#machine learning
Nov 2025
SynGFN: learning across chemical space with generative flow-based molecular discovery
This study proposes SynGFN, which models molecular design as a cascade of simulated chemical reactions, enabling the assembly of molecules from synthesizable building blocks, as a bridge linking molecular design and synthesis, accelerating exploration and producing diverse, synthesizable, high-performance molecules.
Yuchen Zhu, Shuwang Li, Jihong Chen et al.
· Nature Computational Science · 3 citations