`

Timezone: »

 
Structure-aware generation of drug-like molecules
Pavol Drotar · Arian Jamasb · Ben Day · Catalina Cangea · Pietro Lió

@ None
in Machine Learning in Structural Biology »

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.

Author Information

Pavol Drotar (University of Cambridge)
Arian Jamasb (University of Cambridge)
Ben Day (University of Cambridge)
Catalina Cangea (University of Cambridge)
Pietro Lió (University of Cambridge)

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors