replace dots with underscores

nf-cmgg · Nov 20, 2024 · ecf67ab · ecf67ab
1 parent deac9d5
commit ecf67ab
Show file tree

Hide file tree

Showing 6 changed files with 19 additions and 12 deletions.
diff --git a/CHANGELOG.md b/CHANGELOG.md
@@ -23,6 +23,7 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 1. Validation of all samples now use an intersect of the golden truth BED files with the BED file used to call the variants. This should fix the WES validation which was broken until this point.
 2. A couple of small fixes to the vardict flow.
 3. Only use the standard chromosomes for UPDio analysis.
+4. Dots in sample and family names are now converted to an underscore automatically.
 
 ## v1.8.2 - Outstanding Oostkamp - [September 30 2024]
 

diff --git a/assets/samplesheet.csv b/assets/samplesheet.csv
@@ -1,4 +1,4 @@
-sample,family,cram,crai,roi,ped,truth_vcf,truth_tbi,truth_bed,vardict_min_af
-NA24143,Proband_12345,https://github.com/nf-cmgg/test-datasets/raw/germline/data/genomics/homo_sapiens/illumina/crams/NA24143.cram,,,https://github.com/nf-cmgg/test-datasets/raw/germline/data/genomics/homo_sapiens/genome/test.ped,https://github.com/nf-cmgg/test-datasets/raw/germline/data/genomics/homo_sapiens/illumina/vcfs/NA24143.vcf.gz,https://github.com/nf-cmgg/test-datasets/raw/germline/data/genomics/homo_sapiens/illumina/vcfs/NA24143.vcf.gz.tbi,https://github.com/nf-cmgg/test-datasets/raw/germline/data/genomics/homo_sapiens/illumina/regions/roi.bed,0.01
-NA24149,Proband_12345,https://github.com/nf-cmgg/test-datasets/raw/germline/data/genomics/homo_sapiens/illumina/crams/NA24149.cram,https://github.com/nf-cmgg/test-datasets/raw/germline/data/genomics/homo_sapiens/illumina/crams/NA24149.cram.crai,https://github.com/nf-cmgg/test-datasets/raw/germline/data/genomics/homo_sapiens/illumina/regions/roi.bed,,https://github.com/nf-cmgg/test-datasets/raw/germline/data/genomics/homo_sapiens/illumina/vcfs/NA24149.vcf.gz,,,
-NA24385,Proband_12345,https://github.com/nf-cmgg/test-datasets/raw/germline/data/genomics/homo_sapiens/illumina/crams/NA24385.cram,https://github.com/nf-cmgg/test-datasets/raw/germline/data/genomics/homo_sapiens/illumina/crams/NA24385.cram.crai,https://github.com/nf-cmgg/test-datasets/raw/germline/data/genomics/homo_sapiens/illumina/regions/roi.bed,,https://github.com/nf-cmgg/test-datasets/raw/germline/data/genomics/homo_sapiens/illumina/vcfs/NA24385.vcf.gz,,,
+sample,family,cram,crai,roi,truth_vcf,truth_tbi,truth_bed,vardict_min_af
+NA24143,Proband_12.345,https://github.com/nf-cmgg/test-datasets/raw/germline/data/genomics/homo_sapiens/illumina/crams/NA24143.cram,,,https://github.com/nf-cmgg/test-datasets/raw/germline/data/genomics/homo_sapiens/illumina/vcfs/NA24143.vcf.gz,https://github.com/nf-cmgg/test-datasets/raw/germline/data/genomics/homo_sapiens/illumina/vcfs/NA24143.vcf.gz.tbi,https://github.com/nf-cmgg/test-datasets/raw/germline/data/genomics/homo_sapiens/illumina/regions/roi.bed,0.01
+NA24149,Proband_12.345,https://github.com/nf-cmgg/test-datasets/raw/germline/data/genomics/homo_sapiens/illumina/crams/NA24149.cram,https://github.com/nf-cmgg/test-datasets/raw/germline/data/genomics/homo_sapiens/illumina/crams/NA24149.cram.crai,https://github.com/nf-cmgg/test-datasets/raw/germline/data/genomics/homo_sapiens/illumina/regions/roi.bed,https://github.com/nf-cmgg/test-datasets/raw/germline/data/genomics/homo_sapiens/illumina/vcfs/NA24149.vcf.gz,,,
+NA24385,Proband_12.345,https://github.com/nf-cmgg/test-datasets/raw/germline/data/genomics/homo_sapiens/illumina/crams/NA24385.cram,https://github.com/nf-cmgg/test-datasets/raw/germline/data/genomics/homo_sapiens/illumina/crams/NA24385.cram.crai,https://github.com/nf-cmgg/test-datasets/raw/germline/data/genomics/homo_sapiens/illumina/regions/roi.bed,https://github.com/nf-cmgg/test-datasets/raw/germline/data/genomics/homo_sapiens/illumina/vcfs/NA24385.vcf.gz,,,
diff --git a/assets/schema_input.json b/assets/schema_input.json
@@ -9,15 +9,15 @@
         "properties": {
             "sample": {
                 "type": "string",
-                "pattern": "^[^\\. ]+$",
+                "pattern": "^[a-zA-Z0-9_\\.]+$",
                 "meta": ["id", "sample"],
-                "errorMessage": "Sample name should be a string that does not contain dots or spaces"
+                "errorMessage": "Sample name should be a string that may contain underscores (_) and dots (.)"
             },
             "family": {
                 "type": "string",
-                "pattern": "^[^\\. ]+$",
+                "pattern": "^[a-zA-Z0-9_\\.]+$",
                 "meta": ["family"],
-                "errorMessage": "Family name should be a string that does not contain dots or spaces"
+                "errorMessage": "Family name should be a string that may contain underscores (_) and dots (.)"
             },
             "cram": {
                 "oneOf": [

