Palmer, D. S. and O'Boyle, N. M. and Glen, R. C. and Mitchell, J. B. (2007) *Random forest models to predict aqueous solubility.* Journal of Chemical Information and Modeling, 47 (1). pp. 150-158.

## Abstract

Random Forest regression (RF), Partial-Least-Squares (PLS) regression, Support Vector Machines (SVM), and Artificial Neural Networks (ANN) were used to develop QSPR models for the prediction of aqueous solubility, based on experimental data for 988 organic molecules. The Random Forest regression model predicted aqueous solubility more accurately than those created by PLS, SVM, and ANN and offered methods for automatic descriptor selection, an assessment of descriptor importance, and an in-parallel measure of predictive ability, all of which serve to recommend its use. The prediction of log molar solubility for an external test set of 330 molecules that are solid at 25 degrees C gave an r2 = 0.89 and RMSE = 0.69 log S units. For a standard data set selected from the literature, the model performed well with respect to other documented methods. Finally, the diversity of the training and test sets are compared to the chemical space occupied by molecules in the MDL drug data report, on the basis of molecular descriptors selected by the regression analysis.

Item type: | Article |
---|---|

ID code: | 39174 |

Keywords: | aqueous solubility , forest models , random forest regression , Physics, Microbiology, Probabilities. Mathematical statistics |

Subjects: | Science > Physics Science > Microbiology Science > Mathematics > Probabilities. Mathematical statistics |

Department: | Faculty of Science > Physics Faculty of Science > Mathematics and Statistics > Statistics and Modelling Science |

Related URLs: | |

Depositing user: | Pure Administrator |

Date Deposited: | 16 Apr 2012 12:22 |

Last modified: | 04 Oct 2012 14:17 |

URI: | http://strathprints.strath.ac.uk/id/eprint/39174 |

### Actions (login required)

View Item |