Genetic algorithm for CoMFA setting optimization: 3D‐QSAR study on α‐aminosuberic acid derivatives as anti‐cancer compounds. (6th August 2013)

• Record Type: Journal Article
• Authors: Ebrahimi, S.; Azimi, G.; Akhlaghi, Y.; Kompany‐Zareh, M.
• Other Names: Abdollahi Hamid guestEditor.
• Is Part Of: Journal of chemometrics. Volume 27:Number 10(2013:Oct.)
• Page Start: 323
• Page End: 329
• Publication Date: 2013-08-06
• Subjects: 3D‐QSAR -- CoMFA -- histone deacetylase inhibitors -- genetic algorithm -- optimization; Chemistry -- Mathematics -- Periodicals; Chemistry -- Statistical methods -- Periodicals; 542.85
• DOI: 10.1002/cem.2524
• Languages: English
• ISSNs: 0886-9383

Abstract

Abstract : In most three‐dimensional quantitative structure–activity relationship studies, default SYBYL parameters for comparative molecular field analysis (CoMFA) have been used to derive the models. In this work, a genetic algorithm has been employed for the first time to select the best set of parameters. Three‐dimensional quantitative structure–activity relationship analysis of a set of 33 analogues of α‐aminosuberic acid as a new generation of histone deacetylase inhibitors was performed. Contrary to the ordinary and region focusing CoMFA models, in genetic algorithm optimized model, H‐bond was the preferred field type. Genetic algorithm optimized model showed a better predictive ability ( r 2 pred = 0.982, q 2 LOO = 0.828, and q 2 LMO = 0.795) compared with ordinary ( r 2 pred = 0.937, q 2 LOO = 0.629, and q 2 LMO = 0.537) and region focusing ( r 2 pred = 0.954, q 2 LOO = 0.665, and q 2 LMO = 0.564) models derived by CoMFA default set of parameters. Copyright © 2013 John Wiley & Sons, Ltd. Abstract : Genetic algorithm has been employed to select the best set of SYBYL parameters for CoMFA modeling. 3D‐QSAR analysis on a set of 33 analogues of α‐amino suberic acid as anticancer compounds was performed. Contrary to the ordinary and region focusing CoMFA models with default parameters in SYBYL, in genetic algorithm optimized model, H‐bond was the preferred field type. Genetic algorithm optimized models showed also a better predictive ability compared with ordinary CoMFA models.