Name | qsarify JSON |
Version |
0.1.1
JSON |
| download |
home_page | |
Summary | QSARify: A tool for QSAR model development |
upload_time | 2023-10-25 11:44:26 |
maintainer | |
docs_url | None |
author | |
requires_python | |
license | |
keywords |
qsar
cheminformatics
machine learning
|
VCS |
![](/static/img/github-24-000000.png) |
bugtrack_url |
|
requirements |
No requirements were recorded.
|
Travis-CI |
No Travis.
|
coveralls test coverage |
No coveralls.
|
# qsarify
qsarify is a library of tools for the analysis of QSAR/QSPR datasets and models. This library is intended to be used to produce models which relate a set of calculated chemical descriptors to a given numeric endpoint. Many great tools will take the geometry or string data of a given chemical and compute **descriptors**, which are numeric measures of the properties of these, but you can generate some of these with another one of my scripts, [Free Descriptors](https://github.com/StephenSzwiec/free_descriptors).
# Dependencies
- Python 3
- [numpy](https://numpy.org/)
- [pandas](https://pandas.pydata.org/)
- [scikit-learn](https://scikit-learn.org)
- [matplotlib](https://matplotlib.org)
# Installation
`pip install qsarify`
# What is included right now?
- Data preprocessing tools: `data_tools`
- Dimensionality reduction via clustering: `clustering`
- Feature selection:
- Single threaded: `feature_selection_single`
- Multi-threaded: `feature_selection_multi`
- Model Export and Visualization: `model_export`
- Cross Valiidation: `cross_validation`
# How to use
The best way to learn how to use this library is to look at the example notebook in the `examples` folder. This notebook will walk you through the workflow of using this library to build a QSAR model.
# Future Plans
- Massively parallel feature selection methods:
- CUDA acceleration
- MPI acceleration
- Include Shannon Entropy as a dimensionality reduction metric in clustering
- Embedded kernel methods
- More visualization tools
- More cross validation tools
- Feature selection tools for categorical data
# Contributing
If you would like to contribute to this project, please feel free to fork this repository and submit a pull request. Otherwise, you may also submit an issue. I will try to respond to issues as quickly as possible.
# License
This project is licensed under the GNU GPLv3 license. See the LICENSE file for more details.
# Citation
If you use this library in your work, please cite it as follows:
Szwiec, Stephen. (2023). qsarify: A high performance library for QSAR model development.
BibTex:
```
@misc{szwiec2023qsarify,
author = {Szwiec, Stephen},
title = {qsarify: A high performance library for QSAR model development},
year = {2023},
publisher = {GitHub},
journal = {GitHub repository},
howpublished = {\url{https://github.com/stephenszwiec/qsarify}},
}
```
Raw data
{
"_id": null,
"home_page": "",
"name": "qsarify",
"maintainer": "",
"docs_url": null,
"requires_python": "",
"maintainer_email": "",
"keywords": "QSAR,cheminformatics,machine learning",
"author": "",
"author_email": "Stephen Szwiec <Stephen.Szwiec@ndsu.edu>",
"download_url": "https://files.pythonhosted.org/packages/ab/0f/2a205bab46480dcf4c89f77adc5d56531bdc7f612945fad8bd13dec8140b/qsarify-0.1.1.tar.gz",
"platform": null,
"description": "# qsarify\n\nqsarify is a library of tools for the analysis of QSAR/QSPR datasets and models. This library is intended to be used to produce models which relate a set of calculated chemical descriptors to a given numeric endpoint. Many great tools will take the geometry or string data of a given chemical and compute **descriptors**, which are numeric measures of the properties of these, but you can generate some of these with another one of my scripts, [Free Descriptors](https://github.com/StephenSzwiec/free_descriptors).\n\n# Dependencies\n\n- Python 3\n- [numpy](https://numpy.org/)\n- [pandas](https://pandas.pydata.org/)\n- [scikit-learn](https://scikit-learn.org)\n- [matplotlib](https://matplotlib.org)\n\n\n# Installation\n\n`pip install qsarify`\n\n# What is included right now?