Quantitative modeling for prediction of thermodynamic properties of some pyridine derivatives using molecular descriptors and genetic algorithm‐multiple linear regressions

This paper deals with developing a linear quantitative structure-activity relationship (QSAR) model for predicting the RSK inhibition activity of some new compounds. A dataset consisting of 62 pyrazino [1,2-?] indole, diazepino [1,2-?] indole, and imidazole derivatives with known inhibitory activities was used. Multiple linear regressions (MLR) technique combined with the stepwise (SW) and the genetic algorithm (GA) methods as variable selection tools was employed. For more checking stability, robustness and predictability of the proposed models, internal and external validation techniques were used. Comparison of the results obtained, indicate that the GA-MLR model is superior to the SW-MLR model and that it isapplicable for designing novel RSK inhibitors.

Download Full-text

QSAR study of VEGFR-2 inhibitors by using genetic algorithm-multiple linear regressions (GA-MLR) and genetic algorithm-support vector machine (GA-SVM): a comparative approach

Medicinal Chemistry Research ◽

10.1007/s00044-015-1354-4 ◽

2015 ◽

Vol 24 (7) ◽

pp. 3037-3046 ◽

Cited By ~ 20

Author(s):

Mehdi Nekoei ◽

Majid Mohammadhosseini ◽

Eslam Pourbasheer

Keyword(s):

Genetic Algorithm ◽

Support Vector Machine ◽

Comparative Approach ◽

Support Vector ◽

Multiple Linear Regressions ◽

Qsar Study ◽

Linear Regressions

Download Full-text

QSAR prediction of HIV inhibition activity of styrylquinoline derivatives by genetic algorithm coupled with multiple linear regressions

Medicinal Chemistry Research ◽

10.1007/s00044-010-9542-8 ◽

2011 ◽

Vol 21 (4) ◽

pp. 437-443 ◽

Cited By ~ 11

Author(s):

Nasser Goudarzi ◽

Mohammad Goodarzi ◽

Tao Chen

Keyword(s):

Genetic Algorithm ◽

Multiple Linear Regressions ◽

Inhibition Activity ◽

Hiv Inhibition ◽

Linear Regressions

Download Full-text

Quantitative Structure-Retention Time Relationship for Retention Time of Coffee Flavor Compounds

Advanced Materials Research ◽

10.4028/www.scientific.net/amr.926-930.1010 ◽

2014 ◽

Vol 926-930 ◽

pp. 1010-1013

Author(s):

De Xiang Zhang ◽

Hong Zong Si ◽

Xun Liu

Keyword(s):

Support Vector Machine ◽

Retention Time ◽

Molecular Descriptors ◽

Flavor Compounds ◽

Support Vector ◽

Multiple Linear Regressions ◽

Quantitative Structure ◽

Structure Retention ◽

Linear Regressions ◽

Statistical Results

The coffee flavor compounds acquire a significant place in the improving the flavor of cigarette. In the present paper, the support vector machine is used to develop quantitative relationships between the retention time and four molecular descriptors of 52 compounds. The model of support vector machine gives good statistical results compared to those give by multiple linear regressions and support vector machine. The contribution of each descriptor to structure-retention time relationships was evaluated. It indicates the importance of the atoms number and type of parameter. The proposed method can be successfully used to predict the retention time with only four molecular descriptors which can be calculated directly from molecular structure alone.

Download Full-text