Three machine learning models for the 2019 Solubility Challenge

Research output: Contribution to journalArticlepeer-review

10 Citations (Scopus)
1 Downloads (Pure)


We describe three machine learning models submitted to the 2019 Solubility Challenge. All are founded on tree-like classifiers, with one model being based on Random Forest and another on the related Extra Trees algorithm. The third model is a consensus predictor combining the former two with a Bagging classifier. We call this consensus classifier Vox Machinarum, and here discuss how it benefits from the Wisdom of Crowds. On the first 2019 Solubility Challenge test set of 100 low-variance intrinsic aqueous solubilities, Extra Trees is our best classifier. One the other, a high-variance set of 32 molecules, we find
that Vox Machinarum and Random Forest both perform a little better than Extra Trees, and almost equally to one another. We also compare the gold standard solubilities from the 2019 Solubility Challenge with a set of literature-based solubilities for most of the same compounds.
Original languageEnglish
Pages (from-to)215-251
Number of pages37
Issue number3
Early online date15 Jun 2020
Publication statusPublished - 27 Sept 2020


  • Aqueous intrinsic solubility
  • Solubility prediction
  • Random forest
  • Extra trees
  • Bagging
  • Consensus classifiers
  • Wisdom of crowds
  • Inter-laboratory error


Dive into the research topics of 'Three machine learning models for the 2019 Solubility Challenge'. Together they form a unique fingerprint.

Cite this