Real world case studies: Predicting pharmacokinetics from limited ADME data with deep learning

To become a successful drug, our active molecule must also display excellent pharmacokinetic (PK) properties, however experimental data on PK parameters can be difficult to come by.

In our previous webinar, Predicting Pharmacokinetic Parameters and Curves we explored a proof-of-concept example of how deep learning imputation can help us to accurately predict PK, even when we may not have much experimental data.

Now, watch Matt Segall, PhD, CEO at Optibrium, as he introduces a real world case study where we applied deep learning to guide a project, in which potential compounds were displaying good activity profiles but the team wanted to improve their PK profile to achieve better efficacy.

Find out more about:

• The challenges we face in using data in drug discovery
• What deep learning imputation is, and how it works in the context of PK
• Real life case studies of deep learning in action for PK prediction, and how our collaborators have found success using these methods
• Optibrium’s Cerella AI drug discovery software

If you have questions about any of the webinar content, or how Cerella could work with your specific projects, please do get in touch.