ReviveMed: MIT Spinout Maps Metabolites to Uncover Disease Drivers

In the complex world of biology, where advancements in gene reading and editing offer new paths for treating diseases, it’s becoming increasingly clear that proteins and metabolites—the substances surrounding our genes—play a crucial role. ReviveMed, an MIT spinout, has developed a platform to measure these metabolites, including lipids, cholesterol, sugars, and carbohydrates, on a large scale. This technology is helping researchers understand why some patients respond to treatments while others don’t, and to gain deeper insights into the causes of diseases.

“Historically, we’ve been able to accurately measure only a small fraction of the metabolites in our bodies,” says ReviveMed CEO Leila Pirhaji PhD ’16, who co-founded the company with Professor Ernest Fraenkel. “Our goal is to bridge the gap between what we can measure and what truly exists in our body, unlocking powerful insights from previously underutilized metabolite data.”

ReviveMed’s work is timely, as the medical community increasingly recognizes the link between dysregulated metabolites and diseases such as cancer, Alzheimer’s, and cardiovascular disease. The company collaborates with major pharmaceutical firms to identify patients who could benefit most from specific treatments and offers free software to academic researchers to facilitate insights from metabolite data.

“With the rise of AI, we believe we can overcome the data challenges that have limited metabolomics research,” Pirhaji explains. “While there isn’t a foundation model for metabolomics yet, we’re inspired by how these models are transforming fields like genomics and are beginning to pioneer their development.”

Pirhaji’s journey began in Iran before she arrived at MIT in 2010 to pursue a PhD in biological engineering. Inspired by Professor Fraenkel’s work on network models integrating data from genomes and proteomes, she sought to expand these models to include metabolites. Fraenkel, now on ReviveMed’s board of directors, notes the initial challenge: “We could only measure about 0.1 percent of the small molecules in the body. We needed a way to achieve a comprehensive view of these molecules, similar to what we have for genes and proteins, to map out changes in cells affected by diseases like cancer and degenerative conditions.”

During her PhD, Pirhaji faced a significant hurdle when a collaborator provided a vast dataset on the metabolome but admitted that most of the data was indecipherable. This challenge sparked her determination to find a solution.

“I began to think that maybe we could use our network models to solve this problem,” Pirhaji recalls. “There was a lot of ambiguity in the data, and it was very interesting to me because no one had tried this before. It seemed like a big gap in the field.”

Pirhaji developed a knowledge graph that included millions of interactions between proteins and metabolites. The data was rich but messy. To make it more useful, she created a new way to characterize metabolic pathways and features. In a 2016 paper in Nature Methods, she described the system and used it to analyze metabolic changes in a model of Huntington’s disease.

Initially, Pirhaji had no intention of starting a company, but she started realizing the technology’s commercial potential in the final years of her PhD.

“There’s no entrepreneurial culture in Iran,” Pirhaji says. “I didn’t know how to start a company or turn science into a startup, so I leveraged everything MIT offered.”

At MIT Sloan School of Management, Pirhaji collaborated with classmates to explore applications for her technology, utilizing resources like the MIT Venture Mentoring Service, MIT Sandbox, and the Martin Trust Center for MIT Entrepreneurship’s delta v startup accelerator.

Since its founding, ReviveMed has partnered with hospitals to study lipid dysregulation in metabolic dysfunction-associated steatohepatitis and, in 2020, collaborated with Bristol Myers Squibb to predict cancer patients’ responses to immunotherapies.

The company has since collaborated with several companies, including four of the top 10 global pharmaceutical companies, to help them understand the metabolic mechanisms behind their treatments. Those insights help identify the patients that stand to benefit the most from different therapies more quickly.

“If we know which patients will benefit from every drug, it would really decrease the complexity and time associated with clinical trials,” Pirhaji says. “Patients will get the right treatments faster.”

Earlier this year, ReviveMed collected a dataset based on 20,000 patient blood samples that it used to create digital twins of patients and generative AI models for metabolomics research. ReviveMed is making its generative models available to nonprofit academic researchers, which could accelerate our understanding of how metabolites influence a range of diseases.

“We’re democratizing the use of metabolomic data,” Pirhaji says. “It’s impossible for us to have data from every single patient in the world, but our digital twins can be used to find patients that could benefit from treatments based on their demographics, for instance, by finding patients that could be at risk of cardiovascular disease.”

This initiative is part of ReviveMed’s broader mission to develop metabolic foundation models that can be used by researchers and pharmaceutical companies to understand how diseases and treatments alter patient metabolites.

“Leila solved a lot of really hard problems you face when you’re trying to take an idea out of the lab and turn it into something that’s robust and reproducible enough to be deployed in biomedicine,” Fraenkel says. “Along the way, she also realized the software that she’s developed is incredibly powerful by itself and could be transformational.”