diff --git a/CHANGELOG.md b/CHANGELOG.md
index 005fc005..abafaa47 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -24,6 +24,7 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
- [#437](https://github.com/nf-core/funcscan/pull/437) Fixed file name error when supplying already preprocessed CARD database for ARG workflow. (by @jasmezz)
- [#446](https://github.com/nf-core/funcscan/pull/446) Updated antiSMASH modules to fix apptainer execution. (by @jasmezz and @jfy133)
- [#448](https://github.com/nf-core/funcscan/pull/448) Fixed taxonomy merge to work with output from GTDB/SILVA/KALAMARI. (by @darcy220606)
+- [#447](https://github.com/nf-core/funcscan/pull/447) Added `--annotation_pyrodigal_usespecialstopcharacter` parameter to improve AMPlify screening. (by @jasmezz)
### `Dependencies`
diff --git a/conf/modules.config b/conf/modules.config
index 5684b042..a348da3c 100644
--- a/conf/modules.config
+++ b/conf/modules.config
@@ -201,6 +201,7 @@ process {
params.annotation_pyrodigal_singlemode ? "-p single" : "-p meta",
params.annotation_pyrodigal_closed ? "-c" : "",
params.annotation_pyrodigal_forcenonsd ? "-n" : "",
+ params.annotation_pyrodigal_usespecialstopcharacter ? '' : '--no-stop-codon',
"-g ${params.annotation_pyrodigal_transtable}",
].join(' ').trim()
}
diff --git a/nextflow.config b/nextflow.config
index 12283ffd..ae6b0038 100644
--- a/nextflow.config
+++ b/nextflow.config
@@ -66,6 +66,7 @@ params {
annotation_pyrodigal_closed = false
annotation_pyrodigal_transtable = 11
annotation_pyrodigal_forcenonsd = false
+ annotation_pyrodigal_usespecialstopcharacter = false
annotation_bakta_db = null
annotation_bakta_db_downloadtype = 'full'
diff --git a/nextflow_schema.json b/nextflow_schema.json
index 46323109..8fc059f9 100644
--- a/nextflow_schema.json
+++ b/nextflow_schema.json
@@ -518,6 +518,13 @@
"fa_icon": "fas fa-barcode",
"description": "Forces Pyrodigal to scan for motifs.",
"help_text": "Forces Pyrodigal to a full scan for motifs rather than activating the Shine-Dalgarno RBS finder, the default scanner for Pyrodigal to train for motifs.\n\nFor more information check the Pyrodigal [documentation](https://pyrodigal.readthedocs.io).\n\n> Modifies tool parameter(s):\n> - PYRODIGAL: `-n`"
+ },
+ "annotation_pyrodigal_usespecialstopcharacter": {
+ "type": "boolean",
+ "fa_icon": "fa fa-star-of-life",
+ "description": "This forces Pyrodigal to append asterisks (`*`) as stop codon indicators. Do not use when running AMP workflow.",
+ "help_text": "Some downstream tools like AMPlify cannot process sequences containing non-sequence characters like the stop codon indicator `*`. Thus, this flag is deactivated by default. Activate this flag to revert the behaviour and have Pyrodigal append `*` as stop codon indicator to annotated sequences.\n\nFor more information check the Pyrodigal [documentation](https://pyrodigal.readthedocs.io).\n\n> Modifies tool parameter(s):\n> - PYRODIGAL: `--no-stop-codon`",
+ "default": false
}
},
"fa_icon": "fas fa-file-signature"
diff --git a/ro-crate-metadata.json b/ro-crate-metadata.json
index 7f40a7cd..63577086 100644
--- a/ro-crate-metadata.json
+++ b/ro-crate-metadata.json
