Mantis Biotech is making ‘digital twins’ of humans to help solve medicine’s data availability problem

Large language models trained on massive data sets can accelerate genomics research, streamline clinical documentation, improve real-time diagnostics, support clinical decision-making, accelerate drug discovery, and even generate synthetic data to advance experiments.

But their promise to transform biomedical research often hits a sticking point: Beyond the structured data that healthcare relies on, these models struggle in edge cases like rare diseases and uncommon conditions, where reliable, representative data is scarce.

Based in New York Praying Mantis Biotech claims it is developing the solution to fill this gap in data availability. The company’s platform integrates disparate data sources to create synthetic data sets that can be used to build so-called “digital twins” of the human body: physics-based, predictive models of anatomy, physiology and behavior.

The company is pitching these digital twins for use in data aggregation and analysis. These digital twins can be used to study and test new medical procedures, train surgical robots, and simulate and predict medical problems or even behavioral patterns. For example, a sports team could predict the likelihood of a specific NFL player developing an Achilles heel injury based on their recent performance, training load, diet and how long they have been active, Mantis founder and CEO Georgia Witchel explained to TechCrunch in a recent interview.

To build these twins, Mantis’ platform first uses data from various sources, such as textbooks, motion capture cameras, biometric sensors, training logs, and medical imaging. It then uses an LLM-based system to route, validate and synthesize the various data streams, and feeds all that information through a physics engine to create high-fidelity representations of that dataset, which can then be used to train predictive models.

“We can take all these disparate data sources and then turn them into predictive models for how people are going to perform. So any time you want to predict how a human is going to perform, that’s a really good use case for our technology,” Witchel said.

The physics engine layer is crucial here, Witchel told TechCrunch, because it helps the platform improve the information available by grounding the synthetic data generated and realistically modeling the physics of anatomy.

“If I asked you to estimate hand posture for someone missing a finger, it would be very, very difficult, because there are no publicly available datasets with labeled hand positions of someone missing a finger. We could generate that dataset very, very easily, because we just take our physics model and say, delete finger X, regenerate the model,” she said.

Because Mantis’ platform fills gaps in data sources, Witchel believes it has the potential to be widely used in the biomedical industry, where information about procedures or patients can be difficult to access, unstructured, or housed in disparate sources. She highlighted edge cases of rare diseases, where data is difficult to obtain because there are often ethical and regulatory constraints around including patient data in public datasets, or using it for training AI models.

“You know how when you see a three-year-old running around, and they have a Barbie, and they’re holding him by one leg and slamming him into a table? I want people to have that mentality with our digital twin,” she said. “I think this opens people up to the idea of ​​what people can be tested for when you use virtual humans. I feel like people are having the exact opposite mentality right now, which makes perfect sense because people’s privacy should be respected. In fact, I don’t really think people’s data should be exploited at all, especially when you have this digital twin.”

For now, Mantis has seen success in professional sports, presumably because there is a need for high-performing athletes. Witchel said one of the startup’s main customers is an NBA team.

“We create these digital representations of the athletes, where it basically shows how this athlete has jumped, not just today, but for every day in the last year, and here’s how their jumps change over time compared to the amount of sleep they have, or compared to how often they raise their arms above their head,” she explained.

The startup recently raised $7.4 million in seed funding led by Decibel VC, with participation from Y Combinator, a pair of angel investors and Liquid 2. The funding will be used for recruiting, advertising, marketing and go-to-market functions.

The next step for Mantis, Witchel said, is to continue building out the technology and eventually release the platform to the general public, focused on preventive healthcare. The company also has pharmaceutical labs and researchers working on FDA studies, with the goal of providing insight into how patients respond to treatments.