Module 4. HierarchicalVS

HierarchicalVS first employs KarmaDock for efficient docking, followed by CarsiDock for accurate docking and RTMscore for re-scoring.

Job Name
Email Address
Input Receptor *
Inference Ligand *
Compound Library *
Ranking-TOP N

Notes: supports for up to 1,000,000 molecules; download local version for larger libraries; TopN is limit to [10, 10000];

Example Files:     Receptor      Ligand      Libraries      Example
For more details, please infer to our papers:
  • Shukai Gu, Chao Shen, Xujun Zhang, et al. Benchmarking AI-powered docking methods from the perspective of virtual screening. Nature Machine Intelligence, 2025, 7, 509–520. [HTML]
  • Xujun Zhang, Odin Zhang, Chao Shen, et al. Efficient and accurate large library ligand docking with KarmaDock. Nature Computational Science, 2023, 3, 789-804. [HTML]
  • Heng Cai, Chao Shen, Tianye Jian, et al. CarsiDock: a deep learning paradigm for accurate protein-ligand docking and screening based on large-scale pre-training. Chemical Science, 2024, 15(4), 1449-1471. [HTML]
  • Chao Shen, Xujun Zhang, Yafeng Deng, et al. Boosting Protein-Ligand Binding Pose Prediction and Virtual Screening Based on Residue-Atom Distance Likelihood Potential and Graph Transformer. Journal of Medicinal Chemistry, 2022, 65(15), 10691-10706. [HTML]
    • Loading structure...
    Submission Rejected
    Notice
    Preprocessing Recommended
    Note: Preprocessing prepares proteins (adding hydrogens, optimizing H-bonds, etc.) and standardizes ligand libraries. These steps can significantly improve accuracy. If you choose to skip preprocessing, result quality may be reduced.