Fix straglr issues, sync philres straglr changes, output straglr tsv …

…as intermediate (#589) * Update minimap 2.26 -> 2.27 * Updata minimap md5 * update minimap sha256 * make nanopore preset for minimap configurable * Output straglr tsv as intermediate for debugging/validation purposes * WIP: fix straglr issues * md5sum straglr * use molgenis straglr fork * update build.sh for new straglr repo * Fix straglr apptainer image * Next version of stragler fixes * Update md5sum * Fix md5sum for straglr * Update documentation for our own fork of straglr * Update workflow.md * Remove accidental commited file
molgenis · Apr 12, 2024 · 7b9cb56 · 7b9cb56
1 parent 28549c3
commit 7b9cb56
Show file tree

Hide file tree

Showing 8 changed files with 11 additions and 9 deletions.
diff --git a/config/nxf_call_str.config b/config/nxf_call_str.config
@@ -2,7 +2,7 @@ includeConfig 'nxf.config'
 
 env {
   CMD_EXPANSIONHUNTER = "apptainer exec --no-mount home --bind \${TMPDIR} ${APPTAINER_CACHEDIR}/expansionhunter-5.0.0.sif ExpansionHunter"
-  CMD_STRAGLR="apptainer exec --no-mount home --bind \${TMPDIR} ${APPTAINER_CACHEDIR}/straglr-philres-1.4.2.sif straglr-genotype"
+  CMD_STRAGLR="apptainer exec --no-mount home --bind \${TMPDIR} ${APPTAINER_CACHEDIR}/straglr-1.4.4_vip_v1.sif straglr-genotype"
 }
 
 params {

diff --git a/docs/usage/workflow.md b/docs/usage/workflow.md
@@ -22,7 +22,7 @@ The `cram` workflow consists of the following steps:
 2. Create validated, indexed `.bam` file from `bam/cram/sam` input
 3. Discover short tandem repeats and publish as intermediate result.
     1. Using [ExpansionHunter](https://github.com/Illumina/ExpansionHunter) for Illumina short read data.
-    2. Using this [fork of Straglr](https://github.com/philres/straglr) for PacBio and Nanopore long read data, this fork is chosen over the original [Straglr](https://github.com/bcgsc/straglr) because of the VCF output that enables VIP to combine it with the SV and SNV data in the VCF workflow.
+    2. Using this [fork of Straglr](https://github.com/molgenis/straglr) for PacBio and Nanopore long read data, this is a fork of this fork(https://github.com/philres/straglr) and is chosen over the original [Straglr](https://github.com/bcgsc/straglr) because of the VCF output that enables VIP to combine it with the SV and SNV data in the VCF workflow.
 4. Parallelize cram in chunks consisting of one or more contigs and for each chunk
     1. Perform short variant calling with [DeepVariant](https://github.com/google/deepvariant) producing a `gvcf` file per chunk per sample, the gvcfs of the samples in a project are than merged to one vcf per project (using [GLnexus](https://github.com/dnanexus-rnd/GLnexus).
     2. Perform structural variant calling with [Manta](https://github.com/Illumina/manta) or [cuteSV](https://github.com/tjiangHIT/cuteSV) producing a `vcf` file per chunk per project.
@@ -58,4 +58,4 @@ The `vcf` workflow consists of the following steps:
 5. If `cram` data is available slice the `cram` files to only keep relevant reads
 6. Create report
 
-For details, see [here](https://github.com/molgenis/vip/blob/main/vip_vcf.nf).
+For details, see [here](https://github.com/molgenis/vip/blob/main/vip_vcf.nf).
diff --git a/install.sh b/install.sh
@@ -82,7 +82,7 @@ download_files() {
   urls+=("7486bd5de526d9888df8eea2d8bdea48" "images/minimap2-2.27.sif")
   urls+=("06ac8a76a307fa42fffd80ab906fd24b" "images/picard-3.1.1.sif")
   urls+=("9a4b685b26744113d3ea0a3904c02706" "images/samtools-1.17-patch1.sif")
-  urls+=("2c18fcda2660792a7c8ba390463ae7ac" "images/straglr-philres-1.4.2.sif")
+  urls+=("d16851058e57ca08417f212b129841ca" "images/straglr-1.4.4_vip_v1.sif")
   urls+=("bcc157242cd9b09c66f015c52ef2d61d" "images/stranger-0.8.1.sif")
   urls+=("4fbbd8642ead7754cb8cc19740e18175" "images/vcf-decision-tree-4.0.0.sif")
   urls+=("9c4d7b48138f29651cdd45eb8d0cc4b6" "images/vcf-inheritance-matcher-3.1.0.sif")

