Extensive language models trained on massive datasets hold the potential to accelerate genomics research, simplify clinical documentation, enhance real-time diagnostics, aid clinical decision-making, speed up drug discovery, and produce synthetic data to propel experiments forward. However, their transformative potential for biomedical research frequently encounters a significant obstacle: beyond the structured data foundational to healthcare, these models falter with edge cases such as rare diseases and unusual conditions, where dependable, representative data is limited.

A New York-based firm, Mantis Biotech, asserts it is creating the solution to bridge this data availability gap. The company's platform merges diverse data sources to produce synthetic datasets, which can then be used to construct "digital twins" of the human body—predictive, physics-based models of anatomy, physiology, and behavior. These digital twins are promoted for applications in data aggregation and analysis, potentially aiding in the study and testing of new medical procedures, training surgical robots, and simulating or predicting medical issues and behavioral patterns.

To develop these twins, the Mantis platform initially gathers data from various sources including textbooks, motion capture cameras, biometric sensors, training logs, and medical imaging. Subsequently, it employs an LLM-based system to direct, validate, and combine these different data streams. All this information is then processed through a physics engine to generate high-fidelity renders of the dataset, which can train predictive models.

"We’re able to take all these disparate data sources and then turn them into predictive models for how people are going to perform. So anytime you want to predict how a human being is going to be performing, that is a really good use case for our technology," explained Witchel. She illustrated this with an example: "If I asked you to do hand-pose estimation for someone who is missing a finger, it would be really, really hard, because there are no publicly available datasets of labeled hand positions of someone who is missing a finger. We could generate that dataset really, really easily, because we just take our physics model and we say, remove finger X, regenerate model."

Given that the Mantis platform addresses deficiencies in data sources, Witchel believes it has broad applicability across the biomedical industry, where information on procedures or patients is often challenging to access, unstructured, or isolated in various silos. She emphasized its value for edge cases or rare diseases, where data collection is difficult due to ethical and regulatory restrictions on including patient data in public datasets or using it for AI model training.

"You know how when you see a three-year-old running around, and they have a Barbie, and they’re holding it by one leg and smashing it against a table. I want people to have that mindset with our digital twins," she remarked. "I think that’s going to open up people to this idea that humans can be tested on when you’re using virtual humans. I feel currently, people operate with the exact opposite mindset, which totally makes 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 these digital twins."

Currently, Mantis has found success in professional sports, likely due to the need to model high-performing athletes. Witchel noted that one of the startup's primary clients is an NBA team. "We create these digital representations of the athletes, where it basically shows here’s how this athlete has jumped, not just today, but for every single day in the past year, and here’s how their jumps are changing over time compared to the amount that they’re sleeping, or compared to how many times they lift their arms above their head," she detailed.

The startup recently secured $7.4 million in seed funding led by Decibel VC, with contributions from Y Combinator, several angel investors, and Liquid 2. These funds will be allocated toward hiring, advertising, marketing, and go-to-market initiatives.

Looking ahead, Witchel stated that Mantis's next steps involve continuing to develop the technology and eventually releasing the platform to the general public, with a focus on preventative healthcare. The company is also working to serve pharmaceutical labs and researchers involved in FDA trials, aiming to provide insights into patient responses to treatments.