Towards equilibrium molecular conformation generation with GFlowNets
This addresses the challenge of predicting molecular properties for drug discovery, though it appears incremental as it applies an existing method (GFlowNets) to a new domain (molecular conformation generation).
The paper tackled the problem of sampling diverse and thermodynamically feasible molecular conformations by using GFlowNets to sample from the Boltzmann distribution, demonstrating that it can reproduce molecular potential energy surfaces and discover a diverse set of low-energy conformations for flexible drug-like molecules.
Sampling diverse, thermodynamically feasible molecular conformations plays a crucial role in predicting properties of a molecule. In this paper we propose to use GFlowNet for sampling conformations of small molecules from the Boltzmann distribution, as determined by the molecule's energy. The proposed approach can be used in combination with energy estimation methods of different fidelity and discovers a diverse set of low-energy conformations for highly flexible drug-like molecules. We demonstrate that GFlowNet can reproduce molecular potential energy surfaces by sampling proportionally to the Boltzmann distribution.