Decoding inflammation

Inflammation is one of the body’s most powerful defenses — and one of its greatest vulnerabilities. It helps to heal after injury and fight infections, yet when it lingers or misfires, it causes damage within the human body and contributes to many serious diseases, from autoimmune disorders to heart disease and cancer.

To understand and control inflammation requires seeing it as it happens: inside living human tissues, over time. Inflammation is not a single switch that turns on or off. It is a constantly changing process, shaped by thousands of signals between molecules, cells, and tissues. Today’s tools can measure parts of this process, but they rarely decode the full story of how inflammation starts, spreads, adapts, or goes wrong.

We are building a new way to study inflammation using instrumented tissues: engineered human tissue models that contain miniaturized devices to continuously measure, map and track inflammation as it unfolds in real time and space. When combined with frontier AI, these systems reveal inflammation in action, showing how complex networks of signals drive injury, healing, and disease, and ultimately provide the ability to influence inflammation.

Our goal is to transform the body’s response to inflammation from being reactive into something that is predictable and controllable. By creating detailed, predictive maps and models of inflammatory dynamics across tissues, our work aims to uncover the design rules that govern human biology and develop tools that can monitor and modulate inflammation before it causes harm — ultimately enabling a new kind of medicine that prevents disease by restoring the body’s balance.

Our focus areas:

  • Live tissue omics — New technologies that map inflammation in living tissues and understand how immune cells behave at the molecular level. Paired with frontier AI, these tools help reveal where inflammation comes from and how it evolves over time.
  • Continuous inflammation monitoring — Bioelectronic tools that can track immune activity in real time by sensing molecular signals. These technologies aim to make inflammation a measurable, monitorable part of everyday health, much like heart rate or blood pressure.
  • Deep profiling of immune cell states — Cutting-edge, high-throughput technologies to study how immune cells shift between healthy and disease-causing states. Large datasets and AI models help uncover new strategies to prevent or reverse these harmful transitions.
  • Virtual Immune System — A comprehensive, AI model that spans molecules, cells, and tissues to predict how the immune system behaves over space and time. The Virtual Immune System is an effort spanning all of Biohub’s scientific grand challenges that will enable simulating inflammation, testing ideas, and guiding real-world interventions.

“We have an incredible, multidisciplinary team that is creating fit-for-purpose tools to measure things that have never been measured before. With this capability in hand, we can develop powerful AI models to predict immune system function.” — Shana Kelley, president of bioengineering

News

  • Scott Fraser: 5 ways imaging and AI are capturing biology across billion-fold scales

    Dynamic imaging technologies are allowing us to watch biology unfold in real time and with unprecedented detail, shares Biohub’s president of imaging.

  • Andrea Califano: 6 strategies for using AI to reprogram the immune system

    The convergence of machine learning, synthetic biology, and immunology is changing what's possible for human health.

  • Shana Kelley: 5 new ways to measure inflammation

    With AI-integrated platforms to watch immune cells in action, we will be able to intervene in inflammation before it becomes disease, says Biohub’s president of bioengineering.

Research

  • Tissue-specific clonal selection and differentiation of CD4⁺ T cells during infection

    Roham Parsa, Helder Assis, Tiago B.R. de Castro, et al. (2025) | bioRxiv

  • rbio1-training scientific reasoning LLMs with biological world models as soft verifiers

    Ana-Maria Istrate, Fausto Milletari, Fabrizio Castrotorres, et al. (2025) | bioRxiv

  • GREmLN: A Cellular Regulatory Network-Aware Transcriptomics Foundation Model

    Mingxuan Zhang, Vinay Swamy, Rowan Cassius, et al. (2025) | bioRxiv

Team leaders

Investigator program

Our investigator and residency programs support research and collaborations by some of the best minds in science, medicine, engineering and technology.

Join us in our mission

We are a collaborative community of scientists, engineers, and AI and machine learning experts from across multiple fields who are passionate about tackling complex challenges and share a unified vision of a world without disease.