Molecular Generative Adversarial Network with Multi-Property Optimization

arXiv:2404.00081v1 Announce Type: cross
Abstract: Deep generative models, such as generative adversarial networks (GANs), have been employed for $de~novo$ molecular generation in drug discovery. Most prior studies have utilized reinforcement learning (RL) algorithms, particularly Monte Carlo tree search (MCTS), to handle the discrete nature of molecular representations in GANs. However, due to the inherent instability in training GANs and RL models, along with the high computational cost associated with MCTS sampling, MCTS RL-based GANs struggle to scale to large chemical …

abstract adversarial algorithms arxiv cs.ai cs.lg deep generative models discovery drug discovery gans generative generative adversarial network generative adversarial networks generative models however nature network networks optimization prior property q-bio.bm reinforcement reinforcement learning search studies tree type