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.
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: https://t.co/cHTcNN1zH4
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: https://t.co/cHTcNN1zH4
The ADIA Lab Symposium opens in Abu Dhabi on Monday, October 26. @dasongle will be delivering a keynote on day two.
@adia_lab is an independent research institute working in data and computational sciences, and this is its flagship event. Le's talk is AIDO Cell: A General-Purpose Simulator for Cell Biology.
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. https://t.co/5M2MeTj0hv
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. https://t.co/5M2MeTj0hv
@dasongle is a featured panelist on the opening panel at Molecules, Models & Agents in San Francisco on Monday, October 5.
From Data to Discovery: AI Across Digital Health and Digital Biology, moderated by @dr_alphalyrae of @NVIDIA NVentures, with Michael Aratow of @EllipsisHealth and @kavi_deniz of @tamarindbio. #SFTechWeek
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
https://t.co/h8S09sQ8G9
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: https://t.co/BLHUOmQHki
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: https://t.co/tcWdNFlJSr
@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.
https://t.co/ph7Vcl4See
Subscribe to our newsletter and get the biggest biotech news straight to your inbox 🧬
https://t.co/uNrxaa7z6R
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 -> 🧵
20/ There are benefits and drawbacks to this, but our strategy is to make biology fully differentiable.
-> 2. BAIDO Cell currently ships with two prototype cell lines: K-562 and Hep-G2.
28/ Simulating the multi-scale, layer-spanning dynamics of a cell remains a challenge to both predict and validate. We are actively working to bridge the gap between what is functionally possible and what benchmarks exist in the field.
Blog post and full report: https://t.co/88J1RSd8S8
27/ Where it doesn't lead: AlphaGenome on ATAC, DNase and the RNA output tracks, AlphaFold3 on protein-DNA, isoDDE on protein-ligand docking.
AIDO Cell is also pushing into territory that no existing model attempts.