Add combining samples with samplesheet input

.github/test-data/nanopore/input.csv

@@ -1,6 +1,6 @@
-sample,reads
-sample1,.github/test-data/nanopore/fastq_pass/barcode01
-sample2,.github/test-data/nanopore/fastq_pass/barcode02
-100_reads,.github/test-data/nanopore/fastq_pass/barcode03
-25_reads,.github/test-data/nanopore/fastq_pass/barcode24
-negative-ctrl,.github/test-data/nanopore/fastq_pass/barcode94
+sample,fastq_1
+sample1,.github/test-data/nanopore/fastq_pass/barcode01/barcode01.fastq.gz
+sample2,.github/test-data/nanopore/fastq_pass/barcode02/barcode02.fastq.gz
+100_reads,.github/test-data/nanopore/fastq_pass/barcode03/barcode03.fastq.gz
+25_reads,.github/test-data/nanopore/fastq_pass/barcode24/barcode24.fastq.gz
+negative-ctrl,.github/test-data/nanopore/fastq_pass/barcode94/barcode94.fastq.gz

docs/usage.md

@@ -83,10 +83,12 @@ Ex.
 | sample | fastq_1 |
 | - | - |
 | sample1 | /path/to/sample.fastq |
+| sample2 | /path/to/sample2-1.fastq |
+| sample2 | /path/to/sample-2.fastq |
 | ntc | /path/to/control.fastq |
 | pos | /path/to/pos.fastq |
 
-This will be expanded upon in future releases to allow more varied inputs for the input sheet.
+A sample can be given multiple fastq files if it was resequenced or needed a top up run. If there are multiple fastq files for a sample they will be concatenated and gzipped. If not, the input fastq file will just be gzipped (if it isn't already).
 
 ## Variant Callers
 Three different variant callers are available with slightly different options regarding running with them. For the most accurate results when running with `clair3` or `medaka` pick a model that best matches the input data!!

modules/local/custom/utils.nf

@@ -1,4 +1,35 @@
 // Custom Utility Modules
+process CAT_FASTQ {
+    label 'process_single'
+    tag "$meta.id"
+
+    conda "conda-forge::pigz=2.3.4"
+    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
+        'https://depot.galaxyproject.org/singularity/pigz:2.3.4' :
+        'biocontainers/pigz:2.3.4' }"
+
+    input:
+    tuple val(meta), path(gzipped_reads), path(reads)
+
+    output:
+    tuple val(meta), path("*.merged.fastq.gz"), emit: fastq
+
+    script:
+    // Check if input lists are empty or not
+    def gzReadsExist = !gzipped_reads.empty
+    def readsExist = !reads.empty
+
+    def outName = "${meta.id}.merged.fastq.gz"
+    """
+    touch $outName
+    if [ "$gzReadsExist" == "true" ]; then
+        cat $gzipped_reads >> $outName
+    fi
+    if [ "$readsExist" == "true" ]; then
+        cat $reads | pigz -ck >> $outName
+    fi
+    """
+}
 process DOWNLOAD_SCHEME {
     label 'process_single'
     tag { params.scheme_repo }

subworkflows/local/format_input.nf

@@ -9,6 +9,7 @@
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
 */
 include { samplesheetToList } from 'plugin/nf-schema'
+include { CAT_FASTQ } from '../../modules/local/custom/utils.nf'
 
 /*
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
@@ -55,11 +56,38 @@ workflow FORMAT_INPUT {
     // Input CSV file with path to fastq single reads to comply with IRIDA Next (eventually)
     //
     else {
-        // Using the samplesheet thing
+        // Using the samplesheet thingy
         Channel.fromList(samplesheetToList(params.input, "assets/schema_input.json"))
+            // Group by name
+            .groupTuple(by: 0)
+            .map{ meta, fastqs ->
+                // Set list of fastqs found
+                def gzfq_list = []
+                def fq_list = []
+
+                // Determine if gzipped or not
+                //  The samplesheetToList part should deal with name/extension reqs
+                for ( fastq in fastqs ) {
+                    if ( fastq.isFile() ) {
+                        if ( fastq.getName().endsWith('.gz') ) { 
+                            gzfq_list << fastq
+                        }else {
+                            fq_list << fastq 
+                        }
+                    }
+                }
+                return [meta, gzfq_list, fq_list]
+            }.set{ ch_initial_fastqs }
+
+        // Concatenate fastqs to allow gzipped and non-gzipped together
+        CAT_FASTQ(
+            ch_initial_fastqs
+        )
+
+        CAT_FASTQ.out.fastq
             .branch{
+                empty: it[1].isEmpty()
                 pass: it[1].countFastq() >= 1
-                empty: it[1].countFastq() == 0
             }.set{ ch_fastqs }
     }