Harmonic Self-Conditioned Flow Matching for Multi-Ligand Docking and Binding Site Design
This work addresses the problem of designing protein binding pockets for small molecules, with applications in drug synthesis and energy storage, representing an incremental advancement in generative modeling for this domain.
The authors tackled the problem of designing protein binding pockets for small molecules by developing HarmonicFlow, an improved generative process for 3D protein-ligand binding structures, and FlowSite, which extends this to jointly generate pocket residue types and binding structures, resulting in better performance than baseline approaches in docking and binding site design.
A significant amount of protein function requires binding small molecules, including enzymatic catalysis. As such, designing binding pockets for small molecules has several impactful applications ranging from drug synthesis to energy storage. Towards this goal, we first develop HarmonicFlow, an improved generative process over 3D protein-ligand binding structures based on our self-conditioned flow matching objective. FlowSite extends this flow model to jointly generate a protein pocket's discrete residue types and the molecule's binding 3D structure. We show that HarmonicFlow improves upon state-of-the-art generative processes for docking in simplicity, generality, and average sample quality in pocket-level docking. Enabled by this structure modeling, FlowSite designs binding sites substantially better than baseline approaches.