/access_data_analysis_nf/assets/test_accessv2_include.csv"
input = "/data1/bergerm1/guturus1/juno_transfer_oct_22_latest/testing_cohort/nf_inputs/v1/nf_v1_patients.csv"
keep_research_samples_file = "/data1/bergerm1/guturus1/juno_transfer_oct_22_latest/testing_cohort/nf_inputs/v1/nf_v1_samples.csv"
exclude_samples_file = null

//input = "/data1/bergerm1/guturus1/juno_transfer_oct_22_latest/testing_cohort/nf_inputs/v2/nf_C-0093HD_P-0094719.csv"
//keep_research_samples_file = "/data1/bergerm1/guturus1/juno_transfer_oct_22_latest/testing_cohort/nf_inputs/v2/nf_C-0093HD_P-0094719_samples.csv"

// Output dir
outdir = "./results_accessv2/biometrics_only/"
outdir = "/data1/bergerm1/guturus1/juno_transfer_oct_22_latest/testing_cohort/nf_outputs/iris_testing_oct/v1"

variant_filter_rules = [
exclude_genes : "RP11-",
Expand Down