Out today in @cellpressnews: "A world model of the virtual cell," from our co-founders @ericxing and @dasongle. Their definition of a virtual cell is a stateful, multi-modal, multi-scale simulator, judged on whether it stays coherent across a sequence of interventions. Open access: cell.com/cell/fulltext/S0092…

A model that makes one prediction and resets only captures a snapshot. AIDO Cell holds the cell's state: perturb it, read it out, then further experiment on the cell you just changed. @DrugDiscovNews on where the virtual cell came from, what's left to prove and how world models are redefining cellular simulation: drugdiscoverynews.com/what-i…

Join the waitlist for early access: genbio.ai/waitlist/

It’s been a week since we revealed AIDO Cell. Here’s some of the coverage that encapsulates the overall mission and reception (🧵):

1/ AIDO Cell is a simulator for cell biology. You instantiate a virtual cell, perturb it, read out experimental measurements, branch it, and perturb it again. An example of how it works, and what it does and doesn't do -> 🧵

AIDO Cell is in @statnews this morning. AlphaFold predicts the structure of a single protein; AIDO Cell predicts how the machinery of an entire cell responds when you knock out a gene or add a drug. Story (STAT+): statnews.com/2026/08/18/davi… Technical report and demo: genbio.ai/aido-cell-simulato…

AIDO Cell is the first step toward AIDO, an AI-Driven Digital Organism. Blog and early access waitlist: genbio.ai/aido-cell-simulato…

This is a preview. The case studies in the technical report reproduce established biology. It shows multi-scale stateful simulation works. It is not a finished high-fidelity model of any one cell line. Expect even more capable versions through the rest of this year and into next.

The part that matters most: AIDO Cell holds its state. The next thing you do lands on the cell you just changed, not a fresh copy of the original. That’s what makes it a stateful simulation you can act on, rather than a predictor you can query.

Until now, each layer had its own instruments, its own specialists, its own software. AIDO Cell holds all of them in a single model. Silence a gene, overexpress one, add a compound – the consequences propagate through every level.

A cell isn’t one layer. DNA is read out by regulatory networks that decide which genes turn on, that RNA is transcribed and spliced into isoforms, translated into protein, and proteins move to their compartments and do their jobs — and the whole cell changes shape and behavior as a result.

Today we're releasing a preview of AIDO Cell, a world model of the human cell. It simulates one cell across DNA, RNA, protein, through regulatory networks and whole-cell behavior. Not four models handing results to each other. One system.

GenBio AI researchers' new Perspective paper in @NatureMedicine lays out a blueprint for a simulator of biology: the AI-Driven Digital Organism (AIDO), a system of integrated multiscale foundation models spanning every scale, from molecules to cells to individuals. Not siloed predictors but a connected, hierarchical system: central-dogma sequence FMs, 2D positional encodings, and differentiable computation graphs propagating information bidirectionally across scales. The endpoint is a world model of biology: condition on a state, apply an intervention, roll out counterfactual trajectories. Read the paper: nature.com/articles/s41591-0…

Today at 12 pm in #ICML2026 Hall B2: @dasongle’s will present a novel architecture for a virtual cell world model - one that enables simulated cells as an end-to-end platform: from actionable biological prompts to anticipated outcomes at all levels (molecular, structural, interactional, and morphological) in a fully aligned, integrative, multi-modal, and multi-scale fashion. More details: icml.cc/virtual/2026/80215

@icmlconf is the field's leading venue for machine learning research. Next week, GenBio AI will be on-site speaking on virtual cell world models. Where to find us in Seoul, July 6 to 11. All times local. Monday July 6, 4:00 PM, Hall B2 Co-founder and CTO @dasongle presents "A World Model of the Virtual Cell" in the AI for Science Expo Workshop. Monday July 6, 6:30 PM, Hall B2 Le’s panel will break down foundation models and agentic systems for closed-loop discovery. Saturday, July 11, from 8:00 AM, Room 317 Le co-organizes the 3rd Workshop on Multimodal Foundation Models for Life Sciences. Come find the team at #ICML2026

Months of research compressed into days. That's the promise of virtual cell world models. GenBio AI Co-founder & CTO @dasongle breaks down how we're building them and what it means for drug discovery. Full piece by @jennschenker in @theinnovator here: x.genbio.ai/EI7RMW

Tomorrow at @wef's Annual Meeting of the New Champions, GenBio AI Co-Founder and CTO @dasongle takes the stage for "Innovating at Scale: How Can Technology Be Harnessed for Outcomes in the Real Economy?" June 25, 11:15–11:45 CST. Watch live: x.genbio.ai/cmikue

🧬 Excited to announce our collaboration with @NVIDIA to accelerate virtual-cell world models! Our agentic system VCHarness autonomously builds, tests, and refines AI models of human cells, discovering novel architectures in days, not months. Together, we're shortening the path to drug discovery. 🔬 👉 genbio.ai/advancing-agentic-…

What should a virtual cell actually be able to do? Our latest paper argues it should work like, and functionally be, a world model for cellular biology: a system you can run experiments on, apply multiple perturbations in sequence and trace how the cell moves from one state to the next across every scale, molecular to cellular, rather than a model that predicts a single readout, on a single biological scale, at a single point in time. @peterottsjo broke down five of the core ideas in his excellent newsletter BAIO. Worth a read: x.genbio.ai/NVpMIX

🧬 GenBio AI is heading to #BIO2026 by @IAmBiotech, the world's largest biotech gathering! Connect with Head of Business and Corporate Development Aaron Lifland in San Diego, June 22–25. Learn more: convention.bio.org/