@@ -22,8 +22,8 @@
"@id": "./",
"@type": "Dataset",
"creativeWorkStatus": "InProgress",
- "datePublished": "2025-01-27T14:45:55+00:00",
- "description": "
\n \n \n \n \n
\n\n[](https://github.com/nf-core/funcscan/actions/workflows/ci.yml)\n[](https://github.com/nf-core/funcscan/actions/workflows/linting.yml)[](https://nf-co.re/funcscan/results)[](https://doi.org/10.5281/zenodo.XXXXXXX)\n[](https://www.nf-test.com)\n\n[](https://www.nextflow.io/)\n[](https://docs.conda.io/en/latest/)\n[](https://www.docker.com/)\n[](https://sylabs.io/docs/)\n[](https://cloud.seqera.io/launch?pipeline=https://github.com/nf-core/funcscan)\n\n[](https://nfcore.slack.com/channels/funcscan)[](https://twitter.com/nf_core)[](https://mstdn.science/@nf_core)[](https://www.youtube.com/c/nf-core)\n\n## Introduction\n\n**nf-core/funcscan** is a bioinformatics pipeline that ...\n\n\n\n\n2. Present QC for raw reads ([`MultiQC`](http://multiqc.info/))\n\n## Usage\n\n> [!NOTE]\n> If you are new to Nextflow and nf-core, please refer to [this page](https://nf-co.re/docs/usage/installation) on how to set-up Nextflow. Make sure to [test your setup](https://nf-co.re/docs/usage/introduction#how-to-run-a-pipeline) with `-profile test` before running the workflow on actual data.\n\n\n\nNow, you can run the pipeline using:\n\n\n\n```bash\nnextflow run nf-core/funcscan \\\n -profile \\\n --input samplesheet.csv \\\n --outdir \n```\n\n> [!WARNING]\n> Please provide pipeline parameters via the CLI or Nextflow `-params-file` option. Custom config files including those provided by the `-c` Nextflow option can be used to provide any configuration _**except for parameters**_; see [docs](https://nf-co.re/docs/usage/getting_started/configuration#custom-configuration-files).\n\nFor more details and further functionality, please refer to the [usage documentation](https://nf-co.re/funcscan/usage) and the [parameter documentation](https://nf-co.re/funcscan/parameters).\n\n## Pipeline output\n\nTo see the results of an example test run with a full size dataset refer to the [results](https://nf-co.re/funcscan/results) tab on the nf-core website pipeline page.\nFor more details about the output files and reports, please refer to the\n[output documentation](https://nf-co.re/funcscan/output).\n\n## Credits\n\nnf-core/funcscan was originally written by Jasmin Frangenberg, Anan Ibrahim, Louisa Perelo, Moritz E. Beber, James A. Fellows Yates.\n\nWe thank the following people for their extensive assistance in the development of this pipeline:\n\n\n\n## Contributions and Support\n\nIf you would like to contribute to this pipeline, please see the [contributing guidelines](.github/CONTRIBUTING.md).\n\nFor further information or help, don't hesitate to get in touch on the [Slack `#funcscan` channel](https://nfcore.slack.com/channels/funcscan) (you can join with [this invite](https://nf-co.re/join/slack)).\n\n## Citations\n\n\n\n\n\n\nAn extensive list of references for the tools used by the pipeline can be found in the [`CITATIONS.md`](CITATIONS.md) file.\n\nYou can cite the `nf-core` publication as follows:\n\n> **The nf-core framework for community-curated bioinformatics pipelines.**\n>\n> Philip Ewels, Alexander Peltzer, Sven Fillinger, Harshil Patel, Johannes Alneberg, Andreas Wilm, Maxime Ulysse Garcia, Paolo Di Tommaso & Sven Nahnsen.\n>\n> _Nat Biotechnol._ 2020 Feb 13. doi: [10.1038/s41587-020-0439-x](https://dx.doi.org/10.1038/s41587-020-0439-x).\n",
