Advancing molecular machine learning representations with stereoelectronics-infused molecular graphs

📅 2024-08-08
🏛️ Nature Machine Intelligence
📈 Citations: 1
Influential: 0
📄 PDF
🤖 AI Summary
To address the low information density of 2D graph representations and their inability to model stereoelectronic effects in molecular machine learning, this work introduces a novel molecular graph representation that explicitly incorporates quantum-chemical stereoelectronic features—such as orbital interactions. Leveraging a dual-graph neural network architecture coupled with physics-informed representation learning, our method is the first to encode stereoelectronic information directly into the message-passing process without relying on costly quantum mechanical calculations. The approach significantly improves prediction accuracy across diverse molecular properties and demonstrates cross-scale generalizability—successfully transferring from small-molecule training sets to ultra-large systems such as proteins. We release an open-source web platform (simg.cheme.cmu.edu) enabling real-time stereoelectronic analysis and interactive visualization. The framework achieves state-of-the-art predictive performance while maintaining strong interpretability grounded in physical principles.

Technology Category

Application Category

📝 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.
Problem

Research questions and friction points this paper is trying to address.

Enhancing molecular graphs with stereoelectronic effects for better machine learning
Improving molecular property prediction via quantum-chemical-rich information infusion
Enabling accurate extrapolation of learned representations to larger molecular systems
Innovation

Methods, ideas, or system contributions that make the work stand out.

Infusing stereoelectronic effects into molecular graphs
Using double graph neural network workflow
Enhancing molecular property prediction accuracy
🔎 Similar Papers
No similar papers found.
Carnegie Mellon University | Federal University of Santa Maria | Google DeepMind | University of Toronto | Vector Institute for Artificial Intelligence | Lawrence Berkeley National Laboratory
D
Daniil A. Boiko
Department of Chemical Engineering, Carnegie Mellon University, Pittsburgh, PA 15213, USA
T
Thiago Reschutzegger
Department of Chemical Engineering, Federal University of Santa Maria, Santa Maria, RS, Brazil
B
Benjamín Sánchez-Lengeling
Google DeepMind, Cambridge, MA, USA (previous affiliation, where most of this work was done); Department of Chemical Engineering and Applied Chemistry, University of Toronto, Toronto, ON M5S 3E5, Canada (current affiliation); Vector Institute for Artificial Intelligence, Toronto, ON, Canada (current affiliation)
S
Samuel M. Blau
Energy Technologies Area, Lawrence Berkeley National Laboratory, Berkeley, CA 94720, USA
G
Gabe Gomes
Department of Chemistry, Carnegie Mellon University, Pittsburgh, PA 15213, USA; Wilton E. Scott Institute for Energy Innovation, Carnegie Mellon University, Pittsburgh, PA 15213, USA