Abstract
The ability to find novel bioactive scaffolds in compound similarity-based virtual screening experiments has been studied comparing Tanimoto-based, ranking-based, voting, and consensus scoring protocols. Ligand sets for seven well-known drug targets (CDK2, COX2, estrogen receptor, neuraminidase, HIV-1 protease, p38 MAP kinase, thrombin) have been assembled such that each ligand represents its own unique chemotype, thus ensuring that each similarity recognition event between ligands constitutes a scaffold hopping event. In a series of virtual screening studies involving 9969 MDDR compounds as negative controls it has been found that atom pair descriptors and 3D pharmacophore fingerprints combined with ranking, voting, and consensus scoring strategies perform well in finding novel bioactive scaffolds. In addition, often superior performance has been observed for similarity-based virtual screening compared to structure-based methods. This finding suggests that information about a target obtained from known bioactive ligands is as valuable as knowledge of the target structures for identifying novel bioactive scaffolds through virtual screening.
Keywords
Virtual screeningPharmacophoreRanking (information retrieval)Similarity (geometry)ChemistryVotingMajority ruleComputational biologyIn silicoChemical similarityArtificial intelligenceComputer scienceData miningMachine learningStructural similarityImage (mathematics)BiochemistryGeneBiology
Affiliated Institutions
Related Publications
Protein-Based Virtual Screening of Chemical Databases. 1. Evaluation of Different Docking/Scoring Combinations
Three different database docking programs (Dock, FlexX, Gold) have been used in combination with seven scoring functions (Chemscore, Dock, FlexX, Fresno, Gold, Pmf, Score) to as...
InteractionGraphNet: A Novel and Efficient Deep Graph Representation Learning Framework for Accurate Protein–Ligand Interaction Predictions
Accurate quantification of protein-ligand interactions remains a key challenge to structure-based drug design. However, traditional machine learning (ML)-based methods based on ...
<i>In silico</i>pharmacology for drug discovery: applications to targets and beyond
Computational ( in silico ) methods have been developed and widely applied to pharmacology hypothesis development and testing. These in silico methods include databases, quantit...
A general approach for developing system‐specific functions to score protein–ligand docked complexes using support vector inductive logic programming
Abstract Despite the increased recent use of protein–ligand and protein–protein docking in the drug discovery process due to the increases in computational power, the difficulty...
Predicting Protein–Ligand Docking Structure with Graph Neural Network
Modern day drug discovery is extremely expensive and time consuming. Although computational approaches help accelerate and decrease the cost of drug discovery, existing computat...
Publication Info
- Year
- 2006
- Type
- article
- Volume
- 49
- Issue
- 5
- Pages
- 1536-1548
- Citations
- 176
- Access
- Closed
External Links
Social Impact
Altmetric
PlumX Metrics
Social media, news, blog, policy document mentions
Citation Metrics
176
OpenAlex
Cite This
Qiang Zhang,
Ingo Muegge
(2006).
Scaffold Hopping through Virtual Screening Using 2D and 3D Similarity Descriptors: Ranking, Voting, and Consensus Scoring.
Journal of Medicinal Chemistry
, 49
(5)
, 1536-1548.
https://doi.org/10.1021/jm050468i
Identifiers
- DOI
- 10.1021/jm050468i