Merge pull request #3 from CarsonJM/fix-samplesheet

Re-structured pipeline so tests run

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,fasta
+test1,/workspace/rnafoldanalyzer/assets/test-datasets/input/test_alphavirus.fasta.gz
+test2,/workspace/rnafoldanalyzer/assets/test-datasets/input/test_alphavirus.fasta.gz

assets/schema_input.json

@@ -13,21 +13,14 @@
                 "errorMessage": "Sample name must be provided and cannot contain spaces",
                 "meta": ["id"]
             },
-            "fastq_1": {
+            "fasta": {
                 "type": "string",
                 "format": "file-path",
                 "exists": true,
-                "pattern": "^\\S+\\.f(ast)?q\\.gz$",
-                "errorMessage": "FastQ file for reads 1 must be provided, cannot contain spaces and must have extension '.fq.gz' or '.fastq.gz'"
-            },
-            "fastq_2": {
-                "type": "string",
-                "format": "file-path",
-                "exists": true,
-                "pattern": "^\\S+\\.f(ast)?q\\.gz$",
-                "errorMessage": "FastQ file for reads 2 cannot contain spaces and must have extension '.fq.gz' or '.fastq.gz'"
+                "pattern": "^\\S+\\.f(ast|n)?a\\.gz$",
+                "errorMessage": "FastA file must be provided, cannot contain spaces and must have extension '.fa.gz', '.fna.gz', or '.fasta.gz'"
             }
         },
-        "required": ["sample", "fastq_1"]
+        "required": ["sample", "fasta"]
     }
 }

conf/test.config

@@ -20,10 +20,5 @@ params {
     max_time   = '6.h'
 
     // 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'
-
-    // Genome references
-    genome = 'R64-1-1'
+    input  = "${projectDir}/assets/samplesheet.csv"
 }

modules.json

@@ -15,6 +15,11 @@
                         "git_sha": "f4ae1d942bd50c5c0b9bd2de1393ce38315ba57c",
                         "installed_by": ["modules"]
                     },
+                    "gunzip": {
+                        "branch": "master",
+                        "git_sha": "3a5fef109d113b4997c9822198664ca5f2716208",
+                        "installed_by": ["modules"]
+                    },
                     "multiqc": {
                         "branch": "master",
                         "git_sha": "b7ebe95761cd389603f9cc0e0dc384c0f663815a",

subworkflows/local/utils_nfcore_rnafoldanalyzer_pipeline/main.nf

@@ -82,22 +82,9 @@ workflow PIPELINE_INITIALISATION {
     //
     Channel
         .fromSamplesheet("input")
-        .map {
-            meta, fastq_1, fastq_2 ->
-                if (!fastq_2) {
-                    return [ meta.id, meta + [ single_end:true ], [ fastq_1 ] ]
-                } else {
-                    return [ meta.id, meta + [ single_end:false ], [ fastq_1, fastq_2 ] ]
-                }
-        }
-        .groupTuple()
         .map {
             validateInputSamplesheet(it)
         }
-        .map {
-            meta, fastqs ->
-                return [ meta, fastqs.flatten() ]
-        }
         .set { ch_samplesheet }
 
     emit:
@@ -158,15 +145,9 @@ def validateInputParameters() {
 // Validate channels from input samplesheet
 //
 def validateInputSamplesheet(input) {
-    def (metas, fastqs) = input[1..2]
-
-    // Check that multiple runs of the same sample are of the same datatype i.e. single-end / paired-end
-    def endedness_ok = metas.collect{ it.single_end }.unique().size == 1
-    if (!endedness_ok) {
-        error("Please check input samplesheet -> Multiple runs of a sample must be of the same datatype i.e. single-end or paired-end: ${metas[0].id}")
-    }
+    def (metas, fasta) = input
 
-    return [ metas[0], fastqs ]
+    return [ metas, fasta ]
 }
 //
 // Get attribute from genome config file e.g. fasta

workflows/rnafoldanalyzer.nf

@@ -11,6 +11,7 @@ include { paramsSummaryMultiqc   } from '../subworkflows/nf-core/utils_nfcore_pi
 include { softwareVersionsToYAML } from '../subworkflows/nf-core/utils_nfcore_pipeline'
 include { methodsDescriptionText } from '../subworkflows/local/utils_nfcore_rnafoldanalyzer_pipeline'
 
+include { GUNZIP                 } from '../modules/nf-core/gunzip/main'
 include { CLUSTALO_ALIGN         } from '../modules/nf-core/clustalo/align/main'
 /*
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
@@ -28,19 +29,19 @@ workflow RNAFOLDANALYZER {
     ch_versions = Channel.empty()
     ch_multiqc_files = Channel.empty()
 
+    ch_samplesheet.view()
+
     //
-    // MODULE: Run FastQC
+    // MODULE: Gunzip FASTA files for input into Clustal Omega
     //
-    FASTQC (
-        ch_samplesheet
-    )
-    ch_multiqc_files = ch_multiqc_files.mix(FASTQC.out.zip.collect{it[1]})
-    ch_versions = ch_versions.mix(FASTQC.out.versions.first())
+    ch_fasta = GUNZIP ( ch_samplesheet ).gunzip
+    ch_versions = ch_versions.mix ( GUNZIP.out.versions )
 
     //
     // MODULE: Run Clustal Omega align
     //
-    CLUSTALO_ALIGN ( <fasta>, <tree>, true )
+    CLUSTALO_ALIGN ( ch_fasta, [[:],[]], true )
+    ch_versions = ch_versions.mix( CLUSTALO_ALIGN.out.versions )
 
     //
     // Collate and save software versions