Molecular characterization takes time

Companies cannot waste valuable time on expensive techniques to determine properties of molecules.

We are using artificial intelligence to predict the activity of molecules such as pesticides. Our proprietary algorithms can sift through terabytes of data to pinpoint specific structures and properties that give rise to optimal properties.

Meet the team

Scott Hopkins

Scott Hopkins is an Associate Professor of Chemistry at the University of Waterloo. His expertise in is experimental, computational, and theoretical physical chemistry, including machine learning techniques. Dr. Hopkins has received numerous awards for his research, including the Ramsay Memorial Fellowship (held at Oxford University), and the Early Researcher Award from the Province of Ontario. Dr. Hopkins has published more than 50 peer-reviewed articles in top-tier journals, including 9 cover articles, and he has been granted 3 patents.

View Citations

Jeff Crouse

VP, Research and Development

Jeff Crouse is a post-doctoral fellow at the University of Waterloo. He is an expert is in computational and theoretical physical chemistry, with a focus on machine learning. His PhD work focused on processing and interpreting large data arrays from molecular dynamics simulations.


Josh Featherstone

Data Scientist

Josh Featherstone is a PhD candidate (physical chemistry) at the University of Waterloo. His expertise is in computational and theoretical physical chemistry. Josh has a passion for designing pythonic solutions to computational problems that arise in the analysis of data.

Our Mission

We are a technology company that aims to use artificial intelligence to predict characteristics of molecules.

Differential Mobility Spectroscopy

Differential mobility spectrometry (DMS) is a relatively new technique in ion chromatography, which enables the separation and characterization of compounds in complex mixtures. For example, we can use DMS to quickly determine the properties of pesticides, and we can separate and quantify species of interest in environmental contamination. Our methodology requires very little sample and it is much faster and environmentally friendly than traditional liquid chromatography-based methods.