diff --git a/conf/test.config b/conf/test.config
@@ -37,6 +37,7 @@ params {
     elfasta         = "https://github.com/nf-cmgg/test-datasets/raw/germline/data/genomics/homo_sapiens/genome/hg38_chr21_22000000_23000000.elfasta"
     sdf             = "https://github.com/nf-cmgg/test-datasets/raw/germline/data/genomics/homo_sapiens/genome/hg38_chr21_22000000_23000000_sdf.tar.gz"
     strtablefile    = "https://github.com/nf-cmgg/test-datasets/raw/germline/data/genomics/homo_sapiens/genome/hg38_chr21_22000000_23000000.strtable.zip"
+    ped             = "https://github.com/nf-cmgg/test-datasets/raw/germline/data/genomics/homo_sapiens/genome/test_dots.ped"
 
     // Pipeline specific parameters
     filter             = true

diff --git a/lib/Pedigree.groovy b/lib/Pedigree.groovy
@@ -84,15 +84,15 @@ class PedigreeEntry {
         // Family ID
         id = lineSplit[0]
         if (id ==~ idRegex) {
-            familyId = id
+            familyId = id.replace(".", "_") // Replace dots with underscores to prevent breaking the multiqc report
         } else {
             exceptions.add("Invalid family ID (${id}). It should only contain these characters: a-z, A-Z, 0-9, _ and ." as String)
         }
 
         // Individual ID
         id = lineSplit[1]
         if (id ==~ idRegex) {
-            individualId = id
+            individualId = id.replace(".", "_") // Replace dots with underscores to prevent breaking the multiqc report
         } else {
             exceptions.add("Invalid individual ID (${id}). It should only contain these characters: a-z, A-Z, 0-9, _ and ." as String)
         }
@@ -102,15 +102,15 @@ class PedigreeEntry {
         // Paternal ID
         id = lineSplit[2]
         if (id ==~ idRegex) {
-            paternalId = id
+            paternalId = id.replace(".", "_") // Replace dots with underscores to prevent breaking the multiqc report
         } else if (!validMissingIDs.contains(id)) {
             exceptions.add("Invalid paternal ID (${id}). It should only contain these characters: a-z, A-Z, 0-9, _ and .; Use 0 if the paternal ID is missing" as String)
         }
 
         // Maternal ID
         id = lineSplit[3]
         if (id ==~ idRegex) {
-            maternalId = id
+            maternalId = id.replace(".", "_") // Replace dots with underscores to prevent breaking the multiqc report
         } else if (!validMissingIDs.contains(id)) {
             exceptions.add("Invalid maternal ID (${id}). It should only contain these characters: a-z, A-Z, 0-9, _ and .; Use 0 if the maternal ID is missing" as String)
         }

diff --git a/subworkflows/local/watchpath_handling/main.nf b/subworkflows/local/watchpath_handling/main.nf
@@ -37,6 +37,11 @@ workflow WATCHPATH_HANDLING {
     def samplesheet_list = samplesheetToList(input_samplesheet, samplesheet_schema)
         // Do some calculations and manipulations here
         .collect { row ->
+            // Replace dots with underscores in sample and family names to prevent breaking the multiqc report
+            row[0].id = row[0].id.replace(".", "_")
+            row[0].sample = row[0].sample.replace(".", "_")
+            row[0].family = row[0].family.replace(".", "_")
+
             // Watchpath logic
             def is_watch = false
             row = row.collect { input ->