Update nf-hello-gatk to match format in hello-gatk training

Changes:
 - Uses samplesheet input (with raw Github URLs)
 - Uses file() on reference data objects instead of channels
 - Uses reads_bam as channel name
 - calling_intervals variable becomes intervals

.github/workflows/ci.yml

@@ -0,0 +1,21 @@
+name: test-pipeline
+
+on: [push, pull_request]
+
+# Cancel if a newer run is started
+concurrency:
+  group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.ref }}
+  cancel-in-progress: true
+
+jobs:
+  nextflow:
+    runs-on: ubuntu-latest
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@v2
+
+      - name: setup-nextflow
+        uses: nf-core/setup-nextflow@v1
+
+      - name: run-nextflow
+        run: nextflow run .

data/sample_bams.txt

@@ -0,0 +1,3 @@
+https://github.com/seqeralabs/nf-hello-gatk/raw/refs/heads/main/data/bam/reads_mother.bam
+https://github.com/seqeralabs/nf-hello-gatk/raw/refs/heads/main/data/bam/reads_father.bam
+https://github.com/seqeralabs/nf-hello-gatk/raw/refs/heads/main/data/bam/reads_son.bam

main.nf

@@ -137,43 +137,39 @@ workflow {
     */
 
     // Primary input
-    params.reads_bam = "${workflow.projectDir}/data/bam/*.bam"
+    params.reads_bam = "${workflow.projectDir}/data/sample_bams.txt"
 
     // Accessory files
     params.reference = "${workflow.projectDir}/data/ref/ref.fasta"
     params.reference_index = "${workflow.projectDir}/data/ref/ref.fasta.fai"
     params.reference_dict = "${workflow.projectDir}/data/ref/ref.dict"
-    params.calling_intervals = "${workflow.projectDir}/data/ref/intervals.bed"
+    params.intervals = "${workflow.projectDir}/data/ref/intervals.bed"
 
     // Base name for final output file
     params.cohort_name = "family_trio"
 
     // Output directory
     params.outdir = "results"
 
-    // Create input channel from BAM files
-    // We convert it to a tuple with the file name and the file path
-    // See https://www.nextflow.io/docs/latest/script.html#getting-file-attributes
-    bam_ch = Channel.fromPath(params.reads_bam, checkIfExists: true)
+    // Create input channel from list of input files in plain text
+    reads_ch = Channel.fromPath(params.reads_bam).splitText()
 
-    // Create reference channels using the fromPath channel factory
-    // The collect converts from a queue channel to a value channel
-    // See https://www.nextflow.io/docs/latest/channel.html#channel-types for details
-    ref_ch               = Channel.fromPath(params.reference, checkIfExists: true).collect()
-    ref_index_ch         = Channel.fromPath(params.reference_index, checkIfExists: true).collect()
-    ref_dict_ch          = Channel.fromPath(params.reference_dict, checkIfExists: true).collect()
-    calling_intervals_ch = Channel.fromPath(params.calling_intervals, checkIfExists: true).collect()
+    // Create channels for the accessory files (reference and intervals)
+    ref_file        = file(params.reference)
+    ref_index_file  = file(params.reference_index)
+    ref_dict_file   = file(params.reference_dict)
+    intervals_file  = file(params.intervals)
 
     // Create index file for input BAM file
-    SAMTOOLS_INDEX(bam_ch)
+    SAMTOOLS_INDEX(reads_ch)
 
     // Call variants from the indexed BAM file
     GATK_HAPLOTYPECALLER(
         SAMTOOLS_INDEX.out,
-        ref_ch,
-        ref_index_ch,
-        ref_dict_ch,
-        calling_intervals_ch
+        ref_file,
+        ref_index_file,
+        ref_dict_file,
+        intervals_file
     )
 
     all_vcfs = GATK_HAPLOTYPECALLER.out[0].collect()
@@ -184,10 +180,10 @@ workflow {
         all_vcfs,
         all_tbis,
         params.cohort_name,
-        ref_ch,
-        ref_index_ch,
-        ref_dict_ch,
-        calling_intervals_ch
+        ref_file,
+        ref_index_file,
+        ref_dict_file,
+        intervals_file
     )
 
     BCFTOOLS_STATS(

nextflow_schema.json

@@ -19,7 +19,8 @@
         "outdir": {
           "type": "string",
           "description": "Output directory to write results to.",
-          "default": "results"
+          "default": "results",
+          "format": "path"
         },
         "reference": {
           "type": "string",
@@ -36,7 +37,7 @@
           "description": "Path to genome GATK dictionary file (.dict)",
           "format": "file-path"
         },
-        "calling_intervals": {
+        "intervals": {
           "type": "string",
           "description": "Path to intervals for variant calling in BED format (.bed)",
           "format": "file-path"