Drug Discovery 2015
Poster
129

Eve: Integration of machine learning with compound testing in a robot scientist

Discussion

Eve is a robot scientist created to automate the process of drug screening and design. A Robot Scientist is a laboratory automation system that uses artificial intelligence (AI) techniques to discover scientific knowledge through cycles of experimentation. Eve integrates and automates library-screening, hit-confirmation, and lead generation through cycles of quantitative structure activity relationship learning and testing. Eve uses a standardized form of assay to compute Boolean functions of compound properties, which can be quickly and cheaply engineered using synthetic biology, enabling more targets to be assayed for a given budget. Eve has repositioned several drugs against specific targets in parasites that cause tropical diseases. In a recent proof of concept study, Eve was used to identify the anti-cancer compound TNP-470 as a potent inhibitor of dihydrofolate reductase from the malaria-causing parasite Plasmodium vivax. Econometric modelling demonstrates that the use of AI to select compounds economically outperforms standard drug screening. Having originally been developed for use with yeast strains, Eve's protocols are now being adapted for use with human cell lines as part of the DARPA Big Mechanism project.

Programme

Hosted By

ELRIG

The European Laboratory Research & Innovation Group Our Vision : To provide outstanding, leading edge knowledge to the life sciences community on an open access basis