HIGHLIGHTS
- who: Lewis H. Mervin from the Molecular AI, Discovery Sciences, RandD, AstraZeneca, Cambridge, UK have published the paper: Probabilistic Random Forest improves bioactivity predictions close to the classification threshold by taking into account experimental uncertainty, in the Journal: (JOURNAL)
- what: The analysis aimed to evaluate the influence of experimental variability in target prediction models by simulating experimental error on 12 Machine Learning algorithms in bioactivity modelling using 12 diverse data sets (15,840 models in total) from ChEMBL (version 19) . Naturally, the focus of this work is concerned with (activity) label uncertainties, and_(chemical) feature . . .
If you want to have access to all the content you need to log in!
Thanks :)
If you don't have an account, you can create one here.