Torsional-GFN: a conditional conformation generator for small molecules
This addresses the need for efficient conformation generation in drug discovery, offering a novel method that improves upon molecular dynamics but is incremental in scaling to larger systems.
The paper tackles the problem of generating stable molecular conformations for drug discovery by introducing Torsional-GFN, a conditional GFlowNet that samples conformations proportionally to the Boltzmann distribution using only a reward function, achieving zero-shot generalization to unseen bond lengths and angles from MD simulations.
Generating stable molecular conformations is crucial in several drug discovery applications, such as estimating the binding affinity of a molecule to a target. Recently, generative machine learning methods have emerged as a promising, more efficient method than molecular dynamics for sampling of conformations from the Boltzmann distribution. In this paper, we introduce Torsional-GFN, a conditional GFlowNet specifically designed to sample conformations of molecules proportionally to their Boltzmann distribution, using only a reward function as training signal. Conditioned on a molecular graph and its local structure (bond lengths and angles), Torsional-GFN samples rotations of its torsion angles. Our results demonstrate that Torsional-GFN is able to sample conformations approximately proportional to the Boltzmann distribution for multiple molecules with a single model, and allows for zero-shot generalization to unseen bond lengths and angles coming from the MD simulations for such molecules. Our work presents a promising avenue for scaling the proposed approach to larger molecular systems, achieving zero-shot generalization to unseen molecules, and including the generation of the local structure into the GFlowNet model.