From a114f3c2a45cc038a08fba605f83be8e3b792557 Mon Sep 17 00:00:00 2001 From: Nicole Zeltser Date: Wed, 20 Mar 2024 13:58:36 -0700 Subject: [PATCH 01/12] use function to generate filenames --- module/depth_to_bed.nf | 13 +++++++++- module/filter_off_target_depth.nf | 38 ++++++++++++++++++++++++++---- module/get_depth_samtools.nf | 11 ++++++++- module/merge_bedfiles_bedtools.nf | 13 +++++++++- module/merge_intervals_bedtools.nf | 13 +++++++++- module/run_HS_metrics.nf | 25 ++++++++++++++++++-- 6 files changed, 103 insertions(+), 10 deletions(-) diff --git a/module/depth_to_bed.nf b/module/depth_to_bed.nf index 31f30ea..44f41fe 100644 --- a/module/depth_to_bed.nf +++ b/module/depth_to_bed.nf @@ -1,3 +1,4 @@ +include { generate_standard_filename } from '../external/pipeline-Nextflow-module/modules/common/generate_standardized_filename/main.nf' /* * Module/process description here * @@ -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 + > ${output_filename} """ } diff --git a/module/filter_off_target_depth.nf b/module/filter_off_target_depth.nf index 9c648bf..7d44a7a 100644 --- a/module/filter_off_target_depth.nf +++ b/module/filter_off_target_depth.nf @@ -1,4 +1,4 @@ - +include { generate_standard_filename } from '../external/pipeline-Nextflow-module/modules/common/generate_standardized_filename/main.nf' /* * Filter for sites with read depth above a minimum threshold. * Important for excluding near-target regions from off-target calculations. @@ -28,6 +28,16 @@ process run_depth_filter { path ".command.*" script: + + output_filename = generate_standard_filename( + "SAMtools-${params.samtools_version}", + params.dataset_id, + params.sample_id, + [ + 'additional_information': "depth-filtered.bed" + ] + ) + """ set -euo pipefail @@ -35,7 +45,7 @@ process run_depth_filter { -v min_depth="${params.min_read_depth}" \ '\$4 >= min_depth' \ ${input} \ - > ${params.sample_id}.depth-filtered.bed + > ${output_filename} """ } @@ -73,6 +83,16 @@ process run_slop_BEDtools { path ".command.*" script: + + output_filename = generate_standard_filename( + "BEDtools-${params.bedtools_version}", + params.dataset_id, + params.sample_id, + [ + 'additional_information': "${tag}_slop-${slop}.bed" + ] + ) + """ set -euo pipefail @@ -81,7 +101,7 @@ process run_slop_BEDtools { -i ${target_bed} \ -g ${genome_sizes} \ -b ${slop} \ - > ${params.sample_id}.${tag}_slop-${slop}.bed + > ${output_filename} """ } @@ -113,6 +133,16 @@ process run_intersect_BEDtools { path ".command.*" script: + + output_filename = generate_standard_filename( + "BEDtools-${params.bedtools_version}", + params.dataset_id, + params.sample_id, + [ + 'additional_information': "off-target-dbSNP_depth-per-base.bed" + ] + ) + """ set -euo pipefail @@ -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 + > ${output_filename} """ } diff --git a/module/get_depth_samtools.nf b/module/get_depth_samtools.nf index dc285a4..175eb10 100644 --- a/module/get_depth_samtools.nf +++ b/module/get_depth_samtools.nf @@ -1,3 +1,4 @@ +include { generate_standard_filename } from '../external/pipeline-Nextflow-module/modules/common/generate_standardized_filename/main.nf' /* * Module/process description here * @@ -28,6 +29,14 @@ process run_depth_SAMtools { path ".command.