# torchtree
[](https://github.com/4ment/torchtree/actions/workflows/python-package.yml)
[](https://www.gnu.org/licenses/gpl-3.0)
[](https://github.com/4ment/torchtree/actions/workflows/publish_documentation.yml)
torchtree is a program designed for inferring phylogenetic trees from molecular sequences. Implemented in Python, it leverages [PyTorch] for automatic differentiation. The suite of inference algorithms encompasses variational inference, Hamiltonian Monte Carlo, maximum *a posteriori*, and Markov chain Monte Carlo.
- [Getting Started](#getting-started)
- [Dependencies](#dependencies)
- [Installation](#installation)
- [Quick start](#quick-start)
- [Plug-ins](#torchtree-plug-in)
## Getting Started
### Dependencies
- [DendroPy]
- [PyTorch]
### Installation
Use an Anaconda environment (Optional)
```bash
conda env create -f environment.yml
conda activate torchtree
```
To install the latest stable version you can run
```bash
pip install torchtree
```
To build torchtree from source you can run
```bash
git clone https://github.com/4ment/torchtree
pip install torchtree/
```
Check install
```bash
torchtree --help
```
## Quick start
`torchtree` requires a JSON file containing models and algorithms. A configuration file can be generated using `torchtree-cli`, a command line-based tool. This two-step process allows the user to adjust values in the configuration file, such as hyperparameters.
### 1 - Generating a configuration file
Some examples of models using variational inference:
#### Unrooted tree with GTR+W4 model
*W4* refers to a site model with 4 rates categories coming from a discretized Weibull distribution. This is similar to the more commonly used discretized Gamma distribution site model.
```bash
torchtree-cli advi -i data/fluA.fa -t data/fluA.tree -m GTR -C 4 > fluA.json
```
#### Time tree with strict clock and constant coalescent model
```bash
torchtree-cli advi -i data/fluA.fa -t data/fluA.tree -m JC69 --clock strict --coalescent constant > fluA.json
```
### 2 - Running torchtree
This will generate `sample.csv` and `sample.trees` files containing parameter and tree samples drawn from the variational distribution
```bash
torchtree fluA.json
```
## torchtree plug-in
torchtree can be easily extended without modifying the code base thanks its modular implementation. Some examples of external packages
- [torchtree-bito]
- [torchtree-physher]
- [torchtree-scipy]
- [torchtree-tensorflow]
## License
Distributed under the GPLv3 License. See [LICENSE](LICENSE) for more information.
## Acknowledgements
torchtree makes use of the following libraries and tools, which are under their own respective licenses:
- [PyTorch]
- [DendroPy]
[DendroPy]: https://github.com/jeetsukumaran/DendroPy
[PyTorch]: https://pytorch.org
[torchtree-bito]: https://github.com/4ment/torchtree-bito
[torchtree-physher]: https://github.com/4ment/torchtree-physher
[torchtree-scipy]: https://github.com/4ment/torchtree-scipy
[torchtree-tensorflow]: https://github.com/4ment/torchtree-tensorflow
Raw data
{
"_id": null,
"home_page": "https://github.com/4ment/torchtree",
"name": "torchtree",
"maintainer": null,
"docs_url": null,
"requires_python": ">=3.7",
"maintainer_email": null,
"keywords": "phylogenetics, variational, Bayes, pytorch",
"author": "Mathieu Fourment",
"author_email": "mathieu.fourment@uts.edu.au",
"download_url": "https://files.pythonhosted.org/packages/70/07/aaf7efe7d895c7c1f48b11220f73348c30227fa873565bc8384da47ea331/torchtree-1.0.2.tar.gz",
"platform": null,
"description": "# torchtree\n\n[](https://github.com/4ment/torchtree/actions/workflows/python-package.yml)\n[](https://www.gnu.org/licenses/gpl-3.0)\n[](https://github.com/4ment/torchtree/actions/workflows/publish_documentation.yml)\n\n\n\n\ntorchtree is a program designed for inferring phylogenetic trees from molecular sequences. Implemented in Python, it leverages [PyTorch] for automatic differentiation. The suite of inference algorithms encompasses variational inference, Hamiltonian Monte Carlo, maximum *a posteriori*, and Markov chain Monte Carlo.