TY - JOUR
T1 - Application of a new SPA-SVM coupling method for QSPR study of electrophoretic mobilities of some organic and inorganic compounds
AU - Goudarzi, Nasser
AU - Goodarzi, Mohammad
AU - Arab Chamjangali, M.
AU - Fatemi, M. H.
PY - 2013/10
Y1 - 2013/10
N2 - In this work, two chemometrics methods are applied for the modeling and prediction of electrophoretic mobilities of some organic and inorganic compounds. The successive projection algorithm, feature selection (SPA) strategy, is used as the descriptor selection and model development method. Then, the support vector machine (SVM) and multiple linear regression (MLR) model are utilized to construct the non-linear and linear quantitative structure-property relationship models. The results obtained using the SVM model are compared with those obtained using MLR reveal that the SVM model is of much better predictive value than the MLR one. The root-mean-square errors for the training set and the test set for the SVM model were 0.1911 and 0.2569, respectively, while by the MLR model, they were 0.4908 and 0.6494, respectively. The results show that the SVM model drastically enhances the ability of prediction in QSPR studies and is superior to the MLR model.
AB - In this work, two chemometrics methods are applied for the modeling and prediction of electrophoretic mobilities of some organic and inorganic compounds. The successive projection algorithm, feature selection (SPA) strategy, is used as the descriptor selection and model development method. Then, the support vector machine (SVM) and multiple linear regression (MLR) model are utilized to construct the non-linear and linear quantitative structure-property relationship models. The results obtained using the SVM model are compared with those obtained using MLR reveal that the SVM model is of much better predictive value than the MLR one. The root-mean-square errors for the training set and the test set for the SVM model were 0.1911 and 0.2569, respectively, while by the MLR model, they were 0.4908 and 0.6494, respectively. The results show that the SVM model drastically enhances the ability of prediction in QSPR studies and is superior to the MLR model.
KW - Electrophoretic mobility
KW - Multiple linear regression
KW - Quantitative structure-mobility relationship
KW - Successive projection algorithm
KW - Support vector machine
UR - http://www.scopus.com/inward/record.url?scp=84883740210&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84883740210&partnerID=8YFLogxK
U2 - 10.1016/j.cclet.2013.06.002
DO - 10.1016/j.cclet.2013.06.002
M3 - Article
AN - SCOPUS:84883740210
SN - 1001-8417
VL - 24
SP - 904
EP - 908
JO - Chinese Chemical Letters
JF - Chinese Chemical Letters
IS - 10
ER -