Development of a Gaussian Process – Feature Selection Model to Characterise (poly)dimethylsiloxane (Silastic®) Membrane Permeation

Yi Sun, Mark Hewitt, Simon C Wilkinson, Neil Davey, Roderick Adams, Darren Gullick, Gary Moss

Research output: Contribution to journalArticlepeer-review

1 Citation (Scopus)
47 Downloads (Pure)


The current study aims to determine the effect of physicochemical descriptor selection on models of polydimethylsiloxane permeation.

2,942 descriptors were calculated for a dataset of 77 chemicals. Data was processed to remove redundancy, single values, imbalanced and highly correlated data, yielding 1,363 relevant descriptors. For four independent test sets feature selection methods were applied and modelled via a variety of Machine Learning methods.

Key findings
Two sets of molecular descriptors which can provide improved predictions, compared to existing models, have been identified. Best permeation predictions were found with Gaussian Process methods. The molecular descriptors describe lipophilicity, partial charge and hydrogen bonding as key determinants of PDMS permeation.

This study highlights important considerations in the development of relevant models and in the construction and use of the datasets used in such studies, particularly that highly correlated descriptors should be removed from datasets. Predictive models are improved by the methodology adopted in this study, notably the systematic evaluation of descriptors, rather than simply using any and all available descriptors, often based empirically on in vitro experiments. Such findings also have clear relevance to a number of other fields
Original languageEnglish
Pages (from-to)873-888
Number of pages15
JournalJournal of Pharmacy and Pharmacology
Issue number7
Early online date8 Apr 2020
Publication statusPublished - Jul 2020


Dive into the research topics of 'Development of a Gaussian Process – Feature Selection Model to Characterise (poly)dimethylsiloxane (Silastic®) Membrane Permeation'. Together they form a unique fingerprint.

Cite this