Welcome to CVSP-AIE


CVSP-AIE is a cutting-edge platform integrating three state-of-the-art protein-ligand docking and re-scoring models:

  • KarmaDock: Efficient large library ligand docking method.
  • CarsiDock: Accurate protein-ligand docking method.
  • RTMscore: Advanced scoring function based on residue-atom distance likelihood potential and graph transformer.
Get Started  >>

Cite us

Facilitating structure-based drug discovery with an artificial intelligence-driven virtual screening platform

Shukai Gu, Xujun Zhang, Mengwu Xiao, et al.

Nature Protocols, 2026, DOI: 10.1038/s41596-026-01389-z.

View Paper CVSP-AIE
Benchmarking AI-powered docking methods from the perspective of virtual screening

Shukai Gu, Chao Shen, Xujun Zhang, et al.

Nature Machine Intelligence, 2025, 7, 509–520.

View Paper Hierarchical Virtual Screening
Efficient and accurate large library ligand docking with KarmaDock

Xujun Zhang, Odin Zhang, Chao Shen, et al.

Nature Computational Science, 2023, 3, 789-804.

View Paper KarmaDock
CarsiDock: a deep learning paradigm for accurate protein-ligand docking and screening based on large-scale pre-training

Heng Cai, Chao Shen, Tianye Jian, et al.

Chemical Science, 2024, 15(4), 1449-1471.

View Paper CarsiDock
Boosting Protein-Ligand Binding Pose Prediction and Virtual Screening Based on Residue-Atom Distance Likelihood Potential and Graph Transformer

Chao Shen, Xujun Zhang, Yafeng Deng, et al.

Journal of Medicinal Chemistry, 2022, 65(15), 10691-10706.

View Paper RTMscore

Contact Us

Prof. Tingjun Hou

College of Pharmaceutical Sciences

Zhejiang University

tingjunhou@zju.edu.cn
Dr. Shukai Gu
3160101168@zju.edu.cn