Merge pull request #2 from mahesh-panchal/input_workflow

Input workflow

Author: alneberg

assets/samplesheet.csv

@@ -1,3 +1,3 @@
-sample,fastq_1,fastq_2
-SAMPLE_PAIRED_END,/path/to/fastq/files/AEG588A1_S1_L002_R1_001.fastq.gz,/path/to/fastq/files/AEG588A1_S1_L002_R2_001.fastq.gz
-SAMPLE_SINGLE_END,/path/to/fastq/files/AEG588A4_S4_L003_R1_001.fastq.gz,
+sample,lane,project,fastq_1,fastq_2,rundir
+SAMPLE_PAIRED_END,1,P001,/path/to/fastq/files/AEG588A1_S1_L002_R1_001.fastq.gz,/path/to/fastq/files/AEG588A1_S1_L002_R2_001.fastq.gz,/path/to/rundir
+SAMPLE_SINGLE_END,2,P002,/path/to/fastq/files/AEG588A4_S4_L003_R1_001.fastq.gz,,/path/to/rundir

assets/schema_input.json

@@ -11,7 +11,19 @@
                 "type": "string",
                 "pattern": "^\\S+$",
                 "errorMessage": "Sample name must be provided and cannot contain spaces",
-                "meta": ["id"]
+                "meta": ["sample"]
+            },
+            "lane": {
+                "type": "integer",
+                "pattern": "^\\d+$",
+                "errorMessage": "Lane ID must be a number",
+                "meta": ["lane"]
+            },
+            "project": {
+                "type": "string",
+                "pattern": "^\\S+$",
+                "errorMessage": "Project ID cannot contain spaces",
+                "meta": ["project"]
             },
             "fastq_1": {
                 "type": "string",
@@ -26,8 +38,18 @@
                 "exists": true,
                 "pattern": "^\\S+\\.f(ast)?q\\.gz$",
                 "errorMessage": "FastQ file for reads 2 cannot contain spaces and must have extension '.fq.gz' or '.fastq.gz'"
+            },
+            "rundir": {
+                "type": "string",
+                "format": "path",
+                "exists": true,
+                "errorMessage": "Run directory must be a path",
+                "meta": ["rundir"]
             }
         },
-        "required": ["sample", "fastq_1"]
+        "required": ["sample", "lane", "fastq_1"],
+        "dependentRequired": {
+            "fastq_2": ["fastq_1"]
+        }
     }
 }

conf/test.config

@@ -22,7 +22,7 @@ params {
     // Input data
     // TODO nf-core: Specify the paths to your test data on nf-core/test-datasets
     // TODO nf-core: Give any required params for the test so that command line flags are not needed
-    input  = 'https://raw.githubusercontent.com/nf-core/test-datasets/viralrecon/samplesheet/samplesheet_test_illumina_amplicon.csv'
+    input  = 'https://raw.githubusercontent.com/KarNair/test-datasets/seqinspector/testdata/MiSeq/samplesheet.csv'
 
     // Genome references
     genome = 'R64-1-1'

main.nf

@@ -17,7 +17,7 @@ nextflow.enable.dsl = 2
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
 */
 
-include { SEQINSPECTOR  } from './workflows/seqinspector'
+include { SEQINSPECTOR            } from './workflows/seqinspector'
 include { PIPELINE_INITIALISATION } from './subworkflows/local/utils_nfcore_seqinspector_pipeline'
 include { PIPELINE_COMPLETION     } from './subworkflows/local/utils_nfcore_seqinspector_pipeline'
 
@@ -32,7 +32,7 @@ include { getGenomeAttribute      } from './subworkflows/local/utils_nfcore_seqi
 // TODO nf-core: Remove this line if you don't need a FASTA file
 //   This is an example of how to use getGenomeAttribute() to fetch parameters
 //   from igenomes.config using `--genome`
-params.fasta = getGenomeAttribute('fasta')
+// params.fasta = getGenomeAttribute('fasta')
 
 /*
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~

subworkflows/local/utils_nfcore_seqinspector_pipeline/main.nf

@@ -57,7 +57,7 @@ workflow PIPELINE_INITIALISATION {
     pre_help_text = nfCoreLogo(monochrome_logs)
     post_help_text = '\n' + workflowCitation() + '\n' + dashedLine(monochrome_logs)
     def String workflow_command = "nextflow run ${workflow.manifest.name} -profile <docker/singularity/.../institute> --input samplesheet.csv --outdir <OUTDIR>"
-    UTILS_NFVALIDATION_PLUGIN (
+    UTILS_NFVALIDATION_PLUGIN ( // Validates parameters against $projectDir/nextflow_schema.json
         help,
         workflow_command,
         pre_help_text,
@@ -75,29 +75,33 @@ workflow PIPELINE_INITIALISATION {
     //
     // Custom validation for pipeline parameters
     //
-    validateInputParameters()
+    validateInputParameters() // Runs additional validation that is not done by $projectDir/nextflow_schema.json
 
     //
     // Create channel from input file provided through params.input
     //
     Channel
-        .fromSamplesheet("input")
+        .fromSamplesheet("input") // Validates samplesheet against $projectDir/assets/schema_input.json. Path to validation schema is defined by $projectDir/nextflow_schema.json
         .map {
             meta, fastq_1, fastq_2 ->
+                def id_string = "${meta.sample}_${meta.project ?: "ungrouped"}_${meta.lane}"
+                def updated_meta = meta + [ id: id_string ]
                 if (!fastq_2) {
-                    return [ meta.id, meta + [ single_end:true ], [ fastq_1 ] ]
+                    return [ updated_meta.id, updated_meta + [ single_end:true ], [ fastq_1 ] ]
                 } else {
-                    return [ meta.id, meta + [ single_end:false ], [ fastq_1, fastq_2 ] ]
+                    return [ updated_meta.id, updated_meta + [ single_end:false ], [ fastq_1, fastq_2 ] ]
                 }
         }
         .groupTuple()
         .map {
-            validateInputSamplesheet(it)
-        }
-        .map {
-            meta, fastqs ->
-                return [ meta, fastqs.flatten() ]
+            validateInputSamplesheet(it) // Applies additional group validation checks that schema_input.json cannot do.
         }
+        .transpose() // Replace the map below
+        // .map {
+        //     meta, fastqs ->
+        //         return [ meta, fastqs.flatten() ]
+        // }
+        .view()
         .set { ch_samplesheet }
 
     emit:
@@ -151,7 +155,9 @@ workflow PIPELINE_COMPLETION {
 // Check and validate pipeline parameters
 //
 def validateInputParameters() {
-    genomeExistsError()
+    // genomeExistsError()
+
+    // TODO: Add code to further validate pipeline parameters here
 }
 
 //