Merge pull request #104 from Daniel-VM/dev

Add module dragonflye for long-reads assembly

CHANGELOG.md

@@ -9,6 +9,8 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ### `Added`
 
+- [#104](https://github.com/nf-core/bacass/pull/104) - Added dragonflye module for long-reads assembly
+
 ### `Fixed`
 
 ### `Dependencies`

README.md

@@ -30,7 +30,9 @@ This pipeline is primarily for bacterial assembly of next-generation sequencing
 ### Long Read Assembly
 
 For users that only have Nanopore data, the pipeline quality trims these using [PoreChop](https://github.com/rrwick/Porechop) and assesses basic sequencing QC utilizing [NanoPlot](https://github.com/wdecoster/NanoPlot) and [PycoQC](https://github.com/a-slide/pycoQC).
-The pipeline can then perform long read assembly utilizing [Unicycler](https://github.com/rrwick/Unicycler), [Miniasm](https://github.com/lh3/miniasm) in combination with [Racon](https://github.com/isovic/racon), or [Canu](https://github.com/marbl/canu). Long reads assembly can be polished using [Medaka](https://github.com/nanoporetech/medaka) or [NanoPolish](https://github.com/jts/nanopolish) with Fast5 files.
+The pipeline can then perform long read assembly utilizing [Unicycler](https://github.com/rrwick/Unicycler), [Miniasm](https://github.com/lh3/miniasm) in combination with [Racon](https://github.com/isovic/racon), [Canu](https://github.com/marbl/canu) or [Flye](https://github.com/fenderglass/Flye) by using the [Dragonflye](https://github.com/rpetit3/dragonflye)(\*) pipeline. Long reads assembly can be polished using [Medaka](https://github.com/nanoporetech/medaka) or [NanoPolish](https://github.com/jts/nanopolish) with Fast5 files.
+
+> **\*Note**: Dragonflye is a comprehensive pipeline designed for genome assembly of Oxford Nanopore Reads. It facilitates the utilization of Flye (default), Miniasm, and Raven assemblers, along with Racon(default) and Medaka polishers. For more information, visit the [Dragonflye GitHub](https://github.com/rpetit3/dragonflye) repository.
 
 ### Hybrid Assembly
 

assets/schema_input.json

@@ -73,6 +73,7 @@
             },
             "GenomeSize": {
                 "errorMessage": "A number (including decimals) ending with 'm', representing genome size. No spaces allowed.",
+                "meta": ["gsize"],
                 "anyOf": [
                     {
                         "type": ["string", "null"],

conf/modules.config

@@ -94,6 +94,33 @@ process {
         ]
     }
 
+    withName: 'DRAGONFLYE' {
+        ext.args = {
+            if ( !$meta.gsize?.equals('NA') ){
+                if ( !params.dragonflye_args.contains("--gsize") ) {
+                    "--gsize ${meta.gsize} ${params.dragonflye_args}"
+                } else {
+                    params.dragonflye_args ?: ''
+                }
+            } else {
+                params.dragonflye_args ?: ''
+            }
+        }
+
+        publishDir = [
+            path: { "${params.outdir}/Dragonflye" },
+            mode: params.publish_dir_mode,
+            pattern: "*.{fa,log}",
+            saveAs: { filename ->
+                if (filename.equals('versions.yml')) {
+                    null
+                } else {
+                    "${meta.id}.${filename}"
+                }
+            }
+        ]
+    }
+
     withName: 'RACON' {
         ext.args = ''
         publishDir = [

conf/test_long_dragonflye.config

@@ -0,0 +1,26 @@
+/*
+========================================================================================
+    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/bacass -profile test_long_dragonflye,<docker/singularity>
+
+----------------------------------------------------------------------------------------
+*/
+
+params {
+    config_profile_name        = 'Test_long_dragonfyle profile'
+    config_profile_description = 'Minimal test dataset to check pipeline function'
+
+    // Input data
+    input = 'https://raw.githubusercontent.com/nf-core/test-datasets/bacass/bacass_long_miniasm.tsv'
+
+    // some extra args to speed tests up
+    prokka_args = " --fast"
+    assembly_type = 'long'
+    assembler = 'dragonflye'
+    skip_kraken2 = true
+    skip_polish = true
+}

docs/output.md

@@ -146,6 +146,12 @@ Check out the [Canu documentation](https://canu.readthedocs.io/en/latest/index.h
 
 Check out the [Miniasm documentation](https://github.com/lh3/miniasm) for more information on Miniasm output.
 
+- `Dragonflye/`
+  - `*.contigs.fa`: Assembly in Fasta format
+  - `*.dragonflye.log`: Log file containing the report of the dragonflye process
+
+Checkout the [Dragonflye](https://github.com/rpetit3/dragonflye) documentation for more information of the Dragonflye output.
+
 </details>
 
 ### Polished assemblies

modules.json

@@ -25,6 +25,11 @@
                         "git_sha": "05c280924b6c768d484c7c443dad5e605c4ff4b4",
                         "installed_by": ["modules"]
                     },
+                    "dragonflye": {
+                        "branch": "master",
+                        "git_sha": "516189e968feb4ebdd9921806988b4c12b4ac2dc",
+                        "installed_by": ["modules"]
+                    },
                     "fastp": {
                         "branch": "master",
                         "git_sha": "d497a4868ace3302016ea8ed4b395072d5e833cd",

nextflow.config

@@ -20,11 +20,12 @@ params {
     kraken2db                       = ""
 
     // Assembly parameters
-    assembler                       = 'unicycler'   // Allowed: ['unicycler', 'canu', 'miniasm']
+    assembler                       = 'unicycler'   // Allowed: ['unicycler', 'canu', 'miniasm', 'dragonflye']
     assembly_type                   = 'short'       // Allowed: ['short', 'long', 'hybrid'] (hybrid works only with Unicycler)
     unicycler_args                  = ""
     canu_mode                       = '-nanopore'   // Allowed: ['-pacbio', '-nanopore', '-pacbio-hifi']
     canu_args                       = ''            // Default no extra options, can be adjusted by the user
+    dragonflye_args                 = ''
 
     // Assembly polishing
     polish_method                   = 'medaka'
@@ -195,12 +196,13 @@ profiles {
         executor.cpus          = 4
         executor.memory        = 8.GB
     }
-    test              { includeConfig 'conf/test.config'              }
-    test_dfast        { includeConfig 'conf/test_dfast.config'        }
-    test_hybrid       { includeConfig 'conf/test_hybrid.config'       }
-    test_long         { includeConfig 'conf/test_long.config'         }
-    test_long_miniasm { includeConfig 'conf/test_long_miniasm.config' }
-    test_full         { includeConfig 'conf/test_full.config'         }
+    test                { includeConfig 'conf/test.config'                  }
+    test_dfast          { includeConfig 'conf/test_dfast.config'            }
+    test_hybrid         { includeConfig 'conf/test_hybrid.config'           }
+    test_long           { includeConfig 'conf/test_long.config'             }
+    test_long_miniasm   { includeConfig 'conf/test_long_miniasm.config'     }
+    test_long_dragonflye{ includeConfig 'conf/test_long_dragonflye.config'  }
+    test_full           { includeConfig 'conf/test_full.config'             }
 }
 
 // Set default registry for Apptainer, Docker, Podman and Singularity independent of -profile