Static types

bin/fastqc.sh

@@ -1,6 +1,6 @@
 #!/usr/bin/env bash
-sample_id="$1"
+id="$1"
 reads="$2"
 
-mkdir fastqc_${sample_id}_logs
-fastqc -o fastqc_${sample_id}_logs -f fastq -q ${reads}
+mkdir fastqc_${id}_logs
+fastqc -o fastqc_${id}_logs -f fastq -q ${reads}

data/allreads.csv

@@ -0,0 +1,4 @@
+gut,https://raw.githubusercontent.com/nextflow-io/rnaseq-nf/refs/heads/master/data/ggal/ggal_gut_1.fq,https://raw.githubusercontent.com/nextflow-io/rnaseq-nf/refs/heads/master/data/ggal/ggal_gut_2.fq
+liver,https://raw.githubusercontent.com/nextflow-io/rnaseq-nf/refs/heads/master/data/ggal/ggal_liver_1.fq,https://raw.githubusercontent.com/nextflow-io/rnaseq-nf/refs/heads/master/data/ggal/ggal_liver_2.fq
+lung,https://raw.githubusercontent.com/nextflow-io/rnaseq-nf/refs/heads/master/data/ggal/ggal_lung_1.fq,https://raw.githubusercontent.com/nextflow-io/rnaseq-nf/refs/heads/master/data/ggal/ggal_lung_2.fq
+spleen,https://raw.githubusercontent.com/nextflow-io/rnaseq-nf/refs/heads/master/data/ggal/ggal_spleen_1.fq,https://raw.githubusercontent.com/nextflow-io/rnaseq-nf/refs/heads/master/data/ggal/ggal_spleen_2.fq

data/gut.csv

@@ -0,0 +1 @@
+gut,https://raw.githubusercontent.com/nextflow-io/rnaseq-nf/refs/heads/master/data/ggal/ggal_gut_1.fq,https://raw.githubusercontent.com/nextflow-io/rnaseq-nf/refs/heads/master/data/ggal/ggal_gut_2.fq

main.nf

@@ -4,36 +4,86 @@
  * Proof of concept of a RNAseq pipeline implemented with Nextflow
  */
 
+// enable v2 operators (required for static type checking)
+nextflow.preview.operators = true
 
-/*
- * Default pipeline parameters. They can be overriden on the command line eg.
- * given `params.foo` specify on the run command line `--foo some_value`.
- */
-
-params.reads = "$baseDir/data/ggal/ggal_gut_{1,2}.fq"
-params.transcriptome = "$baseDir/data/ggal/ggal_1_48850000_49020000.Ggal71.500bpflank.fa"
-params.outdir = "results"
-params.multiqc = "$baseDir/multiqc"
-
+// 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}
+      outdir       : ${workflow.outputDir}
+    """.stripIndent()
+
+  (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 --> ${workflow.outputDir}/multiqc_report.html\n"
+      : "Oops .. something went wrong"
+  )
+}
+
+/*
+ * Pipeline outputs. By default they will be saved to the 'results' directory.
+ */
+output {
+  index: Path {
+    path '.'
+  }
+
+  samples: Channel<Sample> {
+    path { sample ->
+      sample.fastqc >> "fastqc/${sample.id}"
+      sample.quant >> "quant/${sample.id}"
+    }
+    index {
+      path 'samples.csv'
+      header true
+    }
+  }
 
-log.info """\
-  R N A S E Q - N F   P I P E L I N E
-  ===================================
-  transcriptome: ${params.transcriptome}
-  reads        : ${params.reads}
-  outdir       : ${params.outdir}
-  """
-
-  read_pairs_ch = channel.fromFilePairs( params.reads, checkIfExists: true ) 
-  RNASEQ( params.transcriptome, read_pairs_ch )
-  MULTIQC( RNASEQ.out, params.multiqc )
+  multiqc_report: Path {
+    path '.'
+  }
 }

modules/fastqc/main.nf

@@ -1,18 +1,19 @@
-params.outdir = 'results'
 
 process FASTQC {
-    tag "FASTQC on $sample_id"
+    tag "$id"
     conda 'bioconda::fastqc=0.12.1'
-    publishDir params.outdir, mode:'copy'
 
     input:
-    tuple val(sample_id), path(reads)
+    id      : String
+    fastq_1 : Path
+    fastq_2 : Path
 
     output:
-    path "fastqc_${sample_id}_logs", emit: logs
+    id      : String = id
+    fastqc  : Path = file("fastqc_${id}_logs")
 
     script:
     """
-    fastqc.sh "$sample_id" "$reads"
+    fastqc.sh "$id" "$fastq_1 $fastq_2"
     """
 }

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

@@ -1,15 +1,13 @@
-params.outdir = 'results'
 
 process MULTIQC {
     conda 'bioconda::multiqc=1.27.1'
-    publishDir params.outdir, mode:'copy'
 
