Related Experiment Video
Updated: Jul 15, 2025
Incorporating Target Protein Structure Flexibility and Dynamics in Computational Drug Discovery Using Ensemble-Based Docking Analysis
Published on: June 20, 2025
Benchmarking Cross-Docking Strategies for Structure-Informed Machine Learning in Kinase Drug Discovery
David Schaller1,2, Clara D Christ3, John D Chodera2
1In Silico Toxicology and Structural Bioinformatics, Institute of Physiology, Charité-Universitätsmedizin Berlin, corporate member of Freie Universität Berlin and Humboldt-Universität zu Berlin, Augustenburger Platz 1, 13353 Berlin, Germany.
Accurately predicting protein:ligand complex structures is key for machine learning in drug discovery. Combining docking methods, particularly Posit, significantly improves the prediction of binding poses for kinase inhibitors.
Area of Science:
- Computational chemistry
- Structural biology
- Machine learning in drug discovery
Background:
- Machine learning (ML) is revolutionizing drug discovery, especially small molecule design.
- Accurate prediction of protein:ligand complex structures is crucial for ML-based bioactivity prediction.
- Current methods face limitations in reliably and automatically predicting these complex structures.
Conclusions:
- Ligand-biased and multi-structure docking strategies enhance the accuracy of protein:ligand complex structure prediction.
- The Posit approach offers an efficient method for generating reliable binding poses.
- The findings, while focused on kinases, are potentially transferable to other protein families for ML applications.
Related Concept Videos
01:22Protein-Drug Binding: Determination Methods
Indirect methods involve isolating the bound drug from its free form in biological samples such as blood, serum, or plasma. These techniques aim to measure the percentage of drugs bound to proteins. Equilibrium dialysis is a commonly used method where the free drug concentration at equilibrium is measured by separating the bound...
01:26Drug Discovery: Overview