Assembly subworkflow

.nf-core.yml

@@ -2,6 +2,8 @@ lint:
   files_exist:
     - conf/igenomes.config
     - conf/igenomes_ignored.config
+  nextflow_config:
+    - params.input
   files_unchanged:
     - .github/PULL_REQUEST_TEMPLATE.md
 nf_core_version: 3.4.1

assets/samplesheet_assembly.csv

@@ -0,0 +1,2 @@
+id,fasta,fastq_1,fastq_2,accession
+contigs_1,https://github.com/nf-core/test-datasets/raw/seqsubmit/test_data/contigs.fasta.gz,ftp://ftp.sra.ebi.ac.uk/vol1/fastq/ERR011/ERR011322/ERR011322_1.fastq.gz,ftp://ftp.sra.ebi.ac.uk/vol1/fastq/ERR011/ERR011322/ERR011322_2.fastq.gz,ERR011322

assets/schema_input_assembly.json

@@ -0,0 +1,51 @@
+{
+    "$schema": "https://json-schema.org/draft/2020-12/schema",
+    "$id": "https://raw.githubusercontent.com/nf-core/seqsubmit/main/assets/schema_input_assembly.json",
+    "title": "nf-core/seqsubmit pipeline - params.input schema",
+    "description": "Schema for the file provided with params.input",
+    "type": "array",
+    "items": {
+        "type": "object",
+        "properties": {
+            "id": {
+                "type": "string",
+                "pattern": "^\\S+$",
+                "errorMessage": "ID name must be provided and cannot contain spaces",
+                "meta": ["id"]
+            },
+            "fasta": {
+                "type": "string",
+                "format": "file-path",
+                "exists": true,
+                "pattern": "^([\\S\\s]*\\/)?[^\\s\\/]+\\.f(ast)?a\\.gz$",
+                "errorMessage": "FASTA file must be provided, cannot contain spaces and must have extension '.fa.gz' or '.fasta.gz'",
+                "description": "Metagenomic assembly sequence file"
+            },
+            "fastq_1": {
+                "type": "string",
+                "format": "file-path",
+                "exists": true,
+                "pattern": "^([\\S\\s]*\\/)?[^\\s\\/]+\\.f(ast)?q\\.gz$",
+                "errorMessage": "FastQ file for reads 1 cannot contain spaces and must have extension '.fq.gz' or '.fastq.gz'",
+                "description": "Reads sequence file"
+            },
+            "fastq_2": {
+                "type": "string",
+                "format": "file-path",
+                "exists": true,
+                "pattern": "^([\\S\\s]*\\/)?[^\\s\\/]+\\.f(ast)?q\\.gz$",
+                "errorMessage": "FastQ file for reads  cannot contain spaces and must have extension '.fq.gz' or '.fastq.gz'",
+                "description": "Reads sequence file"
+            },
+            "coverage": {
+                "type": "number",
+                "description": "Mean assembly coverage"
+            },
+            "accession": {
+                "type": "string",
+                "description": "FASTQ ENA accession"
+            }
+        },
+        "required": ["id", "fasta", "accession"]
+    }
+}

assets/schema_input.json → assets/schema_input_genome.json

@@ -1,6 +1,6 @@
 {
     "$schema": "https://json-schema.org/draft/2020-12/schema",
-    "$id": "https://raw.githubusercontent.com/nf-core/seqsubmit/main/assets/schema_input.json",
+    "$id": "https://raw.githubusercontent.com/nf-core/seqsubmit/main/assets/schema_input_genome.json",
     "title": "nf-core/seqsubmit pipeline - params.input schema",
     "description": "Schema for the file provided with params.input",
     "type": "array",

conf/test.config

@@ -25,7 +25,7 @@ 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 + 'seqsubmit/samplesheets/samplesheet_genomesubmit.csv'
+    input_genome  = params.pipelines_testdata_base_path + 'seqsubmit/samplesheets/samplesheet_genomesubmit.csv'
 
     mode                       = "mags"
     ena_genome_study_accession = "PRJEB98843"