*" script: + output_filename = generate_standard_filename( + "SAMtools-${params.samtools_version}", + params.dataset_id, + params.sample_id, + [ + 'additional_information': "${tag}-depth-per-base.tsv" + ] + ) """ set -euo pipefail @@ -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} \ ${params.samtools_depth_extra_args} """ } diff --git a/module/merge_bedfiles_bedtools.nf b/module/merge_bedfiles_bedtools.nf index 5a6bfe4..5818b0f 100644 --- a/module/merge_bedfiles_bedtools.nf +++ b/module/merge_bedfiles_bedtools.nf @@ -1,3 +1,4 @@ +include { generate_standard_filename } from '../external/pipeline-Nextflow-module/modules/common/generate_standardized_filename/main.nf' /* * Module/process description here * @@ -26,6 +27,16 @@ process merge_bedfiles_BEDtools { path ".command.*" script: + + output_filename = generate_standard_filename( + "BEDtools-${params.bedtools_version}", + params.dataset_id, + params.sample_id, + [ + 'additional_information': "target-with-enriched-off-target-intervals.bed" + ] + ) + """ set -euo pipefail @@ -33,6 +44,6 @@ process merge_bedfiles_BEDtools { sort -k1,1 -k2,2n | \ awk '{OFS = "\t"}{print \$1, \$2, \$3}' | \ bedtools merge \ - > ${params.sample_id}.target_with_enriched_off-target_intervals.bed + > ${output_filename} """ } diff --git a/module/merge_intervals_bedtools.nf b/module/merge_intervals_bedtools.nf index 6919bef..d48d883 100644 --- a/module/merge_intervals_bedtools.nf +++ b/module/merge_intervals_bedtools.nf @@ -1,3 +1,4 @@ +include { generate_standard_filename } from '../external/pipeline-Nextflow-module/modules/common/generate_standardized_filename/main.nf' /* * Module/process description here * @@ -25,6 +26,16 @@ process run_merge_BEDtools { path ".command.*" script: + + output_filename = generate_standard_filename( + "BEDtools-${params.bedtools_version}", + params.dataset_id, + params.sample_id, + [ + 'additional_information': "collapsed-coverage.bed" + ] + ) + """ set -euo pipefail @@ -33,6 +44,6 @@ process run_merge_BEDtools { -i ${input_depth_bed} \ -c 4 \ -o ${params.merge_operation} \ - > ${params.sample_id}.collapsed_coverage.bed + > ${output_filename} """ } diff --git a/module/run_HS_metrics.nf b/module/run_HS_metrics.nf index 72541d7..7fddf41 100644 --- a/module/run_HS_metrics.nf +++ b/module/run_HS_metrics.nf @@ -1,3 +1,4 @@ +include { generate_standard_filename } from '../external/pipeline-Nextflow-module/modules/common/generate_standardized_filename/main.nf' /* * Module/process description here * @@ -34,6 +35,16 @@ process run_BedToIntervalList_picard { path ".command.*" script: + + output_filename = generate_standard_filename( + "Picard-${params.picard_version}", + params.dataset_id, + params.sample_id, + [ + 'additional_information': "${tag}.interval_list" + ] + ) + """ set -euo pipefail @@ -41,7 +52,7 @@ process run_BedToIntervalList_picard { -jar /usr/local/share/picard-slim-${params.picard_version}-0/picard.jar \ BedToIntervalList \ --INPUT $input_bed \ - --OUTPUT ${params.sample_id}.${tag}.interval_list \ + --OUTPUT ${output_filename} \ --SEQUENCE_DICTIONARY $reference_dict \ --SORT false """ @@ -70,6 +81,16 @@ process run_CollectHsMetrics_picard { path ".command.