In this study, the researchers look to solve classification quantitative structure−activity relationship (QSAR) modelling problems using Gaussian processes.
They cover two different approaches, describing how these methods work and applying them to build category models of target activity data and absorption, distribution, metabolism, excretion, toxicity (ADMET) properties. They compare this Gaussian processes method to other computational modelling methods, including decision trees, random forest, support vector machines, and probit partial least squares. Whilst none of the methods were consistently best, Gaussian processes often produced better models than random forest or support vector machines and was rarely significantly outperformed.
O. Obrezanova and M. D. Segall, J. Chem. Inf. Model., 2010, 50 (6), pp 1053–1061.
Find out more
You can view the final published version on the journal webpage via the button below. Alternatively, download an e-print of this article on Gaussian processes via the ACS “Articles on Request” service using the following link:
Please note: To access the Articles on Request link, please log in to the Publications website using your ACS ID. If you do not have an ACS ID, you will need to Register for one for free by clicking on ‘Register’ near the top right corner of the website.
INTERESTED IN DRUG OPTIMIZATION?
With its comprehensive suite of integrated software, StarDrop™ delivers best-in-class in silico technologies within a highly visual and user-friendly interface. StarDrop™ enables a seamless flow from the latest data through predictive modelling to decision-making regarding the next round of synthesis and research, improving the speed, efficiency, and productivity of the drug optimisation and discovery process.