TY - JOUR
T1 - QSPR study of partition coefficient (Ko/w) of some organic compounds using radial basic function-partial least square (RBF-PLS)
AU - Goudarzi, Nasser
AU - Goodarzi, Mohammad
N1 - Copyright:
Copyright 2020 Elsevier B.V., All rights reserved.
PY - 2010
Y1 - 2010
N2 - In this work, we introduce a new method ability radial basic function-partial least square (RBFPLS) with high accuracy and precision in QSPR studies. Three quantitative structure-propertty relationship (QSPR) methods have been compared for the prediction of n-octanol-water partition coefficients (Ko/w) of some organic compounds. The multiple linear regressions (MLR), partial least square (PLS) and radial basis function-partial least squares (RBF-PLS) models were employed to construct linear and nonlinear models to predict of Ko/w. The theoretical descriptors that calculated by Dragon and Gaussian 98 were explored by stepwise regressions, encoding different aspects of the topological, geometrical and electronic molecular structures. The root means square error of prediction (RMSEP) for training and prediction sets by MLR, PLS and RBF-PLS models were 0.4022, 0.4128, 0.3050, 0.3564, 0.0364 and 0.0533, respectively. Also, the relative standard error of prediction (RSEP) for training and prediction sets by MLR, PLS and RBF-PLS models were 13.24, 13.60, 10.04, 11.74, 1.197 and 1.757 respectively. The resultant data explained that RBFPLS produced better results than PLS and MLR.
AB - In this work, we introduce a new method ability radial basic function-partial least square (RBFPLS) with high accuracy and precision in QSPR studies. Three quantitative structure-propertty relationship (QSPR) methods have been compared for the prediction of n-octanol-water partition coefficients (Ko/w) of some organic compounds. The multiple linear regressions (MLR), partial least square (PLS) and radial basis function-partial least squares (RBF-PLS) models were employed to construct linear and nonlinear models to predict of Ko/w. The theoretical descriptors that calculated by Dragon and Gaussian 98 were explored by stepwise regressions, encoding different aspects of the topological, geometrical and electronic molecular structures. The root means square error of prediction (RMSEP) for training and prediction sets by MLR, PLS and RBF-PLS models were 0.4022, 0.4128, 0.3050, 0.3564, 0.0364 and 0.0533, respectively. Also, the relative standard error of prediction (RSEP) for training and prediction sets by MLR, PLS and RBF-PLS models were 13.24, 13.60, 10.04, 11.74, 1.197 and 1.757 respectively. The resultant data explained that RBFPLS produced better results than PLS and MLR.
KW - MLR
KW - N-octanol-water partition coefficients
KW - PLS
KW - Quantitative structure-activity relationship
KW - RBF-PLS
UR - http://www.scopus.com/inward/record.url?scp=77956443698&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=77956443698&partnerID=8YFLogxK
U2 - 10.1590/S0103-50532010000900027
DO - 10.1590/S0103-50532010000900027
M3 - Article
AN - SCOPUS:77956443698
SN - 0103-5053
VL - 21
SP - 1776
EP - 1783
JO - Journal of the Brazilian Chemical Society
JF - Journal of the Brazilian Chemical Society
IS - 9
ER -