QUBO-inspired Molecular Fingerprint for Chemical Property Prediction

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 finger...

Full description

Saved in:
Bibliographic Details
Published inarXiv.org
Main Authors Yawata, Koichiro, Osakabe, Yoshihiro, Okuyama, Takuya, Asahara, Akinori
Format Paper Journal Article
LanguageEnglish
Published Ithaca Cornell University Library, arXiv.org 17.03.2023
Subjects
Chemical fingerprinting
Chemical properties
Computer Science - Learning
Computer Science - Logic in Computer Science
Optimization
Predictions
Quantitative Biology - Biomolecules
Online AccessGet full text

Cover

More Information
Summary: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.
ISSN:2331-8422
DOI:10.48550/arxiv.2303.10179