Generative flow model on distance geometry for predicting transition states of chemical reactions

This paper addresses the challenge of predicting transition states, which are essential for understanding reaction mechanisms but difficult to obtain through experiments or conventional computations. We formulate transition state prediction as conditional probability flow learning in molecular distance geometry space rather than Cartesian coordinates. By operating on interatomic distances, the generative flow model on distance geometry employs a chemically constrained representation that captures bond reorganization. An optimal transport inspired evolution path directs the generative process toward chemically consistent intermediates through a dual branch network architecture. On the benchmark datasets, the proposed model improves pre-optimization structural fidelity over Cartesian baselines, accelerates transition state refinement, and generalizes to unseen reactions. This work shows that aligning generative modeling with chemically constrained geometric representations enables practical and accelerated transition state modeling pipelines. Predicting transition states of chemical reactions is demanding. A generative flow model in distance geometry space, dubbed TS-DFM, is proposed, achieving higher structural accuracy and better generalizability than Cartesian-based approaches.