Gecco convert

CHANGELOG.md

@@ -9,6 +9,7 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 - [#500](https://github.com/nf-core/funcscan/pull/500) Updated pipeline template to nf-core/tools version 3.4.1 (by @jfy133)
 - [#508](https://github.com/nf-core/funcscan/pull/508) Added support for antiSMASH's --clusterhmmer, --fullhmmer, and --tigrfam options (❤️ to @yusukepockyby for requesting, @jfy133)
+- [#506](https://github.com/nf-core/funcscan/pull/506) Added support GECCO convert for generation of additional files useful for downstream analysis (by @SkyLexS)
 
 ### `Fixed`
 

README.md

@@ -92,7 +92,7 @@ nf-core/funcscan was originally written by Jasmin Frangenberg, Anan Ibrahim, Lou
 
 We thank the following people for their extensive assistance in the development of this pipeline:
 
-Adam Talbot, Alexandru Mizeranschi, Hugo Tavares, Júlia Mir Pedrol, Martin Klapper, Mehrdad Jaberi, Robert Syme, Rosa Herbst, Vedanth Ramji, @Microbion.
+Adam Talbot, Alexandru Mizeranschi, Hugo Tavares, Júlia Mir Pedrol, Martin Klapper, Mehrdad Jaberi, Robert Syme, Rosa Herbst, Vedanth Ramji, @Microbion, Dediu Octavian-Codrin.
 
 ## Contributions and Support
 

conf/modules.config

@@ -532,6 +532,14 @@ process {
         ].join(' ').trim()
     }
 
+    withName: GECCO_CONVERT {
+        publishDir = [
+            path: { "${params.outdir}/bgc/gecco/${meta.id}" },
+            mode: params.publish_dir_mode,
+            saveAs: { filename -> filename.equals('versions.yml') ? null : filename },
+        ]
+    }
+
     withName: HAMRONIZATION_ABRICATE {
         publishDir = [
             path: { "${params.outdir}/arg/hamronization/abricate" },

conf/test_bgc_bakta.config

@@ -23,7 +23,7 @@ params {
     config_profile_description       = 'Minimal test dataset to check BGC workflow function'
 
     // Input data
-    input                            = params.pipelines_testdata_base_path + 'funcscan/samplesheet_reduced.csv'
+    input                            = params.pipelines_testdata_base_path + 'funcscan/samplesheet_hits.csv'
     bgc_antismash_db                 = params.pipelines_testdata_base_path + 'funcscan/databases/antismash_trimmed_8_0_1.tar.gz'
 
     annotation_tool                  = 'bakta'
@@ -33,6 +33,10 @@ params {
     run_amp_screening                = false
     run_bgc_screening                = true
 
+    bgc_gecco_runconvert             = true
+    bgc_gecco_convertmode            = 'gbk'
+    bgc_gecco_convertformat          = 'bigslice'
+
     bgc_run_hmmsearch                = true
     bgc_hmmsearch_models             = 'https://raw.githubusercontent.com/antismash/antismash/fd61de057e082fbf071732ac64b8b2e8883de32f/antismash/detection/hmm_detection/data/ToyB.hmm'
 }

conf/test_bgc_prokka.config

@@ -23,7 +23,7 @@ params {
     config_profile_description = 'Minimal test dataset to check BGC workflow function'
 
     // Input data
-    input                      = params.pipelines_testdata_base_path + 'funcscan/samplesheet_reduced.csv'
+    input                      = params.pipelines_testdata_base_path + 'funcscan/samplesheet_hits.csv'
     bgc_antismash_db           = params.pipelines_testdata_base_path + 'funcscan/databases/antismash_trimmed_8_0_1.tar.gz'
 
     annotation_tool            = 'prokka'
@@ -32,6 +32,10 @@ params {
     run_amp_screening          = false
     run_bgc_screening          = true
 
