Attempt to auto-detect if SWIFT/SNAP protocol is being used and add a warning

CHANGELOG.md

@@ -7,22 +7,23 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ### :warning: Major enhancements
 
-* Pipeline has been re-implemented in [Nextflow DSL2](https://www.nextflow.io/docs/latest/dsl2.html).
-* All software containers are now exclusively obtained from [Biocontainers](https://biocontainers.pro/#/registry).
-* Updated Nextflow version to `v21.04.0-edge` (see [nextflow#572](https://github.com/nextflow-io/nextflow/issues/1964)).
-* Default human `--kraken2_db` link has been changed from Zenodo to an AWS S3 bucket for more reliable downloads.
-* Illumina and Nanopore runs containing the same 48 samples sequenced on both platforms have been uploaded to the nf-core AWS account for full-sized tests on release.
-* Variant graph processes to call variants relative to the reference genome directly from _de novo_ assemblies have been deprecated and removed.
-* Variant calling with Varscan 2 has been deprecated and removed due to [licensing restrictions](https://github.com/dkoboldt/varscan/issues/12).
+* Pipeline has been re-implemented in [Nextflow DSL2](https://www.nextflow.io/docs/latest/dsl2.html)
+* All software containers are now exclusively obtained from [Biocontainers](https://biocontainers.pro/#/registry)
+* Updated Nextflow version to `v21.04.0-edge` (see [nextflow#572](https://github.com/nextflow-io/nextflow/issues/1964))
+* Default human `--kraken2_db` link has been changed from Zenodo to an AWS S3 bucket for more reliable downloads
+* Illumina and Nanopore runs containing the same 48 samples sequenced on both platforms have been uploaded to the nf-core AWS account for full-sized tests on release
+* Variant graph processes to call variants relative to the reference genome directly from _de novo_ assemblies have been deprecated and removed
+* Variant calling with Varscan 2 has been deprecated and removed due to [licensing restrictions](https://github.com/dkoboldt/varscan/issues/12)
 
 ### Other enhancements & fixes
 
-* Updated pipeline template to nf-core/tools `1.13.3`.
-* Bumped Nextflow version `19.10.0` -> `21.03.0-edge`.
-* Optimise MultiQC configuration and input files for faster run-time on huge sample numbers.
-* [#122](https://github.com/nf-core/viralrecon/issues/122) - Single SPAdes command to rule them all.
-* [#138](https://github.com/nf-core/viralrecon/issues/138) - Problem masking the consensus sequence.
-* [#142](https://github.com/nf-core/viralrecon/issues/142) - Unknown method invocation `toBytes` on String type.
+* Updated pipeline template to nf-core/tools `1.13.3`
+* Bumped Nextflow version `19.10.0` -> `21.04.0-edge`
+* Optimise MultiQC configuration and input files for faster run-time on huge sample numbers
+* [#122](https://github.com/nf-core/viralrecon/issues/122) - Single SPAdes command to rule them all
+* [#138](https://github.com/nf-core/viralrecon/issues/138) - Problem masking the consensus sequence
+* [#142](https://github.com/nf-core/viralrecon/issues/142) - Unknown method invocation `toBytes` on String type
+* [#170](https://github.com/nf-core/viralrecon/issues/170) - ivar trimming of Swift libraries new offset feature
 
 ### Parameters
 
@@ -42,6 +43,7 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 |                               | `--enable_conda`                      |
 |                               | `--fast5_dir`                         |
 |                               | `--fastq_dir`                         |
+|                               | `--ivar_trim_offset`                  |
 |                               | `--kraken2_assembly_host_filter`      |
 |                               | `--kraken2_variants_host_filter`      |
 |                               | `--min_barcode_reads`                 |
@@ -108,7 +110,7 @@ Note, since the pipeline is now using Nextflow DSL2, each process will be run wi
 | `cutadapt`                    | 2.10        | 3.2         |
 | `ivar`                        | 1.2.2       | 1.3.1       |
 | `kraken2`                     | 2.0.9beta   | 2.1.1       |
-| `nanoplot`                    |             | 1.32.1      |
+| `nanoplot`                    |             | 1.36.1      |
 | `markdown`                    | 3.2.2       |             |
 | `minimap2`                    | 2.17        |             |
 | `mosdepth`                    | 0.2.6       | 0.3.1       |