+ "datePublished": "2025-02-05T10:21:25+00:00",
+ "description": "
\n \n \n \n \n
\n\n[](https://github.com/nf-core/funcscan/actions/workflows/ci.yml)\n[](https://github.com/nf-core/funcscan/actions/workflows/linting.yml)[](https://nf-co.re/funcscan/results)[](https://doi.org/10.5281/zenodo.7643099)\n[](https://www.nf-test.com)\n\n[](https://www.nextflow.io/)\n[](https://docs.conda.io/en/latest/)\n[](https://www.docker.com/)\n[](https://sylabs.io/docs/)\n[](https://cloud.seqera.io/launch?pipeline=https://github.com/nf-core/funcscan)\n\n[](https://nfcore.slack.com/channels/funcscan)[](https://twitter.com/nf_core)[](https://mstdn.science/@nf_core)[](https://www.youtube.com/c/nf-core)\n\n## Introduction\n\n**nf-core/funcscan** is a bioinformatics best-practice analysis pipeline for the screening of nucleotide sequences such as assembled contigs for functional genes. It currently features mining for antimicrobial peptides, antibiotic resistance genes and biosynthetic gene clusters.\n\nThe pipeline is built using [Nextflow](https://www.nextflow.io), a workflow tool to run tasks across multiple compute infrastructures in a very portable manner. It uses Docker/Singularity containers making installation trivial and results highly reproducible. The [Nextflow DSL2](https://www.nextflow.io/docs/latest/dsl2.html) implementation of this pipeline uses one container per process which makes it much easier to maintain and update software dependencies. Where possible, these processes have been submitted to and installed from [nf-core/modules](https://github.com/nf-core/modules) in order to make them available to all nf-core pipelines, and to everyone within the Nextflow community!\n\nOn release, automated continuous integration tests run the pipeline on a full-sized dataset on the AWS cloud infrastructure. This ensures that the pipeline runs on AWS, has sensible resource allocation defaults set to run on real-world datasets, and permits the persistent storage of results to benchmark between pipeline releases and other analysis sources. The results obtained from the full-sized test can be viewed on the [nf-core website](https://nf-co.re/funcscan/results).\n\nThe nf-core/funcscan AWS full test dataset are contigs generated by the MGnify service from the ENA. We used contigs generated from assemblies of chicken cecum shotgun metagenomes (study accession: MGYS00005631).\n\n## Pipeline summary\n\n1. Quality control of input sequences with [`SeqKit`](https://bioinf.shenwei.me/seqkit/)\n2. Taxonomic classification of contigs of **prokaryotic origin** with [`MMseqs2`](https://github.com/soedinglab/MMseqs2)\n3. Annotation of assembled prokaryotic contigs with [`Prodigal`](https://github.com/hyattpd/Prodigal), [`Pyrodigal`](https://github.com/althonos/pyrodigal), [`Prokka`](https://github.com/tseemann/prokka), or [`Bakta`](https://github.com/oschwengers/bakta)\n4. Screening contigs