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…

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 -> 🧵

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-…

An excellent piece in @Nature on the promise and challenges of virtual cells, including insights from GenBio AI's @ericxing and @Prof_Lundberg on why multi-scale, multimodal approaches are the future, and why world models are key to building them. Learn more → x.genbio.ai/dTHCHh

What if AI could build its own biology models — and beat human experts? We built VCHarness: an autonomous system that proposes models, writes code, runs experiments, and learns from results in a closed loop. Tested on CRISPR gene knockdown across 4 human cell lines — it outperforms expert-designed baselines. From months of manual model-building → days of autonomous search. 🔬 Blog: genbio.ai/harnessing-ai-to-b… 📄 Paper: biorxiv.org/content/10.64898… 🌐 Website: genbio-ai.github.io/VCHarnes…

Cells aren't islands. Their representation and function depend on neighbors. We introduce AIDO.Tissue, a foundation model that learns biology by thinking in cellular neighborhoods. It not only outperforms competing models but also demonstrates a scaling behavior with neighboring context. Learn more👇 genbio.ai/aido-tissue/

⏰ Last chance to register! Tomorrow at 9AM PT, Professor @anshulkundaje @Stanford joins the #FM4Bio Seminar to discuss his work on lightweight, interpretable models that outperform massive foundation models for decoding the regulatory genome. Don't miss it 👇 x.genbio.ai/fm4bio-seminar

Bigger isn't always better in genomics AI Join us Tue, Mar 24 at 9 AM PT for the next #FM4Bio Seminar with Professor @anshulkundaje @Stanford — on building smarter, interpretable models of regulatory DNA that outperform massive foundation models. x.genbio.ai/fm4bio-seminar

Many “virtual cell” efforts restrict themselves to cell-level assays like scRNA-seq. To build a true world model for biology, we need to move beyond the individual cell and model the tissue context as well. GenBio-PathFM is a new histopathology foundation model from GenBio AI. It is the only SOTA model trained without using proprietary image archives, and the strongest open-weight model to date. Highlights: - SOTA performance on public pathology benchmarks (THUNDER, HEST, PathoROB - shown below). - Unprecedented data efficiency, requiring 5x-15x fewer WSIs for training. - Novel two-stage pretraining strategy combining DINO and JEPA. Blog post: genbio.ai/genbio-pathfm Paper: genbio.ai/papers/genbio-path… GitHub: github.com/genbio-ai/genbio-…

Don’t miss GenBio AI Co-Founder & Chief Scientific Advisor @Prof_Lundberg at #NVIDIAGTC: 🧬Scaling Laws in Biology: Why Bigger Models Alone Aren’t Enough [S81652] March 18, 10:00–10:40 AM PT An in-person panel on breaking the data wall in Bio x AI through at-scale data generation and new scaling laws. Save your seat → nvda.ws/3OAKT1T 🎟️ Register → nvda.ws/4cCOiY2 v/ @NVIDIAHealth

Happy Holidays from all of us at GenBio AI! 🎄⭐️🎅

Join GenBio AI Co-Founder and Chief Scientist @ericxing at #NeurIPS2025 for his invited talk at the Biosecurity Safeguards for Generative AI Workshop. He will discuss how AIDO supports molecular design and cell-level modeling, including AI-based perturbation simulation. 📍 Room 27AB 🕒 3:35 to 4:05 PM PT Full details → biosafe-gen-ai.github.io/ind…

GenBio AI will be at @NeurIPSConf. Members of our founding team will share invited talks at the 2nd Workshop on Multi-modal Foundation Models and Large Language Models for Life Sciences. • Co-Founder and Chief Scientist, @ericxing — 9:30 am PT • Co-Founder and Chief Strategic Advisor, @Prof_Lundberg — 1:25 pm PT • Co-Founder and Chief Scientific Officer, Ziv Bar-Joseph — 1:50 pm PT 📅 December 7 📍 Room 31ABC, NeurIPS 2025 Don't miss out on your chance to hear from world-renowned leaders in AI and Biology → nips2025fm4ls.github.io/inde… #NeurIPS2025

Halloween around the world at GenBio AI 🎃 Our teams in Palo Alto, Paris, and Abu Dhabi got into the spirit with costumes, pumpkin carving, and plenty of spooky fun. #HappyHalloween from all of us at GenBio AI! 🌍 🧬

1/ How can large models learn to predict how a single cell responds to a drug or genetic edit? In his FM4Bio Seminar talk, @HAOTIANCUI1 explores how large models are transforming single-cell biology and drug discovery. Watch the full talk: piped.video/watch?v=QE4H_BUW…