*" script: + + output_filename = generate_standard_filename( + "Picard-${params.picard_version}", + params.dataset_id, + params.sample_id, + [ + 'additional_information': ["${tag}.HsMetrics.txt"] + ] + ) + """ set -euo pipefail @@ -79,7 +100,7 @@ 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} \ From 847aa17703914f40b7601e4f144e734c91068057 Mon Sep 17 00:00:00 2001 From: Nicole Zeltser Date: Wed, 20 Mar 2024 14:10:24 -0700 Subject: [PATCH 02/12] update test cases --- nftest.yml | 12 ++++++------ test/configtest-F16.json | 2 +- test/nftest.config | 2 +- 3 files changed, 8 insertions(+), 8 deletions(-) diff --git a/nftest.yml b/nftest.yml index e391b7c..80748c1 100644 --- a/nftest.yml +++ b/nftest.yml @@ -12,21 +12,21 @@ 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 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 + - actual: calculate-targeted-coverage-*/TWGSAMIN000001-T002-S02-F/SAMtools-*/output/BEDtools-*_TWGSAMIN000001_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 + - actual: calculate-targeted-coverage-*/TWGSAMIN000001-T002-S02-F/SAMtools-*/output/BEDtools-*_TWGSAMIN000001_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 + - actual: calculate-targeted-coverage-*/TWGSAMIN000001-T002-S02-F/SAMtools-*/output/BEDtools-*_TWGSAMIN000001_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 diff --git a/test/configtest-F16.json b/test/configtest-F16.json index 6078e46..c5dff61 100644 --- a/test/configtest-F16.json +++ b/test/configtest-F16.json @@ -43,7 +43,7 @@ "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", diff --git a/test/nftest.config b/test/nftest.config index 15d79ab..6ce26ac 100644 --- a/test/nftest.config +++ b/test/nftest.config @@ -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 From c654349b45d5c80e0d563cc103bffda0bc620b9f Mon Sep 17 00:00:00 2001 From: Nicole Zeltser Date: Wed, 20 Mar 2024 17:21:39 -0700 Subject: [PATCH 03/12] typo fixes --- module/run_HS_metrics.nf | 8 +++++--- nftest.yml | 2 +- 2 files changed, 6 insertions(+), 4 deletions(-) diff --git a/module/run_HS_metrics.nf b/module/run_HS_metrics.nf index 7fddf41..251fde3 100644 --- a/module/run_HS_metrics.nf +++ b/module/run_HS_metrics.nf @@ -36,15 +36,17 @@ process run_BedToIntervalList_picard { script: - output_filename = generate_standard_filename( + output_filename_base = generate_standard_filename( "Picard-${params.picard_version}", params.dataset_id, params.sample_id, [ - 'additional_information': "${tag}.interval_list" + 'additional_information': "${tag}" ] ) + output_filename = "${output_filename_base}.interval_list" + """ set -euo pipefail @@ -87,7 +89,7 @@ process run_CollectHsMetrics_picard { params.dataset_id, params.sample_id, [ - 'additional_information': ["${tag}.HsMetrics.txt"] + 'additional_information': ".HsMetrics.txt" ] ) diff --git a/nftest.yml b/nftest.yml index 80748c1..a60fabc 100644 --- a/nftest.yml +++ b/nftest.yml @@ -12,7 +12,7 @@ cases: skip: false verbose: true asserts: - - actual: calculate-targeted-coverage-*/TWGSAMIN000001-T002-S02-F/SAMtools-*/output/BEDtools-*_TWGSAMIN000001_TWGSAMIN000001-T002-S02-F_collapsed-coverage + - 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/BEDtools-*_TWGSAMIN000001_TWGSAMIN000001-T002-S02-F_collapsed-coverage.bed.sha512 From 8f08318a52d9d56adfc21898057ed4f34973df1b Mon Sep 17 00:00:00 2001 From: Nicole Zeltser Date: Thu, 21 Mar 2024 13:50:12 -0700 Subject: [PATCH 04/12] update HsMetrics extension --- module/run_HS_metrics.nf | 2 +- nftest.yml | 9 --------- 2 files changed, 1 insertion(+), 10 deletions(-) diff --git a/module/run_HS_metrics.nf b/module/run_HS_metrics.nf index 251fde3..ef8e060 100644 --- a/module/run_HS_metrics.nf +++ b/module/run_HS_metrics.nf @@ -89,7 +89,7 @@ process run_CollectHsMetrics_picard { params.dataset_id, params.sample_id, [ - 'additional_information': ".HsMetrics.txt" + 'additional_information': "HsMetrics.txt" ] ) diff --git