Three Machine Learning Models for the 2019 Solubility Challenge

Overview

Journal ADMET DMPK

Specialty Pharmacology

Date 2022 Mar 18

PMID 35300305

Authors

John B O Mitchell

Affiliations

Soon will be listed here.

Abstract

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.

Citing Articles

CrystalClear: an open, modular protocol for predicting molecular crystal growth from solution.

Spackman P, Walisinghe A, Anderson M, Gale J Chem Sci. 2023; 14(26):7192-7207.

PMID: 37416706 PMC: 10321482. DOI: 10.1039/d2sc06761g.

Assessing Metabolic Markers in Glioblastoma Using Machine Learning: A Systematic Review.

Neil Z, Pierzchajlo N, Boyett C, Little O, Kuo C, Brown N Metabolites. 2023; 13(2).

PMID: 36837779 PMC: 9958885. DOI: 10.3390/metabo13020161.

Intrinsic Aqueous Solubility: Mechanistically Transparent Data-Driven Modeling of Drug Substances.

Oja M, Sild S, Piir G, Maran U Pharmaceutics. 2022; 14(10).

PMID: 36297685 PMC: 9611068. DOI: 10.3390/pharmaceutics14102248.

Pilot Behavior Recognition Based on Multi-Modality Fusion Technology Using Physiological Characteristics.

Li Y, Li K, Wang S, Chen X, Wen D Biosensors (Basel). 2022; 12(6).

PMID: 35735552 PMC: 9221330. DOI: 10.3390/bios12060404.

Strategies of solubility enhancement and perspectives in solubility measurements of pharmaceutical compounds.

Bergstrom C, Llinas A ADMET DMPK. 2022; 8(3):176-179.

PMID: 35300302 PMC: 8915603. DOI: 10.5599/admet.910.

References

Williams H, Trevaskis N, Charman S, Shanker R, Charman W, Pouton C . Strategies to address low drug solubility in discovery and development. Pharmacol Rev. 2013; 65(1):315-499. DOI: 10.1124/pr.112.005660. View

Kovdienko N, Polishchuk P, Muratov E, Artemenko A, Kuzmin V, Gorb L . Application of Random Forest and Multiple Linear Regression Techniques to QSPR Prediction of an Aqueous Solubility for Military Compounds. Mol Inform. 2016; 29(5):394-406. DOI: 10.1002/minf.201000001. View

Di L, Kerns E, Carter G . Drug-like property concepts in pharmaceutical design. Curr Pharm Des. 2009; 15(19):2184-94. DOI: 10.2174/138161209788682479. View

Luder K, Lindfors L, Westergren J, Nordholm S, Kjellander R . In silico prediction of drug solubility. 3. Free energy of solvation in pure amorphous matter. J Phys Chem B. 2007; 111(25):7303-11. DOI: 10.1021/jp071687d. View

Rytting E, Lentz K, Chen X, Qian F, Vakatesh S . Aqueous and cosolvent solubility data for drug-like organic compounds. AAPS J. 2005; 7(1):E78-105. PMC: 2751500. DOI: 10.1208/aapsj070110. View

Abramov Y, Sun G, Zeng Q, Zeng Q, Yang M . Guiding Lead Optimization for Solubility Improvement with Physics-Based Modeling. Mol Pharm. 2020; 17(2):666-673. DOI: 10.1021/acs.molpharmaceut.9b01138. View

Abraham M, Le J . The correlation and prediction of the solubility of compounds in water using an amended solvation energy relationship. J Pharm Sci. 1999; 88(9):868-80. DOI: 10.1021/js9901007. View

Palmer D, Mitchell J . Is experimental data quality the limiting factor in predicting the aqueous solubility of druglike molecules?. Mol Pharm. 2014; 11(8):2962-72. DOI: 10.1021/mp500103r. View

Boothroyd S, Kerridge A, Broo A, Buttar D, Anwar J . Solubility prediction from first principles: a density of states approach. Phys Chem Chem Phys. 2018; 20(32):20981-20987. DOI: 10.1039/c8cp01786g. View

10.

Box K, Comer J, Gravestock T, Stuart M . New ideas about the solubility of drugs. Chem Biodivers. 2009; 6(11):1767-88. DOI: 10.1002/cbdv.200900164. View

11.

Lusci A, Pollastri G, Baldi P . Deep architectures and deep learning in chemoinformatics: the prediction of aqueous solubility for drug-like molecules. J Chem Inf Model. 2013; 53(7):1563-75. PMC: 3739985. DOI: 10.1021/ci400187y. View

12.

Llinas A, Avdeef A . Solubility Challenge Revisited after Ten Years, with Multilab Shake-Flask Data, Using Tight (SD ∼ 0.17 log) and Loose (SD ∼ 0.62 log) Test Sets. J Chem Inf Model. 2019; 59(6):3036-3040. DOI: 10.1021/acs.jcim.9b00345. View

13.

Wassvik C, Holmen A, Bergstrom C, Zamora I, Artursson P . Contribution of solid-state properties to the aqueous solubility of drugs. Eur J Pharm Sci. 2006; 29(3-4):294-305. DOI: 10.1016/j.ejps.2006.05.013. View

14.

Palmer D, McDonagh J, Mitchell J, van Mourik T, Fedorov M . First-Principles Calculation of the Intrinsic Aqueous Solubility of Crystalline Druglike Molecules. J Chem Theory Comput. 2015; 8(9):3322-37. DOI: 10.1021/ct300345m. View

15.

Svetnik V, Liaw A, Tong C, Culberson J, Sheridan R, Feuston B . Random forest: a classification and regression tool for compound classification and QSAR modeling. J Chem Inf Comput Sci. 2003; 43(6):1947-58. DOI: 10.1021/ci034160g. View

16.

Bergstrom C, Larsson P . Computational prediction of drug solubility in water-based systems: Qualitative and quantitative approaches used in the current drug discovery and development setting. Int J Pharm. 2018; 540(1-2):185-193. PMC: 5861307. DOI: 10.1016/j.ijpharm.2018.01.044. View

17.

Boobier S, Osbourn A, Mitchell J . Can human experts predict solubility better than computers?. J Cheminform. 2017; 9(1):63. PMC: 5729181. DOI: 10.1186/s13321-017-0250-y. View

18.

Lind P, Maltseva T . Support vector machines for the estimation of aqueous solubility. J Chem Inf Comput Sci. 2003; 43(6):1855-9. DOI: 10.1021/ci034107s. View

19.

Nigsch F, Bender A, van Buuren B, Tissen J, Nigsch E, Mitchell J . Melting point prediction employing k-nearest neighbor algorithms and genetic parameter optimization. J Chem Inf Model. 2006; 46(6):2412-22. DOI: 10.1021/ci060149f. View

20.

Hopfinger A, Esposito E, Llinas A, Glen R, Goodman J . Findings of the challenge to predict aqueous solubility. J Chem Inf Model. 2009; 49(1):1-5. DOI: 10.1021/ci800436c. View