Premium
Development of migration models for acids in capillary electrophoresis using heuristic and radial basis function neural network methods
Author(s) -
Xue Chunxia,
Yao Xiaojun,
Liu Huanxiang,
Liu Mancang,
Hu Zhide,
Fan Botao
Publication year - 2005
Publication title -
electrophoresis
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.666
H-Index - 158
eISSN - 1522-2683
pISSN - 0173-0835
DOI - 10.1002/elps.200410175
Subject(s) - heuristic , capillary electrophoresis , artificial neural network , set (abstract data type) , biological system , mean squared error , test set , radial basis function , nonlinear system , root mean square , function (biology) , electrophoresis , computer science , mathematics , chromatography , artificial intelligence , chemistry , statistics , physics , biology , quantum mechanics , evolutionary biology , programming language
A quantitative structure–mobility relationship (QSMR) was developed for the absolute mobilities of a diverse set of 277 organic and inorganic acids in capillary electrophoresis based on the descriptors calculated from the structure alone. The heuristic method (HM) and the radial basis function neural networks (RBFNN) were utilized to construct the linear and nonlinear prediction models, respectively. The prediction results were in agreement with the experimental values. The HM model gave a root‐mean‐square (RMS) error of 3.66 electrophoretic mobility units for the training set, 4.67 for the test set, and 3.88 for the whole data set, while the RBFNN gave an RMS error of 2.49, 3.19, and 2.65, respectively. The heuristic linear model could give some insights into the factors that are likely to govern the mobilities of the compounds, however, the prediction results of the RBFNN model seem to be better than that of the HM.