From 6e4a9833d7a68ccb0772bd4e4e6a7ab5fa546041 Mon Sep 17 00:00:00 2001 From: Priyanka Date: Wed, 16 Sep 2026 12:04:21 +0530 Subject: [PATCH 1/5] Expose additional Kraken2 parameters and document omitted STAR/Qualimap parameters (#168) --- tools/kraken2.wdl | 12 ++++++++++++ tools/qualimap.wdl | 7 ++++++- tools/star.wdl | 10 ++++++++++ 3 files changed, 28 insertions(+), 1 deletion(-) diff --git a/tools/kraken2.wdl b/tools/kraken2.wdl index f2bfca345..b607e5910 100644 --- a/tools/kraken2.wdl +++ b/tools/kraken2.wdl @@ -358,6 +358,12 @@ task kraken { group: "Common", } min_base_quality: "Minimum base quality used in classification" + confidence: { + description: "Confidence score threshold. Classifications below this threshold are unclassified.", + external_help: "https://github.com/DerrickWood/kraken2/blob/master/docs/MANUAL.markdown#confidence-scoring", + } + minimum_hit_groups: "Minimum number of hit groups (overlapping k-mers sharing the same minimizer) needed to make a classification call" + quick: "Stop classification at the first hit instead of an exhaustive k-mer search? Faster but less accurate." ncpu: { description: "Number of cores to allocate for task", group: "Common", @@ -378,6 +384,9 @@ task kraken { Boolean use_names = true Boolean use_all_cores = false Int min_base_quality = 0 + Float confidence = 0.0 + Int minimum_hit_groups = 2 + Boolean quick = false Int ncpu = 4 Int modify_memory_gb = 0 Int modify_disk_size_gb = 0 @@ -415,6 +424,9 @@ task kraken { } \ --threads "$n_cores" \ --minimum-base-quality ~{min_base_quality} \ + --confidence ~{confidence} \ + --minimum-hit-groups ~{minimum_hit_groups} \ + ~{if quick then "--quick" else ""} \ --report "~{out_report}" \ --report-zero-counts \ ~{if use_names diff --git a/tools/qualimap.wdl b/tools/qualimap.wdl index 498bdc797..0eb5b08ae 100755 --- a/tools/qualimap.wdl +++ b/tools/qualimap.wdl @@ -4,7 +4,12 @@ version 1.1 task rnaseq { meta { description: "Generates runs QualiMap's rnaseq tool on the input BAM file." - help: "Note that we don't expose the `-p` parameter. This is used to set strandedness protocol of the sample, however in practice it only disables certain calculations. We do not expose the parameter so that the full suite of calculations is always performed." + omitted_parameters: [ + { + flag: "-p", + reason: "Used to set the strandedness protocol of the sample; in practice it only disables certain calculations. Omitted so that the full suite of calculations is always performed.", + }, + ] outputs: { raw_summary: "Raw text summary of QualiMap's results. Can be parsed by MultiQC.", raw_coverage: "Raw text of QualiMap's coverage analysis results. Can be parsed by MultiQC.", diff --git a/tools/star.wdl b/tools/star.wdl index e08c5d2ce..8184316e0 100755 --- a/tools/star.wdl +++ b/tools/star.wdl @@ -146,6 +146,16 @@ task build_star_db { task alignment { meta { description: "Runs the STAR aligner on a set of RNA-Seq FASTQ files" + omitted_parameters: [ + { + flag: "--outSAMtype", + reason: "STAR's default sort implementation is inefficient in the worst case and can blow up memory/time on some samples. Sorting is disabled here and handled by a dedicated downstream sorting task instead.", + }, + { + flag: "--outMultimapperOrder", + reason: "Hardcoded to `Random`. The alternative, `Old_2.4`, is a biased quasi-random order used before STAR 2.5.0 and is expected to be deprecated in future STAR releases.", + }, + ] external_help: "https://github.com/alexdobin/STAR/blob/2.7.11b/doc/STARmanual.pdf" outputs: { star_log: { From e322d0b257c1e47f106b78565d46b6f7a67d51dd Mon Sep 17 00:00:00 2001 From: Priyanka Date: Wed, 16 Sep 2026 17:43:07 +0530 Subject: [PATCH 2/5] Add CHANGELOG entry for #331 --- tools/CHANGELOG.md | 2 ++ 1 file changed, 2 insertions(+) diff --git a/tools/CHANGELOG.md b/tools/CHANGELOG.md index 156e5170e..f6468ff49 100644 --- a/tools/CHANGELOG.md +++ b/tools/CHANGELOG.md @@ -9,6 +9,8 @@ The format is based on [Keep a Changelog](http://keepachangelog.com/). ### Added - Added WDL implementation for Salmon (`index` and `quant` tasks) [#326](https://github.com/stjudecloud/workflows/pull/326) +- `kraken2.wdl` `kraken` task now exposes `confidence`, `minimum_hit_groups`, and `quick` parameters [#331](https://github.com/stjudecloud/workflows/pull/331) +- Documented previously unexposed/undocumented parameters in `star.wdl` (`outSAMtype`, `outMultimapperOrder`) and `qualimap.wdl` (`-p`) using a new `omitted_parameters` `meta` convention [#331](https://github.com/stjudecloud/workflows/pull/331) ## 2026 August From 10e8886d412449e2cef884b8e040ced3d13a24c4 Mon Sep 17 00:00:00 2001 From: Andrew Thrasher Date: Thu, 17 Sep 2026 11:11:08 -0400 Subject: [PATCH 3/5] chore: update spelling list --- cspell.json | 1 + 1 file changed, 1 insertion(+) diff --git a/cspell.json b/cspell.json index 9c85392d4..b59dbd602 100644 --- a/cspell.json +++ b/cspell.json @@ -171,6 +171,7 @@ "Nanopore", "PACBIO", "unpatterned", + "mers", // STAR / Picard / GATK option fragments "Ftag", "Ffile", From 6211c188a8b4a8a175e4e4065dc13aa70c035a6e Mon Sep 17 00:00:00 2001 From: Priyanka Date: Fri, 18 Sep 2026 11:41:02 +0530 Subject: [PATCH 4/5] Address review: document --memory-mapping omission, add long-form flag for qualimap -p --- tools/kraken2.wdl | 6 ++++++ tools/qualimap.wdl | 2 +- 2 files changed, 7 insertions(+), 1 deletion(-) diff --git a/tools/kraken2.wdl b/tools/kraken2.wdl index b9b1654af..18cf9345b 100644 --- a/tools/kraken2.wdl +++ b/tools/kraken2.wdl @@ -306,6 +306,12 @@ task build_db { task kraken { meta { description: "Runs Kraken2 on a pair of fastq files" + omitted_parameters: [ + { + flag: "--memory-mapping", + reason: "Would trade an unknown amount of RAM savings for slower runtime and potentially higher disk usage. WDL execution environments are rarely memory-constrained, and time is typically the more limited resource, so this tradeoff isn't worth the added complexity without further investigation.", + }, + ] outputs: { report: { description: "A Kraken2 summary report", diff --git a/tools/qualimap.wdl b/tools/qualimap.wdl index 62a6f6ac1..638ed77ae 100755 --- a/tools/qualimap.wdl +++ b/tools/qualimap.wdl @@ -6,7 +6,7 @@ task rnaseq { description: "Generates runs QualiMap's rnaseq tool on the input BAM file." omitted_parameters: [ { - flag: "-p", + flag: "-p, --sequencing-protocol", reason: "Used to set the strandedness protocol of the sample; in practice it only disables certain calculations. Omitted so that the full suite of calculations is always performed.", }, ] From bba86523fa7ae3f10f2c31fcf4bf18a6ae26f949 Mon Sep 17 00:00:00 2001 From: Ari Frantz Date: Fri, 18 Sep 2026 09:51:04 -0400 Subject: [PATCH 5/5] Update tools/kraken2.wdl --- tools/kraken2.wdl | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/kraken2.wdl b/tools/kraken2.wdl index 18cf9345b..9a1e77a64 100644 --- a/tools/kraken2.wdl +++ b/tools/kraken2.wdl @@ -309,7 +309,7 @@ task kraken { omitted_parameters: [ { flag: "--memory-mapping", - reason: "Would trade an unknown amount of RAM savings for slower runtime and potentially higher disk usage. WDL execution environments are rarely memory-constrained, and time is typically the more limited resource, so this tradeoff isn't worth the added complexity without further investigation.", + reason: "Enabling this would reduce RAM usage at the cost of a slower run time and higher disk usage. This trade is usually undesirable. Without further investigation to determine the generalized costs and benefits, this option will not be exposed.", }, ] outputs: {