Browse by author
Lookup NU author(s): Dr Simon Wilkinson
Full text for this publication is not currently held within this repository. Alternative links are provided below where available.
© 2018 Royal Pharmaceutical Society. Objectives: The aim of this study was to investigate how to improve predictions from Gaussian Process models by optimising the model hyperparameters. Methods: Optimisation methods, including Grid Search, Conjugate Gradient, Random Search, Evolutionary Algorithm and Hyper-prior, were evaluated and applied to previously published data. Data sets were also altered in a structured manner to reduce their size, which retained the range, or 'chemical space' of the key descriptors to assess the effect of the data range on model quality. Key findings: The Hyper-prior Smoothbox kernel results in the best models for the majority of data sets, and they exhibited significantly better performance than benchmark quantitative structure-permeability relationship (QSPR) models. When the data sets were systematically reduced in size, the different optimisation methods generally retained their statistical quality, whereas benchmark QSPR models performed poorly. Conclusions: The design of the data set, and possibly also the approach to validation of the model, is critical in the development of improved models. The size of the data set, if carefully controlled, was not generally a significant factor for these models and that models of excellent statistical quality could be produced from substantially smaller data sets.
Author(s): Ashrafi P, Sun Y, Davey N, Adams RG, Wilkinson SC, Moss GP
Publication type: Article
Publication status: Published
Journal: Journal of Pharmacy and Pharmacology
Print publication date: 01/03/2018
Online publication date: 17/01/2018
Acceptance date: 22/11/2017
ISSN (print): 0022-3573
ISSN (electronic): 2042-7158
Publisher: John Wiley & Sons Ltd
Altmetrics provided by Altmetric