←
Le Cong@Stanford, AI+Bio+Gene-Editing186 posts
Le Cong@Stanford, AI+Bio+Gene-Editing avatar

Le Cong@Stanford, AI+Bio+Gene-Editing

@lecong

Stanford Professor | Gene-Editing & AI+Bio & RNA programming | Stanford University School of Medicine, Genetics and Pathology | NIH and ASGCT Genomics Innovator

◷ Joined May 2009▧ 26 Photos and videos
Le Cong@Stanford, AI+Bio+Gene-Editing avatar
Le Cong@Stanford, AI+Bio+Gene-Editing@lecong·50m

Speaking Thursday at the 14th International mRNA Health Conference in Boston: "From Code to Cure: Building Models, Agents, and Co-scientists for RNA Design and Genomic Medicines." 8:30am ET. Find me there if you work on RNA design or AI+Bio to drive the next generation of programmable medicine! mrna-conference.com/agenda/

Post attachment
Le Cong@Stanford, AI+Bio+Gene-Editing avatar
Le Cong@Stanford, AI+Bio+Gene-Editing@lecong·Nov 6

Future of running agentic research from any coding environment, congratulations on the release @phylo_bio @KexinHuang5 @YuanhaoQ

Introducing the Biomni Lab API: Programmatic access to agentic science. Run Biomni agents directly from your own code. Analyze datasets in parallel, chain agents into multi-step research workflows, and start scaling your scientific tasks. Move beyond individual AI-assisted tasks to build and scale entire research workflows. Explore more at: phylo.bio/blog/biomni-lab-ap…

Post attachment
Andrew Dunn avatar
⟳ Le Cong@Stanford, AI+Bio+Gene-Editing retweeted
Andrew Dunn@AndrewE_Dunn·Sep 30

Baker is just one headliner among a full day of AI bio heavy hitters: @AdamRodmanMD @zavaindar @lecong @nc_frey @exnx & many more We're sold out for in-person. But virtual access to livestreams + recordings is free and open now: events.endpoints.news/aiday2…

Le Cong@Stanford, AI+Bio+Gene-Editing avatar
Le Cong@Stanford, AI+Bio+Gene-Editing@lecong·Sep 26

Excited to share AutoScreen—our AI co-scientist for target discovery that changes how we can work with CRISPR screen, human genetics and genomics data, benchmarked on >320 wet-lab screens and enabled a “AutoScreen AI hub” with AI-extracted insights from >500 datasets across BioGrid CRISPR database, EMBL expression atlas, and UK Biobank GWAS studies. The multi-agent AI can automate design and analysis of target discovery. We validated 3 novel genes that help cancer cells evade immune attack, using previously unpublished, fresh CRISPR screens across melanoma, leukemia, and colon cancer models. AI predictions → real experiments, closing the loop for discovering novel drug target and insights at scale. This work started by @YuanhaoQ in collaboration with @MengdiWang10 @jure groups, esp @KexinHuang5 now both at @phylo_bio building scientific AI system. With talented members Xuefeng, Xiaotong Wang, Meitong Chen, Xiao Luo, Luna Lyu, Ravi Dinesh, Ming Yin, amazing collaborator including @hcwww_ from Aviv Regev group. Special thanks to our team who drove the wet-lab validation and took this work further into finding cancer immune targets that may one day turn into life-saving drugs. We are recruiting talents to build models and agentic AI with real lab verifier and discovery impacts to life and medicine, come join us!!! Preprint: biorxiv.org/content/10.64898… Blog from Phylo: phylo.bio/blog/autoscreen

Post attachment
Yuanhao Qu avatar
⟳ Le Cong@Stanford, AI+Bio+Gene-Editing retweeted
Yuanhao Qu@YuanhaoQ·Sep 25

Excited to share AutoScreen, the last piece of my thesis work and an AI co-scientist system for target discovery! I started this in 2024 after CRISPR-GPT. Having spent a lot of time working with CRISPR screens, I saw opportunities for agents to speed up the work of deciding which genes to test. We built agents for literature research, data curation and information synthesis to prioritize screen hits and suggest starting gene libraries. We also wanted to look beyond the familiar genes that tend to dominate these searches. Really glad to see the work continue through multiple cancer immunology experiments in my mentor Le Cong’s lab. AutoScreen helped prioritize genes whose activation was then shown to increase cancer cells’ resistance to immune-cell killing. AutoScreen was an early attempt to put agents to work alongside scientists in target discovery. We wanted to make the process faster and improve the quality of target selection, helping researchers pick out real biological hits from noisy experimental data. Thank you to my mentor, Professor @lecong , Professor @MengdiWang10 , and our co-authors Xuefeng Liu, Xiaotong Wang, Meitong Chen, Xiao Luo, Luna Lyu, Ming Yin, and the rest of the team. Special thanks to the teammates who drove the wet-lab validation and took this work further. Blog: phylo.bio/blog/autoscreen Paper: phylo.bio/papers/autoscreen.…

