Biology isn’t easy. As researchers make strides in studying and modifying genes to deal with disease, as an illustration, a rising physique of proof means that the proteins and metabolites surrounding these genes can’t be ignored.
The MIT spinout ReviveMed has created a platform for measuring metabolites — merchandise of metabolism like lipids, ldl cholesterol, sugar, and carbs — at scale. The firm is utilizing these measurements to uncover why some sufferers reply to remedies when others don’t and to higher perceive the drivers of disease.
“Historically, we’ve been able to measure a few 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 based the firm with Professor Ernest Fraenkel. “There’s a massive gap between what we’re accurately measuring and what exists in our body, and that’s what we want to tackle. We want to tap into the powerful insights from underutilized metabolite data.”
ReviveMed’s progress comes as the broader medical neighborhood is more and more linking dysregulated metabolites to illnesses like most cancers, Alzheimer’s, and cardiovascular disease. ReviveMed is utilizing its platform to assist some of the largest pharmaceutical firms in the world discover sufferers that stand to profit from their remedies. It’s additionally providing software program to educational researchers without cost to assist achieve insights from untapped metabolite knowledge.
“With the field of AI booming, we think we can overcome data problems that 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 such as genomics, so we’re starting to pioneer their development.”
Finding a problem
Pirhaji was born and raised in Iran earlier than coming to MIT in 2010 to pursue her PhD in organic engineering. She had beforehand learn Fraenkel’s analysis papers and was excited to contribute to the community fashions he was constructing, which built-in knowledge from sources like genomes, proteomes, and different molecules.
“We were thinking about the big picture in terms of what you can do when you can measure everything — the genes, the RNA, the proteins, and small molecules like metabolites and lipids,” says Fraenkel, who at the moment serves on ReviveMed’s board of administrators. “We’re probably only able to measure something like 0.1 percent of small molecules in the body. We thought there had to be a way to get as comprehensive a view of those molecules as we have for the other ones. That would allow us to map out all of the changes occurring in the cell, whether it’s in the context of cancer or development or degenerative diseases.”
About midway by her PhD, Pirhaji despatched some samples to a collaborator at Harvard University to accumulate knowledge on the metabolome — the small molecules which are the merchandise of metabolic processes. The collaborator despatched Pirhaji again an enormous excel sheet with 1000’s of strains of knowledge — however they instructed her she’s higher off ignoring every little thing past the high 100 rows as a result of they’d no thought what the different knowledge meant. She took that as a problem.
“I started thinking maybe we could use our network models to solve this problem,” Pirhaji remembers. “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 an enormous information graph that included hundreds of thousands of interactions between proteins and metabolites. The knowledge was wealthy however messy — Pirhaji known as it a “hair ball” that couldn’t inform researchers something about disease. To make it extra helpful, she created a brand new means to characterize metabolic pathways and options. In a 2016 paper in Nature Methods, she described the system and used it to analyze metabolic modifications in a mannequin of Huntington’s disease.
Initially, Pirhaji had no intention of beginning an organization, however she began realizing the expertise’s business potential in the remaining 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.”
Pirhaji started taking courses at the MIT Sloan School of Management, together with Course 15.371 (Innovation Teams), the place she teamed up with classmates to take into consideration how to apply her expertise. She additionally used the MIT Venture Mentoring Service and MIT Sandbox, and took half in the Martin Trust Center for MIT Entrepreneurship’s delta v startup accelerator.
When Pirhaji and Fraenkel formally based ReviveMed, they labored with MIT’s Technology Licensing Office to entry the patents round their work. Pirhaji has since additional developed the platform to clear up different issues she found from talks with tons of of leaders in pharmaceutical firms.
ReviveMed started by working with hospitals to uncover how lipids are dysregulated in a disease generally known as metabolic dysfunction-associated steatohepatitis. In 2020, ReviveMed labored with Bristol Myers Squibb to predict how subsets of most cancers sufferers would reply to the firm’s immunotherapies.
Since then, ReviveMed has labored with a number of firms, together with 4 of the high 10 international pharmaceutical firms, to assist them perceive the metabolic mechanisms behind their remedies. Those insights assist establish the sufferers that stand to profit the most from completely different therapies extra shortly.
“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.”
Generative fashions for metabolomics
Earlier this yr, ReviveMed collected a dataset based mostly on 20,000 affected person blood samples that it used to create digital twins of sufferers and generative AI fashions for metabolomics analysis. ReviveMed is making its generative fashions out there to nonprofit educational researchers, which may speed up our understanding of how metabolites affect a variety of illnesses.
“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.”
The work is a component of ReviveMed’s mission to create metabolic basis fashions that researchers and pharmaceutical firms can use to perceive how illnesses and coverings change the metabolites of sufferers.
“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.”