Mantis Biotech raises $7.4M to build digital human twins

New York-based Mantis Biotech has raised $7.4 million in seed funding to develop a platform that creates digital twins of the human body. The seed round was led by Decibel VC, a venture capital firm, with participation from the startup accelerator Y Combinator and investment firm Liquid 2. The startup plans to use the capital for hiring, advertising, marketing, and go-to-market functions.

The company’s platform is designed to fill the data availability gap in medicine by integrating disparate data sources. It creates digital twins of the human body using physics-based, predictive models of anatomy, physiology, and behavior. To build these models, the platform takes data from sources such as textbooks, motion capture cameras, biometric sensors, training logs, and medical imaging. It then uses a system based on large language models to route, validate, and synthesize these data streams, running the information through a physics engine to create high-fidelity renders.

This physics engine layer is key to grounding the generated synthetic data and realistically modeling the physics of anatomy. Founder and CEO Georgia Witchel explained the utility of this approach: “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.”

While the platform is intended to address broader data availability issues in medicine, Mantis Biotech has already seen success in professional sports. One of the startup’s main clients is an NBA team, where the technology is used to track and analyze athlete performance over time. However, the technology could also be used for studying and testing new medical procedures, training surgical robots, and simulating medical issues or behavior patterns. This includes predicting injuries, such as an Achilles’ heel injury, or addressing data scarcity for rare diseases where representative data is difficult to obtain due to ethical and regulatory constraints.

Looking forward, Mantis Biotech plans to release the platform to the general public for preventative healthcare. The company is also working to cater to pharmaceutical labs and researchers working on clinical trials for the FDA, the US food and drug regulator, to deliver insights into how patients respond to treatments.

Why it matters

Mantis Biotech is using physics-based digital twins to address data scarcity in biomedical research, particularly for edge cases like rare diseases where representative data is difficult to obtain.