\n\n- [Getting Started](#getting-started)\n - [Dependencies](#dependencies)\n - [Installation](#installation)\n- [Quick start](#quick-start)\n- [Plug-ins](#torchtree-plug-in)\n\n## Getting Started\n\n### Dependencies\n - [DendroPy]\n - [PyTorch]\n\n ### Installation\nUse an Anaconda environment (Optional)\n```bash\nconda env create -f environment.yml\nconda activate torchtree\n```\n\nTo install the latest stable version you can run\n```bash\npip install torchtree\n```\n\nTo build torchtree from source you can run\n```bash\ngit clone https://github.com/4ment/torchtree\npip install torchtree/\n```\n\nCheck install\n```bash\ntorchtree --help\n```\n\n## Quick start\n`torchtree` requires a JSON file containing models and algorithms. A configuration file can be generated using `torchtree-cli`, a command line-based tool. This two-step process allows the user to adjust values in the configuration file, such as hyperparameters.\n\n### 1 - Generating a configuration file\nSome examples of models using variational inference:\n\n#### Unrooted tree with GTR+W4 model\n*W4* refers to a site model with 4 rates categories coming from a discretized Weibull distribution. This is similar to the more commonly used discretized Gamma distribution site model.\n\n```bash\ntorchtree-cli advi -i data/fluA.fa -t data/fluA.tree -m GTR -C 4 > fluA.json\n```\n\n#### Time tree with strict clock and constant coalescent model\n```bash\ntorchtree-cli advi -i data/fluA.fa -t data/fluA.tree -m JC69 --clock strict --coalescent constant > fluA.json\n```\n\n### 2 - Running torchtree\nThis will generate `sample.csv` and `sample.trees` files containing parameter and tree samples drawn from the variational distribution\n```bash\ntorchtree fluA.json\n```\n\n## torchtree plug-in\ntorchtree can be easily extended without modifying the code base thanks its modular implementation. Some examples of external packages\n- [torchtree-bito]\n- [torchtree-physher]\n- [torchtree-scipy]\n- [torchtree-tensorflow]\n\n## License\n\nDistributed under the GPLv3 License. See [LICENSE](LICENSE) for more information.\n\n## Acknowledgements\n\ntorchtree makes use of the following libraries and tools, which are under their own respective licenses:\n\n - [PyTorch]\n - [DendroPy]\n\n[DendroPy]: https://github.com/jeetsukumaran/DendroPy\n[PyTorch]: https://pytorch.org\n[torchtree-bito]: https://github.com/4ment/torchtree-bito\n[torchtree-physher]: https://github.com/4ment/torchtree-physher\n[torchtree-scipy]: https://github.com/4ment/torchtree-scipy\n[torchtree-tensorflow]: https://github.com/4ment/torchtree-tensorflow\n",
"bugtrack_url": null,
"license": "GPL3",
"summary": "Phylogenetic inference with pytorch",
"version": "1.0.2",
"project_urls": {
"Homepage": "https://github.com/4ment/torchtree"
},
"split_keywords": [
"phylogenetics",
" variational",
" bayes",
" pytorch"
],
"urls": [
{
"comment_text": "",
"digests": {
"blake2b_256": "70ffb0bbc1082a8a6a905f4491df6aec990ba802c2ca8ba005fb5eb5364d3364",
"md5": "25235412e23f417b3fc938775ec6e106",
"sha256": "6c0f62e8d533ec29e90cd1579fd68e5b1e5a19e889d0ac5fc858afc51f912d9c"
},
"downloads": -1,
"filename": "torchtree-1.0.2-py3-none-any.whl",
"has_sig": false,
"md5_digest": "25235412e23f417b3fc938775ec6e106",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": ">=3.7",
"size": 176513,
"upload_time": "2024-07-10T04:34:35",
"upload_time_iso_8601": "2024-07-10T04:34:35.125148Z",
"url": "https://files.pythonhosted.org/packages/70/ff/b0bbc1082a8a6a905f4491df6aec990ba802c2ca8ba005fb5eb5364d3364/torchtree-1.0.2-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": "",
"digests": {
"blake2b_256": "7007aaf7efe7d895c7c1f48b11220f73348c30227fa873565bc8384da47ea331",
"md5": "a88d43eb21d5135aa6bd2de8be8bd024",
"sha256": "79d37e31d6617c40343165abdb1494ad8467c920fc33f80019659ef6c3616988"
},
"downloads": -1,
"filename": "torchtree-1.0.2.tar.gz",
"has_sig": false,
"md5_digest": "a88d43eb21d5135aa6bd2de8be8bd024",
"packagetype": "sdist",
"python_version": "source",
"requires_python": ">=3.7",
"size": 145415,
"upload_time": "2024-07-10T04:34:37",
"upload_time_iso_8601": "2024-07-10T04:34:37.407069Z",
"url": "https://files.pythonhosted.org/packages/70/07/aaf7efe7d895c7c1f48b11220f73348c30227fa873565bc8384da47ea331/torchtree-1.0.2.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2024-07-10 04:34:37",
"github": true,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"github_user": "4ment",
"github_project": "torchtree",
"travis_ci": false,
"coveralls": false,
"github_actions": true,
"requirements": [
{
"name": "dendropy",
"specs": []
},
{
"name": "numpy",
"specs": [
[
">=",
"1.7"
]
]
},
{
"name": "torch",
"specs": [
[
">=",
"1.9"
]
]
}
],
"lcname": "torchtree"
}
JSON
