Open AccessDibenzoylhydrazines as Insect Growth Modulators: Topology-Based QSAR Modelling
Author(s) -
Jean Doucet,
A. DoucetPanaye
Publication year - 2020
Publication title -
advances in sciences and engineering
Language(s) - English
Resource type - Journals
ISSN - 2046-0392
DOI - 10.32732/ase.2020.12.1.28
Subject(s) - multilinear map , quantitative structure–activity relationship , robustness (evolution) , support vector machine , multilayer perceptron , perceptron , partial least squares regression , computer science , projection pursuit , artificial neural network , artificial intelligence , projection (relational algebra) , linear regression , regression , regression analysis , biological system , mathematics , topology (electrical circuits) , machine learning , algorithm , chemistry , biology , statistics , pure mathematics , biochemistry , combinatorics , gene
Dibenzoylhydrazines Xa-(C6H5)a-CO-N-(t-Bu)-NH-CO-(C6H5)b-Yb are efficient insect growth regulators with high activity and selectivity toward lepidopteran and coleopteran pests. For 123 congeneric molecules, a quantitative structure activity relationship model was built in the framework of the QSARINS package using 2D, Topology-based, PaDEL descriptors. Variable selection by GA-MLR allows building an efficient multilinear regression linking pEC50 values to nine structural variables. Robustness and quality of the model were carefully examined at various levels: data-fitting (recall), leave-one (or some) - out, internal and external validation (including random splitting), points not in depth investigated in previous works. Various Machine Learning approaches (Partial Least Squares Regression, Projection Pursuit Regression, Linear Support Vector Machine or Three Layer Perceptron Artificial Neural Network) confirm the validity of the analysis, giving highly consistent results of comparable quality, with only a slight advantage for the three-layer perceptron.