Electron flow matching for generative reaction mechanism prediction obeying conservation laws

TL;DR

FlowER is a deep generative model that predicts chemical reactions by modeling electron redistribution, strictly conserving mass, improving mechanistic accuracy, and generalizing well to new reaction types with minimal data.

Contribution

This work introduces FlowER, a flow matching-based model that enforces exact mass conservation in reaction prediction, enhancing mechanistic insights and out-of-domain generalization.

Findings

Enforces exact mass conservation in reaction prediction

Recovers mechanistic reaction sequences for unseen substrates

Generalizes effectively to new reaction classes with minimal data

Abstract

Central to our understanding of chemical reactivity is the principle of mass conservation, which is fundamental for ensuring physical consistency, balancing equations, and guiding reaction design. However, data-driven computational models for tasks such as reaction product prediction rarely abide by this most basic constraint. In this work, we recast the problem of reaction prediction as a problem of electron redistribution using the modern deep generative framework of flow matching. Our model, FlowER, overcomes limitations inherent in previous approaches by enforcing exact mass conservation, thereby resolving hallucinatory failure modes, recovering mechanistic reaction sequences for unseen substrate scaffolds, and generalizing effectively to out-of-domain reaction classes with extremely data-efficient fine-tuning. FlowER additionally enables estimation of thermodynamic or kinetic feasibility and manifests a degree of chemical intuition in reaction prediction tasks. This inherently interpretable framework represents a significant step in bridging the gap between predictive accuracy and mechanistic understanding in data-driven reaction outcome prediction.