Add support for uBAM and multisample test (genomic-medicine-sweden#51)

Add ubam support and multisample test

.github/workflows/ci.yml

@@ -23,6 +23,9 @@ jobs:
     runs-on: ubuntu-latest
     strategy:
       matrix:
+        parameters:
+          - ""
+          - "--input assets/samplesheet_multisample_bam.csv --split_fastq 250 --parallel_snv 1"
         NXF_VER:
           - "23.04.0"
           - "latest-everything"
@@ -43,4 +46,4 @@ jobs:
         # For example: adding multiple test runs with different parameters
         # Remember that you can parallelise this by using strategy.matrix
         run: |
-          nextflow run ${GITHUB_WORKSPACE} -profile test,docker --outdir ./results
+          nextflow run ${GITHUB_WORKSPACE} -profile test,docker --outdir ./results ${{ matrix.parameters }}

CHANGELOG.md

@@ -9,6 +9,7 @@ Initial release of genomic-medicine-sweden/skierfe, created with the [nf-core](h
 
 ### `Added`
 
+- Added uBAM support and multisample test [#51](https://github.com/genomic-medicine-sweden/skierfe/pull/51)
 - Added Revio BAM test data [#50](https://github.com/genomic-medicine-sweden/skierfe/pull/50)
 - Update template to 2.13.1 [#38](https://github.com/genomic-medicine-sweden/skierfe/pull/38)
 - Update pipeline to run with a small test dataset [#35](https://github.com/genomic-medicine-sweden/skierfe/pull/35)

assets/schema_input.json

@@ -16,8 +16,8 @@
             "file": {
                 "format": "file-path",
                 "type": "string",
-                "pattern": "^\\S+\\.f(ast)?q\\.gz$",
-                "errorMessage": "FastQ file must be provided, cannot contain spaces and must have extension '.fq.gz' or '.fastq.gz'"
+                "pattern": "^\\S+\\.(f(ast)?q\\.gz|bam)$",
+                "errorMessage": "FastQ or BAM file must be provided, cannot contain spaces and must have extension '.fq.gz', '.fastq.gz' or '.bam'"
             },
             "family_id": {
                 "type": "string",

conf/modules/bam_to_fastq.config

@@ -0,0 +1,35 @@
+/*
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+    Config file for defining DSL2 per module options and publishing paths
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+    Available keys to override module options:
+        ext.args   = Additional arguments appended to command in module.
+        ext.args2  = Second set of arguments appended to command in module (multi-tool modules).
+        ext.args3  = Third set of arguments appended to command in module (multi-tool modules).
+        ext.prefix = File name prefix for output files.
+----------------------------------------------------------------------------------------
+*/
+
+process {
+
+    /*
+    ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+    BAM TO FASTQ
+    ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+    */
+
+    withName: '.*:BAM_TO_FASTQ:.*' {
+        publishDir = [
+            enabled: false,
+        ]
+    }
+
+    withName: '.*:BAM_TO_FASTQ:SAMTOOLS_FASTQ' {
+
+        // Maybe should only allow unmapped data
+        // Unsure why SA tag is still there after reset
+        ext.args = '-x SA'   // samtools reset
+        ext.args2 = '-T \\*' // samtools fastq
+
+    }
+}

modules.json

@@ -102,6 +102,11 @@
                         "git_sha": "911696ea0b62df80e900ef244d7867d177971f73",
                         "installed_by": ["modules"]
                     },
+                    "samtools/fastq": {
+                        "branch": "master",
+                        "git_sha": "897c33d5da084b61109500ee44c01da2d3e4e773",
+                        "installed_by": ["modules"]
+                    },
                     "samtools/index": {
                         "branch": "master",
                         "git_sha": "911696ea0b62df80e900ef244d7867d177971f73",