This repository contains PySIDT a low-data machine learning algorithm for predicting chemical properties. PySIDT is a general implementation of the subgraph isomorphic tree generation (SIDT) machine learning algorithm developed in Johnson and Green 2021. While the algorithm in that work was specific to rate coefficients this implementation can be applied to prediction of arbitrary properties.
- Install molecule from source
git clone https://github.com/ReactionMechanismGenerator/molecule.gitcd moleculegit checkout ts_len_improvementsconda env create -f environment.yml --name=pysidtconda activate pysidtmakepip install -e .
- Install PySIDT from source
git clone https://github.com/zadorlab/PySIDT.gitcd PySIDTconda activate pysidtconda install pydotpip install -e .