Template-Guided 3D Molecular Pose Generation via Flow Matching and Differentiable Optimization
This addresses a key challenge in drug design for pharmaceutical researchers, but it is incremental as it builds on existing template-guided approaches.
The paper tackles the problem of predicting 3D conformations of small molecules in protein binding sites using crystallized reference ligands as templates, and shows that their two-stage method outperforms standard docking tools and alignment methods, particularly for low-similarity or flexible ligands.
Predicting the 3D conformation of small molecules within protein binding sites is a key challenge in drug design. When a crystallized reference ligand (template) is available, it provides geometric priors that can guide 3D pose prediction. We present a two-stage method for ligand conformation generation guided by such templates. In the first stage, we introduce a molecular alignment approach based on flow-matching to generate 3D coordinates for the ligand, using the template structure as a reference. In the second stage, a differentiable pose optimization procedure refines this conformation based on shape and pharmacophore similarities, internal energy, and, optionally, the protein binding pocket. We introduce a new benchmark of ligand pairs co-crystallized with the same target to evaluate our approach and show that it outperforms standard docking tools and open-access alignment methods, especially in cases involving low similarity to the template or high ligand flexibility.