lib/Workflow.groovy

@@ -210,10 +210,10 @@ class Workflow {
                     count++
                     if (count > 1) {
                         log.warn "=============================================================================\n" +
-                                "  This pipeline does not officially support multi-fasta genome files!\n\n" + 
-                                "  The parameters and processes are tailored for viral genome analysis.\n" +
-                                "  Please amend the '--fasta' parameter.\n" +
-                                "==================================================================================="
+                                 "  This pipeline does not officially support multi-fasta genome files!\n\n" + 
+                                 "  The parameters and processes are tailored for viral genome analysis.\n" +
+                                 "  Please amend the '--fasta' parameter.\n" +
+                                 "==================================================================================="
                         break
                     }
                 }
@@ -254,13 +254,36 @@ class Workflow {
         }
         if (total != (left + right)) {
             log.warn "=============================================================================\n" +
-                    "  Please check the name field (column 4) in the file supplied via --primer_bed.\n\n" +
-                    "  All of the values in that column do not end with those supplied by:\n" +
-                    "      --primer_left_suffix : $primer_left_suffix\n" +
-                    "      --primer_right_suffix: $primer_right_suffix\n\n" +
-                    "  This information is required to collapse the primer intervals into amplicons\n" + 
-                    "  for the coverage plots generated by the pipeline.\n" +
-                    "==================================================================================="
+                     "  Please check the name field (column 4) in the file supplied via --primer_bed.\n\n" +
+                     "  All of the values in that column do not end with those supplied by:\n" +
+                     "      --primer_left_suffix : $primer_left_suffix\n" +
+                     "      --primer_right_suffix: $primer_right_suffix\n\n" +
+                     "  This information is required to collapse the primer intervals into amplicons\n" + 
+                     "  for the coverage plots generated by the pipeline.\n" +
+                     "==================================================================================="
+        }
+    }
+
+    // Check if the primer BED file supplied to the pipeline is from the SWIFT/SNAP protocol
+    public static void checkIfSwiftProtocol(primer_bed_file, name_prefix, log) {
+        def count = 0
+        def line  = null
+        primer_bed_file.withReader { reader ->
+            while (line = reader.readLine()) {
+                def name = line.split('\t')[3]
+                if (name.contains(name_prefix)) {
+                    count++
+                    if (count > 1) {
+                        log.warn "=============================================================================\n" +
+                                 "  Found '${name_prefix}' in the name field of the primer BED file!\n" + 
+                                 "  This suggests that you have used the SWIFT/SNAP protocol to prep your samples.\n" + 
+                                 "  If so, please set '--ivar_trim_offset 5' as suggested in the issue below:\n" +
+                                 "  https://github.com/nf-core/viralrecon/issues/170\n" +
+                                 "==================================================================================="
+                        break
+                    }
+                }
+            }
         }
     }
 

