Estimating the domain of applicability for machine learning QSAR models: a study on aqueous solubility of drug discovery molecules
- 14 July 2007
- journal article
- research article
- Published by Springer Nature in Journal of Computer-Aided Molecular Design
- Vol. 21 (9) , 485-498
Abstract
We investigate the use of different Machine Learning methods to construct models for aqueous solubility. Models are based on about 4000 compounds, including an in-house set of 632 drug discovery molecules of Bayer Schering Pharma. For each method, we also consider an appropriate method to obtain error bars, in order to estimate the domain of applicability (DOA) for each model. Here, we investigate error bars from a Bayesian model (Gaussian Process (GP)), an ensemble based approach (Random Forest), and approaches based on the Mahalanobis distance to training data (for Support Vector Machine and Ridge Regression models). We evaluate all approaches in terms of their prediction accuracy (in cross-validation, and on an external validation set of 536 molecules) and in how far the individual error bars can faithfully represent the actual prediction error.Keywords
This publication has 31 references indexed in Scilit:
- Predicting Lipophilicity of Drug‐Discovery Molecules using Gaussian Process ModelsChemMedChem, 2007
- Machine Learning Models for Lipophilicity and Their Domain of ApplicabilityMolecular Pharmaceutics, 2007
- Recent progress in the computational prediction of aqueous solubility and absorptionThe AAPS Journal, 2006
- In Silico Prediction of Buffer Solubility Based on Quantum-Mechanical and HQSAR- and Topology-Based DescriptorsJournal of Chemical Information and Modeling, 2006
- logD7.4 Modeling Using Bayesian Regularized Neural Networks. Assessment and Correction of the Errors of PredictionJournal of Chemical Information and Modeling, 2005
- Screening for Dihydrofolate Reductase Inhibitors Using MOLPRINT 2D, a Fast Fragment-Based Method Employing the Naïve Bayesian Classifier: Limitations of the Descriptor and the Importance of Balanced Chemistry in Training and Test SetsSLAS Discovery, 2005
- Assessment of Prediction Confidence and Domain Extrapolation of Two Structure–Activity Relationship Models for Predicting Estrogen Receptor Binding ActivityEnvironmental Health Perspectives, 2004
- Prediction of Aqueous Solubility of Organic Compounds by Topological DescriptorsQSAR & Combinatorial Science, 2003
- A Consensus Neural Network-Based Technique for Discriminating Soluble and Poorly Soluble CompoundsJournal of Chemical Information and Computer Sciences, 2003
- An introduction to kernel-based learning algorithmsIEEE Transactions on Neural Networks, 2001