diff --git a/modules/cram/straglr.nf b/modules/cram/straglr.nf
@@ -6,7 +6,7 @@ process straglr_call {
   input:
     tuple val(meta), path(cram), path(cramCrai)
   output:
-    tuple val(meta), path(vcfOut), path(vcfOutIndex), path(vcfOutStats)
+    tuple val(meta), path(tsvOut), path(vcfOut), path(vcfOutIndex), path(vcfOutStats)
   shell:
     paramReference = params[meta.project.assembly].reference.fasta
     paramReferenceFai = params[meta.project.assembly].reference.fastaFai
@@ -17,6 +17,7 @@ process straglr_call {
     sampleSex = meta.sample.sex
 
     vcfOut = "${meta.project.id}_${meta.sample.family_id}_${meta.sample.individual_id}_str.vcf.gz"
+    tsvOut = "${meta.project.id}_${meta.sample.family_id}_${meta.sample.individual_id}_str.tsv"
     vcfOutIndex = "${vcfOut}.csi"
     vcfOutStats = "${vcfOut}.stats"
 

diff --git a/modules/cram/templates/straglr_call.sh b/modules/cram/templates/straglr_call.sh
@@ -6,6 +6,7 @@ call_short_tandem_repeats () {
     args+=("--loci" "!{paramLoci}")
     args+=("--sample" "!{sampleId}")
     args+=("--vcf" "straglr.vcf")
+    args+=("--tsv" "!{tsvOut}")
     if [ -z "!{sampleSex}" ]; then
         args+=("--sex" "!{sampleSex}")
     fi

diff --git a/subworkflows/call_str.nf b/subworkflows/call_str.nf
@@ -48,7 +48,7 @@ workflow str {
     ch_str_by_platform.straglr
       | map { meta -> [meta, meta.sample.cram.data, meta.sample.cram.index] }
       | straglr_call
-      | map { meta, vcf, vcfIndex, vcfStats -> [meta, [data: vcf, index: vcfIndex, stats: vcfStats]] }
+      | map { meta, tsv, vcf, vcfIndex, vcfStats -> [meta, [data: vcf, index: vcfIndex, stats: vcfStats]] }
       | set { ch_str_straglr }
 
     // group by project

diff --git a/utils/apptainer/build.sh b/utils/apptainer/build.sh
@@ -93,7 +93,7 @@ main() {
   images+=("picard-3.1.1")
   images+=("samtools-1.17-patch1")
   images+=("stranger-0.8.1")
-  images+=("straglr-philres-1.4.2")
+  images+=("straglr-1.4.4_vip_v1")
   images+=("vcf-decision-tree-4.0.0")
   images+=("vcf-inheritance-matcher-3.1.0")
   images+=("vcf-report-6.0.1")

diff --git a/...s/apptainer/def/straglr-philres-1.4.2.def → utils/apptainer/def/straglr-1.4.4_vip_v1.def b/...s/apptainer/def/straglr-philres-1.4.2.def → utils/apptainer/def/straglr-1.4.4_vip_v1.def
@@ -11,8 +11,8 @@ From: sif/build/ubuntu-22.04.sif
     curl -Ls -o /opt/trf/trf "https://github.com/Benson-Genomics-Lab/TRF/releases/download/v4.09.1/trf409.linux64"
     chmod +x /opt/trf/trf
 
-    # ce7d96cad4630d6a73114657e082f2402b1b1213 = v1.4.2
-    pip install git+https://github.com/philres/straglr.git@ce7d96cad4630d6a73114657e082f2402b1b1213#egg=straglr
+    #b894775d2917c4c36b29c256e7db977a12f56e57 == v1.4.4_vip_v1
+    pip install git+https://github.com/molgenis/straglr.git@b894775d2917c4c36b29c256e7db977a12f56e57#egg=straglr
 
     # cleanup
     pip cache purge