Article

QSPR Study of Fluorescence Wavelengths (λex/λem) Based on the Heuristic Method and Radial Basis Function Neural Networks

University of Paris-Est, La Haye-Descartes, Centre, France
QSAR & Combinatorial Science (Impact Factor: 1.55). 02/2006; 25(2):147 - 155. DOI: 10.1002/qsar.200510142

ABSTRACT The Quantitative Structure–Property Relationship (QSPR) method was performed to study the fluorescence excitation wavelengths (λex) and emission wavelengths (λem) of 64 fluorescent probes. The probes included the derivatives of dansyl, bimane, pyrene, benzofurazan, nonaphthalene, coumarin, anthracene and fluorescein, with the wavelength ranging from 300 nm to 600 nm. The Heuristic Method (HM) and Radial Basis Function Neural Networks (RBFNNs) were employed to construct linear and nonlinear prediction models, respectively. The proposed linear models for λex and λem contain five descriptors with the squared correlation coefficients R2 of 0.888 and 0.897, respectively. Better prediction results were obtained from RBFNN model, with the squared correlation coefficients R2 of 0.948 and 0.939 for λex and λem, respectively. The descriptors used in the models were discussed in detail too.

0 Followers
 · 
321 Views
  • [Show abstract] [Hide abstract]
    ABSTRACT: Quantitative structure–activity relationship (QSAR) model was used to predict and explain binding constant (log K) determined by fluorescence quenching. This method allowed us to predict binding constants of a variety of compounds with human serum albumin (HSA) based on their structures alone. Stepwise multiple linear regression (MLR) and nonlinear radial basis function neural network (RBFNN) were performed to build the models. The statistical parameters provided by the MLR model (R2=0.8521, RMS=0.2678) indicated satisfactory stability and predictive ability while the RBFNN predictive ability is somewhat superior (R2=0.9245, RMS=0.1736). The proposed models were used to predict the binding constants of two bioactive components in traditional Chinese medicines (isoimperatorin and chrysophanol) whose experimental results were obtained in our laboratory and the predicted results were in good agreement with the experimental results. This QSAR approach can contribute to a better understanding of structural factors of the compounds responsible for drug–protein interactions, and can be useful in predicting the binding constants of other compounds.Research Highlights► QSAR models for binding constants of some compounds to HSA were developed. ► The models provide a simple and straightforward way to predict binding constant. ► QSAR can give some insight into structural features related to binding behavior.
    Journal of Luminescence 01/2011; 131(1):126-133. DOI:10.1016/j.jlumin.2010.09.036 · 2.37 Impact Factor
  • [Show abstract] [Hide abstract]
    ABSTRACT: Models to predict binding constant (logK) to bovine serum albumin (BSA) should be very useful in the pharmaceutical industry to help speed up the design of new compounds, especially as far as pharmacokinetics is concerned. We present here an extensive list of logK binding constants for thirty-five compounds to BSA determined by florescence quenching from the literature. These data have allowed us the derivation of a quantitative structure-property relationship (QSPR) model to predict binding constants to BSA of compounds on the basis of their structure. A stepwise multiple linear regression (MLR) was performed to build the model. The statistical parameter provided by the MLR model (R = 0.9200, RMS = 0.3305) indicated satisfactory stability and predictive ability for the model. Using florescence quenching spectroscopy, we also experimentally determined the binding constants to BSA for two bioactive components in traditional Chinese medicines. Using the proposed model it was possible to predict the binding constants for each, which were in good agreement with the experimental results. This QSPR approach can contribute to a better understanding of structural factors of the compounds responsible for drug-protein interactions, and be useful in predicting the binding constants of other compounds.
    Central European Journal of Chemistry 01/2009; 7(1):59-65. DOI:10.2478/s11532-008-0095-3 · 1.33 Impact Factor
  • [Show abstract] [Hide abstract]
    ABSTRACT: Quantitative relationships between molecular structures and bioactivities of a set of CCR5 inhibitor derivatives were discovered. We have demonstrated the detailed application of two efficient nonlinear methods, general regression and radial basis function neural networks, for evaluation of quantitative structure–activity relationships of the studied compounds. Components produced by principal component analysis were used as input of the developed nonlinear models. Comparison between predictability of PC-GRNNs and PC-RBFNNs indicated that later method has higher ability to predict the activity of the studied molecules. In order to design novel derivatives of inhibitors with high activity and low side effects, and because experimental and calculated activities of molecules employed in the model development step, shown a good correlation, developed PC-RBFNNs QSAR model was used to calculate inhibitory activities of some suggested compounds.
    Medicinal Chemistry Research 10/2011; 21(10). DOI:10.1007/s00044-011-9863-2 · 1.61 Impact Factor