{"id":41685250,"url":"https://github.com/zellerlab/chamois","last_synced_at":"2026-01-24T19:21:29.952Z","repository":{"id":280665502,"uuid":"770246257","full_name":"zellerlab/CHAMOIS","owner":"zellerlab","description":"Chemical Hierarchy Approximation for secondary Metabolism clusters Obtained In Silico.","archived":false,"fork":false,"pushed_at":"2025-12-11T18:00:47.000Z","size":65270,"stargazers_count":7,"open_issues_count":0,"forks_count":1,"subscribers_count":7,"default_branch":"main","last_synced_at":"2026-01-05T00:27:38.386Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":"https://chamois.readthedocs.io","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"gpl-3.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/zellerlab.png","metadata":{"files":{"readme":"README.md","changelog":"CHANGELOG.md","contributing":"CONTRIBUTING.md","funding":null,"license":"COPYING","code_of_conduct":null,"threat_model":null,"audit":null,"citation":"CITATION.cff","codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null,"notice":null,"maintainers":null,"copyright":null,"agents":null,"dco":null,"cla":null}},"created_at":"2024-03-11T08:03:37.000Z","updated_at":"2025-12-11T18:00:51.000Z","dependencies_parsed_at":"2025-03-26T12:21:10.280Z","dependency_job_id":"0a07bf2e-149f-4ac5-93c8-29e2142f534b","html_url":"https://github.com/zellerlab/CHAMOIS","commit_stats":null,"previous_names":["zellerlab/chamois"],"tags_count":4,"template":false,"template_full_name":null,"purl":"pkg:github/zellerlab/CHAMOIS","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/zellerlab%2FCHAMOIS","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/zellerlab%2FCHAMOIS/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/zellerlab%2FCHAMOIS/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/zellerlab%2FCHAMOIS/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/zellerlab","download_url":"https://codeload.github.com/zellerlab/CHAMOIS/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/zellerlab%2FCHAMOIS/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":28735077,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-01-24T17:51:25.893Z","status":"ssl_error","status_checked_at":"2026-01-24T17:50:48.377Z","response_time":89,"last_error":"SSL_read: unexpected eof while reading","robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":false,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":[],"created_at":"2026-01-24T19:21:29.314Z","updated_at":"2026-01-24T19:21:29.944Z","avatar_url":"https://github.com/zellerlab.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"\u003cimg align=\"right\" width=\"180\" height=\"180\" src=\"https://raw.githubusercontent.com/zellerlab/CHAMOIS/refs/heads/main/docs/_images/logo-square.png\"\u003e\n\n# 🐐 CHAMOIS [![Stars](https://img.shields.io/github/stars/zellerlab/CHAMOIS.svg?style=social\u0026maxAge=3600\u0026label=Star)](https://github.com/zellerlab/CHAMOIS/stargazers)\n\n*Chemical Hierarchy Approximation for secondary Metabolism clusters Obtained In Silico.*\n\n[![Actions](https://img.shields.io/github/actions/workflow/status/zellerlab/CHAMOIS/test.yml?branch=main\u0026logo=github\u0026style=flat-square\u0026maxAge=300)](https://github.com/zellerlab/CHAMOIS/actions)\n[![PyPI](https://img.shields.io/pypi/v/chamois-tool.svg?logo=pypi\u0026style=flat-square\u0026maxAge=3600)](https://pypi.org/project/chamois-tool)\n[![Bioconda](https://img.shields.io/conda/vn/bioconda/chamois?logo=anaconda\u0026style=flat-square\u0026maxAge=3600)](https://anaconda.org/bioconda/chamois)\n[![Wheel](https://img.shields.io/pypi/wheel/chamois-tool.svg?style=flat-square\u0026maxAge=3600)](https://pypi.org/project/chamois-tool/#files)\n[![Python