Frequent substructure-based approaches for classifying chemical compounds
Authors:
- 27 June 2005
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Knowledge and Data Engineering
- Vol. 17 (8) , 1036-1050
Abstract
Computational techniques that build models to correctly assign chemical compounds to various classes of interest have many applications in pharmaceutical research and are used extensively at various phases during the drug development process. These techniques are used to solve a number of classification problems such as predicting whether or not a chemical compound has the desired biological activity, is toxic or nontoxic, and filtering out drug-like compounds from large compound libraries. This paper presents a substructure-based classification algorithm that decouples the substructure discovery process from the classification model construction and uses frequent subgraph discovery algorithms to find all topological and geometric substructures present in the data set. The advantage of this approach is that during classification model construction, all relevant substructures are available allowing the classifier to intelligently select the most discriminating ones. The computational scalability is ensured by the use of highly efficient frequent subgraph discovery algorithms coupled with aggressive feature selection. Experimental evaluation on eight different classification problems shows that our approach is computationally scalable and, on average, outperforms existing schemes by 7 percent to 35 percent.Keywords
This publication has 64 references indexed in Scilit:
- Comparison of Support Vector Machine and Artificial Neural Network Systems for Drug/Nondrug ClassificationJournal of Chemical Information and Computer Sciences, 2003
- Scalable algorithms for association miningIEEE Transactions on Knowledge and Data Engineering, 2000
- Recursive Partitioning Analysis of a Large Structure−Activity Data Set Using Three-Dimensional DescriptorsJournal of Chemical Information and Computer Sciences, 1998
- New perspectives in lead generation II: Evaluating molecular diversityDrug Discovery Today, 1996
- Diversity Profiling and Design Using 3D Pharmacophores: Pharmacophore-Derived Queries (PDQ)Journal of Chemical Information and Computer Sciences, 1996
- Electrotopological State Indices for Atom Types: A Novel Combination of Electronic, Topological, and Valence State InformationJournal of Chemical Information and Computer Sciences, 1995
- Inductive Logic Programming: Theory and methodsThe Journal of Logic Programming, 1994
- Automatic generation of 3D-atomic coordinates for organic moleculesTetrahedron Computer Methodology, 1990
- Atom pairs as molecular features in structure-activity studies: definition and applicationsJournal of Chemical Information and Computer Sciences, 1985
- The Correlation of Biological Activity of Plant Growth Regulators and Chloromycetin Derivatives with Hammett Constants and Partition CoefficientsJournal of the American Chemical Society, 1963