Back to top


Retrievium is a unique data-driven modeling tool in the chemical sciences.  Computational modelling is a powerful predictive tool in the search for new drugs, materials, and insight into the properties of chemical systems, but models are limited by either the accuracy of the simulations or the computing power required to get useful results.  retrievium solves this problem by merging one of the world’s largest repositories of high-accuracy simulation data with machine learning technology so that it can “learn” how to predict accurate molecular properties in a fraction of the time. This allows users to rapidly predict properties of candidate molecules and filter chemical space to identify the most promising targets for R&D in their specific context.

Retrieivium in the news:

The Chronicle Herald: "Community Computing to Help Chemists"

Emergence Bioincubator

ACENET Annual Report

Development of the retrievium platform is ongoing, and is made possible by the following organizations.