Static types

Author: bentsherman

main.nf

@@ -4,59 +4,75 @@
  * Proof of concept of a RNAseq pipeline implemented with Nextflow
  */
 
-nextflow.preview.output = true
-
-/*
- * Default pipeline parameters. They can be overriden on the command line eg.
- * given `params.reads` specify on the run command line `--reads some_value`.
- */
-
-params.reads = null
-params.transcriptome = null
-params.outdir = "results"
-params.multiqc = "$projectDir/multiqc"
+// enable v2 operators (required for static type checking)
+nextflow.preview.operators = true
 
+// enable static type checking
+nextflow.preview.typeChecking = true
 
 // import modules
 include { RNASEQ } from './modules/rnaseq'
+include { FastqPair ; Sample } from './modules/rnaseq'
 include { MULTIQC } from './modules/multiqc'
 
+/*
+ * Pipeline parameters. They can be overridden on the command line, e.g.
+ * `params.reads` can be specified as `--reads '...'`.
+ */
+params {
+  // The input read-pair files
+  reads: List<FastqPair>
+
+  // The input transcriptome file
+  transcriptome: Path
+
+  // Directory containing multiqc configuration
+  multiqc: Path = "${projectDir}/multiqc"
+}
+
 /* 
- * main script flow
+ * Entry workflow
  */
 workflow {
   main:
   log.info """\
       R N A S E Q - N F   P I P E L I N E
       ===================================
+      reads        : ${params.reads*.id.join(',')}
       transcriptome: ${params.transcriptome}
-      reads        : ${params.reads}
-      outdir       : ${params.outdir}
+      outdir       : ${workflow.outputDir}
     """.stripIndent()
 
-  inputs_ch = channel.fromPath(params.reads)
-    .splitCsv()
-    .map { id, fastq_1, fastq_2 ->
-      tuple(id, file(fastq_1, checkIfExists: true), file(fastq_2, checkIfExists: true))
-    }
-
-  samples_ch = RNASEQ( params.transcriptome, inputs_ch )
-    .map { id, fastqc, quant ->
-      [id: id, fastqc: fastqc, quant: quant]
-    }
+  (samples_ch, index) = RNASEQ( channel.fromList(params.reads), params.transcriptome )
 
   multiqc_files_ch = samples_ch
     .flatMap { sample -> [sample.fastqc, sample.quant] }
     .collect()
+
   multiqc_report = MULTIQC( multiqc_files_ch, params.multiqc )
 
   publish:
+  index = index
   samples = samples_ch
   multiqc_report = multiqc_report
+
+  onComplete:
+  log.info(
+    workflow.success
+      ? "\nDone! Open the following report in your browser --> ${workflow.outputDir}/multiqc_report.html\n"
+      : "Oops .. something went wrong"
+  )
 }
 
+/*
+ * Pipeline outputs. By default they will be saved to the 'results' directory.
+ */
 output {
-  samples {
+  index: Path {
+    path '.'
+  }
+
+  samples: Channel<Sample> {
     path { sample ->
       sample.fastqc >> "fastqc/${sample.id}"
       sample.quant >> "quant/${sample.id}"
@@ -67,6 +83,7 @@ output {
     }
   }
 
-  multiqc_report {
+  multiqc_report: Path {
+    path '.'
   }
 }

modules/fastqc/main.nf

@@ -4,10 +4,13 @@ process FASTQC {
     conda 'bioconda::fastqc=0.12.1'
 
     input:
-    tuple val(id), path(fastq_1), path(fastq_2)
+    id      : String
+    fastq_1 : Path
+    fastq_2 : Path
 
     output:
-    tuple val(id), path("fastqc_${id}_logs")
+    id      : String = id
+    fastqc  : Path = file("fastqc_${id}_logs")
 
     script:
     """

modules/index/main.nf

@@ -4,10 +4,10 @@ process INDEX {
     conda 'bioconda::salmon=1.10.3'
 
     input:
-    path transcriptome 
+    transcriptome   : Path
 
     output:
-    path 'index' 
+    file('index')
 
     script:
     """

modules/multiqc/main.nf

@@ -3,11 +3,11 @@ process MULTIQC {
     conda 'bioconda::multiqc=1.27.1'
 
     input:
-    path '*'
-    path config
+    inputs  : Bag<Path>
+    config  : Path
 
     output:
-    path 'multiqc_report.html', emit: report
+    file('multiqc_report.html')
 
     script:
     """

modules/quant/main.nf

@@ -4,11 +4,14 @@ process QUANT {
     conda 'bioconda::salmon=1.10.3'
 
     input:
-    path index
-    tuple val(id), path(fastq_1), path(fastq_2)
+    id      : String
+    fastq_1 : Path
+    fastq_2 : Path
+    index   : Path
 
     output:
-    tuple val(id), path("quant_${id}")
+    id      : String = id
+    quant   : Path = file("quant_${id}") 
 
     script:
     """

modules/rnaseq.nf

@@ -5,15 +5,28 @@ include { FASTQC } from './fastqc'
 
 workflow RNASEQ {
     take:
-    transcriptome
-    samples_ch
+    reads         : Channel<FastqPair>
+    transcriptome : Path
 
     main:
     index = INDEX(transcriptome)
-    fastqc_ch = FASTQC(samples_ch)
-    quant_ch = QUANT(index, samples_ch)
-    samples_ch = fastqc_ch.join(quant_ch)
+    fastqc_ch = reads.map(FASTQC)
+    quant_ch = reads.map(QUANT, index: index)
+    samples_ch = fastqc_ch.join(quant_ch, 'id')
 
     emit:
-    samples_ch
-}
+    samples : Channel<Sample> = samples_ch
+    index   : Path = index
+}
+
+record FastqPair {
+  id      : String
+  fastq_1 : Path
+  fastq_2 : Path
+}
+
+record Sample {
+  id      : String
+  fastqc  : Path
+  quant   : Path
+}

nextflow_schema.json

@@ -11,15 +11,27 @@
       "fa_icon": "fas fa-terminal",
       "description": "Define where the pipeline should find input data and save output data.",
       "properties": {
-        "outdir": {
-          "type": "string",
-          "format": "directory-path",
-          "description": "The output directory where the results will be saved. You have to use absolute paths to storage on Cloud infrastructure.",
-          "fa_icon": "fas fa-folder-open",
-          "default": "results"
-        },
         "reads": {
-          "type": "string",
+          "type": "array",
+          "items": {
+            "type": "object",
+            "properties": {
+              "id": {
+                "type": "string"
+              },
+              "fastq_1": {
+                  "type": "string",
+                  "format": "file-path",
+                  "exists": true
+              },
+              "fastq_2": {
+                  "type": "string",
+                  "format": "file-path",
+                  "exists": true
+              }
+            },
+            "required": ["id", "fastq_1", "fastq_2"]
+          },
           "description": "The input read-pair files",
           "fa_icon": "fas fa-folder-open",
           "default": "${projectDir}/data/ggal/ggal_gut_{1,2}.fq"
@@ -32,6 +44,7 @@
         },
         "multiqc": {
           "type": "string",
+          "description": "Directory containing multiqc configuration",
           "fa_icon": "fas fa-folder-open",
           "default": "${projectDir}/multiqc"
         }