Artificial Intelligence + Metabolomics

The core of our technology is based on a network-based machine learning algorithm for integrative analysis of untargeted metabolomic data with other large-scale molecular information such as data from genes, proteins, drugs and diseases. Our technology is developed at the Fraenkel lab at MIT Biological Engineering department, and published in Nature Methods.



Harnessing Metabolomics

Among various types of molecular data, metabolomics provides the most functional information. However, most existing technologies solely rely on mRNA, excluding  metabolomics, because of the ambiguity in using large-scale metabolomics data. With other approaches that do integrate metabolomics, additional time-consuming and costly experiments are still limited to characterizing a small fraction of the metabolite masses.

We have pioneered a AI-driven technology that can measure metabolite masses fast and inexpensively.  Using our proprietary database and machine-learning algorithm, we reduce the need for these additional experiments, predict the identity of each metabolite mass, and integrate these data with other large-scale molecular datasets such as genomics and proteomics.