Versions](https://img.shields.io/pypi/pyversions/chamois-tool.svg?logo=python\u0026style=flat-square\u0026maxAge=3600)](https://pypi.org/project/chamois-tool/#files)\n[![License](https://img.shields.io/badge/license-GPLv3-blue.svg?style=flat-square\u0026maxAge=2678400)](https://choosealicense.com/licenses/gpl-3.0/)\n[![Source](https://img.shields.io/badge/source-GitHub-303030.svg?maxAge=2678400\u0026style=flat-square)](https://github.com/zellerlab/CHAMOIS/)\n[![Mirror](https://img.shields.io/badge/mirror-EMBL-009f4d?style=flat-square\u0026maxAge=2678400)](https://git.embl.de/larralde/CHAMOIS)\n[![Issues](https://img.shields.io/github/issues/zellerlab/CHAMOIS.svg?style=flat-square\u0026maxAge=600)](https://github.com/zellerlab/CHAMOIS/issues)\n[![Docs](https://img.shields.io/readthedocs/chamois/latest?style=flat-square\u0026maxAge=600)](https://chamois.readthedocs.io)\n[![Changelog](https://img.shields.io/badge/keep%20a-changelog-8A0707.svg?maxAge=2678400\u0026style=flat-square)](https://github.com/zellerlab/CHAMOIS/blob/main/CHANGELOG.md)\n[![Preprint](https://img.shields.io/badge/preprint-bioRxiv-darkblue?style=flat-square\u0026maxAge=2678400)](https://www.biorxiv.org/content/10.1101/2025.03.13.642868)\n\n## 🗺️  ️Overview\n\nCHAMOIS is a fast method for predicting chemical features of natural products\nproduced by Biosynthetic Gene Clusters (BGCs) using only their genomic\nsequence. It can be used to get chemical features from BGCs predicted in\nsilico with tools such as [GECCO](https://gecco.embl.de) or\n[antiSMASH](https://antismash.secondarymetabolites.org).\n\n## 💡 Usage\n\nThis section shows only the basic commands for installing and running CHAMOIS.\nThe [online documentation](https://chamois.readthedocs.io)\ncontains a more detailed\n[installation guide](https://chamois.readthedocs.io/en/latest/guide/install.html),\n[examples](https://chamois.readthedocs.io/en/latest/examples/index.html),\nan [API reference](https://chamois.readthedocs.io/en/latest/api/index.html),\nand a [CLI reference](https://chamois.readthedocs.io/en/latest/cli/index.html)\n\n### 🔧 Installing CHAMOIS\n\nCHAMOIS is implemented in [Python](https://www.python.org/), and supports\n[all versions](https://endoflife.date/python) from Python 3.7 onwards.\nIt requires additional libraries that can be installed directly from\n[PyPI](https://pypi.org), the Python Package Index.\n\n```console\n$ pip install chamois-tool\n```\n\nInstalling the package is instantaneous, but requires downloading an extra\n44 MiB of data (profile HMMs) from GitHub, which will add to the install\ntime depending on the speed of your Internet connection.\n\n*Since release `v0.2.1`, CHAMOIS can now run on Windows! This uses\nthe PyHMMER `v0.12.0` experimental [MinGW-w64](https://www.mingw-w64.org/)\nbuild which supports Windows 10 and later. See the PyHMMER\ndocumentation for more information about\n[Windows support](https://pyhmmer.readthedocs.io/en/stable/guide/windows.html)*.\n\n### 🧬 Running CHAMOIS\n\nOnce CHAMOIS is installed, you can run it from the terminal by providing\nit with one or more GenBank file the genomic records of the BGCs to analyze,\nand an output path where to write the results in HDF5 format. For instance to\npredict the classes for [BGC0000703](https://mibig.secondarymetabolites.org/repository/BGC0000703.4/index.html#r1c1),\na kanamycin-producing BGC from MIBiG:\n\n```console\n$ chamois predict -i tests/data/BGC0000703.4.gbk -o tests/data/BGC0000703.4.hdf5\n```\n\n*This takes about 3 seconds and 600 MiB of RAM on a higher-end laptop\n(Linux 6.13.8, i7-1255U @ 4.70 GHz). The runtime and memory usage scales\nlinearly with the number of BGCs to process.*\n\nAdditional examples for running CHAMOIS can be found in the [online\ndocumentation](https://chamois.readthedocs.io/en/latest/examples/index.html).\n\n### 🔎 Viewing results\n\nThe output file can be loaded with the `anndata` package, and corresponds\nto a probability matrix where rows are the input BGCs, and columns are the\nChemOnt classes.