Molecule property prediction with molecular orbitals

Yan Zhang, Khang Ngo, Sékou-Oumar Kaba, Daniel T. Levy, Siamak Ravanbakhsh, Aristide Baratin, Kisoo Kwon, MiYoung Jang, Eun Hyun Cho, Sangha Park, Sanghyun Yoo, Young-Seok Kim, Hasup Lee

Keywords: molecules, molecular orbitals, equivariance

TL;DR: Using molecular orbital features improves results and sample efficiency of state-of-the-art pretrained models for molecule property prediction

Abstract: Molecular orbitals describe the distribution of electrons in a molecule and are frequently used by chemists to understand properties of molecules, yet machine learning has neglected them so far. If atom coordinates are obtained through DFT anyway, they can be obtained for free at the same time and are thus a useful source of additional data, particularly when data is scarce We give an introduction to molecular orbitals for a machine learning audience and propose models to process three different representations of them. Experiments on a dataset with experimental properties show that including MOs significantly improves performance and sample efficiency over a pretrained molecular foundation model on this real-world task.

Submission Track: Full Paper

Submission Category: AI-Guided Design

Submission Number: 12