#artificial intelligence
#machine learning
#large language models
#generative ai
#reinforcement learning
#diffusion models
#federated learning
#explainable ai
#protein folding
#small language model
Review
Facilitating structure-based drug discovery with an artificial intelligence-driven virtual screening platform.
Shu-kai Gu
Xujun Zhang
Mengwu Xiao
Yuntao Qian
Bo Liu
Hao Luo
Hong-yan Du
Odin Zhang
Minjie Mou
Tingting Fu
Xiaorui Wang
Jingxuan Ge
Chao Shen
Feng Zhu
X. Yao
Huanxiang Liu
Tingjun Hou
Yu Kang
Medicine
TL;DR
The Comprehensive VS Platform with AI Engine (CVSP-AIE) for drug discovery from compound libraries integrates three AI models: KarmaDock, a fast docking model that directly updates atomic coordinates; CarsiDock, an accurate docking model that predicts protein-ligand distances and reconstructs binding poses; and RTMScore, an accurate scoring model that learns residue-atom distance distributions for affinity prediction.