     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

@@ -1,17 +1,20 @@
 
 process QUANT {
-    tag "$pair_id"
+    tag "$id"
     conda 'bioconda::salmon=1.10.3'
 
     input:
-    path index 
-    tuple val(pair_id), path(reads) 
+    id      : String
+    fastq_1 : Path
+    fastq_2 : Path
+    index   : Path
 
     output:
-    path pair_id 
+    id      : String = id
+    quant   : Path = file("quant_${id}") 
 
     script:
     """
-    salmon quant --threads $task.cpus --libType=U -i $index -1 ${reads[0]} -2 ${reads[1]} -o $pair_id
+    salmon quant --threads $task.cpus --libType=U -i $index -1 ${fastq_1} -2 ${fastq_2} -o quant_$id
     """
 }

modules/rnaseq.nf

@@ -1,19 +1,32 @@
-params.outdir = 'results'
 
 include { INDEX } from './index'
 include { QUANT } from './quant'
 include { FASTQC } from './fastqc'
 
 workflow RNASEQ {
-  take:
-    transcriptome
-    read_pairs_ch
-
-  main: 
-    INDEX(transcriptome)
-    FASTQC(read_pairs_ch)
-    QUANT(INDEX.out, read_pairs_ch)
+    take:
+    reads         : Channel<FastqPair>
+    transcriptome : Path
 
-  emit: 
-     QUANT.out | concat(FASTQC.out) | collect
-}
+    main:
+    index = INDEX(transcriptome)
+    fastqc_ch = reads.map(FASTQC)
+    quant_ch = reads.map(QUANT, index: index)
+    samples_ch = fastqc_ch.join(quant_ch, 'id')
+
+    emit:
+    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.config

@@ -17,16 +17,20 @@ manifest {
 }
 
 /*
- * default params
+ * params for default test data
  */
 
-params.outdir = "results"
-params.reads = "${projectDir}/data/ggal/ggal_gut_{1,2}.fq"
-params.transcriptome = "${projectDir}/data/ggal/ggal_1_48850000_49020000.Ggal71.500bpflank.fa"
-params.multiqc = "${projectDir}/multiqc"
+params.reads = "${projectDir}/data/gut.csv"
+params.transcriptome = "https://raw.githubusercontent.com/nextflow-io/rnaseq-nf/refs/heads/master/data/ggal/ggal_1_48850000_49020000.Ggal71.500bpflank.fa"
 
 /*
- * defines execution profiles for different environments
+ * publish settings
+ */
+
+workflow.output.mode = 'copy'
+
+/*
+ * execution profiles for different environments
  */
 
 profiles {
@@ -35,7 +39,7 @@ profiles {
   }
 
   'all-reads' {
-    params.reads = "${projectDir}/data/ggal/ggal_*_{1,2}.fq"
+    params.reads = "${projectDir}/data/allreads.csv"
   }
 
   'arm64' {
@@ -84,8 +88,6 @@ profiles {
   }
 
   'batch' {
-    params.reads = 's3://rnaseq-nf/data/ggal/lung_{1,2}.fq'
-    params.transcriptome = 's3://rnaseq-nf/data/ggal/transcript.fa'
     process.container = 'docker.io/nextflow/rnaseq-nf:v1.3.1'
     process.executor = 'awsbatch'
     process.queue = 'nextflow-ci'
@@ -94,15 +96,7 @@ profiles {
     aws.batch.cliPath = '/home/ec2-user/miniconda/bin/aws'
   }
 
-  's3-data' {
-    process.container = 'docker.io/nextflow/rnaseq-nf:v1.3.1'
-    params.reads = 's3://rnaseq-nf/data/ggal/lung_{1,2}.fq'
-    params.transcriptome = 's3://rnaseq-nf/data/ggal/transcript.fa'
-  }
-
   'google-batch' {
-      params.transcriptome = 'gs://rnaseq-nf/data/ggal/transcript.fa'
-      params.reads = 'gs://rnaseq-nf/data/ggal/gut_{1,2}.fq'
       params.multiqc = 'gs://rnaseq-nf/multiqc'
       process.executor = 'google-batch'
       process.container = 'docker.io/nextflow/rnaseq-nf:v1.3.1'
@@ -113,12 +107,6 @@ profiles {
       google.region  = 'europe-west2'
   }
 
-  'gs-data' {
-      process.container = 'docker.io/nextflow/rnaseq-nf:v1.3.1'
-      params.transcriptome = 'gs://rnaseq-nf/data/ggal/transcript.fa'
-      params.reads = 'gs://rnaseq-nf/data/ggal/gut_{1,2}.fq'
-  }
-
   'azure-batch' {
     process.container = 'docker.io/nextflow/rnaseq-nf:v1.3.1'
     workDir = 'az://nf-scratch/work'

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"
         }