Artificial neural network-based transformation for nonlinear partial least-square regression with application to QSAR studies.

In the present study a new version of nonlinear partial least-square method based on artificial neural network transformation (ANN-NLPLS) has been proposed. This algorithm firstly transforms the training descriptors into the hidden layer outputs using the universal nonlinear mapping carried by an artificial neural network, and then utilizes PLS to relate the outputs of the hidden layer to the bioactivities. The weights between the input and hidden layers are optimized by a particle swarm optimization (PSO) method using the criterion of minimized model error via PLS modeling. An F-statistic is introduced to determine automatically the number of PLS components during the weight optimization. The performance is assessed using a simulated data set and two quantitative structure-activity relation (QSAR) data sets. Results of these three data sets demonstrate that ANN-NLPLS offers enhanced capacity in modeling nonlinearity while circumventing the overfitting frequently involved in nonlinear modeling.

[1]  J. Gasteiger,et al.  ITERATIVE PARTIAL EQUALIZATION OF ORBITAL ELECTRONEGATIVITY – A RAPID ACCESS TO ATOMIC CHARGES , 1980 .

[2]  Jian-Hui Jiang,et al.  Optimized Block-wise Variable Combination by Particle Swarm Optimization for Partial Least Squares Modeling in Quantitative Structure-Activity Relationship Studies , 2005, J. Chem. Inf. Model..

[3]  B. Ghosh,et al.  Synthesis, screening and quantitative structure-activity relationship (QSAR) studies of some glutamine analogues for possible anticancer activity. , 2002, Bioorganic & medicinal chemistry.

[4]  Josef Havel,et al.  Artificial neural networks based on genetic input selection for quantification in overlapped capillary electrophoresis peaks. , 2004, Talanta.

[5]  Lemont B. Kier,et al.  The Electrotopological State: An Atom Index for QSAR , 1991 .

[6]  Jian-Hui Jiang,et al.  Piecewise Hypersphere Modeling by Particle Swarm Optimization in QSAR Studies of Bioactivities of Chemical Compounds , 2005, J. Chem. Inf. Model..

[7]  P. Jurs,et al.  Development and use of charged partial surface area structural descriptors in computer-assisted quantitative structure-property relationship studies , 1990 .

[8]  Desire L. Massart,et al.  Detection of nonlinearity in multivariate calibration , 1998 .

[9]  Lemont B. Kier,et al.  The electrotopological state: structure information at the atomic level for molecular graphs , 1991, J. Chem. Inf. Comput. Sci..

[10]  Rajni Garg,et al.  Comparative quantitative structure-activity relationship studies (QSAR) on non-benzodiazepine compounds binding to benzodiazepine receptor (BzR). , 2004, Chemical reviews.

[11]  Ru-Qin Yu,et al.  Hybridized particle swarm algorithm for adaptive structure training of multilayer feed‐forward neural network: QSAR studies of bioactivity of organic compounds , 2004, J. Comput. Chem..

[12]  S. Wold.  Nonlinear partial least squares modelling II. Spline inner relation , 1992 .

[13]  S. Gayen,et al.  5-N-Substituted-2-(substituted benzenesulphonyl) glutamines as antitumor agents. Part II: synthesis, biological activity and QSAR study. , 2004, Bioorganic & medicinal chemistry.

[14]  Thomas J. McAvoy,et al.  Nonlinear PLS Modeling Using Neural Networks , 1992 .

[15]  Lemont B. Kier,et al.  Electrotopological State Indices for Atom Types: A Novel Combination of Electronic, Topological, and Valence State Information , 1995, J. Chem. Inf. Comput. Sci..

[16]  Bogdan Suchacz,et al.  The recognition of similarities in trace elements content in medicinal plants using MLP and RBF neural networks. , 2006, Talanta.