Molecular fingerprints are widely used for predicting chemical properties, and selecting appropriate fingerprints is important. We generate new fingerprints based on the assumption that a performance of prediction using a more effective fingerprint is better. We generate effective interaction fingerprints that are the product of multiple base fingerprints. It is difficult to evaluate all combinations of interaction fingerprints because of computational limitations. Against this problem, we transform a problem of searching more effective interaction fingerprints into a quadratic unconstrained binary optimization problem. In this study, we found effective interaction fingerprints using QM9 dataset.
@article{arxiv.2303.10179,
title = {QUBO-inspired Molecular Fingerprint for Chemical Property Prediction},
author = {Koichiro Yawata and Yoshihiro Osakabe and Takuya Okuyama and Akinori Asahara},
journal= {arXiv preprint arXiv:2303.10179},
year = {2023}
}
Comments
2022 IEEE International Conference on Big Data (Big Data). arXiv admin note: substantial text overlap with arXiv:2303.09772