ReactFormer: A Reaction-Aware Graph Transformer for Barrier Height Prediction without Explicit Transition State Geometries

Accurate prediction of chemical reaction barrier heights is crucial, yet traditional quantum mechanical methods are computationally expensive, and existing deep learning models often rely on costly three-dimensional transition state geometries or struggle with out-of-distribution generalization. This work introduces ReactFormer, a novel deep learning framework designed to predict reaction barrier heights with high accuracy solely from two-dimensional molecular graphs of reactants, thus eliminating the need for explicit transition state information. ReactFormer employs a reaction-aware graph Transformer architecture, which includes multi-view reactant encoding and a unique Virtual Reaction Center Node, enabling it to effectively capture complex reaction features and implicitly infer transition state characteristics. Evaluated on the RDB7 dataset, ReactFormer achieves a Mean Absolute Error of 2.40 $\pm$ 0.12 kcal/mol on the random split, matching or even slightly surpassing the performance of three-dimensional dependent models. Furthermore, ReactFormer demonstrates significantly improved computational efficiency and robust generalization across various out-of-distribution scenarios, including splits based on molecular size, target barrier height, reaction core, and reactant scaffold. An ablation study confirms the critical contributions of its core components. ReactFormer represents a significant step towards efficient, accurate, and generalizable deep learning models for chemical reaction dynamics, fostering advancements in drug discovery, materials science, and catalysis.