Accurate Prediction of Aquatic Toxicity of Aromatic Compounds Based on Genetic Algorithm and Least Squares Support Vector Machines

Abstract

Quantitative Structure -Toxicity Relationship (QSTR) plays an important role in ecotoxicology for its fast and practical ability to assess the potential negative effects of chemicals. The aim of this investigation was to develop accurate QSTR models for the aquatic toxicity of a large set of aromatic compounds through the combination of Least Squares Support Vector Machines (LS-SVMs) and a Genetic Algorithm (GA). Molecular descriptors calculated by DRAGON package and log P were used to describe the molecular structures. The most relevant descriptors used to build QSTR models were selected by a GA-Variable Subset Selection procedure. Multiple Linear Regression (MLR) and nonlinear LS-SVMs methods were employed to build QSTR models. The predictive ability of the derived models was validated using both the test set, selected from the whole data set by the Kennard -Stone Algorithm, and an external prediction set. The model applicability domain was checked by the leverage approach and the external prediction set was used to verify the predictive reliability of the models. The results indicated that the proposed QSTR models are robust and satisfactory, and can provide a feasible and promising tool for the rapid assessment of the toxicity of chemicals.

Simultaneously Optimized Support Vector Regression Combined With Genetic Algorithm for QSAR Analysis of KDR/VEGFR‐2 Inhibitors

“…Genetic algorithm, derived from Darwin’s theory of natural selection and evolution, is a highly efficient optimization algorithm, which has already been extensively applied in QSAR analysis (15,27,28). Genetic algorithm always coexists with other classification and/or regression techniques, which play the role of fitness function.…”

Bagging for robust non-linear multivariate calibration of spectroscopy

“…Hence, the SPXY-partition is repeated 20 times with different random initializations, and the average RMSEP of the 20 repeats is reported to evaluate the prediction performance. It is to note that the SPXY algorithm is based on a linear distance function; nevertheless its effectiveness for non-linear regression models has been reported in the literature [54].…”

Predicting Skin Permeability by Means of Computational Approaches: Reliability and Caveats in Pharmaceutical Studies

“…59,61 A more statistically rigorous approach was used by Chauhan and Shakya, 86 who used a broad variety of descriptors (Dragon descriptors and Abraham descriptors). They divided the training and the test set by the Kennard−Stone algorithm, 87,88 developed a model combining regression methods and partial least square (PLS) and determined an applicability domain for the model obtained. The descriptors retrieved were the octanol−water partition coefficient, the hydrogen bond number, and the Narumi simple topological index (a descriptor related to molecular branching 89 ).…”