\n\nTo get a summary for each predicted BGC, use the `render` command:\n\n```console\n$ chamois render -i tests/data/BGC0000703.4.hdf5\n```\n\nPredictions for each BGC will be shown as a tree with their computed\nprobabilities:\n\n```\nCHEMONTID:0000002 (Organoheterocyclic compounds): 0.996\n├── CHEMONTID:0002012 (Oxanes): 0.996│\n└── CHEMONTID:0004140 (Oxacyclic compounds): 0.976\nCHEMONTID:0004150 (Hydrocarbon derivatives): 0.999\nCHEMONTID:0004557 (Organopnictogen compounds): 0.948\nCHEMONTID:0004603 (Organic oxygen compounds): 1.000\n└── CHEMONTID:0000323 (Organooxygen compounds): 1.000\n    ├── CHEMONTID:0000011 (Carbohydrates and carbohydrate conjugates): 0.996\n    │   ├── CHEMONTID:0001540 (Monosaccharides): 0.996\n    │   ├── CHEMONTID:0002105 (Glycosyl compounds): 0.977\n    │   │   └── CHEMONTID:0002207 (O-glycosyl compounds): 0.977\n    │   └── CHEMONTID:0003305 (Aminosaccharides): 0.995\n    │       └── CHEMONTID:0000282 (Aminoglycosides): 0.995\n    │           └── CHEMONTID:0001675 (Aminocyclitol glycosides): 0.995\n    │               └── CHEMONTID:0003575 (2-deoxystreptamine aminoglycosides): 0.961\n    ├── CHEMONTID:0000129 (Alcohols and polyols): 1.000\n    │   ├── CHEMONTID:0000286 (Primary alcohols): 0.891\n    │   ├── CHEMONTID:0001292 (Cyclic alcohols and derivatives): 0.998\n    │   │   └── CHEMONTID:0002509 (Cyclitols and derivatives): 0.996\n    │   │       └── CHEMONTID:0002510 (Aminocyclitols and derivatives): 0.987\n    │   ├── CHEMONTID:0001661 (Secondary alcohols): 0.999\n    │   │   └── CHEMONTID:0002647 (Cyclohexanols): 0.995\n    │   └── CHEMONTID:0002286 (Polyols): 0.972\n    └── CHEMONTID:0000254 (Ethers): 0.959\n        └── CHEMONTID:0001656 (Acetals): 0.959\nCHEMONTID:0004707 (Organic nitrogen compounds): 0.999\n└── CHEMONTID:0000278 (Organonitrogen compounds): 0.999\n    ├── CHEMONTID:0002449 (Amines): 0.999\n    │   ├── CHEMONTID:0002450 (Primary amines): 0.989\n    │   │   └── CHEMONTID:0000469 (Monoalkylamines): 0.989\n    │   └── CHEMONTID:0002460 (Alkanolamines): 0.999\n    │       └── CHEMONTID:0001897 (1,2-aminoalcohols): 0.992\n    └── CHEMONTID:0002674 (Cyclohexylamines): 0.987\n```\n\n### 🎛️ Training CHAMOIS\n\nTraining CHAMOIS is also done with the CLI, provided you have training data\navailable. You can use the [CHAMOIS datasets](https://zenodo.org/records/15009032)\nreleased on [Zenodo](https://zenodo.org/) to reproduce our results.\n\nFor instance, to train on the MIBiG 3.1 BGCs, the dataset used to train\nthe CHAMOIS classifier distributed with the code, run the following command:\n\n```console\n$ chamois train -f data/datasets/mibig3.1/features.hdf5 -c data/datasets/mibig3.1/classes.hdf5 -o model.json\n```\n\n*This takes about 12 seconds and 600 MiB of RAM on a higher-end laptop\n(Linux 6.13.8, i7-1255U @ 4.70 GHz).*\n\n## 📝 Requirements\n\n### 🖥️ System requirements\n\nCHAMOIS is a pure-python package but requires HMMER, which only runs on\nPowerPC, x86-64 and Aarch64 systems, and only on POSIX operating systems\n(Linux, MacOS, BSD, Windows w/ MinGW-w64). \n\nCHAMOIS is tested on Linux (Ubuntu 22.04) using the GitHub Actions continuous\nintegration platform.\n\n### 🐍 Software requirements\n\nCHAMOIS supports (and is tested) on all Python versions from Python 3.7 onwards.