AUTHOR=Mukaidaisi Muhetaer , Vu Andrew , Grantham Karl , Tchagang Alain , Li Yifeng 

TITLE=Multi-Objective Drug Design Based on Graph-Fragment Molecular Representation and Deep Evolutionary Learning

JOURNAL=Frontiers in Pharmacology

VOLUME=Volume 13 - 2022

YEAR=2022

URL=https://www.frontiersin.org/journals/pharmacology/articles/10.3389/fphar.2022.920747

DOI=10.3389/fphar.2022.920747

ISSN=1663-9812

ABSTRACT=Drug discovery is a challenging process with a huge molecular space to be explored and numerous pharmacological properties to be appropriately considered. Among a range of drug design protocols, fragment-based drug design is an effective way of constraining the search space and better utilizing biologically active compounds. This work advances the field of in silico drug design by integrating a graph fragmentation-based deep generative model with the deep evolutionary learning process for large-scale multi-objective molecular optimization. Through applying protein-ligand binding affinity scores together with other desired physicochemical properties as objectives, our method is able to generate novel molecules with improved property values and binding affinities.