nf-cmgg · nvnieuwk · Jun 25, 2025 · Jun 24, 2025 · Jun 24, 2025 · Jun 24, 2025
diff --git a/CHANGELOG.md b/CHANGELOG.md
@@ -3,6 +3,13 @@
 The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/)
 and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
 
+## v1.11.0dev
+
+## New features
+
+1. Added a new option to the samplesheet (`msi`). This option takes a boolean to indicate whether or not the MSI status of the sample should be checked. A baseline should be provided using the `--msi_baseline` parameter to run MSI calling.
+2. The Multiqc module now generates branded reports.
+
 ## v1.10.1 - Mighty Mechelen - [May 26 2025]
 
 ## Fixes

diff --git a/assets/multiqc_config.yml b/assets/multiqc_config.yml
@@ -17,6 +17,12 @@ extra_fn_clean_exts:
   - type: regex_keep
     pattern: "^[^\\.]*"
     module: bcftools
+  - type: regex
+    pattern: "_summary_msi$"
+  - type: regex
+    pattern: "_all_msi$"
+
+template: "cmgg"
 
 mosdepth_config:
   general_stats_coverage:

diff --git a/conf/test.config b/conf/test.config
@@ -38,6 +38,7 @@ params {
     sdf             = "https://github.com/nf-cmgg/test-datasets/raw/smallvariants/data/genomics/homo_sapiens/genome/hg38_chr21_22000000_23000000_sdf.tar.gz"
     strtablefile    = "https://github.com/nf-cmgg/test-datasets/raw/smallvariants/data/genomics/homo_sapiens/genome/hg38_chr21_22000000_23000000.strtable.zip"
     ped             = "https://github.com/nf-cmgg/test-datasets/raw/smallvariants/data/genomics/homo_sapiens/genome/test_dots.ped"
+    msi_baseline    = "https://github.com/nf-cmgg/test-datasets/raw/smallvariants/data/genomics/homo_sapiens/genome/msi_subset.baseline.list"
 
     // Pipeline specific parameters
     filter             = true

diff --git a/docs/parameters.md b/docs/parameters.md
@@ -34,6 +34,7 @@ Reference genome related files and options required for the workflow.
 | `genomes_ignore`   | Do not load the local references from the path specified with `--genomes_base`                                                                                                                                                                                                    | `boolean` |              |          | True   |
 | `igenomes_base`    | Directory / URL base for iGenomes references.                                                                                                                                                                                                                                     | `string`  |              |          | True   |
 | `igenomes_ignore`  | Do not load the iGenomes reference config. <details><summary>Help</summary><small>Do not load `igenomes.config` when running the pipeline. You may choose this option if you observe clashes between custom parameters and those supplied in `igenomes.config`.</small></details> | `boolean` |              |          | True   |
+| `msi_baseline`     | Path to the MSI baseline VCF file.                                                                                                                                                                                                                                                | `string`  |              |          |        |
 
 ## Pipeline specific parameters
 

diff --git a/docs/usage.md b/docs/usage.md
@@ -101,6 +101,7 @@ The samplesheet can have following columns:
 | `truth_bed`      | OPTIONAL - Full path to the BED file containing the golden truth regions in the `truth_vcf` file. File has to have the extensions `.bed`                                                                                                                                                                                                                              |
 | `roi`            | OPTIONAL - Full path to a BED file containing the regions of interest for the current sample to call on. When this file is given, the pipeline will run this sample in WES mode. (The flag `--roi <path>` can also be given to run WES mode for all samples using the file specified by the flag) File has to have the extension `.bed` or `.bed.gz`.                 |
 | `vardict_min_af` | OPTIONAL - The minimum AF value to use for the vardict variant caller (`--callers vardict`). This can be set in the samplesheet when it differs for all samples. A default can be set using the `--vardict_min_af` parameter (whichs defaults to 0.1)                                                                                                                 |
+| `msi`            | OPTIONAL - Set this to `true` when MSI calling should be performed on this sample. MSI calling is only done when a CRAM file is supplied and a baseline file has been provided via the `--msi_baseline` parameter. (By default this option is `false`)                                                                                                                |
 
 <!-- prettier-ignore -->
 !!!note

diff --git a/main.nf b/main.nf
@@ -213,6 +213,7 @@ workflow {
     merged_crams        = SMALLVARIANTS.out.merged_crams
     mosdepth_reports    = SMALLVARIANTS.out.mosdepth_reports
     gvcfs               = SMALLVARIANTS.out.gvcfs.filter { _meta, gvcf, _tbi -> gvcf.startsWith(workflow.workDir) } // Filtering out input GVCFs from the output publishing fixes an issue in the current implementation of the workflow output definitions: https://github.com/nextflow-io/nextflow/issues/5480
+    msi                 = SMALLVARIANTS.out.msi
     single_beds         = SMALLVARIANTS.out.single_beds
     perbase_beds        = SMALLVARIANTS.out.perbase_beds
     validation          = SMALLVARIANTS.out.validation
@@ -244,6 +245,9 @@ output {
         gvcf >> "${meta.family}/${meta.id}_${params.unique_out}/${meta.id}.${meta.caller}.g.vcf.gz"
         tbi >> "${meta.family}/${meta.id}_${params.unique_out}/${meta.id}.${meta.caller}.g.vcf.gz.tbi"
     } }
+    msi { path { meta, msi ->
+        msi >> "${meta.family}/${meta.id}_${params.unique_out}/msi/${msi.name}"
+    } }
     single_beds { path { meta, bed ->
         bed >> "${meta.family}/${meta.id}_${params.unique_out}/${meta.id}.bed"
     } }

diff --git a/nextflow.config b/nextflow.config
@@ -43,7 +43,7 @@ params {
     merge_distance             = 100000
     updio_common_cnvs          = null
     disable_hc_dict_validation = false
-    msi_baseline               = "https://github.com/nf-cmgg/test-datasets/raw/refs/heads/smallvariants/data/genomics/homo_sapiens/genome/msi_subset.baseline.list"
+    msi_baseline               = null
 
