The Receptor-like Neural Network for Modeling Corticosteroid and Testosterone Binding Globulins

A neural-net method for simulation of corticosteroid and testosterone binding globulin (CBG, TBG)-ligand interactions is presented. Molecular modeling provides the geometry and partial atomic charges of 31 steroid molecules. The atomic coordinates within the molecule of the compound of the highest affinity are then used to train a self-organizing map (SOM) that forms a template for the comparison to other molecules. Comparison is done using a series of normalized patterns produced by the SOM. The template SOM, after overlaying on the set of random vectors, mimics the topology of the receptor site and is used to train unsupervisedly a neuron capable of recognizing the degree of similarity between the reference and tested patterns. A good correlation is observed for signals generated by the neuron plotted against the experimental CBG affinities. For TBG affinity modeling a modified procedure is designed which is capable of separating electrostatic and shape effects. The high predictive power of the model is achieved by keeping close analogy to the processes taking place at the real receptor sites.

[1]  Jaroslaw Polanski,et al.  Neural Nets for the Simulation of Molecular Recognition within MS-Windows Environment , 1996, J. Chem. Inf. Comput. Sci..

[2]  Johann Gasteiger,et al.  Abbildung elektrostatischer Potentiale muscarinischer und nicotinischer Agonisten mit künstlichen neuronalen Netzen , 1994 .

[3]  K. Mickelson,et al.  Steroid-protein interactions. Human corticosteroid binding globulin: some physicochemical properties and binding specificity. , 1981, Biochemistry.

[4]  S J Peterson,et al.  QSAR's from similarity matrices. Technique validation and application in the comparison of different similarity evaluation methods. , 1993, Journal of medicinal chemistry.

[5]  G M Crippen,et al.  Combined distance geometry analysis of dihydrofolate reductase inhibition by quinazolines and triazines. , 1983, Journal of medicinal chemistry.

[6]  A. Good,et al.  Structure-activity relationships from molecular similarity matrices. , 1993, Journal of medicinal chemistry.

[7]  L. Kier.  Indexes of molecular shape from chemical graphs , 1987, Medicinal research reviews.

[8]  J. Gasteiger,et al.  FROM ATOMS AND BONDS TO THREE-DIMENSIONAL ATOMIC COORDINATES : AUTOMATIC MODEL BUILDERS , 1993 .

[9]  J. Gasteiger,et al.  Mapping the Electrostatic Potential of Muscarinic and Nicotinic Agonists with Artificial Neural Networks , 1994 .

[10]  J. Zupan,et al.  REPRESENTATION OF MOLECULAR ELECTROSTATIC POTENTIALS BY TOPOLOGICAL FEATURE MAPS , 1994 .

[11]  Ioan Motoc,et al.  Molecular Shape Descriptors , 1983, Steric Effects in Drug Design.

[12]  Norihiko Tanimoto,et al.  Synthese von natürlich vorkommendem (−)‐Calyculin A , 1994 .

[13]  J. White,et al.  Photoassisted Water-Gas Shift Reaction over Platinized TiO2 Catalysts. , 1980 .

[14]  A. Hopfinger.  A QSAR investigation of dihydrofolate reductase inhibition by Baker triazines based upon molecular shape analysis , 1980 .

[15]  J. Gasteiger,et al.  Autocorrelation of Molecular Surface Properties for Modeling Corticosteroid Binding Globulin and Cytosolic Ah Receptor Activity by Neural Networks , 1995 .

[16]  R. Cramer,et al.  Comparative molecular field analysis (CoMFA). 1. Effect of shape on binding of steroids to carrier proteins. , 1988, Journal of the American Chemical Society.

[17]  Gerrit Kateman,et al.  USING ARTIFICIAL NEURAL NETWORKS FOR SOLVING CHEMICAL PROBLEMS .2. KOHONEN SELF-ORGANIZING FEATURE MAPS AND HOPFIELD NETWORKS , 1994 .

[18]  A. J. Hopfinger.  THEORY AND APPLICATION OF MOLECULAR POTENTIAL ENERGY FIELDS IN MOLECULAR SHAPE ANALYSIS: A QUANTITATIVE STRUCTURE-ACTIVITY RELATIONSHIP STUDY OF 2,4-DIAMINO-5-BENZYLPYRIMIDINES AS DIHYDROFOLATE REDUCTASE INHIBITORS , 1983 .

[19]  Zeno Simon,et al.  Specific Interactions. Intermolecular Forces, Steric Requirements, and Molecular Size , 1974 .

[20]  J. Snyder,et al.  7 – Modeling Drug–Receptor Interactions , 1996 .

[21]  T. W. Barlow.  Self-organizing maps and molecular similarity. , 1995, Journal of molecular graphics.