+    bgc_gecco_runconvert       = true
+    bgc_gecco_convertmode      = 'gbk'
+    bgc_gecco_convertformat    = 'fna'
+
     bgc_run_hmmsearch          = true
     bgc_hmmsearch_models       = 'https://raw.githubusercontent.com/antismash/antismash/fd61de057e082fbf071732ac64b8b2e8883de32f/antismash/detection/hmm_detection/data/ToyB.hmm'
 }

conf/test_bgc_pyrodigal.config

@@ -23,7 +23,7 @@ params {
     config_profile_description = 'Minimal test dataset to check BGC workflow function'
 
     // Input data
-    input                      = params.pipelines_testdata_base_path + 'funcscan/samplesheet_reduced.csv'
+    input                      = params.pipelines_testdata_base_path + 'funcscan/samplesheet_hits.csv'
     bgc_antismash_db           = params.pipelines_testdata_base_path + 'funcscan/databases/antismash_trimmed_8_0_1.tar.gz'
 
     annotation_tool            = 'pyrodigal'
@@ -32,6 +32,10 @@ params {
     run_amp_screening          = false
     run_bgc_screening          = true
 
+    bgc_gecco_runconvert       = true
+    bgc_gecco_convertmode      = 'clusters'
+    bgc_gecco_convertformat    = 'gff'
+
     bgc_run_hmmsearch          = true
     bgc_hmmsearch_models       = 'https://raw.githubusercontent.com/antismash/antismash/fd61de057e082fbf071732ac64b8b2e8883de32f/antismash/detection/hmm_detection/data/ToyB.hmm'
 }

conf/test_preannotated_bgc.config

@@ -32,6 +32,8 @@ params {
     run_amp_screening          = false
     run_bgc_screening          = true
 
+    bgc_gecco_runconvert       = true
+
     bgc_run_hmmsearch          = true
     bgc_hmmsearch_models       = 'https://raw.githubusercontent.com/antismash/antismash/fd61de057e082fbf071732ac64b8b2e8883de32f/antismash/detection/hmm_detection/data/ToyB.hmm'
 }

docs/output.md

@@ -457,15 +457,21 @@ Note that filtered FASTA is only used for BGC workflow for run-time optimisation
 <summary>Output files</summary>
 
 - `gecco/`
+  - **GECCO**
   - `*.genes.tsv/`: TSV file containing detected/predicted genes with BGC probability scores
   - `*.features.tsv`: TSV file containing identified domains
   - `*.clusters.tsv`: TSV file containing coordinates of predicted clusters and BGC types
   - `*_cluster_*.gbk`: GenBank file (if clusters were found) containing sequence with annotations; one file per GECCO hit
-
-</details>
+  - `*.gff`: GFF3 converted cluster tables containing the position and metadata for all the predicted clusters (only if `--bgc_gecco_runconvert --bgc_gecco_convertmode clusters --bgc_gecco_convertformat gff`)
+  - `*.region*.gbk`: Converted and aliased GenBank files so that they can be loaded by BiG-SLiCE (only if `--bgc_gecco_runconvert --bgc_gecco_convertmode gbk --bgc_gecco_convertformat bigslice`)
+  - `*.faa`: Amino-acid FASTA converted GenBank files of all the proteins in a cluster (only if `--bgc_gecco_runconvert --bgc_gecco_convertmode gbk --bgc_gecco_convertformat faa`)
+  - `*.fna`:Nucleotide sequence FASTA converted GenBank files from the cluster (only if `--bgc_gecco_runconvert --bgc_gecco_convertmode gbk --bgc_gecco_convertformat fna`)
+  </details>
 
 [GECCO](https://gecco.embl.de) is a fast and scalable method for identifying putative novel Biosynthetic Gene Clusters (BGCs) in genomic and metagenomic data using Conditional Random Fields (CRFs).
 
+The additional GFF3, GenBank, or FASTA files from `--bgc_gecco_runconvert`, can be useful for additional further analysis of the BGC hits.
+
 ### Summary tools
 
 [AMPcombi](#ampcombi), [hAMRonization](#hamronization), [comBGC](#combgc), [MultiQC](#multiqc), [pipeline information](#pipeline-information), [argNorm](#argnorm).