SPARKLE

This repository contains the information about the SPARKLE framework in “Zero-shot Discovery of High-Performance, Low-Cost Organic Battery Materials using Machine Learning.”

Generated Results

./SolvationEnergy and ./SpecificEnergy folders data files for the respective models.

Results Replication

code contains the necessary code and data files to replicate the results. Reproduced results can be compared to the data files in ./SolvationEnergy and ./SpecificEnergy.

Dependencies

1. Mordred Descriptors (https://github.com/mordred-descriptor/mordred) : Python package for calculating molecular descriptors which can be installed using pip install mordred
2. SISSO (https://github.com/rouyang2017/SISSO): Program used for building the models. Fortran implemented package for SISSO.

Citation

@article{doi:10.1021/jacs.4c11663,

    author = Park, Jaehyun and Sorourifar, Farshud and Muthyala, Madhav R. and Houser, Abigail M. and Tuttle, Madison and Paulson, Joel A. and Zhang, Shiyu,

    title = Zero-Shot Discovery of High-Performance, Low-Cost Organic Battery Materials Using Machine Learning,

    journal = Journal of the American Chemical Society,
    volume = 146,
    number = 45,
    pages = 31230-31239,
    year = 2024,
}

Repo DOI: