Related Experiment Video
Updated: Jul 6, 2026
16:41
A Protocol for Computer-Based Protein Structure and Function Prediction
Published on: November 3, 2011
Structure-based virtual screening with supervised consensus scoring: evaluation of pose prediction and enrichment
Reiji Teramoto1, Hiroaki Fukunishi
1Bio-IT Center and Nano Electronics Research Laboratories, NEC Corporation, 34, Miyukigaoka, Tsukuba, Ibaraki 305-8501, Japan. r-teramoto@bq.jp.nec.com
Journal of Chemical Information and Modeling
|March 6, 2008
Summary
Supervised consensus scoring (SCS) improves virtual screening enrichment by combining multiple scoring functions. This method is competitive or superior to single functions and aids in identifying new ligands using protein-ligand complex structures.
Area of Science:
- Computational chemistry
- Drug discovery
- Bioinformatics
Background:
- Accurate evaluation of ligand conformations is vital for structure-based virtual screening.
- Existing scoring functions show variable performance across different target proteins.
- A standardized method to select the best scoring function for a given target is lacking.
Purpose of the Study:
- To develop a novel method for enhancing virtual screening enrichment using existing scoring functions.
- To assess the performance of the supervised consensus scoring (SCS) method against established scoring functions.
Main Methods:
- Applied supervised consensus scoring (SCS), a supervised learning approach correlating binding free energy with root-mean-square deviation (RMSD).
- Evaluated SCS and five other scoring functions (F-Score, G-Score, D-Score, ChemScore, PMF) on three target proteins: thymidine kinase, thrombin, and PPARgamma.
- Analyzed docking poses and enrichment rates to compare method performance.
Main Results:
- SCS demonstrated competitive or superior enrichment compared to the best single scoring function across all tested targets.
- Enrichment performance of SCS was influenced by the performance of the individual scoring functions it integrated.
- A correlation was observed between screening enrichment and the average centroid distance of top-scored docking poses.
Conclusions:
- Supervised consensus scoring (SCS) is a successful and effective method for improving virtual screening enrichment.
- SCS requires only a single 3D structure of a protein-ligand complex, making it practical for identifying novel ligands.
- The findings suggest SCS can be a valuable tool in drug discovery pipelines.
Related Concept Videos
01:49Conserved Binding Sites
Many proteins’ biological role depends on their interactions with their ligands, small molecules that bind to specific locations on the protein known as ligand-binding sites. Ligand-binding sites are often conserved among homologous proteins as these sites are critical for protein function.
Binding sites are often located in large pockets, and if their location on a protein’s surface is unknown, it can be predicted using various approaches. The energetic method computationally analyses the...
Binding sites are often located in large pockets, and if their location on a protein’s surface is unknown, it can be predicted using various approaches. The energetic method computationally analyses the...
01:49Conserved Binding Sites
Many proteins’ biological role depends on their interactions with their ligands, small molecules that bind to specific locations on the protein known as ligand-binding sites. Ligand-binding sites are often conserved among homologous proteins as these sites are critical for protein function.
Binding sites are often located in large pockets, and if their location on a protein’s surface is unknown, it can be predicted using various approaches. The energetic method computationally analyses the...
Binding sites are often located in large pockets, and if their location on a protein’s surface is unknown, it can be predicted using various approaches. The energetic method computationally analyses the...
02:27Predicting Molecular Geometry
VSEPR Theory for Determination of Electron Pair Geometries