Login / Signup

Navigating the frontier of drug-like chemical space with cutting-edge generative AI models.

Antonio Lavecchia
Published in: Drug discovery today (2024)
Deep generative models (GMs) have transformed the exploration of drug-like chemical space (CS) by generating novel molecules through complex, nontransparent processes, bypassing direct structural similarity. This review examines five key architectures for CS exploration: recurrent neural networks (RNNs), variational autoencoders (VAEs), generative adversarial networks (GANs), normalizing flows (NF), and Transformers. It discusses molecular representation choices, training strategies for focused CS exploration, evaluation criteria for CS coverage, and related challenges. Future directions include refining models, exploring new notations, improving benchmarks, and enhancing interpretability to better understand biologically relevant molecular properties.
Keyphrases
  • neural network
  • signaling pathway
  • artificial intelligence
  • emergency department
  • drug induced
  • lps induced
  • current status
  • cell proliferation
  • health insurance
  • affordable care act