Multi-domain Distribution Learning for De Novo Drug Design
This work addresses the challenge of de novo drug design for pharmaceutical research, offering a novel method with uncertainty estimation and preference alignment, though it appears incremental as it builds on existing flow matching and Markov bridge frameworks.
The paper tackles the problem of generating 3D protein-ligand structures for drug design by introducing DrugFlow, a generative model that integrates continuous flow matching with discrete Markov bridges, achieving state-of-the-art performance in learning chemical, geometric, and physical aspects across three domains.
We introduce DrugFlow, a generative model for structure-based drug design that integrates continuous flow matching with discrete Markov bridges, demonstrating state-of-the-art performance in learning chemical, geometric, and physical aspects of three-dimensional protein-ligand data. We endow DrugFlow with an uncertainty estimate that is able to detect out-of-distribution samples. To further enhance the sampling process towards distribution regions with desirable metric values, we propose a joint preference alignment scheme applicable to both flow matching and Markov bridge frameworks. Furthermore, we extend our model to also explore the conformational landscape of the protein by jointly sampling side chain angles and molecules.