modules/nf-core/software/artic/guppyplex/functions.nf

@@ -0,0 +1,70 @@
+/*
+ * -----------------------------------------------------
+ *  Utility functions used in nf-core DSL2 module files
+ * -----------------------------------------------------
+ */
+
+/*
+ * Extract name of software tool from process name using $task.process
+ */
+def getSoftwareName(task_process) {
+    return task_process.tokenize(':')[-1].tokenize('_')[0].toLowerCase()
+}
+
+/*
+ * Function to initialise default values and to generate a Groovy Map of available options for nf-core modules
+ */
+def initOptions(Map args) {
+    def Map options = [:]
+    options.args            = args.args ?: ''
+    options.args2           = args.args2 ?: ''
+    options.args3           = args.args3 ?: ''
+    options.publish_by_meta = args.publish_by_meta ?: []
+    options.publish_dir     = args.publish_dir ?: ''
+    options.publish_files   = args.publish_files
+    options.suffix          = args.suffix ?: ''
+    return options
+}
+
+/*
+ * Tidy up and join elements of a list to return a path string
+ */
+def getPathFromList(path_list) {
+    def paths = path_list.findAll { item -> !item?.trim().isEmpty() }      // Remove empty entries
+    paths     = paths.collect { it.trim().replaceAll("^[/]+|[/]+\$", "") } // Trim whitespace and trailing slashes
+    return paths.join('/')
+}
+
+/*
+ * Function to save/publish module results
+ */
+def saveFiles(Map args) {
+    if (!args.filename.endsWith('.version.txt')) {
+        def ioptions  = initOptions(args.options)
+        def path_list = [ ioptions.publish_dir ?: args.publish_dir ]
+        if (ioptions.publish_by_meta) {
+            def key_list = ioptions.publish_by_meta instanceof List ? ioptions.publish_by_meta : args.publish_by_meta
+            for (key in key_list) {
+                if (args.meta && key instanceof String) {
+                    def path = key
+                    if (args.meta.containsKey(key)) {
+                        path = args.meta[key] instanceof Boolean ? "${key}_${args.meta[key]}".toString() : args.meta[key]
+                    }
+                    path = path instanceof String ? path : ''
+                    path_list.add(path)
+                }
+            }
+        }
+        if (ioptions.publish_files instanceof Map) {
+            for (ext in ioptions.publish_files) {
+                if (args.filename.endsWith(ext.key)) {
+                    def ext_list = path_list.collect()
+                    ext_list.add(ext.value)
+                    return "${getPathFromList(ext_list)}/$args.filename"
+                }
+            }
+        } else if (ioptions.publish_files == null) {
+            return "${getPathFromList(path_list)}/$args.filename"
+        }
+    }
+}

modules/local/artic_guppyplex.nf → modules/nf-core/software/artic/guppyplex/main.nf

@@ -20,7 +20,7 @@ process ARTIC_GUPPYPLEX {
 
     input:
     tuple val(meta), path(fastq_dir)
-    
+
     output:
     tuple val(meta), path("*.fastq.gz"), emit: fastq
     path  "*.version.txt"              , emit: version
@@ -34,9 +34,8 @@ process ARTIC_GUPPYPLEX {
         $options.args \\
         --directory $fastq_dir \\
         --output ${prefix}.fastq
-
-    pigz -p $task.cpus *.fastq
 
+    pigz -p $task.cpus *.fastq
     echo \$(artic --version 2>&1) | sed 's/^.*artic //; s/ .*\$//' > ${software}.version.txt
     """
 }

modules/nf-core/software/artic/guppyplex/meta.yml

@@ -0,0 +1,44 @@
+name: artic_guppyplex
+description: Aggregates fastq files with demultiplexed reads
+keywords:
+  - artic
+  - aggregate
+  - demultiplexed reads
+tools:
+  - artic:
+      description: ARTIC pipeline - a bioinformatics pipeline for working with virus sequencing data sequenced with nanopore
+      homepage: https://artic.readthedocs.io/en/latest/
+      documentation: https://artic.readthedocs.io/en/latest/
+      tool_dev_url: https://github.com/artic-network/fieldbioinformatics
+      doi: ""
+      licence: ['MIT']
+
+input:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test', single_end:false ]
+  - fastq_dir:
+      type: directory
+      description: Directory containing the fastq files with demultiplexed reads
+      pattern: "*"
+
+output:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test', single_end:false ]
+  - fastq:
+      type: file
+      description: Aggregated FastQ files
+      pattern: "*.{fastq.gz}"
+  - version:
+      type: file
+      description: File containing software version
+      pattern: "*.{version.txt}"
+
+authors:
+  - "@joseespinosa"
+  - "@drpatelh"

modules/nf-core/software/nanoplot/main.nf

@@ -11,11 +11,11 @@ process NANOPLOT {
         mode: params.publish_dir_mode,
         saveAs: { filename -> saveFiles(filename:filename, options:params.options, publish_dir:getSoftwareName(task.process), meta:meta, publish_by_meta:['id']) }
 
