Vincent Turon-Lagot

I build measurement systems for biology — CRISPRi screens, live-cell imaging, single-cell analysis. Now auditing what LLM agents get wrong on it. @biohub in SF.

[Vincent Turon-Lagot @vturonlagot]

New preprint! We built V-SWITCH: a fluorescent reporter that lights up when a cell gets infected by an RNA virus. One modular vector, four viruses (DENV, ZIKV, WNV, OC43), no antibodies needed.

Huge team effort from the Arias group at @biohub!

https://t.co/uxO9rYJvGi

[Vincent Turon-Lagot @vturonlagot]

@NeuroLuebbert Very exciting! I have been waiting to test Mythos on virology-related work for a while!

[biohub @biohub]

.@alexrives, our Head of Science, and the Biohub team have been named to @TIME's TIME100AI list for 2026.

Alex is shaping our work at the frontier of AI and biology, including ESM, our world model of protein biology, and the data to build frontier models through our labs and the Virtual Biology Initiative. Thrilled to see our work + the team behind it be recognized.

#TIME100AI https://t.co/6Qkc4IZ0eD

[Vincent Turon-Lagot @vturonlagot]

The code and all the numbers are up. I built it because I want to ask whether models reason about genes or just recall the well-studied ones, and you can't ask that without a fame number you trust first.

https://t.co/2l8UBJwxSd

[5/5]

[Vincent Turon-Lagot @vturonlagot]

This matters more than it sounds, because every time someone says a model proposed an interesting gene, the first question is whether it just proposed a famous one, and for that you need a number for how famous.

That number is 3.6x off for the odd names.

[4/5]

[Vincent Turon-Lagot @vturonlagot]

My favourite is CAT. Papers on CAT and SARS-CoV-2:

402 if you search title and abstract
194 if the paper also has to be about genes

And it's not cats🙀! It's CAT scans, sitting in the methods section of covid papers.

[3/5]

[Vincent Turon-Lagot @vturonlagot]

It turns out you pick up quite a lot of junk.

I ran four versions of the same search over 2,431 genes, and for symbols that are also normal English words you get 3.6x more hits than when you ask the paper to mention genes at all.

For everything else it's 1.05x.

[2/5]

[Alex Rives @alexrives]

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 accelerating 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://t.co/93Nw1QT5iZ

[Vincent Turon-Lagot @vturonlagot]

One modular platform validated across two viral families → Flaviviruses (Dengue, Zika, West Nile) and coronaviruses (OC43). This tool is compatible with live-cell imaging, antiviral screening, and functional genomics.

Key result: fluorescence intensity directly correlates with viral RNA levels, revealing striking cell-to-cell heterogeneity in replication.

Feedback welcome!

#Reporter #Dengue #Zika #Coronavirus #Biohub #Preprint

[Vincent Turon-Lagot @vturonlagot]

New preprint! We built V-SWITCH: a fluorescent reporter that lights up when a cell gets infected by an RNA virus. One modular vector, four viruses (DENV, ZIKV, WNV, OC43), no antibodies needed.

Huge team effort from the Arias group at @biohub!

https://t.co/uxO9rYJvGi