Designing New Prodrugs with Predicted ADME/PK Properties
Case Study 10
Client data, machine-learning models, and an approved-prodrug-fragment database supported prodrug analog design and predictions relating in-vitro stability and conversion to in-vivo pharmacokinetics.
Challenge
The client initially needed to correlate in-vitro and in-vivo data, specifically the stability and conversion of prodrug and active molecules in rat, dog, and human liver microsomes and hepatocytes with in-vivo PK data.
What We Did
-
1
Built models from client data
Used the client's project data to build a large number of machine-learning models.
-
2
Compiled approved prodrug fragments
Developed a database of fragments from approved prodrugs.
-
3
Enumerated and scored prodrug analogs
Generated a library of prodrug analogs and scored them with the machine-learning models.
-
4
Extended the design work with MegaSyn
Updated the models with client data and used MegaSyn to design new prodrug analogs of the molecule of interest.