In silico Prediction of Aqueous Solubility: a Comparative Study of Local and Global Predictive Models
- 18 June 2015
- journal article
- research article
- Published by Wiley in Molecular Informatics
- Vol. 34 (6-7) , 417-430
Abstract
32 Quantitative Structure‐Property Relationship (QSPR) models were constructed for prediction of aqueous intrinsic solubility of liquid and crystalline chemicals. Data sets contained 1022 liquid and 2615 crystalline compounds. Multiple Linear Regression (MLR), Support Vector Machine (SVM) and Random Forest (RF) methods were used to construct global models, and k‐nearest neighbour (kNN), Arithmetic Mean Property (AMP) and Local Regression Property (LoReP) were used to construct local models. A set of the best QSPR models was obtained: for liquid chemicals with RMSE (root mean square error) of prediction in the range 0.50–0.60 log unit; for crystalline chemicals 0.80–0.90 log unit. In the case of global models the large number of descriptors makes mechanistic interpretation difficult. The local models use only one or two descriptors, so that a medicinal chemist working with sets of structurally‐related chemicals can readily estimate their solubility. However, construction of stable local models requires the presence of closely related neighbours for each chemical considered. It is probable that a consensus of global and local QSPR models will be the optimal approach for construction of stable predictive QSPR models with mechanistic interpretation.Keywords
This publication has 57 references indexed in Scilit:
- Comparison of Different Approaches to Define the Applicability Domain of QSAR ModelsMolecules, 2012
- A Model-Based Ensembling Approach for Developing QSARsJournal of Chemical Information and Modeling, 2009
- QSPR Studies on Aqueous Solubilities of Drug-Like CompoundsInternational Journal of Molecular Sciences, 2009
- Current Mathematical Methods Used in QSAR/QSPR StudiesInternational Journal of Molecular Sciences, 2009
- In Silico Pharmaceutical Property PredictionMolecular Pharmaceutics, 2007
- On-the-Fly Selection of a Training Set for Aqueous Solubility PredictionMolecular Pharmaceutics, 2007
- A Novel Automated Lazy Learning QSAR (ALL-QSAR) Approach: Method Development, Applications, and Virtual Screening of Chemical Databases Using Validated ALL-QSAR ModelsJournal of Chemical Information and Modeling, 2006
- QSPR analysis of the partitioning of vaporous chemicals in a water–gas phase system and the water solubility of liquid and solid chemicals on the basis of fragment and physicochemical similarity and HYBOT descriptorsSAR and QSAR in Environmental Research, 2005
- Combining Unsupervised and Supervised Artificial Neural Networks to PredictAquatic ToxicityJournal of Chemical Information and Computer Sciences, 2004
- QSAR of Chemical Polarizability and Nerve Toxicity. 2Journal of Chemical Information and Computer Sciences, 2003