Derek Croote

Introducing Pythia-1, a frontier generative model for protein design. In our new study, we used it to rapidly design full-length human agonist and antagonist antibodies for hard-to-drug targets. We’re sharing complete sequences of all lead antibodies to support independent validation and further research. 1/8

Progress in biology has a curious structure that, as far as I know, has never really been explained Why would we lock in a cell line derived from Chinese Hamster Ovaries and proceed to use it for everything for 60 years? There is no plausible reality in which this random-ass cell line from the 1950s is the global optimum solution for all of its use-cases Part of the answer is that biology needs to be cautious in a way that other fields do not. Lives depend on biologics manufacturing. So CHO cells are harder to discard than say, a programming language, when a better option comes along But if biologists are so cautious that they are unwilling to update a core technology for 6 decades - why has there been any progress at all? Sometimes things move quickly. DNA synthesis, sequencing, gene editors, etc. It isn't the case that biologists globally value caution in all things Biological caution has a kind of jagged frontier. There is a Warhammer 40k quality to it. The tech-priests enforce orthodoxy on CHO cells. But cult of inertia doesn't extend to every planet in the imperium. In isolated pockets, researchers are free to innovate or to adopt xenos technologies Every biologist has had the experience of asking themselves "why do we do things in this weird old way?" Finding a satisfying answer to that question is, I believe, the key to building the new kind of AI-powered biotech pubmed.ncbi.nlm.nih.gov/4292…

Open Access: Human IgE Antibodies Recognize the Vicilin and Alpha-Hairpinin Domains of Peanut Allergen Ara h 1. First author: Taylor M. Cosey; corresponding author: Geoffrey A. Mueller The ɑ-hairpinin of Ara h 1 contains a dominant epitope that is both frequently recognized and blocks a majority of the IgE against this domain. Including this region in tests may improve diagnosis of peanut allergy. The trimeric structure of the vicilin region explains the ability of Ara h 1 to induce anaphylaxis with a single antibody.

starting a collection of quotes like this

I'm lucky to have worked with talented protein sciences teams that did heavy internal QC for any externally purchased proteins. They'd had enough bad experiences receiving unfolded/nonfunctional proteins, wrong PTMs, or the wrong protein entirely.

Living cells can compute — no engineering required. 🦠 Our E. coli reservoir computer classifies COVID-19 severity & solves ML tasks from growth alone. New in Cell Systems: doi.org/10.1016/j.cels.2026.…

Redesign complete! We think you'll really like the new aesthetic and recently added features, including a cleaner Map View and greater search flexibility. Trial Inference is free to try, so get started today.

Today we're launching Intercept: a $500M philanthropic initiative to make respiratory infections, like the common cold and flu, a thing of the past. We treat respiratory infections as a minor nuisance, but that’s really not the case. Most of us will spend 5% of our lives (!) sick from these viruses, they kill 1M people a year, cost $600B annually in productivity, and periodically threaten civilization through pandemics. So, if they’re such a big problem, why haven’t we dealt with them yet? Last year we convened ~40 leading scientists, pharma R&D leaders, biotech investors, and regulatory experts to better understand that. We heard two main reasons: (1) First, it’s just technically very challenging: respiratory viruses represent hundreds of distinct, mutating strains across several families. Fortunately, recent breakthroughs make this newly possible. (2) Second is a lack of funding: broad-spectrum solutions have historically been underfunded, in part because they’re not a great fit for most philanthropic or commercial funding (and while COVID generated a burst of activity around preventing and understanding respiratory infections through an influx of new funding, that hasn't been sustained). We think that with enough focus and funding, this might be solvable. Intercept is a $500 million philanthropic initiative that will take advantage of new tools to catalyze the development and deployment of two types of products: broad-spectrum preventatives and air cleaning technologies. This problem is undoubtedly difficult. But it’s more tractable now than it’s ever been. We think we should give it our best shot. We’re enormously grateful to our anchor funders: @stripe, @AnthropicAI, @TheFluLab, @FoundationOAI and individuals from Jane Street. And, I’m very excited to be building this with @incredutility and the rest of the team.