Title: Models for the prediction of melanocortin-4 receptor agonist activity of 4-substituted piperidin-4-ol

Authors: Monika Gupta; A.K. Madan

Addresses: Faculty of Pharmaceutical Sciences, M.D. University, Rohtak 124 001, India ' Faculty of Pharmaceutical Sciences, Pt. B. D. Sharma University of Health Sciences, Rohtak 124 001, India

Abstract: In the present study both classification and correlation techniques have been successfully employed for the development of the models of diverse nature for the prediction of melanocortin 4-receptor (MC4 R) agonist activity using a dataset comprising of 56 analogues of 4-substituted piperidine-4-ol derivatives. Decision tree (DT), random forest (RF), moving average analysis (MAA) and multiple linear regression (MLR) were utilised for development of the said models. The statistical significance of models was assessed through specificity, sensitivity, overall accuracy, Mathew's correlation coefficient (MCC) and intercorrelation analysis. High accuracy of prediction up to 98% was observed using these models. Proposed models offer vast potential for providing lead structures for the development of potent therapeutic agents for the treatment of male sexual dysfunction.

Keywords: moving average analysis; decision tree; random forest; molecular descriptors; MC4 R agonist; piperidin-4-ol; modelling; melanocortin-4 receptor agonist activity; multiple linear regression; lead structures; therapeutic agents; male sexual dysfunction; treatment.

DOI: 10.1504/IJCBDD.2013.056710

International Journal of Computational Biology and Drug Design, 2013 Vol.6 No.4, pp.294 - 317

Received: 12 Jan 2012
Accepted: 03 Sep 2012

Published online: 27 Aug 2013 *

Full-text access for editors Access for subscribers Purchase this article Comment on this article