Representing Molecules as Random Walks over Interpretable Grammars
Abstract
Recent research in molecular discovery has primarily been devoted to small, drug-like molecules, leaving many similarly important applications in material design without adequate technology. These applications often rely on more complex molecular structures with fewer examples that are carefully designed using known substructures. We propose a data-efficient and interpretable model for representing and reasoning over such molecules in terms of graph grammars that explicitly describe the hierarchical design space featuring motifs to be the design basis. We present a novel representation in the form of random walks over the design space, which facilitates both molecule generation and property prediction. We demonstrate clear advantages over existing methods in terms of performance, efficiency, and synthesizability of predicted molecules, and we provide detailed insights into the method’s chemical interpretability.
Cite
Text
Sun et al. "Representing Molecules as Random Walks over Interpretable Grammars." International Conference on Machine Learning, 2024.Markdown
[Sun et al. "Representing Molecules as Random Walks over Interpretable Grammars." International Conference on Machine Learning, 2024.](https://mlanthology.org/icml/2024/sun2024icml-representing/)BibTeX
@inproceedings{sun2024icml-representing,
title = {{Representing Molecules as Random Walks over Interpretable Grammars}},
author = {Sun, Michael and Guo, Minghao and Yuan, Weize and Thost, Veronika and Owens, Crystal Elaine and Grosz, Aristotle Franklin and Selvan, Sharvaa and Zhou, Katelyn and Mohiuddin, Hassan and Pedretti, Benjamin J and Smith, Zachary P and Chen, Jie and Matusik, Wojciech},
booktitle = {International Conference on Machine Learning},
year = {2024},
pages = {46988-47016},
volume = {235},
url = {https://mlanthology.org/icml/2024/sun2024icml-representing/}
}