Authors: Ghosh, P.; Bagchi, M. C.

Source: Current Medicinal Chemistry, Volume 16, Number 30, October 2009 , pp. 4032-4048(17)

Publisher: Bentham Science Publishers

Abstract:

With a view to the rational design of selective quinoxaline derivatives, 2D and 3D-QSAR models have been developed for the prediction of anti-tubercular activities. Successful implementation of a predictive QSAR model largely depends on the selection of a preferred set of molecular descriptors that can signify the chemico-biological interaction. Genetic algorithm (GA) and simulated annealing (SA) are applied as variable selection methods for model development. 2D-QSAR modeling using GA or SA based partial least squares (GA-PLS and SA-PLS) methods identified some important topological and electrostatic descriptors as important factor for tubercular activity. Kohonen network and counter propagation artificial neural network (CP-ANN) considering GA and SA based feature selection methods have been applied for such QSAR modeling of Quinoxaline compounds. Out of a variable pool of 380 molecular descriptors, predictive QSAR models are developed for the training set and validated on the test set compounds and a comparative study of the relative effectiveness of linear and non-linear approaches has been investigated. Further analysis using 3D-QSAR technique identifies two models obtained by GA-PLS and SA-PLS methods leading to anti-tubercular activity prediction. The influences of steric and electrostatic field effects generated by the contribution plots are discussed. The results indicate that SA is a very effective variable selection approach for such 3D-QSAR modeling.

Keywords: Quinoxaline derivatives; Quantitative Structure Activity Relationship (QSAR; 2D and 3D descriptors; genetic algorithm (GA); simulated annealing (SA); Partial Least Squares (PLS); counter propagation artificial neural network (CP-

Document Type: Research article

DOI: http://dx.doi.org/10.2174/092986709789352303

Affiliations: 1: Structural Biology and Bioinformatics Division, Indian Institute of Chemical Biology, 4 Raja S.C. Mullick Road, Jadavpur, Kolkata-700032, India.

Publication date: 2009-10-01

More about this publication?

• Current Medicinal Chemistry covers all the latest and outstanding developments in medicinal chemistry and rational drug design. Each issue contains a series of timely in-depth reviews written by leaders in the field covering a range of the current topics in medicinal chemistry. Current Medicinal Chemistry is an essential journal for every medicinal chemist who wishes to be kept informed and up-to-date with the latest and most important developments.

Related content

• In this: publication
• By this: publisher
• In this Subject: Pharmacology
• By this author: Ghosh, P. ;  Bagchi, M. C.

Website © Publishing Technology. Article copyright remains with the publisher, society or author(s) as specified within the article.

• Terms and conditions
• Privacy policy
• Information for advertisers