Sylph

assets/samplesheet.csv

@@ -1,7 +1,2 @@
-sample,fastq_1,fastq_2,rundir,tags
-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,/path/to/rundir,paired_sample:lane1
-SAMPLE_PAIRED_END,/path/to/fastq/files/AEG588A2_S2_L002_R1_001.fastq.gz,/path/to/fastq/files/AEG588A2_S2_L002_R2_001.fastq.gz,/path/to/rundir,paired_sample:lane1
-SAMPLE_PAIRED_END,/path/to/fastq/files/AEG588A3_S3_L002_R1_001.fastq.gz,/path/to/fastq/files/AEG588A3_S3_L002_R2_001.fastq.gz,/path/to/rundir,paired_sample:lane2
-SAMPLE_SINGLE_END,/path/to/fastq/files/AEG588A4_S4_L003_R1_001.fastq.gz,,/path/to/rundir,group1
-SAMPLE_SINGLE_END,/path/to/fastq/files/AEG588A4_S4_L003_R1_001.fastq.gz,,/path/to/rundir,group2
-SAMPLE_SINGLE_END,/path/to/fastq/files/AEG588A4_S4_L003_R1_001.fastq.gz,,/path/to/rundir,group3
+sample,fastq_1,fastq_2,rundir,tags,reference
+test2,https://raw.githubusercontent.com/nf-core/test-datasets/modules/data/genomics/sarscov2/illumina/fastq/test2_1.fastq.gz,https://raw.githubusercontent.com/nf-core/test-datasets/modules/data/genomics/sarscov2/illumina/fastq/test2_2.fastq.gz,,,https://raw.githubusercontent.com/nf-core/test-datasets/refs/heads/modules/data/genomics/sarscov2/genome/genome.fasta

assets/schema_input.json

@@ -27,6 +27,12 @@
                 "pattern": "^\\S+\\.f(ast)?q\\.gz$",
                 "errorMessage": "FastQ file for reads 2 cannot contain spaces and must have extension '.fq.gz' or '.fastq.gz'"
             },
+            "reference": {
+                "type": "string",
+                "format": "file-path",
+                "pattern": "^\\S+\\.(fasta|fa|fna|tar)(\\.gz)?$",
+                "errorMessage": "FASTA file must be gzipped with extensions '.fasta.gz', '.fa.gz', 'tar.gz' or '.fna.gz'"            
+            },            
             "rundir": {
                 "type": "string",
                 "format": "path",

conf/test.config

@@ -25,7 +25,10 @@ params {
     // 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  = params.pipelines_testdata_base_path + 'seqinspector/testdata/NovaSeq6000/samplesheet.csv'
+    //input  = params.pipelines_testdata_base_path + 'seqinspector/testdata/NovaSeq6000/samplesheet.csv'
+
+    // In this samplesheet.csv , I added extra references col 
+    input = './assets/samplesheet.csv'
 
     // Genome references
     genome = 'R64-1-1'

modules/local/sylph/profile/environment.yml

@@ -0,0 +1,7 @@
+---
+# yaml-language-server: $schema=https://raw.githubusercontent.com/nf-core/modules/master/modules/environment-schema.json
+channels:
+  - conda-forge
+  - bioconda
+dependencies:
+  - bioconda::sylph==v0.6.1

modules/local/sylph/profile/main.nf

@@ -0,0 +1,47 @@
+process SYLPH_PROFILE {
+    tag "$meta.id"
+    label 'process_high'
+
+    conda "${moduleDir}/environment.yml"
+    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
+        'https://depot.galaxyproject.org/singularity/sylph:0.6.1--h4ac6f70_0' :
+        'biocontainers/sylph:0.6.1--h4ac6f70_0' }"
+
+    input:
+    tuple val(meta), path(sketch_fastq), path(sketch_fastq_genome)   
+
+    output:
+    tuple val(meta), path('profile_out.tsv'), emit: profile_out
+
+    when:
+    task.ext.when == null || task.ext.when
+
+    script:
+    def args = task.ext.args ?: ''
+    def prefix = task.ext.prefix ?: "${meta.id}"
+
+    """
+    sylph profile \\
+          $args \\
+          $sketch_fastq \\
+          $sketch_fastq_genome \\
+          -o profile_out.tsv
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        sylph: \$(sylph -V|awk '{print \$2}')
+    END_VERSIONS
+
+    """
+
+    stub:
+    """
+    touch profile_out.tsv
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        sylph: \$(sylph -V|awk '{print \$2}')
+    END_VERSIONS
+    """
+
+}

modules/local/sylph/sketch/environment.yml

@@ -0,0 +1,7 @@
+---
+# yaml-language-server: $schema=https://raw.githubusercontent.com/nf-core/modules/master/modules/environment-schema.json
+channels:
+  - conda-forge
+  - bioconda
+dependencies:
+  - bioconda::sylph==v0.6.1

