Random forest models to predict aqueous solubility

David S. Palmer, Noel M. O'Boyle, Robert C. Glen, John Blayney Owen Mitchell

Research output: Contribution to journalArticlepeer-review

280 Citations (Scopus)

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 r(2) = 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.

Original languageEnglish
Pages (from-to)150-158
Number of pages9
JournalJournal of Chemical Information and Modeling
Volume47
Issue number1
DOIs
Publication statusPublished - 2007

Keywords

  • STRUCTURE-PROPERTY RELATIONSHIPS
  • ORGANIC-COMPOUNDS
  • MOLECULAR-STRUCTURE
  • DIVERSE SET
  • QSAR
  • ENERGY
  • STATE

Fingerprint

Dive into the research topics of 'Random forest models to predict aqueous solubility'. Together they form a unique fingerprint.

Cite this