Advancing Molecular Machine Learning Representations with Stereoelectronics-Infused Molecular Graphs

TL;DR

This paper introduces a novel stereoelectronic-infused molecular graph representation that enhances the expressivity and interpretability of molecular machine learning models, enabling better predictions and insights into complex molecular systems without costly quantum calculations.

Contribution

The work presents a new method to incorporate quantum-chemical-rich stereoelectronic information into molecular graphs using a double graph neural network, improving model performance and interpretability.

Findings

Enhanced molecular property prediction accuracy

Ability to extrapolate to larger molecular systems

Development of a web tool for stereoelectronic exploration

Abstract

Molecular representation is a critical element in our understanding of the physical world and the foundation for modern molecular machine learning. Previous molecular machine learning models have employed strings, fingerprints, global features, and simple molecular graphs that are inherently information-sparse representations. However, as the complexity of prediction tasks increases, the molecular representation needs to encode higher fidelity information. This work introduces a novel approach to infusing quantum-chemical-rich information into molecular graphs via stereoelectronic effects, enhancing expressivity and interpretability. Learning to predict the stereoelectronics-infused representation with a tailored double graph neural network workflow enables its application to any downstream molecular machine learning task without expensive quantum chemical calculations. We show that the explicit addition of stereoelectronic information significantly improves the performance of message-passing 2D machine learning models for molecular property prediction. We show that the learned representations trained on small molecules can accurately extrapolate to much larger molecular structures, yielding chemical insight into orbital interactions for previously intractable systems, such as entire proteins, opening new avenues of molecular design. Finally, we have developed a web application (simg.cheme.cmu.edu) where users can rapidly explore stereoelectronic information for their own molecular systems.