     // VEP plugins to use
     vep_dbnsfp                 = false

diff --git a/nextflow_schema.json b/nextflow_schema.json
@@ -160,6 +160,13 @@
                     "fa_icon": "fas fa-ban",
                     "hidden": true,
                     "help_text": "Do not load `igenomes.config` when running the pipeline. You may choose this option if you observe clashes between custom parameters and those supplied in `igenomes.config`."
+                },
+                "msi_baseline": {
+                    "type": "string",
+                    "format": "file-path",
+                    "exists": true,
+                    "pattern": "^\\S+\\.list$",
+                    "description": "Path to the MSI baseline VCF file."
                 }
             },
             "required": ["fasta"]
@@ -696,11 +703,5 @@
         {
             "$ref": "#/$defs/annotation_parameters"
         }
-    ],
-    "properties": {
-        "msi_baseline": {
-            "type": "string",
-            "default": "https://github.com/nf-cmgg/test-datasets/raw/refs/heads/smallvariants/data/genomics/homo_sapiens/genome/msi_subset.baseline.list"
-        }
-    }
+    ]
 }
diff --git a/tests/inputs/samplesheet.csv b/tests/inputs/samplesheet.csv
@@ -1,4 +1,4 @@
-sample,family,cram,crai,roi,ped,truth_vcf,truth_tbi,truth_bed,vardict_min_af
-NA24143,Ashkenazim,https://github.com/nf-cmgg/test-datasets/raw/smallvariants/data/genomics/homo_sapiens/illumina/crams/NA24143.cram,,,https://github.com/nf-cmgg/test-datasets/raw/smallvariants/data/genomics/homo_sapiens/genome/test.ped,https://github.com/nf-cmgg/test-datasets/raw/smallvariants/data/genomics/homo_sapiens/illumina/vcfs/NA24143.vcf.gz,https://github.com/nf-cmgg/test-datasets/raw/smallvariants/data/genomics/homo_sapiens/illumina/vcfs/NA24143.vcf.gz.tbi,https://github.com/nf-cmgg/test-datasets/raw/smallvariants/data/genomics/homo_sapiens/illumina/regions/roi.bed,0.01
-NA24149,Ashkenazim,https://github.com/nf-cmgg/test-datasets/raw/smallvariants/data/genomics/homo_sapiens/illumina/crams/NA24149.cram,https://github.com/nf-cmgg/test-datasets/raw/smallvariants/data/genomics/homo_sapiens/illumina/crams/NA24149.cram.crai,https://github.com/nf-cmgg/test-datasets/raw/smallvariants/data/genomics/homo_sapiens/illumina/regions/roi.bed,,https://github.com/nf-cmgg/test-datasets/raw/smallvariants/data/genomics/homo_sapiens/illumina/vcfs/NA24149.vcf.gz,,,
+sample,family,cram,crai,roi,ped,truth_vcf,truth_tbi,truth_bed,vardict_min_af,msi
+NA24143,Ashkenazim,https://github.com/nf-cmgg/test-datasets/raw/smallvariants/data/genomics/homo_sapiens/illumina/crams/NA24143.cram,,,https://github.com/nf-cmgg/test-datasets/raw/smallvariants/data/genomics/homo_sapiens/genome/test.ped,https://github.com/nf-cmgg/test-datasets/raw/smallvariants/data/genomics/homo_sapiens/illumina/vcfs/NA24143.vcf.gz,https://github.com/nf-cmgg/test-datasets/raw/smallvariants/data/genomics/homo_sapiens/illumina/vcfs/NA24143.vcf.gz.tbi,https://github.com/nf-cmgg/test-datasets/raw/smallvariants/data/genomics/homo_sapiens/illumina/regions/roi.bed,0.01,true
+NA24149,Ashkenazim,https://github.com/nf-cmgg/test-datasets/raw/smallvariants/data/genomics/homo_sapiens/illumina/crams/NA24149.cram,https://github.com/nf-cmgg/test-datasets/raw/smallvariants/data/genomics/homo_sapiens/illumina/crams/NA24149.cram.crai,https://github.com/nf-cmgg/test-datasets/raw/smallvariants/data/genomics/homo_sapiens/illumina/regions/roi.bed,,https://github.com/nf-cmgg/test-datasets/raw/smallvariants/data/genomics/homo_sapiens/illumina/vcfs/NA24149.vcf.gz,,,,true
 NA24385,Ashkenazim,https://github.com/nf-cmgg/test-datasets/raw/smallvariants/data/genomics/homo_sapiens/illumina/crams/NA24385.cram,https://github.com/nf-cmgg/test-datasets/raw/smallvariants/data/genomics/homo_sapiens/illumina/crams/NA24385.cram.crai,https://github.com/nf-cmgg/test-datasets/raw/smallvariants/data/genomics/homo_sapiens/illumina/regions/roi.bed,,https://github.com/nf-cmgg/test-datasets/raw/smallvariants/data/genomics/homo_sapiens/illumina/vcfs/NA24385.vcf.gz,,,
diff --git a/tests/nextflow.config b/tests/nextflow.config
@@ -17,6 +17,7 @@ params {
     sdf             = "https://github.com/nf-cmgg/test-datasets/raw/smallvariants/data/genomics/homo_sapiens/genome/hg38_chr21_22000000_23000000_sdf.tar.gz"
     strtablefile    = "https://github.com/nf-cmgg/test-datasets/raw/smallvariants/data/genomics/homo_sapiens/genome/hg38_chr21_22000000_23000000.strtable.zip"
     vep_cache       = null
+    msi_baseline    = "https://github.com/nf-cmgg/test-datasets/raw/smallvariants/data/genomics/homo_sapiens/genome/msi_subset.baseline.list"
 
     vcfanno_config    = "${baseDir}/assets/vcfanno.toml"
     vcfanno_resources = "https://github.com/brentp/vcfanno/raw/master/example/exac.vcf.gz;https://github.com/brentp/vcfanno/raw/master/example/exac.vcf.gz.tbi"

