Replying to @nytimes
@nytimes covered @genbioai and its #VirtualCell work today, following a great conversation with the brilliant @carlzimmer! While companies like Isomorphic claim to "cure all diseases" with a drug design engine, we focus on "simulating diseases" for Virtual Trial of Drugs or Other Therapeutics, as well as for biological research, via virtual cell, virtual tissue, and eventually AI-driven digital organism (#AIDO). It is perhaps less ambitious, but in my opinion more realistic and accessible. We have a great team that includes luminaries like David Baker, @Prof_Lundberg, @zivbj, @deboramarks, @segal_eran, @dasongle, and many more superb engineers and researchers. Come join us!
nytimes.com/2026/11/18/scien…
AIDO Cell simulated every layer of this HepG2 cell, from gene expression to cell shape, in one model. Outputs are delivered through the API and explorable in AIDO Lab.
Want to run your own experiments? Join the waitlist: genbio.ai/waitlist/
Asked by @AlAinNews whether a virtual cell could replace clinical trials, CTO @dasongle said the better word is reduce. AIDO Cell is there to help researchers run fewer experiments and pick the right ones. The interview, in Arabic: bit.ly/4zyFwCF
Drugs that fail in clinical trials most often fail on efficacy or unexpected toxicity. In @Forbes, our CTO @dasongle traces both to one gap: no tool can yet predict how a molecule behaves inside a living cell. That gap is what AIDO Cell is for. bit.ly/3VjUoGn
We discussed fundamental issues in the definition, model architecture, computational algorithm, and meaningful evaluation/qualification of a fully steerable virtual cell that is multi-modal, multi-scale, dynamic, and stateful.
@dasongle , @genbioai , @mbzuai , @CarnegieMellon
cell.com/cell/fulltext/S0092…
GenBio AI retweeted
Replying to @genbioai
@genbioai has released a preview of AIDO Cell—a stateful, multiscale world model designed to simulate cellular responses from DNA and RNA through proteins to whole-cell behavior. Early access for researchers is planned.
businesswire.com/news/home/2…
Subscribe to our newsletter and get the biggest biotech news straight to your inbox 🧬
syntheticbiologysummit.com/?…
GenBio AI retweeted
GenBio was founded with the audacious goal of simulating all of biology. The natural starting point for biological simulation is the cell: the smallest unit of life. Today we're sharing a preview of our first version of that simulator, AIDO Cell.
GenBio AI retweeted
Whoa, the virtual cell is finally here! GenBio just launched version 1.0 of what it calls a “cell biology simulator.” Here’s what you need to know. 🧵 (1/6)
GenBio AI retweeted
Why stop at virtual cells when you can aim for an AI-Driven Digital Organism?
Startup GenBio has just published a Nature Medicine blueprint for using AI to “model and simulate biology and life.”
Here’s what you need to know. 🧵 (1/6)
AI is more than LLMs and agentic systems thereupon that deliver "book intelligence", it can help better understand nature and life by simulating it computationally. In our @NatureMedicine paper "How to build an AI-driven digital organism (#AIDO)", we present a perspective and roadmap on how to use AI to simulate diseases and biology, using an AIDO that is multi-modal, multi-scale, dynamic, and stateful. It can completely transform biological research, healthcare industry, and drug development process in terms of how possibility is explored, shifting discovery and validation from slow, expensive, often ad hoc and risky experimental search to efficient and structured navigation within learned biological worlds, bringing biology and medicine closer to an industrial age of predictive design and programmable systems.
@dasongle, @segal_eran, @mbzuai, @genbioai, @CarnegieMellon, @CMUCompBio, @mldcmu
Link to the paper: rdcu.be/fzGf1
GenBio AI retweeted
"can eventually help us better decode and improve life"
Some big thinking here on building and integrating multi-scale models @NatureMedicine
by @segal_eran @dasongle @ericxing @WeizmannScience @genbioai @CarnegieMellon
Replying to @icmlconf
@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
The outlook of an AI-driven Digital Organism (AIDO), such as a virtual cell (VC), has recently captivated much excitement and imagination from both AI and Biology communities, but there remain many open questions, in particular, what model presents the best path to realize an #AIDO or a #VC?
In this paper we present a definition of the virtual cell based on World Model — an architecture recently emerged in AI that supports advanced capabilities such as action-conditioned simulation, dynamic state-evolution, counterfactual reasoning, and long-horizon planning in complex dynamic environments. When applied to biological scenarios, a world model of the virtual cell is a generative model that simulates biological possibilities of a cell under any natural or artificial interventions and environments.
Such a virtual cell world model (VCWM) contrasts predictive foundation models on specific tasks, such as gene-expression perturbation prediction, as seen in some recent definitions of the virtual cell. At the same time not every biological foundation model built on sequence or structure or expression only can be repositioned as a world model if there is no multi- or pan-modality, stateful embedding, continuous action-conditioning, and dynamic state-transition and rollout.
We presents a novel architecture for #VCWM based on the GLP (generative latent prediction) framework that enables simulated cell as an end-to-end platform. Stay tuned for the release of the first implementation of VCWM from @genbioai soon.