🚀 Introducing AIDO.DNA2, GenBio AI’s next-generation multi-species genomic foundation model. Built with a Mixture-of-Experts architecture and trained on the massive OpenGenome2 dataset, AIDO.DNA2 delivers higher accuracy, better efficiency, and stronger generalization across species, from variant prediction to regulatory genomics. Explore how it outperforms baselines and advances clinical genomics: 🔗 genbio.ai/aido-dna2-multi-sp…

📢 Happening today! GenBio AI Co-Founder & CTO @dasongle will be presenting at the MedInvest Biotech & Pharma Investor Conference in Palo Alto, CA. 📍 Session: Decode Biology Holistically, Revolutionize Biomedicine 🗓️ September 24, 2025 – 3:20 PM PT We are proud to contribute to a gathering with 125+ investors, 50+ presenting companies, and leading voices shaping the future of biotech. 🔗 Learn more and register: x.genbio.ai/medinvest

⏰ Happening tomorrow! Don’t miss the next Foundation Models for Biology (#FM4Bio) Seminar on September 17 at 9 AM PT. @HAOTIANCUI1 will present “Large Models for Single-Cell Omics and Drug Discovery: Data, Pretraining, and Closed-Loop Environment.” The talk will cover the development of scGPT, a generative transformer trained on more than 33 million single-cell profiles, and LUMI-lab, a closed-loop self-driving platform for model-guided mRNA delivery. Together, these advances show how large-scale pretraining and closed-loop systems can accelerate discovery in single-cell biology and therapeutic design. 🔗 Last chance to save your spot → genbio.ai/fm4bio-seminar/

📡 Join us for the next #FM4Bio Seminar on Sept 17 at 9 AM PT featuring @HAOTIANCUI1 Haotian will present “Large Models for Single-Cell Omics and Drug Discovery: Data, Pretraining, and Closed-Loop Environment.” Save your spot → genbio.ai/fm4bio-seminar/

1/ 🚀 New from the Foundation Models for Biology Seminar Series (#FM4Bio) at GenBio AI: 🔬 @manntis4 introduces Egret-1, a family of large pretrained neural network potentials (NNPs) for efficient & accurate bio-organic simulation. 🧵 👇 piped.video/watch?v=-g012inw…

⏰ Happening tomorrow! Don’t miss the next Foundation Models for Biology (#FM4Bio) Seminar on Aug 5 at 9 AM PT. @abhinadduri will present “Predicting Cellular Responses to Perturbation Across Diverse Contexts With STATE.” STATE is a machine learning architecture for predicting cellular responses to perturbations, trained on over 100M perturbed cells and 167M single‑cell profiles. Secure your spot now → genbio.ai/fm4bio-seminar/

1/ How can we model each tumor’s unique biology instead of relying on one-size-fits-all approaches? In our latest blog post, we highlight findings from the recent PNAS paper with GenBio AI Research Scientist @probablybots and Co-Founder and Chief Scientist @ericxing, showing how contextualized networks pave the way for an interactome module in AIDO.

📡🧬 Join us for the next #FM4Bio Seminar on Aug 5 at 9 AM PT featuring @abhinadduri Abhi will present “Predicting Cellular Responses to Perturbation Across Diverse Contexts With STATE.” This work introduces a machine learning architecture that predicts cellular responses to perturbations across diverse contexts with over 50% improved accuracy, enabling scalable development of virtual cell models. 🔗 Save your spot → genbio.ai/fm4bio-seminar/

1/ 🚨 Just published in @NatureMedicine An international team of researchers, including GenBio AI Co-Founder @ericxing, Senior Scientific Fellow @segal_eran, @MBZUAI, and others, shares a major advancement from the Human Phenotype Project (HPP). 📄 nature.com/articles/s41591-0… 🎥 Video courtesy of @MBZUAI below ↓

Thank you to everyone who joined us at GenBio AI’s private reception in Vancouver, BC. We’re grateful to be surrounded by such a vibrant, forward-looking scientific community in AI and biology. Stay tuned and learn more: genbio.ai/blog

1/ 🚀 Introducing AIDO.StructureDiffusion: A generative model for structural protein design—enabling high-quality, controllable generation of monomers, complexes, and antibodies. 🧵

📍 GenBio AI at #ICML2025 Generative AI and Biology Workshop We were thrilled to be part of the ICML 2025 Workshop on Generative AI & Biology in Vancouver. 🎤 GenBio AI Co-Founder and Chief Scientist @ericxing delivered a keynote talk titled: “Multiscale Foundation Models for Predicting, Simulating, and Programming Biology at All Levels” The talk introduced our vision for AIDO, a system of integrated multiscale foundation models designed to simulate and design biology across all levels. 🧠 Key ideas included: – Simulating biology with foundation models – Linking sequence, structure, phenotype, and disease – Building programmable systems for biological design 🧬 Coming up next, Prof. Xing will join a panel discussion alongside @ArashVahdat, David Li-Bland, @marinkazitnik, and Martin Renqiang Min, leaders from academia and industry, to explore the future of generative AI in life sciences. Thank you to the organizers and community for the engaging conversations. 🔗 Learn more about our work: genbio.ai

