Comparison of a Neural Net-Based QSAR Algorithm (PCANN) with Hologram- and Multiple Linear Regression-Based QSAR Approaches: Application to 1, 4-Dihydropyridine-Based Calcium Channel Antagonists

A QSAR algorithm (PCANN) has been developed and applied to a set of calcium channel blockers which are of special interest because of their role in cardiac disease and also because many of them interact with P-glycoprotein, a membrane protein associated with multidrug resistance to anticancer agents. A database of 46 1,4-dihydropyridines with known Ca2+ channel binding affinities was employed for the present analysis. The QSAR algorithm can be summarized as follows: (1) a set of 90 graph theoretic and information theoretic descriptors representing various structural and topological characteristics was calculated for each of the 1,4-dihydropyridines and (2) principal component analysis (PCA) was used to compress these 90 into the eight best orthogonal composite descriptors for the database. These eight sufficed to explain 96% of the variance in the original descriptor set. (3) Two important empirical descriptors, the Leo-Hansch lipophilic constant and the Hammet electronic parameter, were added to the list of eight. (4) The 10 resulting descriptors were used as inputs to a back-propagation neural network whose output was the predicted binding affinity. (5) The predictive ability of the network was assessed by cross-validation. A comparison of the present approach with two other QSAR approaches (multiple linear regression using the same variables and a Hologram QSAR model) is made and shows that the PCANN approach can yield better predictions, once the right network configuration is identified. The present approach (PCANN) may prove useful for rapid assessment of the potential for biological activity when dealing with large chemical libraries.

[1]  Gerald J. Niemi,et al.  Optimal characterization of structure for prediction of properties , 1990 .

[2]  Hans Lohninger.  Evaluation of neural networks based on radial basis functions and their application to the prediction of boiling points from structural parameters , 1993, J. Chem. Inf. Comput. Sci..

[3]  Subhash C. Basak,et al.  Determining structural similarity of chemicals using graph-theoretic indices , 1988, Discret. Appl. Math..

[4]  D. Manallack,et al.  Analysis of linear and nonlinear QSAR data using neural networks. , 1994, Journal of medicinal chemistry.

[5]  S C Basak,et al.  Use of graph theoretic parameters in risk assessment of chemicals. , 1995, Toxicology letters.

[6]  R. M. Hyde,et al.  Physiochemical-activity relations in practice. 1. A rational and self-consistent data bank. , 1975, Journal of medicinal chemistry.

[7]  R L Fine,et al.  Effect of calcium channel blockers on human CFU-GM with cytotoxic drugs. , 1987, Journal of clinical oncology : official journal of the American Society of Clinical Oncology.

[8]  J N Weinstein,et al.  Neural computing in cancer drug development: predicting mechanism of action. , 1992, Science.

[9]  G. S. Johnson,et al.  An Information-Intensive Approach to the Molecular Pharmacology of Cancer , 1997, Science.

[10]  Jonathan D. Hirst,et al.  Quantitative structure-activity relationships by neural networks and inductive logic programming. I. The inhibition of dihydrofolate reductase by pyrimidines , 1994, J. Comput. Aided Mol. Des..

[11]  T. A. Andrea,et al.  Applications of neural networks in quantitative structure-activity relationships of dihydrofolate reductase inhibitors. , 1991, Journal of medicinal chemistry.

[12]  J. Zupan,et al.  Neural networks: A new method for solving chemical problems or just a passing phase? , 1991 .

[13]  Subhash C. Basak,et al.  Molecular Similarity and Estimation of Molecular Properties , 1995, J. Chem. Inf. Comput. Sci..

[14]  César Hervás-Martínez,et al.  Computational Neural Networks in Conjunction with Principal Component Analysis for Resolving Highly Nonlinear Kinetics , 1997, J. Chem. Inf. Comput. Sci..

[15]  H. Wiener.  Structural determination of paraffin boiling points. , 1947, Journal of the American Chemical Society.

[16]  Geoffrey E. Hinton,et al.  Learning representations by back-propagating errors , 1986, Nature.

[17]  Robert D Clark,et al.  Neighborhood behavior: a useful concept for validation of "molecular diversity" descriptors. , 1996, Journal of medicinal chemistry.

[18]  David Weininger,et al.  SMILES, a chemical language and information system. 1. Introduction to methodology and encoding rules , 1988, J. Chem. Inf. Comput. Sci..

[19]  D. Ferry,et al.  P-glycoprotein possesses a 1,4-dihydropyridine-selective drug acceptor site which is alloserically coupled to a vinca-alkaloid-selective binding site. , 1992, Biochemical and biophysical research communications.

[20]  I. Pastan,et al.  Genetic analysis of the multidrug transporter. , 1995, Annual review of genetics.

[21]  B. Kowalski,et al.  Partial least-squares regression: a tutorial , 1986 .

[22]  K. Honn,et al.  In vivo characterization of combination antitumor chemotherapy with calcium channel blockers and cis-diamminedichloroplatinum(II). , 1989, Cancer research.

[23]  C. Raychaudhury,et al.  Discrimination of isomeric structures using information theoretic topological indices , 1984 .

[24]  W G Richards,et al.  QSAR of binding of dihydropyridine‐type calcium antagonists to their receptor on ileal smooth muscle preparations , 1986, The Journal of pharmacy and pharmacology.

[25]  D Faraggi,et al.  Discrimination techniques applied to the NCI in vitro anti-tumour drug screen: predicting biochemical mechanism of action. , 1994, Statistics in medicine.

[26]  C. Hansch.  Quantitative approach to biochemical structure-activity relationships , 1969 .

[27]  A M Triggle,et al.  1,4-Dihydropyridine antagonist activities at the calcium channel: a quantitative structure-activity relationship approach. , 1988, Journal of medicinal chemistry.

[28]  Keith L. Peterson.  Quantitative Structure-Activity Relationships in Carboquinones and Benzodiazepines Using Counter-Propagation Neural Networks , 1995, J. Chem. Inf. Comput. Sci..

[29]  J. Riordan,et al.  Cell surface P-glycoprotein associated with multidrug resistance in mammalian cell lines. , 1983, Science.

[30]  J N Weinstein,et al.  Use of the Kohonen self-organizing map to study the mechanisms of action of chemotherapeutic agents. , 1994, Journal of the National Cancer Institute.

[31]  A Hedberg,et al.  Active conformation of 1,4-dihydropyridine calcium entry blockers. Effect of size of 2-aryl substituent on rotameric equilibria and receptor binding. , 1991, Journal of medicinal chemistry.

[32]  V. R. Magnuson,et al.  Topological indices: their nature, mutual relatedness, and applications , 1987 .

[33]  Gerald J. Niemi,et al.  Predicting properties of molecules using graph invariants , 1991 .

[34]  D C Spellmeyer,et al.  Measuring diversity: experimental design of combinatorial libraries for drug discovery. , 1995, Journal of medicinal chemistry.

[35]  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.

[36]  Roberto Todeschini,et al.  Structure-activity relationship of Ca2+ channel blockers: A study using conformational analysis and chemometric methods , 1991, J. Comput. Aided Mol. Des..

[37]  Anderson Coser Gaudio,et al.  A comparative study of principal component and linear multiple regression analysis in SAR and QSAR applied to 1,4-dihydropyridine calcium channel antagonists (nifedipine analogues) , 1997 .