Use of support vector machine to predict the toxicity of aromatic compounds

Support vector machine (SVM) is employed to quantitatively predict the toxicity of 65 aromatic compounds with diverse structure features, and the obtained results are compared systematically with multiple linear regression (MLR), partial least square regression (PLS) and artificial neural network (ANN). It is suggested that SVM possesses higher modeling stability and better generalization ability, especially suitable for nonlinearity and small samples. Therefore it is suggested that SVM has a broad prospect for the evaluation of environmentally toxic chemicals.