modules/local/sylph/sketch/main.nf

@@ -0,0 +1,52 @@
+process SYLPH_SKETCH {
+    tag "$meta.id"
+    label 'process_high'
+
+    conda "${moduleDir}/environment.yml"
+    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
+        'https://depot.galaxyproject.org/singularity/sylph:0.6.1--h4ac6f70_0' :
+        'biocontainers/sylph:0.6.1--h4ac6f70_0' }"
+
+    input:
+    tuple val(meta), path(reads), path(reference)
+
+    output:
+    tuple val(meta), path('my_sketches/*.sylsp'), path('database.syldb'), emit: sketch_fastq_genome
+
+    when:
+    task.ext.when == null || task.ext.when
+
+    script:
+    def args = task.ext.args ?: ''
+    def prefix = task.ext.prefix ?: "${meta.id}"
+    def fastq = meta.single_end ? "-r ${reads[0]}" : "-1 ${reads[0]} -2 ${reads[1]}"
+    """
+    sylph sketch \\
+          $args \\
+          $fastq \\
+          -g $reference \\
+          -S $prefix \\
+          -d my_sketches \\
+          -c 200 \\
+          -k 31
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        sylph: \$(sylph -V|awk '{print \$2}')
+    END_VERSIONS
+    """
+
+    stub:
+    def prefix = task.ext.prefix ?: "${meta.id}"
+    def end = meta.single_end ?"": ".paired"
+    """
+    touch ${prefix}${end}.slysp
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        sylph: \$(sylph -V|awk '{print \$2}')
+    END_VERSIONS
+    """
+
+
+}

subworkflows/local/utils_nfcore_seqinspector_pipeline/main.nf

@@ -77,20 +77,22 @@ workflow PIPELINE_INITIALISATION {
         .toList()
         .flatMap { it.withIndex().collect {  entry, idx -> entry + "${idx+1}" } }
         .map {
-            meta, fastq_1, fastq_2, idx ->
+            meta, fastq_1, fastq_2, reference, idx ->
                 def tags = meta.tags ? meta.tags.tokenize(":") : []
                 def updated_meta = meta + [ id:"${meta.sample}_${idx}", tags:tags ]
                 if (!fastq_2) {
                     return [
                         updated_meta.id,
                         updated_meta + [ single_end:true ],
-                        [ fastq_1 ]
+                        [ fastq_1 ],
+                        reference
                     ]
                 } else {
                     return [
                         updated_meta.id,
                         updated_meta + [ single_end:false ],
-                        [ fastq_1, fastq_2 ]
+                        [ fastq_1, fastq_2 ],
+                        reference
                     ]
                 }
         }
@@ -103,11 +105,12 @@ workflow PIPELINE_INITIALISATION {
         //     meta, fastqs ->
         //         return [ meta, fastqs.flatten() ]
         // }
+        .view{"dadadad$it"}
         .set { ch_samplesheet }
 
     ch_samplesheet
         .map {
-            meta, fastqs -> meta.tags
+            meta, fastqs, reference -> meta.tags
         }
         .flatten()
         .unique()
@@ -189,15 +192,15 @@ def validateInputParameters() {
 // Validate channels from input samplesheet
 //
 def validateInputSamplesheet(input) {
-    def (metas, fastqs) = input[1..2]
+    def (metas, fastqs, reference) = input[1..3]
 
     // Check that multiple runs of the same sample are of the same datatype i.e. single-end / paired-end
     def endedness_ok = metas.collect{ meta -> meta.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}")
     }
 
-    return [ metas[0], fastqs ]
+    return [ metas[0], fastqs, reference ]
 }
 //
 // Get attribute from genome config file e.g. fasta

workflows/seqinspector.nf

@@ -7,6 +7,9 @@
 include { SEQTK_SAMPLE                  } from '../modules/nf-core/seqtk/sample/main'
 include { FASTQC                        } from '../modules/nf-core/fastqc/main'
 
+include {SYLPH_SKETCH                   } from '../modules/local/sylph/sketch/main'
+include {SYLPH_PROFILE                  } from '../modules/local/sylph/profile/main'
+
 include { MULTIQC as MULTIQC_GLOBAL     } from '../modules/nf-core/multiqc/main'
 include { MULTIQC as MULTIQC_PER_TAG    } from '../modules/nf-core/multiqc/main'
 
@@ -38,7 +41,7 @@ workflow SEQINSPECTOR {
     if (params.sample_size > 0 ) {
         ch_sample_sized = SEQTK_SAMPLE(
             ch_samplesheet.map {
-                meta, reads -> [meta, reads, params.sample_size]
+                meta, reads, reference -> [meta, reads, params.sample_size]
             }
         ).reads
         ch_versions = ch_versions.mix(SEQTK_SAMPLE.out.versions.first())
@@ -52,7 +55,7 @@ workflow SEQINSPECTOR {
     //
     FASTQC (
         ch_sample_sized.map {
-            meta, subsampled -> [meta, subsampled]
+            meta, subsampled, reference -> [meta, subsampled]
         }
     )
     ch_multiqc_files = ch_multiqc_files.mix(FASTQC.out.zip)
@@ -69,6 +72,18 @@ workflow SEQINSPECTOR {
             newLine: true
         ).set { ch_collated_versions }
 
+    //
+    // MODULE: Run SYLPH
+    //
+    SYLPH_SKETCH (
+        ch_samplesheet
+    )
+
+    sketch_files = SYLPH_SKETCH.out.sketch_fastq_genome
+
+    SYLPH_PROFILE (
+        sketch_files
+    )
 
     //
     // MODULE: MultiQC