diff --git a/tests/pipeline/callers/main.nf.test.snap b/tests/pipeline/callers/main.nf.test.snap
@@ -11,6 +11,10 @@
                 "Ashkenazim/NA24143_<version>_<date>/mosdepth/NA24143.global.dist.txt",
                 "Ashkenazim/NA24143_<version>_<date>/mosdepth/NA24143.region.dist.txt",
                 "Ashkenazim/NA24143_<version>_<date>/mosdepth/NA24143.summary.txt",
+                "Ashkenazim/NA24143_<version>_<date>/msi/NA24143_all_msi",
+                "Ashkenazim/NA24143_<version>_<date>/msi/NA24143_dis_msi",
+                "Ashkenazim/NA24143_<version>_<date>/msi/NA24143_summary_msi",
+                "Ashkenazim/NA24143_<version>_<date>/msi/NA24143_unstable_msi",
                 "Ashkenazim/NA24149_<version>_<date>/NA24149.bed",
                 "Ashkenazim/NA24149_<version>_<date>/NA24149.haplotypecaller.bcftools_stats.txt",
                 "Ashkenazim/NA24149_<version>_<date>/NA24149.haplotypecaller.g.vcf.gz",
@@ -20,6 +24,10 @@
                 "Ashkenazim/NA24149_<version>_<date>/mosdepth/NA24149.global.dist.txt",
                 "Ashkenazim/NA24149_<version>_<date>/mosdepth/NA24149.region.dist.txt",
                 "Ashkenazim/NA24149_<version>_<date>/mosdepth/NA24149.summary.txt",
+                "Ashkenazim/NA24149_<version>_<date>/msi/NA24149_all_msi",
+                "Ashkenazim/NA24149_<version>_<date>/msi/NA24149_dis_msi",
+                "Ashkenazim/NA24149_<version>_<date>/msi/NA24149_summary_msi",
+                "Ashkenazim/NA24149_<version>_<date>/msi/NA24149_unstable_msi",
                 "Ashkenazim/NA24385_<version>_<date>/NA24385.bed",
                 "Ashkenazim/NA24385_<version>_<date>/NA24385.haplotypecaller.bcftools_stats.txt",
                 "Ashkenazim/NA24385_<version>_<date>/NA24385.haplotypecaller.g.vcf.gz",
@@ -43,7 +51,7 @@
             "nf-test": "0.9.2",
             "nextflow": "25.04.2"
         },
-        "timestamp": "2025-05-21T11:40:04.509699536"
+        "timestamp": "2025-06-24T16:19:39.591022899"
     },
     "pipeline_callers - vardict + haplotypecaller": {
         "content": [
@@ -57,6 +65,10 @@
                 "Ashkenazim/NA24143_<version>_<date>/mosdepth/NA24143.global.dist.txt",
                 "Ashkenazim/NA24143_<version>_<date>/mosdepth/NA24143.region.dist.txt",
                 "Ashkenazim/NA24143_<version>_<date>/mosdepth/NA24143.summary.txt",
+                "Ashkenazim/NA24143_<version>_<date>/msi/NA24143_all_msi",
+                "Ashkenazim/NA24143_<version>_<date>/msi/NA24143_dis_msi",
+                "Ashkenazim/NA24143_<version>_<date>/msi/NA24143_summary_msi",
+                "Ashkenazim/NA24143_<version>_<date>/msi/NA24143_unstable_msi",
                 "Ashkenazim/NA24149_<version>_<date>/NA24149.bed",
                 "Ashkenazim/NA24149_<version>_<date>/NA24149.haplotypecaller.bcftools_stats.txt",
                 "Ashkenazim/NA24149_<version>_<date>/NA24149.haplotypecaller.g.vcf.gz",
@@ -66,6 +78,10 @@
                 "Ashkenazim/NA24149_<version>_<date>/mosdepth/NA24149.global.dist.txt",
                 "Ashkenazim/NA24149_<version>_<date>/mosdepth/NA24149.region.dist.txt",
                 "Ashkenazim/NA24149_<version>_<date>/mosdepth/NA24149.summary.txt",
+                "Ashkenazim/NA24149_<version>_<date>/msi/NA24149_all_msi",
+                "Ashkenazim/NA24149_<version>_<date>/msi/NA24149_dis_msi",
+                "Ashkenazim/NA24149_<version>_<date>/msi/NA24149_summary_msi",
+                "Ashkenazim/NA24149_<version>_<date>/msi/NA24149_unstable_msi",
                 "Ashkenazim/NA24385_<version>_<date>/NA24385.bed",
                 "Ashkenazim/NA24385_<version>_<date>/NA24385.haplotypecaller.bcftools_stats.txt",
                 "Ashkenazim/NA24385_<version>_<date>/NA24385.haplotypecaller.g.vcf.gz",
@@ -104,7 +120,7 @@
             "nf-test": "0.9.2",
             "nextflow": "25.04.2"
         },
-        "timestamp": "2025-05-21T11:43:29.234774728"
