Metadata-Version: 2.4
Name: checkamg
Version: 1.0
Summary: Automated discovery and curation of Auxiliary Metabolic Genes (AMGs), Auxiliary Regulatory Genes (AReGs), and Auxiliary Physiology Genes (APGs) encoded by viral genomes.
Author-email: "James C. Kosmopoulos" <kosmopoulos@wisc.edu>
License: GPL-3.0-or-later
Project-URL: Homepage, https://github.com/AnantharamanLab/CheckAMG
Keywords: bioinformatics,metagenomics,viromics,genomics,AMG,phage
Classifier: Programming Language :: Python :: 3
Classifier: License :: OSI Approved :: GNU General Public License v3 or later (GPLv3+)
Classifier: Operating System :: POSIX :: Linux
Classifier: Operating System :: MacOS
Classifier: Topic :: Scientific/Engineering :: Bio-Informatics
Requires-Python: >=3.11
Description-Content-Type: text/markdown
License-File: LICENSE
Requires-Dist: joblib>=1.5.1
Requires-Dist: lightgbm>=4.5.0
Requires-Dist: metapyrodigal>=1.4.1
Requires-Dist: numba<0.62,>=0.61.2
Requires-Dist: numpy<2.3,>=1.24
Requires-Dist: pandas<3,>=2.3.0
Requires-Dist: polars-u64-idx<2,>=1.30.0
Requires-Dist: ptn-set-transformer<3,>=2.8
Requires-Dist: psutil>=7.0.0
Requires-Dist: pyarrow>=20.0.0
Requires-Dist: pyfastatools==2.5.0
Requires-Dist: pyhmmer<0.13,>=0.11.1
Requires-Dist: pyrodigal<4,>=3.5.2
Requires-Dist: pyrodigal-gv<0.4,>=0.3.2
Requires-Dist: pyyaml>=6.0
Requires-Dist: requests>=2.32
Requires-Dist: scikit-learn==1.7.2
Requires-Dist: snakemake==8.23.2
Requires-Dist: tqdm>=4.67.1
Dynamic: license-file

# CheckAMG

**Automated discovery and curation of Auxiliary Metabolic Genes (AMGs), Auxiliary Regulatory Genes (AReGs), and Auxiliary Physiology Genes (APGs) encoded by viral genomes**

> This tool is in active development and has not yet been peer-reviewed.

CheckAMG identifies and curates high-confidence auxiliary viral genes (AVGs) using two complementary approaches: a reference-based path (curated functional annotations plus viral genome context) and a reference-independent path (the Protein Set Transformer genome language model).

## Quick usage

```bash
checkamg download -d /path/to/db/destination

checkamg end-to-end \
  -d /path/to/db/destination \
  -i examples/example_data/single_contig_viruses.fasta \
  -I examples/example_data/multi_contig_vMAGs \
  -o CheckAMG_example_out
```

## Features

* Input: nucleotide or protein sequences
* Handles single-contig viral genomes and multi-contig vMAGs/bins
* Reference-based annotation and genome-context curation (`annotate`)
* Reference-independent prediction with a protein genome language model (`de-novo`)
* Combined reporting (`aggregate`) and one-command runs (`end-to-end`)
* Outputs curated lists and amino-acid sequences of AMGs, AReGs, and APGs

## Modules

```bash
checkamg -h
```

* `download`: get the required databases
* `annotate`: reference-based AVG prediction and curation
* `de-novo`: reference-independent AVG prediction with PST
* `aggregate`: merge `annotate` and `de-novo` results
* `end-to-end`: run annotate, de-novo, and aggregate in tandem
* `train`: finetune a custom CheckAMG-PST model

## License

GPL-3.0-or-later

**Installation, example data, and full documentation:**
[https://github.com/AnantharamanLab/CheckAMG](https://github.com/AnantharamanLab/CheckAMG) and the [CheckAMG Wiki](https://github.com/AnantharamanLab/CheckAMG/wiki).
