Biology is rarely easy. As researchers make strides in reading and editing genes to treat disease, for example, a growing body of evidence suggests that the proteins and metabolites surrounding those genes can’t be ignored.
The MIT spinout ReviveMed has created a platform for measuring metabolites — products of metabolism like lipids, cholesterol, sugar, and carbs — at scale. The corporate is using those measurements to uncover why some patients reply to treatments when others don’t and to higher understand the drivers of disease.
“Historically, we’ve been capable of measure a couple of hundred metabolites with high accuracy, but that’s a fraction of the metabolites that exist in our bodies,” says ReviveMed CEO Leila Pirhaji PhD ’16, who founded the corporate with Professor Ernest Fraenkel. “There’s an enormous gap between what we’re accurately measuring and what exists in our body, and that’s what we would like to tackle. We would like to tap into the powerful insights from underutilized metabolite data.”
ReviveMed’s progress comes because the broader medical community is increasingly linking dysregulated metabolites to diseases like cancer, Alzheimer’s, and heart problems. ReviveMed is using its platform to assist a number of the largest pharmaceutical corporations on the planet find patients that stand to learn from their treatments. It’s also offering software to academic researchers at no cost to assist gain insights from untapped metabolite data.
“With the sector of AI booming, we predict we are able to overcome data problems which have limited the study of metabolites,” Pirhaji says. “There’s no foundation model for metabolomics, but we see how these models are changing various fields similar to genomics, so we’re beginning to pioneer their development.”
Finding a challenge
Pirhaji was born and raised in Iran before coming to MIT in 2010 to pursue her PhD in biological engineering. She had previously read Fraenkel’s research papers and was excited to contribute to the network models he was constructing, which integrated data from sources like genomes, proteomes, and other molecules.
“We were fascinated about the massive picture by way of what you’ll be able to do when you’ll be able to measure every thing — the genes, the RNA, the proteins, and small molecules like metabolites and lipids,” says Fraenkel, who currently serves on ReviveMed’s board of directors. “We’re probably only capable of measure something like 0.1 percent of small molecules within the body. We thought there needed to be a approach to get as comprehensive a view of those molecules as we have now for the opposite ones. That will allow us to map out all the changes occurring within the cell, whether it’s within the context of cancer or development or degenerative diseases.”
About halfway through her PhD, Pirhaji sent some samples to a collaborator at Harvard University to gather data on the metabolome — the small molecules which can be the products of metabolic processes. The collaborator sent Pirhaji back an enormous excel sheet with hundreds of lines of information — but they told her she’s higher off ignoring every thing beyond the highest 100 rows because they’d no idea what the opposite data meant. She took that as a challenge.
“I began pondering perhaps we could use our network models to unravel this problem,” Pirhaji recalls. “There was a whole lot of ambiguity in the information, and it was very interesting to me because nobody had tried this before. It appeared like a giant gap in the sector.”
Pirhaji developed an enormous knowledge graph that included thousands and thousands of interactions between proteins and metabolites. The info was wealthy but messy — Pirhaji called it a “hair ball” that couldn’t tell researchers anything about disease. To make it more useful, she created a brand new approach to characterize metabolic pathways and features. In a 2016 paper in , she described the system and used it to investigate metabolic changes in a model of Huntington’s disease.
Initially, Pirhaji had no intention of beginning a company, but she began realizing the technology’s business potential in the ultimate years of her PhD.
“There’s no entrepreneurial culture in Iran,” Pirhaji says. “I didn’t know how you can start an organization or turn science right into a startup, so I leveraged every thing MIT offered.”
Pirhaji began taking classes on the MIT Sloan School of Management, including Course 15.371 (Innovation Teams), where she teamed up with classmates to take into consideration how you can apply her technology. She also used the MIT Enterprise Mentoring Service and MIT Sandbox, and took part within the Martin Trust Center for MIT Entrepreneurship’s delta v startup accelerator.
When Pirhaji and Fraenkel officially founded ReviveMed, they worked with MIT’s Technology Licensing Office to access the patents around their work. Pirhaji has since further developed the platform to unravel other problems she discovered from talks with tons of of leaders in pharmaceutical corporations.
ReviveMed began by working with hospitals to uncover how lipids are dysregulated in a disease generally known as metabolic dysfunction-associated steatohepatitis. In 2020, ReviveMed worked with Bristol Myers Squibb to predict how subsets of cancer patients would reply to the corporate’s immunotherapies.
Since then, ReviveMed has worked with several corporations, including 4 of the highest 10 global pharmaceutical corporations, to assist them understand the metabolic mechanisms behind their treatments. Those insights help discover the patients that stand to learn essentially the most from different therapies more quickly.
“If we all know which patients will profit from every drug, it could really decrease the complexity and time related to clinical trials,” Pirhaji says. “Patients will get the proper treatments faster.”
Generative models for metabolomics
Earlier this yr, 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 speed up our understanding of how metabolites influence a spread of diseases.
“We’re democratizing the usage of metabolomic data,” Pirhaji says. “It’s not possible for us to have data from each patient on the planet, but our digital twins will be used to search out patients that may gain advantage from treatments based on their demographics, for example, by finding patients that could possibly be liable to heart problems.”
The work is an element of ReviveMed’s mission to create metabolic foundation models that researchers and pharmaceutical corporations can use to grasp how diseases and coverings change the metabolites of patients.
“Leila solved a whole lot of really hard problems you face if you’re attempting to take an idea out of the lab and switch it into something that’s robust and reproducible enough to be deployed in biomedicine,” Fraenkel says. “Along the best way, she also realized the software that she’s developed is incredibly powerful by itself and could possibly be transformational.”
