Merge pull request #106 from Daniel-VM/dev

Revamping Dragonflye: Introducing Hybrid Mode & Patch Updates

.github/workflows/ci.yml

@@ -52,7 +52,7 @@ jobs:
     strategy:
       matrix:
         # Run remaining test profiles with minimum nextflow version
-        profile: [test_long_miniasm, test_hybrid, test_long, test_dfast]
+        profile: [test_long_miniasm, test_hybrid, test_long, test_dfast, test_hybrid_dragonflye]
     steps:
       - name: Check out pipeline code
         uses: actions/checkout@v2

CHANGELOG.md

@@ -9,7 +9,7 @@ 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
+- [#104](https://github.com/nf-core/bacass/pull/104), [#106](https://github.com/nf-core/bacass/pull/106) - Added dragonflye module and enbled draft genome polishing with short-reads.
 
 ### `Fixed`
 

README.md

@@ -36,7 +36,7 @@ The pipeline can then perform long read assembly utilizing [Unicycler](https://g
 
 ### Hybrid Assembly
 
-For users specifying both short read and long read (NanoPore) data, the pipeline can perform a hybrid assembly approach utilizing [Unicycler](https://github.com/rrwick/Unicycler), taking the full set of information from short reads and long reads into account.
+For users specifying both short read and long read (NanoPore) data, the pipeline can perform a hybrid assembly approach utilizing [Unicycler](https://github.com/rrwick/Unicycler) (short read assembly followed by gap closing with long reads) or [Dragonflye](https://github.com/rpetit3/dragonflye) (long read assembly followed by polishing with short reads), taking the full set of information from short reads and long reads into account.
 
 ### Assembly QC and annotation
 

conf/modules.config

@@ -33,6 +33,7 @@ process {
 
     withName: 'PORECHOP_PORECHOP' {
         ext.args = ''
+        ext.prefix = { "${meta.id}.porechop" }
         publishDir = [
             path: { "${params.outdir}/trimming/longreads" },
             mode: params.publish_dir_mode,
@@ -96,7 +97,7 @@ process {
 
     withName: 'DRAGONFLYE' {
         ext.args = {
-            if ( !$meta.gsize?.equals('NA') ){
+            if ( meta.gsize && !meta.gsize.equals('NA') ){
                 if ( !params.dragonflye_args.contains("--gsize") ) {
                     "--gsize ${meta.gsize} ${params.dragonflye_args}"
                 } else {
@@ -106,16 +107,17 @@ process {
                 params.dragonflye_args ?: ''
             }
         }
-
         publishDir = [
             path: { "${params.outdir}/Dragonflye" },
             mode: params.publish_dir_mode,
             pattern: "*.{fa,log}",
             saveAs: { filename ->
                 if (filename.equals('versions.yml')) {
                     null
-                } else {
+                } else if (filename.endsWith('.log')) {
                     "${meta.id}.${filename}"
+                } else {
+                    filename
                 }
             }
         ]

conf/test_hybrid_dragonflye.config

@@ -0,0 +1,30 @@
+/*
+========================================================================================
+    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_hybrid_dragonflye,<docker/singularity>
+
+----------------------------------------------------------------------------------------
+*/
+
+params {
+    config_profile_name        = 'Test hybrid-dragonflye profile'
+    config_profile_description = 'Minimal test dataset to check pipeline function'
+
+    // Limit resources so that this can run on GitHub Actions
+    max_cpus   = 2
+    max_memory = 6.GB
+    max_time   = 6.h
+
+    // Input data
+    input = 'https://raw.githubusercontent.com/nf-core/test-datasets/bacass/bacass_hybrid_dragonflye.tsv'
+
+    // some extra args to speed tests up
+    assembly_type='hybrid'
+    assembler='dragonflye'
+    prokka_args=" --fast"
+    skip_kraken2 = true
+}

modules.json

@@ -28,7 +28,8 @@
                     "dragonflye": {
                         "branch": "master",
                         "git_sha": "516189e968feb4ebdd9921806988b4c12b4ac2dc",
-                        "installed_by": ["modules"]
+                        "installed_by": ["modules"],
+                        "patch": "modules/nf-core/dragonflye/dragonflye.diff"
                     },
                     "fastp": {
                         "branch": "master",

nextflow.config

@@ -196,13 +196,14 @@ 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_long_dragonflye{ includeConfig 'conf/test_long_dragonflye.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_hybrid_dragonflye  { includeConfig 'conf/test_hybrid_dragonflye.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

workflows/bacass.nf

@@ -226,7 +226,7 @@ workflow BACASS {
     ch_assembly = Channel.empty()
 
     //
-    // MODULE: Unicycler, genome assembly, nf-core module allows only short assembly
+    // MODULE: Unicycler, genome assembly, nf-core module allows only short, long and hybrid assembly
     //
     if ( params.assembler == 'unicycler' ) {
         UNICYCLER (
@@ -236,6 +236,7 @@ workflow BACASS {
         ch_versions = ch_versions.mix( UNICYCLER.out.versions.ifEmpty(null) )
     }
 
+
     //
     // MODULE: Canu, genome assembly, long reads
     //
@@ -294,11 +295,11 @@ workflow BACASS {
     }
 
     //
-    // MODULE: Dragonflye, genome assembly, long reads
+    // MODULE: Dragonflye, genome assembly of long reads. Moreover, it provides the option for polishing the draft genome using short reads when both short and long reads are available.
     //
     if( params.assembler == 'dragonflye' ){
         DRAGONFLYE(
-            ch_for_assembly.map { meta, sr, lr -> tuple(meta, lr) }
+            ch_for_assembly
         )
         ch_assembly = ch_assembly.mix( DRAGONFLYE.out.contigs.dump(tag: 'dragonflye') )
         ch_versions = ch_versions.mix( DRAGONFLYE.out.versions.ifEmpty(null) )