update filenames

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

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 |

docs/calculate-targeted-coverage-flow.puml

@@ -25,9 +25,9 @@ rectangle "Target-Focused Workflow" {
     rectangle "Convert to BED" as ConvtoBED1 <<ProcessStep>>
     rectangle "Calculate Coverage Metrics" as CalcCovMetrics <<ProcessStep>>
     ' output files
-    rectangle ".target-depth-per-base.bed" as TargetReadDepthBED <<OutputFile>>
+    rectangle "~*target-depth-per-base.bed" as TargetReadDepthBED <<OutputFile>>
     ' QC files
-    rectangle ".HSMetrics.txt" as HSMetrics <<QCFile>>
+    rectangle "~*HSMetrics.txt" as HSMetrics <<QCFile>>
 }
 
 
@@ -50,8 +50,8 @@ rectangle "Off-Target Workflow" {
     rectangle "Add Slop to Target Intervals" as AddSlopTarget <<ProcessStep>>
 
     ' output files
-    rectangle ".target-with-enriched-off-target-intervals.bed" as TargetPlusOffTargetReadDepthBED <<OutputFile>>
-    rectangle ".off-target-dbSNP_depth-per-base.bed" as OffTargetReadDepth <<OutputFile>>
+    rectangle "~*target-with-enriched-off-target-intervals.bed" as TargetPlusOffTargetReadDepthBED <<OutputFile>>
+    rectangle "~*off-target-dbSNP-depth-per-base.bed" as OffTargetReadDepth <<OutputFile>>
 
     ' end node
     rectangle "recalibrate-BAM" as RecalBAM #White

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}
     """
 }

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.
@@ -28,14 +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}
         """
 }
 
@@ -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}
     """
 }

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}
     """
 }

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
 *
@@ -26,13 +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}
     """
 }

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}
     """
 }

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
 *
@@ -34,14 +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
     """
@@ -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
 
@@ -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} \

nftest.yml

@@ -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