New Hybrid Genetic Based Support Vector Regression as QSAR Approach for Analyzing Flavonoids-GABA(A) Complexes

Abstract

Several studies were conducted in past years which used the evolutionary process of Genetic Algorithms for optimizing the Support Vector Regression parameter values although, however, few of them were devoted to the simultaneously optimization of the type of kernel function involved in the established model. The present work introduces a new hybrid genetic-based Support Vector Regression approach, whose statistical quality and predictive capability is afterward analyzed and compared to other standard chemometric techniques, such as Partial Least Squares, Back-Propagation Artificial Neural Networks, and Support Vector Machines based on Cross-Validation. For this purpose, we employ a data set of experimentally determined binding affinity constants toward the benzodiazepine binding site of the GABA (A) receptor complex on 78 flavonoid ligands.

Sustainable Synthesis of Flavonoid Derivatives, QSAR Study and Insecticidal Activity against the Fall Armyworm, Spodoptera frugiperda (Lep.: Noctuidae)

“…The quality of the results achieved with this technique is quite close to that obtained by performing an exact (combinatorial) full search (FS) of molecular descriptors, although, of course, it requires much less computational work (45). In addition, the RM provides models with statistical parameters better than those from the forward stepwise regression procedure and similar to those from the more elaborated genetic algorithms approach (36,37,46,47). All the models presented here were properly validated.…”

A QSAR Analysis of Flavone Derivatives of Antimalarial Compounds Based on PM3 Semi-Empirical Method

“…The different substituents on the main skeleton of flavone derivatives can lead to differences in the atomic charge and the nature of the compound and may lead to differences in drug activity of the flavone compounds [16,22]. Table-5 shows that the flavone derivatives have a different structure, which can be produced different antimalarial activity.…”

“…Multilinear Regression method is a statistical technique to analyze the dataset of the series flavone derivative compounds, such as some of the development of the equation QSAR models to predict the theoretical IC50 value of a drug compound based on the IC50 value of experimental results is known. In this way, we resort to the replacement method (RM) as a variable selection approach was applied to the pond section that contains more than a thousand descriptors because this technique has managed to select the relevant structural descriptors [14][15][16][17]. Finally, another main interest of present research is to apply the so derived QSAR models for estimating the antiplasmodial potency on some new structures, for which there still are no experimental activities.…”

Chemometrics tools in QSAR/QSPR studies: A historical perspective

“…After the introduction of support vector machine (SVM), the combination of GA and SVM(GA-SVM) have also reported for use in QSAR/QSPR modeling [194][195][196][197]. approaches as the fitness function of GA [198].…”