Letters in Drug Design & Discovery

G. Perry
University of Texas
San Antonio, TX
USA
Email: lddd@benthamscience.org

Back

Prediction of Specificity and Cross-Reactivity of Kinase Inhibitors

Author(s): Nitish Kumar Mishra, Gajendra P.S. Raghava.

Abstract:

Designing kinase inhibitors is always an area of interest because kinases are involved in many diseases. In the last one decade a large number of kinase inhibitors have been launched successfully; six inhibitors have been approved by FDA and more are under clinical trials. Cross-reactivity or off-target is one of the major problems in designing inhibitors against protein kinases; as human, have more than 500 kinases with high sequence similarity. In this study an attempt has been made to develop a model for predicting specificity and cross-reactivity of kinase inhibitors. The dataset used for testing and training consists of binding affinities of 20 chemical kinase inhibitors with protein kinases.

We developed QSAR based SVM models for predicting binding affinity of an inhibitor against protein kinases using most relevant 5,10 and 15 structure descriptors and achieving average correlation of 0.64, 0.488 and 0.442 respectively. In order to predict specificity and cross-reactivity of an inhibitor, we developed 16 QSAR based SVM models for 16 protein kinases; one model for each kinase. We achieved average correlation 0.719 between actual and predicted binding affinity using kinase specific models. Based on the above study a web server DMKPred has been developed for predicting binding affinity of a drug molecule with 16 kinases. The SVM based model used in this study can be used to predict kinase specific inhibitors. This study will be useful for designing kinase specific inhibitors.

Keywords: Support vector machine (SVM), Molecular descriptors, Kinase inhibitors, QSAR, Dissociation constant, Prediction

Order Reprints Order Eprints Rights & PermissionsPrintExport

Article Details

VOLUME: 8
ISSUE: 3
Year: 2011
Page: [223 - 228]
Pages: 6
DOI: 10.2174/157018011794578204
Price: $58