for antimicrobial peptide-like sequences with [`ampir`](https://cran.r-project.org/web/packages/ampir/index.html), [`Macrel`](https://github.com/BigDataBiology/macrel), [`HMMER`](http://hmmer.org/), [`AMPlify`](https://github.com/bcgsc/AMPlify)\n5. Screening contigs for antibiotic resistant gene-like sequences with [`ABRicate`](https://github.com/tseemann/abricate), [`AMRFinderPlus`](https://github.com/ncbi/amr), [`fARGene`](https://github.com/fannyhb/fargene), [`RGI`](https://card.mcmaster.ca/analyze/rgi), [`DeepARG`](https://bench.cs.vt.edu/deeparg). [`argNorm`](https://github.com/BigDataBiology/argNorm) is used to map the outputs of `DeepARG`, `AMRFinderPlus`, and `ABRicate` to the [`Antibiotic Resistance Ontology`](https://www.ebi.ac.uk/ols4/ontologies/aro) for consistent ARG classification terms.\n6. Screening contigs for biosynthetic gene cluster-like sequences with [`antiSMASH`](https://antismash.secondarymetabolites.org), [`DeepBGC`](https://github.com/Merck/deepbgc), [`GECCO`](https://gecco.embl.de/), [`HMMER`](http://hmmer.org/)\n7. Creating aggregated reports for all samples across the workflows with [`AMPcombi`](https://github.com/Darcy220606/AMPcombi) for AMPs, [`hAMRonization`](https://github.com/pha4ge/hAMRonization) for ARGs, and [`comBGC`](https://raw.githubusercontent.com/nf-core/funcscan/master/bin/comBGC.py) for BGCs\n8. Software version and methods text reporting with [`MultiQC`](http://multiqc.info/)\n\n\n\n## Usage\n\n> [!NOTE]\n> If you are new to Nextflow and nf-core, please refer to [this page](https://nf-co.re/docs/usage/installation) on how to set-up Nextflow. Make sure to [test your setup](https://nf-co.re/docs/usage/introduction#how-to-run-a-pipeline) with `-profile test` before running the workflow on actual data.\n\nFirst, prepare a samplesheet with your input data that looks as follows:\n\n`samplesheet.csv`:\n\n```csv\nsample,fasta\nCONTROL_REP1,AEG588A1_001.fasta\nCONTROL_REP2,AEG588A1_002.fasta\nCONTROL_REP3,AEG588A1_003.fasta\n```\n\nEach row represents a (multi-)fasta file of assembled contig sequences.\n\nNow, you can run the pipeline using:\n\n```bash\nnextflow run nf-core/funcscan \\\n -profile \\\n --input samplesheet.csv \\\n --outdir \\\n --run_amp_screening \\\n --run_arg_screening \\\n --run_bgc_screening\n```\n\n> [!WARNING]\n> Please provide pipeline parameters via the CLI or Nextflow `-params-file` option. Custom config files including those provided by the `-c` Nextflow option can be used to provide any configuration _**except for parameters**_; see [docs](https://nf-co.re/docs/usage/getting_started/configuration#custom-configuration-files).\n\nFor more details and further functionality, please refer to the [usage documentation](https://nf-co.re/funcscan/usage) and the [parameter documentation](https://nf-co.re/funcscan/parameters).\n\n## Pipeline output\n\nTo see the results of an example test run with a full size dataset refer to the [results](https://nf-co.re/funcscan/results) tab on the nf-core website pipeline page.\nFor more details about the output files and reports, please refer to the\n[output documentation](https://nf-co.re/funcscan/output).