Uniting Cheminformatics and Chemical Theory To Predict the Intrinsic Aqueous Solubility of Crystalline Druglike Molecules
Open Access
- 24 February 2014
- journal article
- research article
- Published by American Chemical Society (ACS) in Journal of Chemical Information and Modeling
- Vol. 54 (3) , 844-856
Abstract
We present four models of solution free-energy prediction for druglike molecules utilizing cheminformatics descriptors and theoretically calculated thermodynamic values. We make predictions of solution free energy using physics-based theory alone and using machine learning/quantitative structure–property relationship (QSPR) models. We also develop machine learning models where the theoretical energies and cheminformatics descriptors are used as combined input. These models are used to predict solvation free energy. While direct theoretical calculation does not give accurate results in this approach, machine learning is able to give predictions with a root mean squared error (RMSE) of ∼1.1 log S units in a 10-fold cross-validation for our Drug-Like-Solubility-100 (DLS-100) dataset of 100 druglike molecules. We find that a model built using energy terms from our theoretical methodology as descriptors is marginally less predictive than one built on Chemistry Development Kit (CDK) descriptors. Combining both sets of descriptors allows a further but very modest improvement in the predictions. However, in some cases, this is a statistically significant enhancement. These results suggest that there is little complementarity between the chemical information provided by these two sets of descriptors, despite their different sources and methods of calculation. Our machine learning models are also able to predict the well-known Solubility Challenge dataset with an RMSE value of 0.9–1.0 log S units.Keywords
Funding Information
- Biotechnology and Biological Sciences Research Council (BB/I00596X/1)
This publication has 58 references indexed in Scilit:
- The Taverna workflow suite: designing and executing workflows of Web Services on the desktop, web or in the cloudNucleic Acids Research, 2013
- Towards a Universal SMILES representation - A standard method to generate canonical SMILES based on the InChIJournal of Cheminformatics, 2012
- Is EC class predictable from reaction mechanism?BMC Bioinformatics, 2012
- Using cross-validation to evaluate predictive accuracy of survival risk classifiers based on high-dimensional dataBriefings in Bioinformatics, 2011
- myExperiment: a repository and social network for the sharing of bioinformatics workflowsNucleic Acids Research, 2010
- In Silico Prediction of Aqueous Solubility: The Solubility ChallengeJournal of Chemical Information and Modeling, 2009
- The Chemistry Development Kit (CDK): An Open-Source Java Library for Chemo- and BioinformaticsJournal of Chemical Information and Computer Sciences, 2003
- First-principles simulation: ideas, illustrations and the CASTEP codeJournal of Physics: Condensed Matter, 2002
- An overview of statistical learning theoryIEEE Transactions on Neural Networks, 1999
- Calculation of solvation free energies using a density functional/molecular dynamics coupled potentialThe Journal of Physical Chemistry, 1993