Recognition of protease inhibition pattern using topological interaction matrix and genetic algorithm-optimized support vector machines

Proteases are among the most studied diagnostic and therapeutic targets for a variety of human diseases. Intensive research in computational design of protease inhibitors has been done by molecular dynamics simulations, docking and Quantitative Structure-Activity Relationships. In this work, proteochemometrics was applied to the recognition of stable and unstable protease inhibition complexes from a large dataset (>1700) using Genetic Algorithm-optimized Support Vector Machines classifiers. Genetic Algorithm optimized SVM were trained with Topological Autocorrelation Interaction vectors, computed on the protease sequences and the inhibitor 2D structure sketches. Optimum classifier with 10 inputs correctly predicted more than 80% in both training and test sets. PRIB 2008 proceedings found at: http://dx.doi.org/10.1007/978-3-540-88436-1

Contributors: Monash University. Faculty of Information Technology. Gippsland School of Information Technology ;
Chetty, Madhu ;
Ahmad, Shandar ;
Ngom, Alioune ;
Teng, Shyh Wei ;
Third IAPR International Conference on Pattern Recognition in Bioinformatics (PRIB) (3rd : 2008 : Melbourne, Australia) ;
Coverage:
Rights: Copyright by Third IAPR International Conference on Pattern Recognition in Bioinformatics. All rights reserved.