State Key Laboratory of Natural and Biomimetic Drugs

The authors introduce Kairos-GFM, a deterministic equivariant flow-matching model that combines a two-dimensional reaction graph with the Kabsch-aligned mean of three-dimensional reactant and product geometries; on 881 Transition1x reactions whose reference transition states passed strict saddle-point and bidirectional intrinsic reaction coordinate validation, it generates one candidate in 0.0118 s with a median RMSD of 0.14 Å, and a hierarchical physical-validation framework reveals that low RMSD and saddle-point convergence do not guarantee the intended reaction channel, with the model recovering the target channel in 75.94% of reactions, outperforming diffusion-based baselines but remaining below transport-based methods.

The authors introduce Kairos-GFM, a deterministic equivariant flow-matching model that combines a two-dimensional reaction graph with the Kabsch-aligned mean of three-dimensional reactant and product geometries; on 881 Transition1x reactions whose reference transition states passed strict saddle-point and bidirectional intrinsic reaction coordinate validation, it generates one candidate in 0.0118 s with a median RMSD of 0.14 Å, and a hierarchical physical-validation framework reveals that low RMSD and saddle-point convergence do not guarantee the intended reaction channel, with the model recovering the target channel in 75.94% of reactions, outperforming diffusion-based baselines but remaining below transport-based methods.