+        "timestamp": "2025-06-24T16:20:57.091816318"
     },
     "pipeline_callers - vardict": {
         "content": [
@@ -115,12 +131,20 @@
                 "Ashkenazim/NA24143_<version>_<date>/mosdepth/NA24143.global.dist.txt",
                 "Ashkenazim/NA24143_<version>_<date>/mosdepth/NA24143.region.dist.txt",
                 "Ashkenazim/NA24143_<version>_<date>/mosdepth/NA24143.summary.txt",
+                "Ashkenazim/NA24143_<version>_<date>/msi/NA24143_all_msi",
+                "Ashkenazim/NA24143_<version>_<date>/msi/NA24143_dis_msi",
+                "Ashkenazim/NA24143_<version>_<date>/msi/NA24143_summary_msi",
+                "Ashkenazim/NA24143_<version>_<date>/msi/NA24143_unstable_msi",
                 "Ashkenazim/NA24149_<version>_<date>/NA24149.bed",
                 "Ashkenazim/NA24149_<version>_<date>/NA24149.per-base.bed.gz",
                 "Ashkenazim/NA24149_<version>_<date>/NA24149.per-base.bed.gz.csi",
                 "Ashkenazim/NA24149_<version>_<date>/mosdepth/NA24149.global.dist.txt",
                 "Ashkenazim/NA24149_<version>_<date>/mosdepth/NA24149.region.dist.txt",
                 "Ashkenazim/NA24149_<version>_<date>/mosdepth/NA24149.summary.txt",
+                "Ashkenazim/NA24149_<version>_<date>/msi/NA24149_all_msi",
+                "Ashkenazim/NA24149_<version>_<date>/msi/NA24149_dis_msi",
+                "Ashkenazim/NA24149_<version>_<date>/msi/NA24149_summary_msi",
+                "Ashkenazim/NA24149_<version>_<date>/msi/NA24149_unstable_msi",
                 "Ashkenazim/NA24385_<version>_<date>/NA24385.bed",
                 "Ashkenazim/NA24385_<version>_<date>/NA24385.per-base.bed.gz",
                 "Ashkenazim/NA24385_<version>_<date>/NA24385.per-base.bed.gz.csi",
@@ -150,6 +174,6 @@
             "nf-test": "0.9.2",
             "nextflow": "25.04.2"
         },
-        "timestamp": "2025-05-21T11:37:36.502218888"
+        "timestamp": "2025-06-24T16:18:39.878841589"
     }
 }
diff --git a/tests/pipeline/default/main.nf.test.snap b/tests/pipeline/default/main.nf.test.snap
@@ -11,6 +11,10 @@
                 "Ashkenazim/NA24143_<version>_<date>/mosdepth/NA24143.global.dist.txt",
                 "Ashkenazim/NA24143_<version>_<date>/mosdepth/NA24143.region.dist.txt",
                 "Ashkenazim/NA24143_<version>_<date>/mosdepth/NA24143.summary.txt",
+                "Ashkenazim/NA24143_<version>_<date>/msi/NA24143_all_msi",
+                "Ashkenazim/NA24143_<version>_<date>/msi/NA24143_dis_msi",
+                "Ashkenazim/NA24143_<version>_<date>/msi/NA24143_summary_msi",
+                "Ashkenazim/NA24143_<version>_<date>/msi/NA24143_unstable_msi",
                 "Ashkenazim/NA24149_<version>_<date>/NA24149.bed",
                 "Ashkenazim/NA24149_<version>_<date>/NA24149.haplotypecaller.bcftools_stats.txt",
                 "Ashkenazim/NA24149_<version>_<date>/NA24149.haplotypecaller.g.vcf.gz",
@@ -20,6 +24,10 @@
                 "Ashkenazim/NA24149_<version>_<date>/mosdepth/NA24149.global.dist.txt",
                 "Ashkenazim/NA24149_<version>_<date>/mosdepth/NA24149.region.dist.txt",
                 "Ashkenazim/NA24149_<version>_<date>/mosdepth/NA24149.summary.txt",
+                "Ashkenazim/NA24149_<version>_<date>/msi/NA24149_all_msi",
+                "Ashkenazim/NA24149_<version>_<date>/msi/NA24149_dis_msi",
+                "Ashkenazim/NA24149_<version>_<date>/msi/NA24149_summary_msi",
+                "Ashkenazim/NA24149_<version>_<date>/msi/NA24149_unstable_msi",
                 "Ashkenazim/NA24385_<version>_<date>/NA24385.bed",
                 "Ashkenazim/NA24385_<version>_<date>/NA24385.haplotypecaller.bcftools_stats.txt",
                 "Ashkenazim/NA24385_<version>_<date>/NA24385.haplotypecaller.g.vcf.gz",
@@ -43,6 +51,6 @@
             "nf-test": "0.9.2",
             "nextflow": "25.04.2"
         },
-        "timestamp": "2025-05-21T11:46:02.23259705"
+        "timestamp": "2025-06-24T16:16:20.341360571"
     }
 }