Kexin Huang avatar
⟳ Le Cong@Stanford, AI+Bio+Gene-Editing retweeted
Kexin Huang@KexinHuang5·Sep 25

Excited to share AutoScreen, an agentic system for target prioritization. Starting from a CRISPRa screen, AutoScreen re-prioritized lower-ranked candidates for follow-up. We then validated these candidates in the wet lab, where activating the prioritized genes increased cancer cells’ resistance to primary human NK-cell killing. Great collaboration with @lecong lab at Stanford:

Excited to share AutoScreen, the last piece of my thesis work and an AI co-scientist system for target discovery! I started this in 2024 after CRISPR-GPT. Having spent a lot of time working with CRISPR screens, I saw opportunities for agents to speed up the work of deciding which genes to test. We built agents for literature research, data curation and information synthesis to prioritize screen hits and suggest starting gene libraries. We also wanted to look beyond the familiar genes that tend to dominate these searches. Really glad to see the work continue through multiple cancer immunology experiments in my mentor Le Cong’s lab. AutoScreen helped prioritize genes whose activation was then shown to increase cancer cells’ resistance to immune-cell killing. AutoScreen was an early attempt to put agents to work alongside scientists in target discovery. We wanted to make the process faster and improve the quality of target selection, helping researchers pick out real biological hits from noisy experimental data. Thank you to my mentor, Professor @lecong , Professor @MengdiWang10 , and our co-authors Xuefeng Liu, Xiaotong Wang, Meitong Chen, Xiao Luo, Luna Lyu, Ming Yin, and the rest of the team. Special thanks to the teammates who drove the wet-lab validation and took this work further. Blog: phylo.bio/blog/autoscreen Paper: phylo.bio/papers/autoscreen.…

Ying Liu avatar
⟳ Le Cong@Stanford, AI+Bio+Gene-Editing retweeted
Ying Liu@liuying04·Aug 11

Excited to share a paper I co-authored: Agentic Laboratories of the Future: Towards World Models for Scientific Discovery– joint effort across @Princeton, @Stanford, @Columbia, @nvidia, @MIT, @scale_AI and more. Our argument: the next generation of labs will be agentic, with scientists, AI, and robots as collaborative discovery partners. But the bottleneck isn't better models. It's that no system maintains a shared laboratory world model — a live representation of hypotheses, evidence, uncertainty, and experimental state. Without it, agents produce plans that read well and fail physically. We propose an L0–L5 autonomy ladder for labs, adapted from self-driving vehicles. Most systems today sit at L1–L3, even when marketed as autonomous. And a robust L3 beats a fragile L4 that needs constant rescue. These labs must stay human-led. Agents handle execution and coordination; scientists decide which questions matter. Thanks to project leads @MengdiWang10 (@Princeton) and @lecong (@Stanford) for organizing such a strong community effort to move AI for science forward. Preprint: preprints.org/frontend/manus…

Post attachmentPost attachment
Tianqiao & Chrissy Chen Institute avatar
⟳ Le Cong@Stanford, AI+Bio+Gene-Editing retweeted
Tianqiao & Chrissy Chen Institute@ChenInstitute·Aug 20

🎙️ Speaker Spotlight #19 | AIAS+ 2026 He helped build the first CRISPR/Cas9 gene editing tools for in vivo therapy. Now he's building AI co-scientists. Dr. Le Cong @lecong ( @StanfordMed ) leads a lab merging genome engineering with agentic AI, from RNAGenesis to CRISPR-GPT to LabOS, turning the lab itself into a programmable, AI-native environment. Hear him speak live at AIAS+ 2026, November 5–7 in San Francisco. Registration is now open at aiasplus.org More incredible speakers dropping soon. Don't miss AIAS+ 2026 👇 🎟️ Get your tickets at aiasplus.org 📅 November 5-7, San Francisco #AIAS2026 #AIASPlus #SpeakerSpotlight #CRISPR

Post attachment
Eric and Wendy Schmidt Center avatar
⟳ Le Cong@Stanford, AI+Bio+Gene-Editing retweeted
Eric and Wendy Schmidt Center@Schmidt_Center·Sep 16

✨ From Code to Cure, Building Foundation Models and AI Co-Scientists for Precision Genomic Medicines 💬 @lecong 🏫 Associate Professor, @StanfordMed; Co-founder, Phylo and Acelegen 📅 Thursday, Sept. 17 (tomorrow) ⏰ 4 - 5 p.m. 📍 Yellowstone at @broadinstitute (in-person only)

Post attachment
Le Cong@Stanford, AI+Bio+Gene-Editing avatar
Le Cong@Stanford, AI+Bio+Gene-Editing@lecong·Sep 18

When would we have “live streaming” of life science / scientific lab work? Perhaps live streaming a Brain implant surgery from @neuralink could be the closest thing? It would be fun to live stream a CRISPR experiment some day but parental DNA test in live session may have more viewers. These you can see something happening within days hopefully. @elonmusk @djseo

Glad to see another live training run! Here's how Marin 535B-A23B is doing today: wandb.ai/marin-community/mar… Anyone else want to share?

