2026-09-22 · Structure-based drug design / virtual screening — generative model (Bayesian flow network) for de novo pose and molecule generation, training-free refinement · Journal of Chemical Information and Modeling (ACS)

Two-Stage Generation Dynamics Enable Training-Free AI Drug Design

generative AIstructure-based drug designvirtual screeningde novo designBayesian flow networksCrossDocked2020

Bayesian flow networks design molecules for protein pockets by jointly generating atom types and 3D coordinates.
The two channels behave differently: atom types shift abruptly at a defined point, while coordinates sharpen gradually, a pattern consistent across model variants.
Timing refinement to these transition points yields a training-free method matching baseline docking performance on a standard benchmark, with no extra predictor needed.

💡 Points

What earns this a second look is the lack of per-target retraining — that's the step that kills most generative tools before they reach my bench, so a training-free trick timed to a phase transition is worth trying. But matching baseline docking, not beating it, is a floor, not a win — and CrossDocked2020 scores say nothing about synthesizability or real binding.

Hierarchical Phase Transitions in Bayesian Flow Networks Enable Training-Free Molecular Design ↗