Prediction of Metabolic Transformations using Cross VennABERS Predictors
[edit]
Proceedings of the Sixth Workshop on Conformal and Probabilistic Prediction and Applications, PMLR 60:118131, 2017.
Abstract
Prediction of drug metabolism is an important topic in the drug discovery process,
and we here present a study using probabilistic predictions applying Cross VennABERS Predictors (CVAPs) on data for siteofmetabolism.
We used a dataset of 73599 biotransformations, applied SMIRKS to define biotransformations of interest and constructed five datasets
where chemical structures were represented using signatures descriptors.
The results show that CVAP produces wellcalibrated predictions for all datasets with good predictive capability,
making CVAP an interesting method for further exploration in drug discovery applications.
Related Material


