Biohub

Inflammation drives nearly every major disease—cancer, heart disease, and autoimmune conditions. Yet science has never been able to watch it unfold in real time. We're funding 15 projects to change that. Inflammation is a dynamic process that begins with subtle molecular signals and unfolds over hours, weeks, or months. Autoimmune and chronic inflammatory diseases are difficult to diagnose and treat in part because researchers have never been able to observe them progressing at the molecular level. It's one of biology's most consequential blind spots. Understanding the dynamics of inflammation is one of the most important steps toward better treatments for some of the world's most common and complex diseases. These 15 projects will develop a new generation of tools for real-time molecular profiling of living tissue—measuring not just where proteins and metabolites are, but when they appear, how they shift, and what their dynamics reveal about disease. Learn more: https://bit.ly/4wFDJej

One of the hardest questions in autoimmune disease isn't just how to treat it—it's figuring out what the immune system is reacting to in the first place. Our team Biohub developed AI models to unlock insights from a high-throughput screening platform built by the Garcia lab at Stanford University and Howard Hughes Medical Institute (HHMI). Using a combination of lab-based protein screening and AI trained on binding data, we can now systematically map what triggers individual T cells—the immune cells at the center of many autoimmune conditions—at a scale that wasn't previously possible. In patients with ankylosing spondylitis and acute anterior uveitis, two conditions that can cause severe joint and eye inflammation, this approach uncovered new candidate targets the immune system may be attacking—including one found in iris tissue. It also outperformed leading computational models in predicting whether a T cell would actually respond. This is what it looks like when AI and biology work together to get at the root of disease. 

Finding the antigens that drive autoimmune disease has been one of immunology's hardest problems. Today, we're sharing a new approach. In a paper published in Nature Biotechnology, our team developed AI models, in collaboration with the Garcia lab at Stanford University / Howard Hughes Medical Institute (HHMI), that pair their high-throughput yeast display platform with fine-tuned protein language models to build deep Peptide Recognition Profiles for individual T cell receptors. Applied to receptors from patients with ankylosing spondylitis and acute anterior uveitis, the platform identified novel candidate autoantigens, including PSG5, a protein expressed in iris tissue, and outperformed leading structural approaches, including AlphaFold3, in predicting T cell activation. This is AI learning the language of T cell recognition from the right experimental data, and a real step toward virtual biology, where computational models grounded in real experiments let us understand and eventually predict immune behavior. More in the paper: https://bit.ly/4d4d0Ar

AI + single-cell biology just opened a new door for treating diffuse midline glioma, one of the rarest childhood brain tumors. We used AI to identify 3 existing drugs that work together to target all 7 of the cancer's distinct cell states — confirmed at ~90% accuracy in the lab. A powerful example of how AI, biology, and medicine can come together to unlock completely new treatment strategies, even for the rarest diseases. #AI #Biology #Science #SciTech

AI models will solve mysteries in human health that the past century of research could not. It will be the biggest challenge the field has faced – and no one institution can solve it alone. Yesterday, we announced the Virtual Biology Initiative, a global effort to build the open data foundation for AI-accelerated biology together. I shared our commitment to this vision in TIME https://bit.ly/4uitM4q #science #AI #health #biology

The AI revolution in science is powered by open source software. Let's fund it. Today, we're launching the Open Source for Science Fund, a new multi-donor philanthropic fund by Renaissance Philanthropy, dedicated to sustaining and evolving the open source software stack that underpins science. Seeded with $20M from Biohub and Wellcome Trust, with support from The Kavli Foundation and the Research Software Alliance. From imaging the universe to modeling life at the molecular scale, science is built on open source software maintained by scientific communities. That infrastructure is systemically underfunded, and not yet designed for AI-native use. We want to build a coalition of public and private funders and industry partners to change that. Our inaugural call for proposals will seek submissions from software project maintainers and contributors whose work supports data-intensive research and AI-driven discovery in the life sciences. There are two funding tracks - up to $250K for domain-specific tools, and up to $1M for foundational libraries and ecosystem initiatives - and applications will open May 11. Find out more here: https://os4science.org/ If you build the tools science runs on, we want to hear from you. Get in touch at info@renphil.org

Scaling laws are powering AI. It’s time to scale biology. Today we’re launching the Virtual Biology Initiative to generate the data to unlock scaling laws in biology and build accurate predictive models of the cell. Digital representations of proteins are already expanding our understanding of life at the molecular level, and enabling the design of molecules and medicines. Accurate digital representations of the cell could reveal the mechanisms that are responsible for disease, and show how to reverse them. The protein data bank, and worldwide repositories of protein sequence biodiversity were created through decades of work by the scientific community. The advances in artificial intelligence for proteins would not have been possible without them. The cell is orders of magnitude more complex, and we will need to create the data in just a few years rather than decades. This will require a coordinated global effort. We're partnering with Broad, Wellcome Sanger, Arc, Allen, Human Cell Atlas, Human Protein Atlas, NVIDIA, and Renaissance Philanthropy. Biohub is contributing to this effort as both a funder and a builder. We are developing microscopy to observe millions of cells in living organisms, and cryo-ET to resolve the cell in atomic detail. We're building instruments that expand the range of modalities and parameters that can be simultaneously measured. We’re developing molecular, cellular, and tissue engineering to create models of disease and design interventions. The data we generate will be available to the worldwide scientific community. We’re also committing $100M over the next five years to support work beyond Biohub. We invite other scientific teams and funders to join. Link: https://lnkd.in/gmEFwAGG

Today, Biohub is announcing a major new commitment to build the data foundation biology needs for its next leap — and it's one of the most important steps we can take toward helping cure or prevent all disease. We are closer than ever to building AI models that can reason about living cells. But those models are only as good as the data they're trained on. Getting the data right is the critical step and Biohub is leading the way. Read more on the Virtual Biology Initiative from our Head of Science Alex Rives: https://lnkd.in/g2dEFb4D

Drug delivery is not just about the carrier — it also depends on the state of the receiving cell. New research from our team in Chicago shows that a cell's metabolic state is a major driver of its ability to take up extracellular vesicles (EVs), which show promise as drug carriers. The study helps explain why so many delivery strategies succeed in the lab but fall short in the body. Using deep omics profiling, Kangfu Chen, Daniel Wang, and Shana Kelley identified a simple fix — adding two common nutrients, pyruvate and methionine — that boosts EV uptake by ~150% and improves EV-delivered chemotherapy outcomes in cancer models by 50%. Featured on the cover of the latest Cell Biomaterials by Cell Press, read the paper here: https://bit.ly/4vLsiRQ