AI Case Study

"To make pesticides safer, we simulate millions of compounds and identify the ones that target pests without causing toxicity in humans or other friendly species. Our technology allows us to investigate larger numbers of compounds via computer simulation and move human and environmental testing earlier into compound discovery, thereby letting us find better and safer compounds faster and more cheaply. We are working with Dr Marlon Manalo at the University of the Philippines, Los Baños, the premier institute in the Philippines focusing on agriculture, to integrate our predictive models into the pesticide development process. This work is supported by Grand Challenges Canada.

Atomwise’s software analyzes simulations of molecules, reducing the time researchers need to spend synthesizing and testing compounds. The company says it currently screens more than 10 million compounds each day. Atomwise’s AtomNet system uses deep learning algorithms to analyze molecules and predict how they might act in the human body, including their potential efficacy as medication, toxicity and side effects, at an earlier stage than in the traditional drug discovery process."