Transformer-based Objective-reinforced Generative Adversarial Network to Generate Desired Molecules
Transformer-based Objective-reinforced Generative Adversarial Network to Generate Desired Molecules
Chen Li, Chikashige Yamanaka, Kazuma Kaitoh, Yoshihiro Yamanishi
Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence
Main Track. Pages 3884-3890.
https://doi.org/10.24963/ijcai.2022/539
Deep generative models of sequence-structure data have attracted widespread attention in drug discovery. However, such models cannot fully extract the semantic features of molecules from sequential representations. Moreover, mode collapse reduces the diversity of the generated molecules. This paper proposes a transformer-based objective-reinforced generative adversarial network (TransORGAN) to generate molecules. TransORGAN leverages a transformer architecture as a generator and uses a stochastic policy gradient for reinforcement learning to generate plausible molecules with rich semantic features. The discriminator grants rewards that guide the policy update of the generator, while an objective-reinforced penalty encourages the generation of diverse molecules. Experiments were performed using the ZINC chemical dataset, and the results demonstrated the usefulness of TransORGAN in terms of uniqueness, novelty, and diversity of the generated molecules.
Keywords:
Multidisciplinary Topics and Applications: Bioinformatics
Multidisciplinary Topics and Applications: Health and Medicine
Multidisciplinary Topics and Applications: Life Science