a/nftest.yml b/nftest.yml index a60fabc..656373d 100644 --- a/nftest.yml +++ b/nftest.yml @@ -15,18 +15,9 @@ cases: - 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/BEDtools-*_TWGSAMIN000001_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/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/BEDtools-*_TWGSAMIN000001_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/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/BEDtools-*_TWGSAMIN000001_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 From ba73a5c2a76b8a3f920ed4d54bf427a2a82ee224 Mon Sep 17 00:00:00 2001 From: Nicole Zeltser Date: Thu, 21 Mar 2024 18:49:24 -0700 Subject: [PATCH 05/12] update changelog --- CHANGELOG.md | 1 + 1 file changed, 1 insertion(+) diff --git a/CHANGELOG.md b/CHANGELOG.md index efe1e44..1db4751 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -20,6 +20,7 @@ This project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.htm ### Changed - Update CI/CD workflow to use current image - Update samtools depth default output options +- Update filenames to standardized format ## [v1.0.0-rc.2] - 2024-02-14 ### Changed From 08a9d29e84b91af710ed0c49008715a2ef462124 Mon Sep 17 00:00:00 2001 From: Nicole Zeltser Date: Thu, 21 Mar 2024 18:57:27 -0700 Subject: [PATCH 06/12] update readme --- README.md | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) diff --git a/README.md b/README.md index ca4af5c..94adce3 100644 --- a/README.md +++ b/README.md @@ -119,12 +119,12 @@ A directed acyclic graph of your pipeline. Output and Output Parameter/Flag | Description | | ------------ | ------------------------ | | `output_dir` | Location where generated output should be saved. | -| `.target-with-enriched-off-target-intervals.bed` | New target file including original target intervals and intervals encompassing coverage-enriched off-target dbSNP sites. | -|`.off-target-dbSNP_depth-per-base.bed`|Per-base read depth at dbSNP loci outside of targeted regions.| -| `.collapsed_coverage.bed` | Per-base read depth at specified target intervals, collapsed by interval. (OPTIONAL) Set `target_depth` in config file. | -|`.target-depth-per-base.bed`|Per-base read depth at target intervals (not collapsed). (OPTIONAL) set `save_raw_target_bed` in config file.| -|`.genome-wide-dbSNP_depth-per-base.bed`| Per-base read depth at all dbSNP loci. (OPTIONAL) Set `save_all_dbSNP` in config file.| -| `.HsMetrics.txt` | QC output from CollectHsMetrics()| +| `*target-with-enriched-off-target-intervals.bed` | New target file including original target intervals and intervals encompassing coverage-enriched off-target dbSNP sites. | +|`*off-target-dbSNP-depth-per-base.bed`|Per-base read depth at dbSNP loci outside of targeted regions.| +| `*collapsed_coverage.bed` | Per-base read depth at specified target intervals, collapsed by interval. (OPTIONAL) Set `target_depth` in config file. | +|`*target-depth-per-base.bed`|Per-base read depth at target intervals (not collapsed). (OPTIONAL) set `save_raw_target_bed` in config file.| +|`*genome-wide-dbSNP-depth-per-base.bed`| Per-base read depth at all dbSNP loci. (OPTIONAL) Set `save_all_dbSNP` in config file.