Gaussian Process: An Efficient Technique to Solve Quantitative Structure-Property Relationship Problems

Abstract We introduce the Gaussian process (GP) model for the empirical modelling of the log P values of 44 1,2-dithiole-3-one molecules. A brief theoretical description of the method is given. Descriptive and predictive abilities of GP are evaluated and compared to multilinear regression results. Special attention is devoted to the automatic relevance determination (ARD) to reduce input variable numbers, which avoid the use of principal component analysis. The present approach was found to be an efficient method and a good alternative to more complicated using artificial neural network systems.

[1]  Frank R. Burden,et al.  New QSAR Methods Applied to Structure-Activity Mapping and Combinatorial Chemistry , 1999, J. Chem. Inf. Comput. Sci..

[2]  Frank R. Burden,et al.  Robust QSAR Models from Novel Descriptors and Bayesian Regularised Neural Networks , 2000 .

[3]  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..

[4]  Radford M. Neal.  Monte Carlo Implementation of Gaussian Process Models for Bayesian Regression and Classification , 1997, physics/9701026.

[5]  Correlations between n-octanol/water partition coefficients and RP-HPLC capacity factors of 1,2-dithiole-3-thiones and 1,2-dithiol-3-ones. , 1996, Journal of pharmaceutical sciences.

[6]  Grover,et al.  Quantitative structure-property relationships in pharmaceutical research - Part 2. , 2000, Pharmaceutical science & technology today.

[7]  F. Burden,et al.  A quantitative structure--activity relationships model for the acute toxicity of substituted benzenes to Tetrahymena pyriformis using Bayesian-regularized neural networks. , 2000, Chemical research in toxicology.

[8]  W. Meylan,et al.  Atom/fragment contribution method for estimating octanol-water partition coefficients. , 1995, Journal of pharmaceutical sciences.

[9]  D. Manallack,et al.  Neural networks in drug discovery: Have they lived up to their promise? , 1999 .

[10]  Singh,et al.  Quantitative structure-property relationships in pharmaceutical research - Part 1. , 2000, Pharmaceutical science & technology today.

[11]  D. Mackay,et al.  Gaussian process modelling of austenite formation in steel , 1999 .

[12]  Carl E. Rasmussen,et al.  In Advances in Neural Information Processing Systems , 2011 .

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

[14]  Frank R. Burden,et al.  Use of Automatic Relevance Determination in QSAR Studies Using Bayesian Neural Networks , 2000, J. Chem. Inf. Comput. Sci..

[15]  Igor V. Tetko,et al.  Neural network studies, 1. Comparison of overfitting and overtraining , 1995, J. Chem. Inf. Comput. Sci..

[16]  F. Burden,et al.  Robust QSAR models using Bayesian regularized neural networks. , 1999, Journal of medicinal chemistry.

[17]  Richard Von Mises,et al.  Mathematical Theory of Probability and Statistics , 1966 .

[18]  S. Gull.  Bayesian Inductive Inference and Maximum Entropy , 1988 .

[19]  Albert J. Leo,et al.  Calculating log P(oct) with no missing fragments; The problem of estimating new interaction parameters , 2000 .

[20]  M. Christen,et al.  Water/n-octanol partition coefficients of 1,2-dithiole-3-thiones. , 1995, Journal of pharmaceutical sciences.

[21]  Geoffrey E. Hinton,et al.  Evaluation of Gaussian processes and other methods for non-linear regression , 1997 .