From part to whole: AI-driven progress in fragment-based drug discovery
Jinhyeok Yoo, Wonkyeong Jang, Woong‐Hee Shin
Abstract
Fragment-based drug discovery is a technique that finds potent binding fragments to the binding hotspots and makes them a hit compound. The combination of fragments allows us to explore the large chemical space. Thus, it becomes an effective methodology for identifying lead compounds. Three concepts have been introduced to make the fragments into the compound: growing, merging, and linking. Recently, growing and merging techniques using AI have significantly improved the accuracy and efficiency of molecular design. In this review, recent techniques such as VAE, reinforcement learning, and SE(3)-equivariant models will be discussed. These methods enable precise molecular structure exploration and optimization. Additionally, we address techniques utilizing diffusion models, language models, and deep evolutionary learning. We also introduce linker optimization methods using reinforcement learning and deep learning-based models. This progress of fragment-based drug discovery methods with AI opens the possibility of discovering the vast chemical space with high efficiency. • Fragment-based drug discovery helps identify lead compounds in drug discovery by combining fragments. • AI and deep learning improve fragment growth and merging in molecular design. • Variational autoencoder, reinforcement learning, and SE(3)-equivariant models optimize fragment growing. • Fragment merging can be conducted using the diffusion model, language model, and 3D convolutional neural network. • The fragment linker is optimized by reinforcement learning and generative models.