Related Experiment Video
Updated: Jun 26, 2026
08:35
Achieving Efficient Fragment Screening at XChem Facility at Diamond Light Source
Published on: May 29, 2021
Facilitating structure-based drug discovery with an artificial intelligence-driven virtual screening platform
Shukai Gu1,2, Xujun Zhang1, Mengwu Xiao3
1College of Pharmaceutical Sciences, Zhejiang University, Hangzhou, China.
Nature Protocols
|June 24, 2026
Summary
This study introduces the Comprehensive VS Platform with AI Engine (CVSP-AIE), a novel drug discovery tool that integrates three artificial intelligence (AI) models for efficient and accurate virtual screening (VS) of compound libraries.
Area of Science:
- Computational Chemistry
- Drug Discovery
- Artificial Intelligence in Bioinformatics
Background:
- Structure-based virtual screening (VS) using molecular docking is crucial for identifying potential drug candidates.
- Artificial intelligence (AI) methods have shown promise in accelerating protein-ligand docking and scoring.
- Challenges remain in selecting and efficiently implementing appropriate AI-driven VS methods for specific drug discovery applications.
Purpose of the Study:
- To present the Comprehensive VS Platform with AI Engine (CVSP-AIE) for efficient drug discovery from compound libraries.
- To integrate and demonstrate the hierarchical application of three AI models for balancing screening speed and accuracy.
- To provide a user-friendly platform, available as a web server and local package, for initiating and managing VS workflows.
Main Methods:
- Integration of three AI models: KarmaDock (fast docking), CarsiDock (accurate docking), and RTMScore (accurate scoring).
- Hierarchical application of AI models to dynamically balance screening speed and accuracy.
- Development of a workflow including protein structure repair, molecule standardization, binding pose and affinity prediction, and postprocessing analysis.
Main Results:
- The CVSP-AIE platform enables hierarchical screening of 100,000 compounds in 30-45 minutes.
- Outputs include ranked lists of molecules with predicted binding scores, interaction profiles, and chemical space analysis.
- The platform is accessible as an online web server and a local software package for flexible deployment.
Conclusions:
- CVSP-AIE offers an efficient and accurate solution for AI-powered virtual screening in drug discovery.
- The hierarchical application of AI models provides a tunable balance between computational speed and predictive accuracy.
- The platform's accessibility and comprehensive workflow facilitate the identification of bioactive compounds from large libraries.
Related Concept Videos
01:26Drug Discovery: Overview
Drug discovery is a multifaceted process involving extensive screening, testing, and optimization of lead compounds to identify potential new drugs for therapeutic use. It combines several approaches, including screening large numbers of natural products, chemical modification of known active molecules, identification of new drug targets, and rational design based on biological mechanisms and drug-receptor structure. These approaches are carried out in both academic research laboratories and...
01:28Structure-Activity Relationships and Drug Design
Drug design is a dynamic field that involves discovering and developing new medications based on specific biological targets. This process heavily relies on structure-activity relationships (SAR) and quantitative structure-activity relationships (QSAR) to guide the design and optimization of efficient drugs.
SAR studies the intricate relationship between a drug's chemical structure and biological activity. It focuses on understanding how modifications to a drug's structure can influence its...
SAR studies the intricate relationship between a drug's chemical structure and biological activity. It focuses on understanding how modifications to a drug's structure can influence its...