feat(nf-validation): Use fromSamplesheet

Borrowed code from rnaseq, had to fix the group pulling for whatever reason Removes old check_samplesheet code as well.
nf-core · Aug 23, 2023 · 40f572d · 40f572d
1 parent 1b86d34
commit 40f572d
Show file tree

Hide file tree

Showing 7 changed files with 56 additions and 350 deletions.
diff --git a/assets/schema_input.json b/assets/schema_input.json
@@ -10,22 +10,26 @@
             "sample": {
                 "type": "string",
                 "pattern": "^\\S+$",
-                "errorMessage": "Sample name must be provided and cannot contain spaces"
+                "errorMessage": "Sample name must be provided and cannot contain spaces",
+                "meta": ["id"]
             },
             "fastq_1": {
                 "type": "string",
+                "format": "file-path",
+                "exists": true,
                 "pattern": "^\\S+\\.f(ast)?q\\.gz$",
                 "errorMessage": "FastQ file for reads 1 must be provided, cannot contain spaces and must have extension '.fq.gz' or '.fastq.gz'"
             },
             "fastq_2": {
                 "errorMessage": "FastQ file for reads 2 cannot contain spaces and must have extension '.fq.gz' or '.fastq.gz'",
+                "type": "string",
+                "format": "file-path",
+                "exists": true,
                 "anyOf": [
                     {
-                        "type": "string",
                         "pattern": "^\\S+\\.f(ast)?q\\.gz$"
                     },
                     {
-                        "type": "string",
                         "maxLength": 0
                     }
                 ]

diff --git a/bin/check_samplesheet.py b/bin/check_samplesheet.py
diff --git a/lib/WorkflowNascent.groovy b/lib/WorkflowNascent.groovy
@@ -20,6 +20,27 @@ class WorkflowNascent {
         }
     }
 
+    //
+    // Function to validate channels from input samplesheet
+    //
+    public static ArrayList validateInput(input) {
+        def (metas, fastqs) = input[1..2]
+
+        // Check that multiple runs of the same sample are of the same strandedness
+        def strandedness_ok = metas.collect{ it.strandedness }.unique().size == 1
+        if (!strandedness_ok) {
+            Nextflow.error("Please check input samplesheet -> Multiple runs of a sample must have the same strandedness!: ${metas[0].id}")
+        }
+
+        // Check that multiple runs of the same sample are of the same datatype i.e. single-end / paired-end
+        def endedness_ok = metas.collect{ it.single_end }.unique().size == 1
+        if (!endedness_ok) {
+            Nextflow.error("Please check input samplesheet -> Multiple runs of a sample must be of the same datatype i.e. single-end or paired-end: ${metas[0].id}")
+        }
+
+        return [ metas[0], fastqs ]
+    }
+
     //
     // Get workflow summary for MultiQC
     //

diff --git a/modules/local/samplesheet_check.nf b/modules/local/samplesheet_check.nf
diff --git a/nextflow_schema.json b/nextflow_schema.json
@@ -17,6 +17,7 @@
                     "format": "file-path",
                     "exists": true,
                     "mimetype": "text/csv",
+                    "schema": "assets/schema_input.json",
                     "pattern": "^\\S+\\.csv$",
                     "description": "Path to comma-separated file containing information about the samples in the experiment.",
                     "help_text": "You will need to create a design file with information about the samples in your experiment before running the pipeline. Use this parameter to specify its location. It has to be a comma-separated file with 3 columns, and a header row. See [usage docs](https://nf-co.re/nascent/usage#samplesheet-input).",