| +| `*HsMetrics.txt` | QC output from CollectHsMetrics()| | `.tsv`,`.bed` | Intermediate outputs of unformatted and unmerged depth files. (OPTIONAL) Set `save_intermediate_files` in config file. | | `.interval_list` | Intermediate output of target bed file converted to picard's interval list format. (OPTIONAL) Set `save_interval_list` in config file. | | `report.html`, `timeline.html` and `trace.txt` | A Nextflowreport, timeline and trace files | From 6e046d811e40fb0c0c8bdb5dbed695e0ad212206 Mon Sep 17 00:00:00 2001 From: Nicole Zeltser Date: Thu, 21 Mar 2024 19:01:13 -0700 Subject: [PATCH 07/12] update diagram labels --- docs/calculate-targeted-coverage-flow.puml | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/docs/calculate-targeted-coverage-flow.puml b/docs/calculate-targeted-coverage-flow.puml index bd1a8ab..fbe24e5 100644 --- a/docs/calculate-targeted-coverage-flow.puml +++ b/docs/calculate-targeted-coverage-flow.puml @@ -25,9 +25,9 @@ rectangle "Target-Focused Workflow" { rectangle "Convert to BED" as ConvtoBED1 <> rectangle "Calculate Coverage Metrics" as CalcCovMetrics <> ' output files - rectangle ".target-depth-per-base.bed" as TargetReadDepthBED <> + rectangle "*target-depth-per-base.bed" as TargetReadDepthBED <> ' QC files - rectangle ".HSMetrics.txt" as HSMetrics <> + rectangle "*HSMetrics.txt" as HSMetrics <> } @@ -50,8 +50,8 @@ rectangle "Off-Target Workflow" { rectangle "Add Slop to Target Intervals" as AddSlopTarget <> ' output files - rectangle ".target-with-enriched-off-target-intervals.bed" as TargetPlusOffTargetReadDepthBED <> - rectangle ".off-target-dbSNP_depth-per-base.bed" as OffTargetReadDepth <> + rectangle "*target-with-enriched-off-target-intervals.bed" as TargetPlusOffTargetReadDepthBED <> + rectangle "*off-target-dbSNP-depth-per-base.bed" as OffTargetReadDepth <> ' end node rectangle "recalibrate-BAM" as RecalBAM #White From ebec90b658dedc2aa7cb7111f0a9dc87ab9e72d7 Mon Sep 17 00:00:00 2001 From: Nicole Zeltser Date: Thu, 21 Mar 2024 19:02:46 -0700 Subject: [PATCH 08/12] remove old drawio diagram --- ...ine-calculate-targeted-coverage.drawio.svg | 518 ------------------ 1 file changed, 518 deletions(-) delete mode 100644 pipeline-calculate-targeted-coverage.drawio.svg diff --git a/pipeline-calculate-targeted-coverage.drawio.svg b/pipeline-calculate-targeted-coverage.drawio.svg deleted file mode 100644 index fb93d48..0000000 --- a/pipeline-calculate-targeted-coverage.drawio.svg +++ /dev/null @@ -1,518 +0,0 @@ - - - - - - - - - - -
-
-
- Bam -
-
-
-
- - Bam - -
-
- - - - - - -
-
-
- Validate -
- Inputs -
-
-
-
- - Validate... - -
-
- - - - -
-
-
- Target File -
-
-
-
- - Target File - -
-
- - - - - - - - -
-
-
- Calculate Read Depth at dbSNP sites -
-
-
-
- - Calculate Read... - -
-
- - - - -
-
-
- dbSNP VCF -
-
-
-
- - dbSNP VCF - -
-
- - - - - - -
-
-
- Filter for minimum read depth -
-
-
-
- - Filter for min... - -
-
- - - - - - -
-
-
- Target + Enriched Off-target read depth BED -
-
-
-
- - Target + Enriched Off-ta... - -
-
- - - - - - - - -
-
-
- Merge with target file -
-
-
-
- - Merge with tar... - -
-
- - - - - - - - -
-
-
- Filter for off-target sites -
-
-
-
- - Filter for off... - -
-
- - - - - - -
-
-
- Off-target dbSNP read depth BED -
-
-
-
- - Off-target dbSNP read de... - -
-
- - - - - - - - - - -
-
-
- Convert to BED -
-
-
-
- - Convert to BED - -
-
- - - - -
-
-
- Calculate Per-base Read Depth -
-
-
-
- - Calculate Per-... - -
-
- - - - - - - - -
-
-
- Calculate Coverage Metrics -
-
-
-
- - Calculate Cove... - -
-
- - - - - - -
-
-
- Target read depth BED -
-
-
-
- - Target read depth BED - -
-
- - - - - - -
-
-
- HS Metrics TXT -
-
-
-
- - HS Metrics TXT - -
-
- - - - - - -
-
-
- Add Slop to Target Intervals -
-
