MedGAN: optimized generative adversarial network with graph convolutional networks for novel molecule design.

ABSTRACT: Generative Artificial Intelligence can be an important asset in the drug discovery process to meet the demand for novel medicines. This work outlines the optimization and fine-tuning steps of MedGAN, a deep learning model based on Wasserstein Generative Adversarial Networks and Graph Convolutional Networks, developed to generate new quinoline-scaffold molecules from complex molecular graphs, including hyperparameter adjustments and evaluations of drug-likeness attributes such as pharmacokinetics, toxicity, and synthetic accessibility. The best model was capable of generating 25% valid molecules, 62% fully connected, from which 92% were quinolines, 93% were novel, and 95% unique, preserving chirality, atom charge, and favorable drug-like properties while generating 4831 novel quinolines. Th

SUBMITTER: Macedo B 

PROVIDER: S-EPMC10786821 | biostudies-literature | 2024 Jan

REPOSITORIES: biostudies-literature