Drift-React: One-step Generation of Reaction Pathways via SE(3) Drifting Fields
Abstract
Mapping reaction pathways and transition states (TS) is fundamental to chemistry but computationally expensive at scale. The minimum energy pathway (MEP) dictates reaction rates and mechanisms, yet recovering it via electronic-structure methods requires thousands of costly force evaluations. Recent generative models accelerate TS identification but rely on iterative inference and only predict isolated saddle-point snapshots, missing the continuous reaction trajectory. We introduce Drift-React, an SE(3)-equivariant generative framework that predicts complete reaction pathways in a single forward pass from only reactant and product geometries. By shifting distribution evolution to training via a Sinkhorn-weighted drifting field, Drift-React eliminates both the iterative force evaluations of NEB-style methods and the sequential ODE/SDE integration of diffusion and flow matching models. Evaluated on the Transition1x and Halo8 datasets, our one-step model generates physically consistent MEPs that accurately capture energetic bottlenecks and enable arbitrary-resolution sampling along the reaction coordinate. For isolated TS prediction, Drift-React matches the sub-Ångström accuracy of state-of-the-art iterative models while delivering orders-of-magnitude acceleration, clearing a major computational bottleneck for large-scale reaction network exploration.
Related
- Excited-state dynamics and photo-reaction pathways of 4-nitrothiophenol in solution investigated by time-resolved soft X-ray absorption spectroscopy
- Efficient Light‐Driven Multi‐Electron Accumulation on Viologens by Molecular Control Over Photochemical Reaction Pathways
- Multiscale Insights into CO2 Chemisorption and Proton Transfer in Choline-Imidazolate based Deep Eutectic solvents: Exploring the Effect of Primary, Secondary and Tertiary Alkanolamine on Reaction Pathways and Product Distribution
- AIMNet2-rxn: A machine-learned potential for generalized reaction modeling on a millions-of-pathways scale
- Resolving Photochemical Reaction Pathways Using Field-Induced Surface Hopping Simulation of fs-EUV-TRPES: The Case of Furan
BibTeX
@misc{schlama2026driftreact,
title = {{Drift-React: One-step Generation of Reaction Pathways via SE(3) Drifting Fields}},
author = {Rémi Schlama and Philippe Schwaller},
howpublished = {arXiv},
year = {2026},
month = nov,
doi = {10.48550/arxiv.2605.22990},
eprint = {2605.22990},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2605.22990},
note = {CC BY 4.0},
}
RIS
TY - UNPB
TI - Drift-React: One-step Generation of Reaction Pathways via SE(3) Drifting Fields
AU - Rémi Schlama
AU - Philippe Schwaller
PY - 2026
DA - 2026/11/04
PB - arXiv
DO - 10.48550/arxiv.2605.22990
UR - https://arxiv.org/abs/2605.22990
AB - Mapping reaction pathways and transition states (TS) is fundamental to chemistry but computationally expensive at scale. The minimum energy pathway (MEP) dictates reaction rates and mechanisms, yet recovering it via electronic-structure methods requires thousands of costly force evaluations. Recent generative models accelerate TS identification but rely on iterative inference and only predict isolated saddle-point snapshots, missing the continuous reaction trajectory. We introduce Drift-React, an SE(3)-equivariant generative framework that predicts complete reaction pathways in a single forward pass from only reactant and product geometries. By shifting distribution evolution to training via a Sinkhorn-weighted drifting field, Drift-React eliminates both the iterative force evaluations of NEB-style methods and the sequential ODE/SDE integration of diffusion and flow matching models. Evaluated on the Transition1x and Halo8 datasets, our one-step model generates physically consistent MEPs that accurately capture energetic bottlenecks and enable arbitrary-resolution sampling along the reaction coordinate. For isolated TS prediction, Drift-React matches the sub-Ångström accuracy of state-of-the-art iterative models while delivering orders-of-magnitude acceleration, clearing a major computational bottleneck for large-scale reaction network exploration.
ER -