\n\n## Credits\n\nnf-core/funcscan was originally written by Jasmin Frangenberg, Anan Ibrahim, Louisa Perelo, Moritz E. Beber, James A. Fellows Yates.\n\nWe thank the following people for their extensive assistance in the development of this pipeline:\n\nAdam Talbot, Alexandru Mizeranschi, Hugo Tavares, J\u00falia Mir Pedrol, Martin Klapper, Mehrdad Jaberi, Robert Syme, Rosa Herbst, Vedanth Ramji, @Microbion.\n\n## Contributions and Support\n\nIf you would like to contribute to this pipeline, please see the [contributing guidelines](.github/CONTRIBUTING.md).\n\nFor further information or help, don't hesitate to get in touch on the [Slack `#funcscan` channel](https://nfcore.slack.com/channels/funcscan) (you can join with [this invite](https://nf-co.re/join/slack)).\n\n## Citations\n\nIf you use nf-core/funcscan for your analysis, please cite it using the following doi: [10.5281/zenodo.7643099](https://doi.org/10.5281/zenodo.7643099)\n\nAn extensive list of references for the tools used by the pipeline can be found in the [`CITATIONS.md`](CITATIONS.md) file.\n\nYou can cite the `nf-core` publication as follows:\n\n> **The nf-core framework for community-curated bioinformatics pipelines.**\n>\n> Philip Ewels, Alexander Peltzer, Sven Fillinger, Harshil Patel, Johannes Alneberg, Andreas Wilm, Maxime Ulysse Garcia, Paolo Di Tommaso & Sven Nahnsen.\n>\n> _Nat Biotechnol._ 2020 Feb 13. doi: [10.1038/s41587-020-0439-x](https://dx.doi.org/10.1038/s41587-020-0439-x).\n",
"hasPart": [
{
"@id": "main.nf"
@@ -31,6 +31,9 @@
{
"@id": "assets/"
},
+ {
+ "@id": "bin/"
+ },
{
"@id": "conf/"
},
@@ -43,6 +46,9 @@
{
"@id": "modules/"
},
+ {
+ "@id": "modules/local/"
+ },
{
"@id": "modules/nf-core/"
},
@@ -99,7 +105,7 @@
},
"mentions": [
{
- "@id": "#a63ff768-a32a-4ee1-8ba3-fafeb18a6793"
+ "@id": "#1f9be113-27d3-4dcb-b12a-d0c1a16703bf"
}
],
"name": "nf-core/funcscan"
@@ -121,14 +127,24 @@
},
{
"@id": "main.nf",
- "@type": ["File", "SoftwareSourceCode", "ComputationalWorkflow"],
+ "@type": [
+ "File",
+ "SoftwareSourceCode",
+ "ComputationalWorkflow"
+ ],
"creator": [
{
"@id": "#jfy133@gmail.com"
+ },
+ {
+ "@id": "#jfy133@gmail.com"
+ },
+ {
+ "@id": "https://orcid.org/0009-0004-5961-4709"
}
],
"dateCreated": "",
- "dateModified": "2025-01-27T14:45:55Z",
+ "dateModified": "2025-02-05T11:21:25Z",
"dct:conformsTo": "https://bioschemas.org/profiles/ComputationalWorkflow/1.0-RELEASE/",
"keywords": [
"nf-core",
@@ -149,17 +165,33 @@
"screening",
"secondary-metabolites"
],
- "license": ["MIT"],
- "name": ["nf-core/funcscan"],
+ "license": [
+ "MIT"
+ ],
+ "maintainer": [
+ {
+ "@id": "#jfy133@gmail.com"
+ },
+ {
+ "@id": "https://orcid.org/0009-0004-5961-4709"
+ }
+ ],
+ "name": [
+ "nf-core/funcscan"
+ ],
"programmingLanguage": {
"@id": "https://w3id.org/workflowhub/workflow-ro-crate#nextflow"
},
"sdPublisher": {
"@id": "https://nf-co.re/"
},
- "url": ["https://github.com/nf-core/funcscan", "https://nf-co.re/funcscan/dev/"],
- "version": ["2.1.0dev"]
-
+ "url": [
+ "https://github.com/nf-core/funcscan",
+ "https://nf-co.re/funcscan/dev/"
+ ],
+ "version": [
+ "2.1.0dev"
+ ]
},
{
"@id": "https://w3id.org/workflowhub/workflow-ro-crate#nextflow",
@@ -174,11 +206,11 @@