@dasongle, @zivbj, @ElijahCole, @probablybots, @EuxhenH, @cfeinau, @deboramarks, @fabian_theis, @mmbronstein, @pkoo562
openreview.net/forum?id=hZNx…
GenBio AI retweeted
Virtual cells are supposed to help drug discovery. Why aren't they evaluated on drug discovery tasks? In our new preprint "Cell-Level Virtual Screening," we investigate this and other fundamental questions about practical applications of virtual cells for drug discovery.
At @genbioai, we use AI to build AI, so virtual cells can be made and harnessed automatically at scale. genbio.ai/harnessing-ai-to-b…
GenBio AI retweeted
Okay, this is very cool: an AI system that autonomously designs virtual cell models. It's called VCHarness, created by GenBio AI. Today, the manual process of designing these models is not just slow - it limits what gets tried.
The system is named after the harness concept that is everywhere in AI right now: the idea that the system wrapped around a model matters as much as the model itself.
I explain it in more detail in the latest issue of BAIO (where I also have a special treat for subscribers). Link below.
GenBio AI retweeted
Look at this speaker lineup! 🔥 Super excited to see the SCALE workshop accepted for #ICML2026. If you're researching multimodal agents, agentic memory, or workflow optimization, you definitely want to submit your work here. Fantastic initiative by an amazing team! 👇 #AgentFlow #AI
Super honored to be co-organizing this event with an amazing team (please see @thisissouvikk's post).
Paper Submission Deadline: April 24, 2026!
We look forward to your amazing works!
🎉🎉Announcing #ICML2026 workshop on "Multi-Modal Agentic AI": scale-icml-2026.github.io/
Topics covered: 1. Agentic memory, 2. Efficient agentic AI systems, 3. Scaling of multi-modal agents, 4. Agents for Planning, 5. Evaluation, guard railing, and benchmarking of agents
🚀Confirmed speakers: @dasongle (GenBio) @mohitban47 (UNCCH) @james_y_zou (Stanford) @chelseabfinn (Stanford) @MengdiWang10 (Princeton) @sunjiao123sun_ (Google) @MikeShou1 (NUS) @MinhyukSung (KAIST)
With @HongyiWang10 @digbose92 @jaeh0ng_yoon @ManlingLi_ @nagsayan112358 @schowdhury671
#AgenticAI #MAS #MultimodalAI
GenBio AI retweeted
If you're excited about AI scientists and biology simulators, we're looking for FTEs and interns @genbioai. Come work with an elite team of nobel laureates and titans of science+engineering on products that both people and agents use to accelerate biomedical research. DM or email
It was a pleasure to share the stage with @Yoshua_Bengio, @YejinChoinka, @harari_yuval, and @nxthompson, at #WEF26 in Davos to discuss "Next Phase of Intelligence". I shared my reservation of current LLM-based systems bringing us toward AGI very soon, and spoke for the needs for substantial innovations in representation, architecture, and learning paradigm before we can reach truly physical, social, and philosophical intelligence.
My candid response to @nxthompson's questions on what to go next, and what existing architecture to avid is: we must move past LLMs to focus on World Model to unlock physical intelligence, and we can't build a consistent, safe, and interactable world model by learning only in the "thought space" (i.e. latent space". We need new architectures like the GLP (Generative Latent Prediction) that support stateful representation, long-horizon reasoning, action-conditioning, and most importantly, close-loop training where learning takes place in both latent (thoughts) and observation (reality) space to ensure grounding, fidelity, and certifiability; and we also must go beyond passive self-supervised learning on pattern matching and reconstruction with a stationary model, but active and proactive learning on task-completion objectives and cost-conscious rewards over a non-stationary model that can improve not just during pre-train, but also in- and post-action during serving. Our PAN world model builds on such design principles.
Is AI actually "intelligent," or just "book smart?" 📚
Speaking at #WEF26 earlier, MBZUAI President and University Professor @ericxing said that we are still in the "primitive age" of AI.
While models like K2-Think (built from scratch by Institute of Foundation Models) are pushing boundaries, Professor Eric breaks down the 4 levels of intelligence AI is yet to master:
* Text-based Intelligence: What we have now. It's "book knowledge" that often lacks real-world consistency.
* Physical Intelligence: The ability to navigate the world. As he shared, while he was hiking the Alps: Map apps are great, but can't tell you what to do when the snow gets too steep.
* Social Intelligence: The nuance of collaboration. AI doesn't yet understand "self" or how to work in a team to run a company.
* Philosophical Intelligence: True agency and curiosity - this is the ability to learn without being asked.
Professor Eric emphasized that reaching these stages requires a fundamental shift toward new architectures that can reason consistently. By prioritizing open-source models, we allow the public to study the nuances of safety and risk while promoting global adoption.
ICYMI, link to recording here: weforum.org/meetings/world-e…
@nxthompson @Yoshua_Bengio @YejinChoinka @harari_yuval





















