Structure-aware generation of drug-like molecules
This work addresses structure-based drug design for pharmaceutical researchers, offering incremental improvements in generating molecules with better binding and drug-like properties.
The paper tackles the problem of generating drug-like molecules that structurally complement protein pockets, proposing a supervised model that jointly generates molecular graphs and 3D poses atom-by-atom, resulting in an 8% improvement in predicted binding affinities and a 10% increase in drug-likeness scores over a baseline.
Structure-based drug design involves finding ligand molecules that exhibit structural and chemical complementarity to protein pockets. Deep generative methods have shown promise in proposing novel molecules from scratch (de-novo design), avoiding exhaustive virtual screening of chemical space. Most generative de-novo models fail to incorporate detailed ligand-protein interactions and 3D pocket structures. We propose a novel supervised model that generates molecular graphs jointly with 3D pose in a discretised molecular space. Molecules are built atom-by-atom inside pockets, guided by structural information from crystallographic data. We evaluate our model using a docking benchmark and find that guided generation improves predicted binding affinities by 8% and drug-likeness scores by 10% over the baseline. Furthermore, our model proposes molecules with binding scores exceeding some known ligands, which could be useful in future wet-lab studies.