"version": "!>=24.04.2"
},
{
- "@id": "#a63ff768-a32a-4ee1-8ba3-fafeb18a6793",
+ "@id": "#1f9be113-27d3-4dcb-b12a-d0c1a16703bf",
"@type": "TestSuite",
"instance": [
{
- "@id": "#f399a53f-20fc-47ed-b389-7e76797884bb"
+ "@id": "#e917d36b-75a7-45b5-86d1-e9157f00ac3b"
}
],
"mainEntity": {
@@ -187,7 +219,7 @@
"name": "Test suite for nf-core/funcscan"
},
{
- "@id": "#f399a53f-20fc-47ed-b389-7e76797884bb",
+ "@id": "#e917d36b-75a7-45b5-86d1-e9157f00ac3b",
"@type": "TestInstance",
"name": "GitHub Actions workflow for testing nf-core/funcscan",
"resource": "repos/nf-core/funcscan/actions/workflows/ci.yml",
@@ -209,6 +241,11 @@
"@type": "Dataset",
"description": "Additional files"
},
+ {
+ "@id": "bin/",
+ "@type": "Dataset",
+ "description": "Scripts that must be callable from a pipeline process"
+ },
{
"@id": "conf/",
"@type": "Dataset",
@@ -229,6 +266,11 @@
"@type": "Dataset",
"description": "Modules used by the pipeline"
},
+ {
+ "@id": "modules/local/",
+ "@type": "Dataset",
+ "description": "Pipeline-specific modules"
+ },
{
"@id": "modules/nf-core/",
"@type": "Dataset",
@@ -320,6 +362,12 @@
"@type": "Person",
"email": "jfy133@gmail.com",
"name": "James Fellows Yates"
+ },
+ {
+ "@id": "https://orcid.org/0009-0004-5961-4709",
+ "@type": "Person",
+ "email": "73216762+jasmezz@users.noreply.github.com",
+ "name": "Jasmin Frangenberg"
}
]
-}
+}
\ No newline at end of file
diff --git a/tests/test.nf.test.snap b/tests/test.nf.test.snap
index c09747ac..d312a612 100644
--- a/tests/test.nf.test.snap
+++ b/tests/test.nf.test.snap
@@ -47,7 +47,7 @@
"deeparg_tsv_ARG": {
"content": [
"sample_1.align.daa.tsv:md5,21822364379fe8f991d27cdb52a33d1d",
- "sample_2.align.daa.tsv:md5,f448465df58785a87cdee53691a77bfe",
+ "sample_2.align.daa.tsv:md5,d59287f357de198639bdca5dbaede173",
"sample_1.mapping.ARG:md5,0e049e99eab4c55666062df21707d5b9",
"sample_2.mapping.ARG:md5,0e049e99eab4c55666062df21707d5b9"
],
diff --git a/tests/test_preannotated.nf.test.snap b/tests/test_preannotated.nf.test.snap
index 107b6e1c..de54e2ba 100644
--- a/tests/test_preannotated.nf.test.snap
+++ b/tests/test_preannotated.nf.test.snap
@@ -3,7 +3,7 @@
"content": [
"sample_1.align.daa.tsv:md5,0e71c37318bdc6cba792196d0455293d",
"sample_2.align.daa.tsv:md5,1092ecd3cd6931653168b46c7afeb9e3",
- "sample_3.align.daa.tsv:md5,b79070fe26acd1a10ae3aaf06b0d5901",
+ "sample_3.align.daa.tsv:md5,a9ed2f0651d75b318fde07a76b06d7b8",
true,
true,
true
@@ -71,8 +71,8 @@
"sample_1.potential.ARG.normalized.tsv:md5,d6732b4b9765bfa47e27ba673e24b6a4",
"sample_2.ARG.normalized.tsv:md5,1a19b894a7315aaae5f799e4539e6619",
"sample_2.potential.ARG.normalized.tsv:md5,b241e22f9116d8f518ba8526d52ac4dc",
- "sample_3.ARG.normalized.tsv:md5,d40d387176649ce80827420fef6a0169",
- "sample_3.potential.ARG.normalized.tsv:md5,f331efd21ea143c180a15ae56a5210d3"
+ "sample_3.ARG.normalized.tsv:md5,d7577c0066a31e173f9cb545820650bf",
+ "sample_3.potential.ARG.normalized.tsv:md5,6d0889215f0ad7f601502ca67c0ca89e"
],
"meta": {
"nf-test": "0.9.0",
![\"nf-core/funcscan\"](\"docs/images/nf-core-funcscan_logo_dark.png\"){kind=logo}
\n ![\"nf-core/funcscan\"](\"docs/images/nf-core-funcscan_logo_flat_dark.png\"){kind=logo}
\n