logD7.4 Modeling Using Bayesian Regularized Neural Networks. Assessment and Correction of the Errors of Prediction
- 22 December 2005
- journal article
- research article
- Published by American Chemical Society (ACS) in Journal of Chemical Information and Modeling
- Vol. 46 (3) , 1379-1387
- https://doi.org/10.1021/ci0504014
Abstract
Bayesian Regularized Neural Networks (BRNNs) employing Automatic Relevance Determination (ARD) are used to construct a predictive model for the distribution coefficient logD7.4 from an in-house data set of 5000 compounds with experimental endpoints. A method for assessing the accuracy of prediction is established based upon a query compound's distance to the training set. logD7.4 predictions are also dynamically corrected with an associated library of compounds of continuously updated, experimentally measured logD7.4 values. A comparison of local models and associated libraries comprising separate ionization class subsets of compounds to compounds of a homogeneous ionization class reveals in this case that local models and libraries have no advantage over global models and libraries.Keywords
This publication has 11 references indexed in Scilit:
- Application of ALOGPS to predict 1‐octanol/water distribution coefficients, logP, and logD, of AstraZeneca in‐house databaseJournal of Pharmaceutical Sciences, 2004
- Application of ALOGPS 2.1 to Predict log D Distribution Coefficient for Pfizer Proprietary CompoundsJournal of Medicinal Chemistry, 2004
- Nonlinear Prediction of Quantitative Structure−Activity RelationshipsJournal of Chemical Information and Computer Sciences, 2004
- A distance measure between models: a tool for similarity/diversity analysis of model populationsChemometrics and Intelligent Laboratory Systems, 2004
- The Problem of OverfittingJournal of Chemical Information and Computer Sciences, 2003
- Theoretical Property PredictionsCurrent Topics in Medicinal Chemistry, 2003
- In silico ADME/Tox: why models failJournal of Computer-Aided Molecular Design, 2003
- Novel Methods for the Prediction of logP, pKa, and logDJournal of Chemical Information and Computer Sciences, 2002
- Search for Predictive Generic Model of Aqueous Solubility Using Bayesian Neural NetsJournal of Chemical Information and Computer Sciences, 2001
- Robust QSAR Models Using Bayesian Regularized Neural NetworksJournal of Medicinal Chemistry, 1999