Post attachment
Le Cong@Stanford, AI+Bio+Gene-Editing avatar
Le Cong@Stanford, AI+Bio+Gene-Editing@lecong·Aug 6

Thrilled to release two new preprints on intelligent labs for driving science and innovation. This is in close coordination with Aviv Regev, Jian Ma (@jmuiuc), Michelle Lee (@michellearning), and the teams at @Genentech, @SCSatCMU, and @Princeton University. In our perspective, we argue that the next generation of labs should be human-in-the-lead and AI-empowered, integrating human intent, machine reasoning, and physical experimentation through scientific world models and an agentic harnessing layer. Done responsibly, these systems have the potential to make scientific discovery more programmable, reproducible, adaptive, and scalable while enabling scientists to focus on higher-level scientific reasoning and discovery. It's been a privilege to pursue this Perspective with @MengdiWang10 and an outstanding group of scientists and innovators advancing the intersection of computation, AI, science, and medicine. We're excited to continue exploring where this vision leads. Our preprint: preprints.org/manuscript/202… Preprint led by Jian and Aviv team: preprints.org/manuscript/202… This also kicks off a new Gladstone-Stanford AI Hub efforts, led by Katie Pollard at @GladstoneInst and myself, with an amazing team of scientists including Emma Lundberg (@Prof_Lundberg), Brian L Trippe (@brianltrippe ), Anshul Kundaje (@anshulkundaje ), Barbara Engelhardt (@BeEngelhardt), Christina Theodoris (@TheodorisLab), Catherine Tcheandjieu (@ines_catherine), Bruce Conklin, Alexander Marson, Stacie Dodgson (@StacieDodgson), Seth Shipman (@seth_shipman), Vijay Ramani, Danielle Swaney (@dlswaney), and Nevan Krogan. Excited to be building together across two great institutions!

Post attachment
Le Cong@Stanford, AI+Bio+Gene-Editing avatar
Le Cong@Stanford, AI+Bio+Gene-Editing@lecong·Jul 19

Heading to SIGGRAPH for the first time! Thanks so much to organizers for inviting me to this cool Graphics4Science workshop next week.

🚀 Excited to kick off the Graphics × Science Workshop at #SIGGRAPH2026! Computer graphics is becoming a foundational tool for scientific discovery. From computational imaging and molecular modeling to physical simulation, robotics, manufacturing, and AI, graphics is helping us model, understand, and design the physical world. Looking forward to an exciting program featuring 3 keynote speakers and 58 highlighted papers. 🔗 graphics4science.github.io/2… #AI4Science #ComputerGraphics #ScientificComputing #Simulation #NVIDIA #NVIDIAOmniverse #NVIDIAAI

Post attachment
Le Cong@Stanford, AI+Bio+Gene-Editing avatar
Le Cong@Stanford, AI+Bio+Gene-Editing@lecong·Jul 10

Big congratulations on the official publication, amazing team work as always. @YuanhaoQ @KexinHuang5 @jure

Biomni is in @ScienceMagazine today. Try it now at biomni.phylo.bio For the past year, we've kept improving Biomni alongside the biologists who use it, building new capabilities together and watching work that once took a team months, or couldn't be done at all, come down to a single person in a single day. We're constantly amazed by how biologists put Biomni to the work. Biologists have never been more powerful. The moment is here to keep pushing the frontier. This is the new way to do biology.

Jim Fan avatar
⟳ Le Cong@Stanford, AI+Bio+Gene-Editing retweeted
Jim Fan@DrJimFan·Jun 16

Today, we enable AutoResearch in the physical world for the first time! Introducing ENPIRE: we give 8 Codex agents a fleet of robots, an allocation of GPUs, and generous token budget. We set them free with a simple goal: solve the task as quickly as possible, keep the robots busy but stay safe, don't waste precious compute. Make no mistake. Then humans step aside and our watch begins. The robot fleet starts to come alive: they learn to look for visual clues, reset the scene, practice novel skills, tinker with control stack, read papers online, debate, reflect, get stuck, and try again directly on the hardware. All we did is to give Codex an API to the world of atoms, and the rest is emergence. ENPIRE is able to solve high-precision tasks like tying zip-ties, organizing fine pins, and installing GPUs all by itself. We also discovered a new type of "physical scaling": 8 robots exploring in parallel improves significantly faster than fewer ones. A part of our NVIDIA GEAR lab now self-improves tirelessly over night. We just read the reports in the morning. /goal: we all take a holiday and Jensen wouldn't even notice ;) We will be open-sourcing everything, so you can host your self-running robot lab at home too! Deep dive in the thread:

1:16