-    conda (params.enable_conda ? "bioconda::nanoplot=1.32.1" : null)
+    conda (params.enable_conda ? "bioconda::nanoplot=1.36.1" : null)
     if (workflow.containerEngine == 'singularity' && !params.singularity_pull_docker_container) {
-        container "https://depot.galaxyproject.org/singularity/nanoplot:1.32.1--py_0"
+        container "https://depot.galaxyproject.org/singularity/nanoplot:1.36.1--pyhdfd78af_0"
     } else {
-        container "quay.io/biocontainers/nanoplot:1.32.1--py_0"
+        container "quay.io/biocontainers/nanoplot:1.36.1--pyhdfd78af_0"
     }
 
     input:

modules/nf-core/software/nanoplot/meta.yml

@@ -26,7 +26,7 @@ input:
     - summary_txt:
         type: file
         description: |
-            List of sequenicng_summary.txt files from running basecalling.
+            List of sequencing_summary.txt files from running basecalling.
 output:
     - meta:
         type: map

nextflow.config

@@ -53,6 +53,7 @@ params {
   callers                      = 'ivar'
   min_mapped_reads             = 1000
   ivar_trim_noprimer           = false
+  ivar_trim_offset             = null
   filter_duplicates            = false
   primer_left_suffix           = '_LEFT'
   primer_right_suffix          = '_RIGHT'
@@ -205,6 +206,9 @@ profiles {
   test_full_nanopore { includeConfig 'conf/test_full_nanopore.config' }
 }
 
+// Increase time available to build Conda environment
+conda { createTimeout = "120 min" }
+
 // Export these variables to prevent local Python/R libraries from conflicting with those in the container
 env {
   PYTHONNOUSERSITE = 1

nextflow_schema.json

@@ -290,6 +290,12 @@
                     "description": "This option unsets the '-e' parameter in 'ivar trim' to discard reads without primers.",
                     "fa_icon": "fas fa-cut"
                 },
+                "ivar_trim_offset": {
+                    "type": "integer",
+                    "description": "This option sets the '-x' parameter in 'ivar trim' so that reads that occur at the specified offset positions relative to primer positions will also be trimmed.",
+                    "fa_icon": "fas fa-cut",
+                    "help_text": "This parameter will need to be set for some amplicon-based sequencing protocols (e.g. SWIFT) as described and implemented [here](https://github.com/andersen-lab/ivar/pull/88)"
+                },
                 "filter_duplicates": {
                     "type": "boolean",
                     "fa_icon": "fas fa-clone",

workflows/illumina.nf

@@ -95,6 +95,7 @@ if (!params.save_reference) {
 
 def ivar_trim_options   = modules['illumina_ivar_trim']
 ivar_trim_options.args += params.ivar_trim_noprimer ? '' : Utils.joinModuleArgs(['-e'])
+ivar_trim_options.args += params.ivar_trim_offset   ? Utils.joinModuleArgs(["-x ${params.ivar_trim_offset}"]) : ''
 
 def ivar_trim_sort_bam_options = modules['illumina_ivar_trim_sort_bam']
 if (params.skip_markduplicates) {
@@ -170,12 +171,20 @@ workflow ILLUMINA {
         .fasta
         .map { Workflow.isMultiFasta(it, log) }
 
-    // Check primer BED file only contains suffixes provided --primer_left_suffix / --primer_right_suffix
     if (params.protocol == 'amplicon' && !params.skip_variants) {
+        // Check primer BED file only contains suffixes provided --primer_left_suffix / --primer_right_suffix
         PREPARE_GENOME
             .out
             .primer_bed
             .map { Workflow.checkPrimerSuffixes(it, params.primer_left_suffix, params.primer_right_suffix, log) }
+
+        // Check if the primer BED file supplied to the pipeline is from the SWIFT/SNAP protocol
+        if (!params.ivar_trim_offset) {
+            PREPARE_GENOME
+                .out
+                .primer_bed
+                .map { Workflow.checkIfSwiftProtocol(it, 'covid19genome', log) }
+        }
     }
 