conf/test_assembly.config

@@ -0,0 +1,34 @@
+/*
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+    Nextflow config file for running minimal tests
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+    Defines input files and everything required to run a fast and simple pipeline test.
+
+    Use as follows:
+        nextflow run nf-core/seqsubmit -profile test,<docker/singularity> --outdir <OUTDIR>
+
+----------------------------------------------------------------------------------------
+*/
+
+process {
+    resourceLimits = [
+        cpus: 2,
+        memory: '8.GB',
+        time: '1.h'
+    ]
+}
+
+params {
+    config_profile_name        = 'Test profile'
+    config_profile_description = 'Minimal test dataset to check pipeline function'
+
+    // 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_assembly  = 'assets/samplesheet_assembly.csv'
+
+    //mode                       = "mags"
+    //ena_genome_study_accession = "PRJEB98843"
+    //centre_name                = "TEST_CENTER"
+
+}

conf/test_genome.config

@@ -0,0 +1,34 @@
+/*
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+    Nextflow config file for running minimal tests
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+    Defines input files and everything required to run a fast and simple pipeline test.
+
+    Use as follows:
+        nextflow run nf-core/seqsubmit -profile test,<docker/singularity> --outdir <OUTDIR>
+
+----------------------------------------------------------------------------------------
+*/
+
+process {
+    resourceLimits = [
+        cpus: 4,
+        memory: '15.GB',
+        time: '1.h'
+    ]
+}
+
+params {
+    config_profile_name        = 'Test profile'
+    config_profile_description = 'Minimal test dataset to check pipeline function'
+
+    // 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_genome  = params.pipelines_testdata_base_path + 'seqsubmit/samplesheets/samplesheet_genomesubmit.csv'
+
+    mode                       = "mags"
+    ena_genome_study_accession = "PRJEB98843"
+    centre_name                = "TEST_CENTER"
+
+}

main.nf

@@ -17,6 +17,7 @@
 
 include { SEQSUBMIT               } from './workflows/seqsubmit'
 include { GENOMESUBMIT            } from './workflows/genomesubmit'
+include { ASSEMBLYSUBMIT          } from './workflows/assemblysubmit'
 include { PIPELINE_INITIALISATION } from './subworkflows/local/utils_nfcore_seqsubmit_pipeline'
 include { PIPELINE_COMPLETION     } from './subworkflows/local/utils_nfcore_seqsubmit_pipeline'
 /*
@@ -38,17 +39,19 @@ workflow NFCORE_SEQSUBMIT {
     //
     // WORKFLOW: Run pipeline
     //
-    if ((params.mode == "mags") || (params.mode == "bins")) {
+    // Depending on the input type (genome or assembly), one or the another workflow will be triggered
+    // Seqsubmit workflow is ignored for now
+    if (params.input_genome) {
         GENOMESUBMIT (
             samplesheet,
             params.mode
         )
         ch_multiqc_report = GENOMESUBMIT.out.multiqc_report
-    } else {
-        SEQSUBMIT (
+    } else if (params.input_assembly) {
+        ASSEMBLYSUBMIT (
             samplesheet
         )
-        ch_multiqc_report = SEQSUBMIT.out.multiqc_report
+        ch_multiqc_report = ASSEMBLYSUBMIT.out.multiqc_report
     }
 
 
@@ -68,13 +71,18 @@ workflow {
     //
     // SUBWORKFLOW: Run initialisation tasks
     //
+
+    // There are two types of input, so define it first
+    input = params.input_genome ? params.input_genome : params.input_assembly
+
     PIPELINE_INITIALISATION (
         params.version,
         params.validate_params,
         params.monochrome_logs,
         args,
         params.outdir,
-        params.input,
+        //params.input,
+        input,
         params.help,
         params.help_full,
         params.show_hidden

modules.json

@@ -5,6 +5,11 @@
         "https://github.com/nf-core/modules.git": {
             "modules": {
                 "nf-core": {
+                    "coverm/contig": {
+                        "branch": "master",
+                        "git_sha": "27e31681fdbf1e511257355a236037a8cd9c2b2e",
+                        "installed_by": ["modules"]
+                    },
                     "fastavalidator": {
                         "branch": "master",
                         "git_sha": "41dfa3f7c0ffabb96a6a813fe321c6d1cc5b6e46",