1/ 🧪 New from #FM4Bio: @KexinHuang5 @Stanford introduces Biomni, a biomedical AI agent that automates diverse scientific tasks using LLMs, planning, and code execution. 📺 Watch the talk: piped.video/watch?v=QjfTWUWq…

1/ GenBio AI will present five papers at the 42nd International Conference on Machine Learning (ICML 2025), highlighting recent work on biological foundation models. 🧬 Read the blog: genbio.ai/icml-2025

1/ 🧬 GenBio AI's AIDO.Protein-RAG (16B) now ranks #1 on ProteinGym, the most widely used benchmark for protein prediction.

1/ 📢 We're excited to welcome Emma Lundberg @Prof_Lundberg as our new Co-Founder and Chief Scientific Advisor. Emma is a leader in spatial proteomics, bioimaging, and AI. She joins GenBio AI to help guide our scientific direction and data strategy. Join us in welcoming Emma to the GenBio AI team!

📡🧬 Join us for the next Foundation Models for Biology Seminar Series (#FM4Bio) session on June 18 at 9 AM PT, featuring @manntis4. Eli will present "Egret-1: Pretrained Neural Network Potentials for Efficient and Accurate Bioorganic Simulation." Simulating atomic systems with both speed and accuracy could reshape molecular and materials design. Egret-1 offers a promising new path. Save your spot → x.genbio.ai/seminar

We’re pleased to share that GenBio AI has been invited to join the @wef's Global Innovator Community. This week, our Co-Founder and CTO, @dasongle, is participating in the WEF Global Tech Summit 2025, where global leaders will explore how technology can help address pressing challenges. We look forward to contributing to the conversations shaping the future of science, technology, and global collaboration.

1/ 🚨 #FM4Bio seminar update! 🚨 Due to strong interest in Biomni, our next Foundation Models for Biology (FM4Bio) seminar with @KexinHuang5 will now focus on: "Biomni: A General-Purpose Biomedical AI Agent." 📅 June 4, 9:00 AM PT 📍 Save your spot: x.genbio.ai/seminar

📡 🧬 Join us for the next Foundation Models for Biology Seminar Series (#FM4Bio) session on June 4 at 9 AM PT, featuring @KexinHuang5. Kexin will present KGWAS, a geometric deep learning method that uses a massive functional genomics graph to enable rare variant discovery in small-cohort GWAS studies. 🔗 Save your spot → x.genbio.ai/seminar

1/ 🧭 What happens when you bring RNA velocity into physical space? In our latest FM4Bio Seminar, @LabWelch presents TopoVelo: a model that infers how cells transition in space and time using spatial transcriptomics. 📺 Watch the talk: piped.video/watch?v=IBBgWaY8…

1/ We had a great week at #MLSys2025!🧬🔬 🧠 GenBio AI Head of Infrastructure, @HongyiWang10, chaired the session on LLM and Diffusion Model Serving. 📝 We also presented “Radius: Range-based Gradient Sparsity for Large Foundation Model Pre-training." And yes, we hit Topgolf too. 🏌️‍♂️

1/ 🚨 We’re at #MLSys2025 this week in Santa Clara! 🎤 Our Head of Infrastructure, @HongyiWang10, is chairing Session 10: LLM and Diffusion Model Serving. 🗓️ May 15, 1:15–2:40 PM PT The session topics include: • Prefix caching • Fused Attention • CPU offloading • Scalable LLM serving Full session details: mlsys.org/virtual/2025/sessi…

🚨 Happening this week at @_odsc #ODSCEast! Join GenBio AI Co-Founder & Chief Scientist @ericxing, on May 14 at 9:30 AM ET for his keynote: "Toward General and Purposeful Reasoning in Real World Beyond Lingual Intelligence." Learn how models like AIDO are shaping the future of AI & biology. Register today👉 x.genbio.ai/7rKanX

📡 Join us for the next session in the Foundation Models for Biology Seminar Series (FM4Bio) on May 16 at 10 AM PT, featuring @jkobject. Jérémie will introduce scPRINT, a large-scale foundation model trained on 50M single cells from the cellxgene database. The model infers gene networks and demonstrates powerful zero-shot capabilities in denoising, batch correction, and cell label prediction. ➡️ Save your spot: genbio.ai/fm4bio-seminar/