\nIt requires the following Python packages:\n\n|                     | Minimum  | Tested | Latest                                                                                                                                                      |\n|---------------------|----------|--------|-------------------------------------------------------------------------------------------------------------------------------------------------------------|\n| anndata             | \u003e=0.8    | 0.9.2  | ![PyPI](https://img.shields.io/pypi/v/anndata?style=flat-square\u0026logo=pypi\u0026cacheSeconds=3600\u0026link=https%3A%2F%2Fpypi.org%2Fproject%2Fanndata%2F)             |\n| gb-io               | \u003e=0.3.1  | 0.3.4  | ![PyPI](https://img.shields.io/pypi/v/gb-io?style=flat-square\u0026logo=pypi\u0026cacheSeconds=3600\u0026link=https%3A%2F%2Fpypi.org%2Fproject%2Fgb-io%2F)                 |\n| lz4                 | \u003e=4.0    | 4.3.3  | ![PyPI](https://img.shields.io/pypi/v/lz4?style=flat-square\u0026logo=pypi\u0026cacheSeconds=3600\u0026link=https%3A%2F%2Fpypi.org%2Fproject%2Flz4%2F)                     |\n| numpy               | \u003e=1.0    | 2.2.4  | ![PyPI](https://img.shields.io/pypi/v/numpy?style=flat-square\u0026logo=pypi\u0026cacheSeconds=3600\u0026link=https%3A%2F%2Fpypi.org%2Fproject%2Fnumpy%2F)                 |\n| pandas              | \u003e=1.3    | 2.2.3  | ![PyPI](https://img.shields.io/pypi/v/pandas?style=flat-square\u0026logo=pypi\u0026cacheSeconds=3600\u0026link=https%3A%2F%2Fpypi.org%2Fproject%2Fpandas%2F)               |\n| platformdirs        | \u003e=3.0    | 4.3.6  | ![PyPI](https://img.shields.io/pypi/v/platformdirs?style=flat-square\u0026logo=pypi\u0026cacheSeconds=3600\u0026link=https%3A%2F%2Fpypi.org%2Fproject%2Fplatformdirs%2F)   |\n| pyhmmer             | \u003e=0.11.0 | 0.11.0 | ![PyPI](https://img.shields.io/pypi/v/pyhmmer?style=flat-square\u0026logo=pypi\u0026cacheSeconds=3600\u0026link=https%3A%2F%2Fpypi.org%2Fproject%2Fpyhmmer%2F)             |\n| pyrodigal           | \u003e=3.0    | 3.6.3  | ![PyPI](https://img.shields.io/pypi/v/pyrodigal?style=flat-square\u0026logo=pypi\u0026cacheSeconds=3600\u0026link=https%3A%2F%2Fpypi.org%2Fproject%2Fpyrodigal%2F)         |\n| rich                | \u003e=12.4   | 13.9.4 | ![PyPI](https://img.shields.io/pypi/v/rich?style=flat-square\u0026logo=pypi\u0026cacheSeconds=3600\u0026link=https%3A%2F%2Fpypi.org%2Fproject%2Frich%2F)                   |\n| rich-argparse       | \u003e=1.1    | 1.6.0  | ![PyPI](https://img.shields.io/pypi/v/rich-argparse?style=flat-square\u0026logo=pypi\u0026cacheSeconds=3600\u0026link=https%3A%2F%2Fpypi.org%2Fproject%2Frich-argparse%2F) |\n| scipy               | \u003e=1.4    | 1.15.2 | ![PyPI](https://img.shields.io/pypi/v/scipy?style=flat-square\u0026logo=pypi\u0026cacheSeconds=3600\u0026link=https%3A%2F%2Fpypi.org%2Fproject%2Fscipy%2F)                 |\n\n\n## 🔖 Reference\n\nCHAMOIS can be cited using the following preprint:\n\n\u003e **Machine learning inference of natural product chemistry across biosynthetic gene cluster types**.\n\u003e Martin Larralde, Georg Zeller.\n\u003e bioRxiv 2025.03.13.642868; [doi:10.1101/2025.03.13.642868](https://doi.org/10.1101/2025.03.13.642868)\n\n\n## 💭 Feedback\n\n### ⚠️ Issue Tracker\n\nFound a bug ? Have an enhancement request ? Head over to the [GitHub issue\ntracker](https://github.com/zellerlab/CHAMOIS/issues) if you need to report\nor ask something. If you are filing in on a bug, please include as much\ninformation as you can about the issue, and try to recreate the same bug\nin a simple, easily reproducible situation.\n\n### 🏗️ Contributing\n\nContributions are more than welcome! See [`CONTRIBUTING.md`](https://github.com/zellerlab/CHAMOIS/blob/master/CONTRIBUTING.md)\nfor more details.\n\n## ⚖️ License\n\nThis software is provided under the [GNU General Public License v3.0 *or later*](https://choosealicense.com/licenses/gpl-3.0/).\nCHAMOIS is developped by the [Zeller Lab](https://zellerlab.org)\nat the [European Molecular Biology Laboratory](https://www.embl.de/) in Heidelberg\nand the [Leiden University Medical Center](https://lumc.nl/en/) in Leiden.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fzellerlab%2Fchamois","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fzellerlab%2Fchamois","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fzellerlab%2Fchamois/lists"}