Equivariant 3D-Conditional Diffusion Models for Molecular Linker Design
This addresses a key challenge in fragment-based drug discovery for pharmaceutical researchers, offering a novel approach that can link arbitrary numbers of fragments, unlike prior methods limited to pairs.
The paper tackles the problem of designing linkers between disconnected molecular fragments in drug discovery, proposing DiffLinker, an E(3)-equivariant 3D-conditional diffusion model that outperforms other methods by generating more diverse and synthetically-accessible molecules.
Fragment-based drug discovery has been an effective paradigm in early-stage drug development. An open challenge in this area is designing linkers between disconnected molecular fragments of interest to obtain chemically-relevant candidate drug molecules. In this work, we propose DiffLinker, an E(3)-equivariant 3D-conditional diffusion model for molecular linker design. Given a set of disconnected fragments, our model places missing atoms in between and designs a molecule incorporating all the initial fragments. Unlike previous approaches that are only able to connect pairs of molecular fragments, our method can link an arbitrary number of fragments. Additionally, the model automatically determines the number of atoms in the linker and its attachment points to the input fragments. We demonstrate that DiffLinker outperforms other methods on the standard datasets generating more diverse and synthetically-accessible molecules. Besides, we experimentally test our method in real-world applications, showing that it can successfully generate valid linkers conditioned on target protein pockets.