     /*

workflows/nanopore.nf

@@ -55,7 +55,6 @@ artic_minion_options.args += params.artic_minion_aligner == 'bwa'    ? Utils.joi
 def multiqc_options   = modules['nanopore_multiqc']
 multiqc_options.args += params.multiqc_title ? Utils.joinModuleArgs(["--title \"$params.multiqc_title\""]) : ''
 
-include { ARTIC_GUPPYPLEX       } from '../modules/local/artic_guppyplex'       addParams( options: modules['nanopore_artic_guppyplex'] )
 include { ARTIC_MINION          } from '../modules/local/artic_minion'          addParams( options: artic_minion_options                )
 include { GET_SOFTWARE_VERSIONS } from '../modules/local/get_software_versions' addParams( options: [publish_files: ['csv':'']]         )
 include { MULTIQC               } from '../modules/local/multiqc_nanopore'      addParams( options: multiqc_options                     )
@@ -89,13 +88,14 @@ include { SNPEFF_SNPSIFT } from '../subworkflows/local/snpeff_snpsift'
 /*
  * MODULE: Installed directly from nf-core/modules
  */
-include { PYCOQC                        } from '../modules/nf-core/software/pycoqc/main'         addParams( options: modules['nanopore_pycoqc']            )
-include { NANOPLOT                      } from '../modules/nf-core/software/nanoplot/main'       addParams( options: modules['nanopore_nanoplot']          )
-include { BCFTOOLS_STATS                } from '../modules/nf-core/software/bcftools/stats/main' addParams( options: modules['nanopore_bcftools_stats']    )
-include { QUAST                         } from '../modules/nf-core/software/quast/main'          addParams( options: modules['nanopore_quast']             )
-include { PANGOLIN                      } from '../modules/nf-core/software/pangolin/main'       addParams( options: modules['nanopore_pangolin']          )
-include { MOSDEPTH as MOSDEPTH_GENOME   } from '../modules/nf-core/software/mosdepth/main'       addParams( options: modules['nanopore_mosdepth_genome']   )
-include { MOSDEPTH as MOSDEPTH_AMPLICON } from '../modules/nf-core/software/mosdepth/main'       addParams( options: modules['nanopore_mosdepth_amplicon'] )
+include { PYCOQC                        } from '../modules/nf-core/software/pycoqc/main'          addParams( options: modules['nanopore_pycoqc']            )
+include { NANOPLOT                      } from '../modules/nf-core/software/nanoplot/main'        addParams( options: modules['nanopore_nanoplot']          )
+include { ARTIC_GUPPYPLEX               } from '../modules/nf-core/software/artic/guppyplex/main' addParams( options: modules['nanopore_artic_guppyplex']   )
+include { BCFTOOLS_STATS                } from '../modules/nf-core/software/bcftools/stats/main'  addParams( options: modules['nanopore_bcftools_stats']    )
+include { QUAST                         } from '../modules/nf-core/software/quast/main'           addParams( options: modules['nanopore_quast']             )
+include { PANGOLIN                      } from '../modules/nf-core/software/pangolin/main'        addParams( options: modules['nanopore_pangolin']          )
+include { MOSDEPTH as MOSDEPTH_GENOME   } from '../modules/nf-core/software/mosdepth/main'        addParams( options: modules['nanopore_mosdepth_genome']   )
+include { MOSDEPTH as MOSDEPTH_AMPLICON } from '../modules/nf-core/software/mosdepth/main'        addParams( options: modules['nanopore_mosdepth_amplicon'] )
 
 /*
  * SUBWORKFLOW: Consisting entirely of nf-core/modules