Applying support-vector machine learning algorithms toward predicting host-guest interactions with cucurbituril.
Pierson Smela, Merrick
Physical chemistry chemical physics : PCCP
MetadataShow full item record
Tabet, A., Gebhart, T., Wu, G., Readman, C., Pierson Smela, M., Rana, V. K., Baker, C., et al. (2020). Applying support-vector machine learning algorithms toward predicting host-guest interactions with cucurbituril.. Physical chemistry chemical physics : PCCP, 22 (26), 14976-14982. https://doi.org/10.1039/c9cp05800a
Machine learning is a valuable tool in the development of chemical technologies but its applications into supramolecular chemistry have been limited. Here, the utility of kernel-based support vector machine learning using density functional theory calculations as training data is evaluated when used to predict equilibrium binding coefficients of small molecules with cucurbituril (CB). We find that utilising SVMs may confer some predictive ability. This algorithm was then used to predict the binding of drugs TAK-580 and Selumetinib. The algorithm did predict strong binding for TAK-580 and poor binding for Selumetinib, and these results were experimentally validated. It was discovered that the larger homologue cucurbituril (CB) is partial to Selumetinib, suggesting an opportunity for tunable release by introducing different concentrations of CB or CB into a hydrogel depot. We qualitatively demonstrated that these drugs may have utility in combination against gliomas. Finally, mass transfer simulations show CB can independently tune the release of TAK-580 without affecting Selumetinib. This work gives specific evidence that a machine learning approach to recognition of small molecules by macrocycles has merit and reinforces the view that machine learning may prove valuable in the development of drug delivery systems and supramolecular chemistry more broadly.
Imidazoles, Benzimidazoles, Heterocyclic Compounds, 3-Ring, Models, Chemical, Support Vector Machine, Bridged-Ring Compounds, Density Functional Theory
Is supplemented by: https://doi.org/10.17863/CAM.54504
A.T. and M.P.S. thank The Winston Churchill Foundation of the United States. A.T. thanks the National Science Foundation graduate research fellowship, the MIT Chemical Engineering first year fellowship, and the Churchill College post-graduate grant program. G.W. thanks the Leverhulme Trust (project: ‘Natural material innovation for sustainable living’). V.K.R. thanks the Swiss National Science Foundation (P2EZP2_168784). O.A.S. acknowledges EPSRC Programme grant Nano-Optics to controlled Nano- Chemistry (NOtCH, EP/L027151/1) for funding.
Embargo Lift Date
External DOI: https://doi.org/10.1039/c9cp05800a
This record's URL: https://www.repository.cam.ac.uk/handle/1810/307110
All rights reserved