-
-
- - Add Slop to Ta... - -
-
- - - - - - -
-
-
- Convert to BED -
-
-
-
- - Convert to BED - -
-
- - - - - - -
-
-
- recalibrate-BAM -
-
-
-
- - recalibrate-BAM - -
-
- - - - -
-
-
- QC -
- File -
-
-
-
- - QC... - -
-
- - - - -
-
-
- Output -
- File -
-
-
-
- - Output... - -
-
- - - - -
-
-
- Input -
- File -
-
-
-
- - Input... - -
-
- - - - - - - - -
-
-
- Target-focused workflow -
-
-
-
- - Target-focused workflow - -
-
- - - - -
-
-
- Off-target workflow -
-
-
-
- - Off-target workflow - -
-
- - - - - - - - -
-
-
- Convert BED to interval.list -
-
-
-
- - Convert BED to... - -
-
- - - - - - -
-
-
- Bait File -
-
-
-
- - Bait File - -
-
- - - - - - -
-
-
- Add Slop to off-target SNPs -
-
-
-
- - Add Slop to of... - -
-
-
- - - - - Text is not SVG - cannot display - - - -
\ No newline at end of file From f20c65132f214d5a2e3d09c8bf4823cc27362168 Mon Sep 17 00:00:00 2001 From: alkaZeltser Date: Fri, 22 Mar 2024 02:03:23 +0000 Subject: [PATCH 09/12] Update SVG images for PlantUML diagrams --- docs/calculate-targeted-coverage-flow.svg | 94 +++++++++++------------ 1 file changed, 47 insertions(+), 47 deletions(-) diff --git a/docs/calculate-targeted-coverage-flow.svg b/docs/calculate-targeted-coverage-flow.svg index 6f6ed1e..17857ed 100644 --- a/docs/calculate-targeted-coverage-flow.svg +++ b/docs/calculate-targeted-coverage-flow.svg @@ -1,37 +1,37 @@ -Target-Focused WorkflowInputOff-Target WorkflowInputLegendOff-Target WorkflowInputLegendBAMValidate InputsCalculate Per-Base Read DepthConvert BED to interval.listConvert to BEDCalculate Coverage Metrics.target-depth-per-base.bed.HSMetrics.txttarget-depth-per-base.bedHSMetrics.txtTarget FileBait FileValidate InputsCacluate Read Depth at dbSNP SitesFilter for Minimum Read DepthFilter for Off-Target SitesConvert to BEDAdd Slop to Off-Target SNPsMerge with Target FileAdd Slop to Target Intervals.target-with-enriched-off-target-intervals.bed.off-target-dbSNP_depth-per-base.bedrecalibrate-BAMTarget FiledbSNP VCFBAMInput FileQuality Control FileOutput FileProcess StepValidate InputsCacluate Read Depth at dbSNP SitesFilter for Minimum Read DepthFilter for Off-Target SitesConvert to BEDAdd Slop to Off-Target SNPsMerge with Target FileAdd Slop to Target Intervalstarget-with-enriched-off-target-intervals.bedoff-target-dbSNP-depth-per-base.bedrecalibrate-BAMTarget FiledbSNP VCFBAMInput FileQuality Control FileOutput FileProcess StepTarget-Focused WorkflowInputOff-Target WorkflowInputLegendOff-Target WorkflowInputLegendBAMValidate InputsCalculate Per-Base Read DepthConvert BED to interval.listConvert to BEDCalculate Coverage Metricstarget-depth-per-base.bedHSMetrics.txt*target-depth-per-base.bed*HSMetrics.txtTarget FileBait FileValidate InputsCacluate Read Depth at dbSNP SitesFilter for Minimum Read DepthFilter for Off-Target SitesConvert to BEDAdd Slop to Off-Target SNPsMerge with Target FileAdd Slop to Target Intervalstarget-with-enriched-off-target-intervals.bedoff-target-dbSNP-depth-per-base.bedrecalibrate-BAMTarget FiledbSNP VCFBAMInput FileQuality Control FileOutput FileProcess StepValidate InputsCacluate Read Depth at dbSNP SitesFilter for Minimum Read DepthFilter for Off-Target SitesConvert to BEDAdd Slop to Off-Target SNPsMerge with Target FileAdd Slop to Target Intervals*target-with-enriched-off-target-intervals.bed*off-target-dbSNP-depth-per-base.bedrecalibrate-BAMTarget FiledbSNP VCFBAMInput FileQuality Control FileOutput FileProcess Step