Modeling Physico-Chemical ADMET Endpoints With Multitask Graph Convolutional Networks

02 August 2019, Version 1
This content is a preprint and has not undergone peer review at the time of posting.


Simple physico-chemical properties like logD, solubility or serum albumin binding have a direct impact on the likelihood of success of compounds in clinical trials. Here, we collected all the Bayer in house data related to these properties and applied machine learning techniques to predict them for new compounds. We report that, for the endpoints studied here, a multitask graph convolutional network appears a highly competitive choice. The new model shows increased predictive performance on all endpoints compared to previous modeling methods.


ADMET – absorption distribution metabolism excretion toxicity
Multitask Deep Learning
graph convolutional networks


Comments are not moderated before they are posted, but they can be removed by the site moderators if they are found to be in contravention of our Commenting Policy [opens in a new tab] - please read this policy before you post. Comments should be used for scholarly discussion of the content in question. You can find more information about how to use the commenting feature here [opens in a new tab] .
This site is protected by reCAPTCHA and the Google Privacy Policy [opens in a new tab] and Terms of Service [opens in a new tab] apply.