\n\n- Data preprocessing tools: `data_tools`\n- Dimensionality reduction via clustering: `clustering`\n- Feature selection:\n\t- Single threaded: `feature_selection_single`\n\t- Multi-threaded: `feature_selection_multi`\n- Model Export and Visualization: `model_export`\n- Cross Valiidation: `cross_validation`\n\n# How to use\n\nThe best way to learn how to use this library is to look at the example notebook in the `examples` folder. This notebook will walk you through the workflow of using this library to build a QSAR model.\n\n# Future Plans\n\n- Massively parallel feature selection methods:\n\t- CUDA acceleration\n\t- MPI acceleration\n- Include Shannon Entropy as a dimensionality reduction metric in clustering\n- Embedded kernel methods\n- More visualization tools\n- More cross validation tools\n- Feature selection tools for categorical data\n\n# Contributing\n\n\nIf you would like to contribute to this project, please feel free to fork this repository and submit a pull request. Otherwise, you may also submit an issue. I will try to respond to issues as quickly as possible.\n\n# License\n\n\nThis project is licensed under the GNU GPLv3 license. See the LICENSE file for more details.\n\n# Citation\n\nIf you use this library in your work, please cite it as follows:\n\nSzwiec, Stephen. (2023). qsarify: A high performance library for QSAR model development.\n\nBibTex:\n```\n@misc{szwiec2023qsarify,\n author = {Szwiec, Stephen},\n title = {qsarify: A high performance library for QSAR model development},\n year = {2023},\n publisher = {GitHub},\n journal = {GitHub repository},\n howpublished = {\\url{https://github.com/stephenszwiec/qsarify}},\n }\n```\n",
"bugtrack_url": null,
"license": "",
"summary": "QSARify: A tool for QSAR model development",
"version": "0.1.1",
"project_urls": {
"documentation": "https://stephenszwiec.github.io/qsarify/",
"homepage": "https://stephenszwiec.github.io/qsarify/",
"issues": "https://github.com/stephenszwiec/qsarify/issues",
"repository": "https://github.com/stephenszwiec/qsarify"
},
"split_keywords": [
"qsar",
"cheminformatics",
"machine learning"
],
"urls": [
{
"comment_text": "",
"digests": {
"blake2b_256": "4031c0033804abf7842b208f99dfd9425c0225abedc371599c6e29828a9cb539",
"md5": "318df7b0917b06f6d65b8b89bd5ddb27",
"sha256": "8611034b44f3a3ba6813e8cb5545a3bd0257a6a61ed749dc3a60a793d5d5459e"
},
"downloads": -1,
"filename": "qsarify-0.1.1-py2.py3-none-any.whl",
"has_sig": false,
"md5_digest": "318df7b0917b06f6d65b8b89bd5ddb27",
"packagetype": "bdist_wheel",
"python_version": "py2.py3",
"requires_python": null,
"size": 33736,
"upload_time": "2023-10-25T11:44:19",
"upload_time_iso_8601": "2023-10-25T11:44:19.209366Z",
"url": "https://files.pythonhosted.org/packages/40/31/c0033804abf7842b208f99dfd9425c0225abedc371599c6e29828a9cb539/qsarify-0.1.1-py2.py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": "",
"digests": {
"blake2b_256": "ab0f2a205bab46480dcf4c89f77adc5d56531bdc7f612945fad8bd13dec8140b",
"md5": "cebc5c44af2f6959980116af81890752",
"sha256": "ab772f520ac53f41645edb72595e398436a6c7f07470ea8ac44aba838884b5fe"
},
"downloads": -1,
"filename": "qsarify-0.1.1.tar.gz",
"has_sig": false,
"md5_digest": "cebc5c44af2f6959980116af81890752",
"packagetype": "sdist",
"python_version": "source",
"requires_python": null,
"size": 3951531,
"upload_time": "2023-10-25T11:44:26",
"upload_time_iso_8601": "2023-10-25T11:44:26.804478Z",
"url": "https://files.pythonhosted.org/packages/ab/0f/2a205bab46480dcf4c89f77adc5d56531bdc7f612945fad8bd13dec8140b/qsarify-0.1.1.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2023-10-25 11:44:26",
"github": true,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"github_user": "stephenszwiec",
"github_project": "qsarify",
"travis_ci": false,
"coveralls": false,
"github_actions": true,
"lcname": "qsarify"
}