Package for prediction of chemical species properties from SMILES.
Project description
tgBoost
tgBoost is a pipeline framework to be used to develop predictive models of chemical species from SMILES notations. The pipeline comes with a ML model that predicts the glasss transition temperature (Tg) of organic compounds.
Motivation
tgBoost is a kickstart project aiming at expanding the use of Machine Learning (ML), Data Engineering and Quantitative Structure–Property Relationships (QSPR) in Physical Chemistry.
Requirements
- Python >=3.6.0 (Python 2.x is not supported)
- NumPy
- pandas
- scikit-learn
- gensim
- RDKit
- mol2vec
- xgboost
Installation
pip install https://github.com/U0M0Z/tgboost
The tgBoost library needs the independent installation of rdkit via conda-forge:
conda install -c conda-forge rdkit
Build status
Build status of continus integration i.e. travis, appveyor etc. Ex. -
Documentation
✨ 🍰 ✨ TODO
Usage
As python module
from tgboost import tgboost.processing.smiles_manager as sm
Contribute
Contact at tommaso.galeazzo@gmail.com
Credits
Initial development was supported by AirUCI, Irvine, CA.
License
BSD 3-clause © Tommaso Galeazzo
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
