From 9713e3807d9f686a9064d5148bd1ce1c5a914a9a Mon Sep 17 00:00:00 2001 From: Shivani Guturu Date: Sat, 25 Oct 2025 11:17:15 -0400 Subject: [PATCH 1/5] update IRIS paths for v1 and v2 config files --- conf/iris_accessv1.config | 18 +++++++++--------- conf/iris_accessv2.config | 25 ++++++++++++------------- 2 files changed, 21 insertions(+), 22 deletions(-) diff --git a/conf/iris_accessv1.config b/conf/iris_accessv1.config index 78e1729..8add115 100644 --- a/conf/iris_accessv1.config +++ b/conf/iris_accessv1.config @@ -5,7 +5,7 @@ executor { } process { - scratch = '/scratch/bergerm1/' + scratch = '/scratch/bergerm1/guturus1' queue = 'cpu' withLabel: genotype_variants { @@ -26,10 +26,10 @@ 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 : [ @@ -38,17 +38,17 @@ params { ], 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", + 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", + 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 : [ @@ -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", @@ -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" ], diff --git a/conf/iris_accessv2.config b/conf/iris_accessv2.config index 1201cd2..71fd8c0 100644 --- a/conf/iris_accessv2.config +++ b/conf/iris_accessv2.config @@ -5,7 +5,7 @@ executor { } process { - scratch = '/scratch/bergerm1/' + scratch = '/scratch/bergerm1/guturus1' queue = 'cpu' withLabel: genotype_variants { @@ -26,12 +26,11 @@ 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" - 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 + fasta_ref = "/data1/core006/access/production/resources/reference/versions/hg19/Homo_sapiens_assembly19.fasta biometrics = [ + 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 : [ @@ -40,17 +39,17 @@ params { ], 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", + 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", + 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 : [ @@ -68,7 +67,7 @@ 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", @@ -79,11 +78,11 @@ 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" ], From 85b044b601f7800851929a6605b57348124f79d3 Mon Sep 17 00:00:00 2001 From: Shivani Guturu Date: Tue, 28 Oct 2025 08:38:08 -0400 Subject: [PATCH 2/5] update queue to cmobic_cpu --- conf/iris_accessv1.config | 2 +- conf/iris_accessv2.config | 5 +++-- modules/local/INFER_SAMPLES/main.nf | 28 ++++++++++------------------ nextflow.config | 11 ++++++----- 4 files changed, 20 insertions(+), 26 deletions(-) diff --git a/conf/iris_accessv1.config b/conf/iris_accessv1.config index 8add115..552d1c1 100644 --- a/conf/iris_accessv1.config +++ b/conf/iris_accessv1.config @@ -6,7 +6,7 @@ executor { process { scratch = '/scratch/bergerm1/guturus1' - queue = 'cpu' + queue = 'cmobic_cpu' withLabel: genotype_variants { cpus = 8 diff --git a/conf/iris_accessv2.config b/conf/iris_accessv2.config index 71fd8c0..34d3df0 100644 --- a/conf/iris_accessv2.config +++ b/conf/iris_accessv2.config @@ -6,7 +6,7 @@ executor { process { scratch = '/scratch/bergerm1/guturus1' - queue = 'cpu' + queue = 'cmobic_cpu' withLabel: genotype_variants { cpus = 8 @@ -26,7 +26,8 @@ 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/versions/hg19/Homo_sapiens_assembly19.fasta biometrics = [ + fasta_ref = "/data1/core006/access/production/resources/reference/versions/hg19/Homo_sapiens_assembly19.fasta" + biometrics = [ 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" diff --git a/modules/local/INFER_SAMPLES/main.nf b/modules/local/INFER_SAMPLES/main.nf index e31af7e..6487371 100644 --- a/modules/local/INFER_SAMPLES/main.nf +++ b/modules/local/INFER_SAMPLES/main.nf @@ -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}" : ""} """ + } diff --git a/nextflow.config b/nextflow.config index f9503cd..a44f179 100644 --- a/nextflow.config +++ b/nextflow.config @@ -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-", From 2f358bfc61105d37883611128755e8aa081e6605 Mon Sep 17 00:00:00 2001 From: Shivani Guturu Date: Tue, 4 Nov 2025 12:02:29 -0500 Subject: [PATCH 3/5] clinical bam mirror path update --- conf/iris_accessv1.config | 4 ++-- conf/iris_accessv2.config | 4 ++-- 2 files changed, 4 insertions(+), 4 deletions(-) diff --git a/conf/iris_accessv1.config b/conf/iris_accessv1.config index 552d1c1..f539a4a 100644 --- a/conf/iris_accessv1.config +++ b/conf/iris_accessv1.config @@ -37,11 +37,11 @@ params { 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}", + 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}", + bam_dir_template : "/data1/share001/share/irb12_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/" ] diff --git a/conf/iris_accessv2.config b/conf/iris_accessv2.config index 34d3df0..9c55765 100644 --- a/conf/iris_accessv2.config +++ b/conf/iris_accessv2.config @@ -39,11 +39,11 @@ params { 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}", + 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}", + bam_dir_template : "/data1/share001/share/irb12_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/" ] From ce1c1f7220b75be61a0db57e74a173535809827a Mon Sep 17 00:00:00 2001 From: Shivani Guturu Date: Tue, 4 Nov 2025 16:03:10 -0500 Subject: [PATCH 4/5] update GBCMS IRIS path --- modules/local/SNV_INDEL_GENOTYPE_VARIANTS/main.nf | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/modules/local/SNV_INDEL_GENOTYPE_VARIANTS/main.nf b/modules/local/SNV_INDEL_GENOTYPE_VARIANTS/main.nf index fe2ba72..3e29ce4 100644 --- a/modules/local/SNV_INDEL_GENOTYPE_VARIANTS/main.nf +++ b/modules/local/SNV_INDEL_GENOTYPE_VARIANTS/main.nf @@ -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} \\ """ From 7ca98f4cb6dd4f16a4cb4120bebf52aecd0285fa Mon Sep 17 00:00:00 2001 From: Shivani Guturu Date: Fri, 21 Nov 2025 12:18:27 -0500 Subject: [PATCH 5/5] update iris paths, increase conda env memory, and set biometrics version --- conf/iris_accessv1.config | 6 +++--- conf/iris_accessv2.config | 4 ++-- modules/local/BIOMETRICS/environment.yml | 2 +- 3 files changed, 6 insertions(+), 6 deletions(-) diff --git a/conf/iris_accessv1.config b/conf/iris_accessv1.config index f539a4a..3e49f64 100644 --- a/conf/iris_accessv1.config +++ b/conf/iris_accessv1.config @@ -10,11 +10,11 @@ process { withLabel: genotype_variants { cpus = 8 - memory = '8 GB' + memory = '16 GB' } withLabel: biometrics_extract { cpus = 8 - memory = '8 GB' + memory = '16 GB' } } @@ -41,7 +41,7 @@ params { variant_dir : "/data1/core006/access/production/resources/cbioportal/versions/msk-impact/msk_solid_heme", ], clinical_impact : [ - bam_dir_template : "/data1/share001/share/irb12_245/{anon_id_fl}/{anon_id_sl}", + 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/" ] diff --git a/conf/iris_accessv2.config b/conf/iris_accessv2.config index 9c55765..ed4c98f 100644 --- a/conf/iris_accessv2.config +++ b/conf/iris_accessv2.config @@ -14,7 +14,7 @@ process { } withLabel: biometrics_extract { cpus = 8 - memory = '8 GB' + memory = '16 GB' } } @@ -43,7 +43,7 @@ params { variant_dir : "/data1/core006/access/production/resources/cbioportal/versions/msk-impact/msk_solid_heme", ], clinical_impact : [ - bam_dir_template : "/data1/share001/share/irb12_245/{anon_id_fl}/{anon_id_sl}", + 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/" ] diff --git a/modules/local/BIOMETRICS/environment.yml b/modules/local/BIOMETRICS/environment.yml index 5c192f5..375884e 100644 --- a/modules/local/BIOMETRICS/environment.yml +++ b/modules/local/BIOMETRICS/environment.yml @@ -9,4 +9,4 @@ dependencies: - pandas - importlib_metadata - pyvcf3 - - biometrics + - biometrics=0.2.15 \ No newline at end of file