Toward a Principled Methodology for Neural Network Design and Performance Evaluation in QSAR. Application to the Prediction of LogP

The prediction of properties of molecules from their structure (QSAR) is basically a nonlinear regression problem. Neural networks are proven to be parsimonious universal approximators of nonlinear functions; therefore, they are excellent candidates for performing the nonlinear regression tasks involved in QSAR. However, their full potential can be exploited only in the framework of a rigorous approach. In the present paper, we describe a principled methodology for designing neural networks for QSAR and estimating their performances, and we apply this approach to the prediction of logP. We compare our results to those obtained on the same molecules by other methods.

[1]  William H. Press,et al.  Numerical Recipes in FORTRAN - The Art of Scientific Computing, 2nd Edition , 1987 .

[2]  Bernd Beck,et al.  Prediction of the n-Octanol/Water Partition Coefficient, logP, Using a Combination of Semiempirical MO-Calculations and a Neural Network , 1997 .

[3]  N. Bodor,et al.  An extended version of a novel method for the estimation of partition coefficients. , 1992, Journal of pharmaceutical sciences.

[4]  Hervé Stoppiglia.  Méthodes statistiques de sélection de modèles neuronaux ; applications financières et bancaires , 1997 .

[5]  Shaomeng Wang,et al.  Computer Automated log P Calculations Based on an Extended Group Contribution Approach , 1994, J. Chem. Inf. Comput. Sci..

[6]  A. Leo.  CALCULATING LOG POCT FROM STRUCTURES , 1993 .

[7]  Peter C. Jurs,et al.  Prediction of boiling points and critical temperatures of industrially important organic compounds from molecular structure , 1994, J. Chem. Inf. Comput. Sci..

[8]  Rainer Herges,et al.  Prediction of Chromatographic Retention Values (RM) and Partition Coefficients (log Poct) Using a Combination of Semiempirical Self-Consistent Reaction Field Calculations and Neural Networks , 1995, J. Chem. Inf. Comput. Sci..

[9]  D. Hoekman.  Exploring QSAR Fundamentals and Applications in Chemistry and Biology, Volume 1. Hydrophobic, Electronic and Steric Constants, Volume 2 J. Am. Chem. Soc. 1995, 117, 9782 , 1996 .

[10]  K H Jogun,et al.  Chemical-structural properties of tetracycline derivatives. 2. Coordination and conformational aspects of oxytetracycline metal ion complexation. , 1976, Journal of the American Chemical Society.

[11]  Gilles Klopman,et al.  Simple method of computing the partition coefficient , 1985 .

[12]  Han van de Waterbeemd,et al.  Lipophilicity in Drug Action and Toxicology: Pliška/Lipophilicity , 1996 .

[13]  Peter C. Jurs,et al.  Prediction of Autoignition Temperatures of Organic Compounds from Molecular Structure , 1997, J. Chem. Inf. Comput. Sci..

[14]  Kurt Hornik,et al.  Multilayer feedforward networks are universal approximators , 1989, Neural Networks.

[15]  Sheng Chen,et al.  Orthogonal least squares methods and their application to non-linear system identification , 1989 .

[16]  I. J. Leontaritis,et al.  Model selection and validation methods for non-linear systems , 1987 .

[17]  F. A. Seiler,et al.  Numerical Recipes in C: The Art of Scientific Computing , 1989 .

[18]  Kurt Hornik,et al.  Degree of Approximation Results for Feedforward Networks Approximating Unknown Mappings and Their Derivatives , 1994, Neural Computation.

[19]  Gilles Klopman,et al.  Calculation of partition coefficients by the charge density method , 1981 .

[20]  J J Stezowski,et al.  Chemical-structural properties of tetracycline derivatives. 1. Molecular structure and conformation of the free base derivatives. , 1976, Journal of the American Chemical Society.

[21]  N. Bodor,et al.  A new method for the estimation of the aqueous solubility of organic compounds. , 1992, Journal of pharmaceutical sciences.

[22]  Igor V. Tetko,et al.  Neural Network Studies, 2. Variable Selection , 1996, J. Chem. Inf. Comput. Sci..

[23]  Matthew D. Wessel,et al.  Prediction of Reduced Ion Mobility Constants from Structural Information Using Multiple Linear Regression Analysis and Computational Neural Networks , 1994 .

[24]  Han van de Waterbeemd,et al.  Lipophilicity in drug action and toxicology , 1996 .

[25]  N. Bodor,et al.  A new method for the estimation of partition coefficient , 1989 .

[26]  Jean-Michel Cense,et al.  Prediction of the Impact Sensitivity by Neural Networks , 1996, J. Chem. Inf. Comput. Sci..

[27]  Peter C. Jurs,et al.  Automated Descriptor Selection for Quantitative Structure-Activity Relationships Using Generalized Simulated Annealing , 1995, J. Chem. Inf. Comput. Sci..

[28]  Christopher M. Bishop,et al.  Neural networks for pattern recognition , 1995 .

[29]  N. Bodor,et al.  Neural network studies: Part 3. Prediction of partition coefficients , 1994 .

[30]  Eamonn F. Healy,et al.  Development and use of quantum mechanical molecular models. 76. AM1: a new general purpose quantum mechanical molecular model , 1985 .