James Zou
@jameszou.bsky.social
@Stanford Professor. AI for science and medicine.
It’s here! #Agents4Science recording is now on YouTube!
🏆 3 Best Paper talks
⚡️ 11 Spotlights
🧠 Panel on the future of AI agent-driven science
📚 Lessons + surprises from this first-of-its kind conf
Full analysis of submissions + reviews coming soon! youtube.com/watch?v=7pXq...
🏆 3 Best Paper talks
⚡️ 11 Spotlights
🧠 Panel on the future of AI agent-driven science
📚 Lessons + surprises from this first-of-its kind conf
Full analysis of submissions + reviews coming soon! youtube.com/watch?v=7pXq...
October 23, 2025 at 3:13 PM
It’s here! #Agents4Science recording is now on YouTube!
🏆 3 Best Paper talks
⚡️ 11 Spotlights
🧠 Panel on the future of AI agent-driven science
📚 Lessons + surprises from this first-of-its kind conf
Full analysis of submissions + reviews coming soon! youtube.com/watch?v=7pXq...
🏆 3 Best Paper talks
⚡️ 11 Spotlights
🧠 Panel on the future of AI agent-driven science
📚 Lessons + surprises from this first-of-its kind conf
Full analysis of submissions + reviews coming soon! youtube.com/watch?v=7pXq...
🧠Can AI agents predict #Alzheimers? Participate in our DREAM challenge agentic track to find out!
We provide unique training + test data for AI agents: snRNA-seq, IHC, stage, etc synapse.org/Synapse:syn6...
Also co-submit your agent paper to agents4science.stanford.edu
We provide unique training + test data for AI agents: snRNA-seq, IHC, stage, etc synapse.org/Synapse:syn6...
Also co-submit your agent paper to agents4science.stanford.edu
August 12, 2025 at 10:59 PM
🧠Can AI agents predict #Alzheimers? Participate in our DREAM challenge agentic track to find out!
We provide unique training + test data for AI agents: snRNA-seq, IHC, stage, etc synapse.org/Synapse:syn6...
Also co-submit your agent paper to agents4science.stanford.edu
We provide unique training + test data for AI agents: snRNA-seq, IHC, stage, etc synapse.org/Synapse:syn6...
Also co-submit your agent paper to agents4science.stanford.edu
⚡️Thrilled that #VirtualLab is published in @nature.com! www.nature.com/articles/s41...
We created a team of AI agents to mirror my Stanford lab 🤖. Led by a PI agent, the AI scientists ran their own group meetings and discovered effective binders to new CoVID variants that we validated.
We created a team of AI agents to mirror my Stanford lab 🤖. Led by a PI agent, the AI scientists ran their own group meetings and discovered effective binders to new CoVID variants that we validated.
July 29, 2025 at 4:05 PM
⚡️Thrilled that #VirtualLab is published in @nature.com! www.nature.com/articles/s41...
We created a team of AI agents to mirror my Stanford lab 🤖. Led by a PI agent, the AI scientists ran their own group meetings and discovered effective binders to new CoVID variants that we validated.
We created a team of AI agents to mirror my Stanford lab 🤖. Led by a PI agent, the AI scientists ran their own group meetings and discovered effective binders to new CoVID variants that we validated.
🏆Thrilled that #CollabLLM won the #ICML2025 Outstanding Paper Award!
We propose a new approach to optimize human-AI collaboration, which is critical for agents. Congratulations to my fantastic co-authors; great job Shirley Wu and Michel Galley driving the project! 👏
Paper: arxiv.org/pdf/2502.00640
We propose a new approach to optimize human-AI collaboration, which is critical for agents. Congratulations to my fantastic co-authors; great job Shirley Wu and Michel Galley driving the project! 👏
Paper: arxiv.org/pdf/2502.00640
July 15, 2025 at 5:55 PM
🏆Thrilled that #CollabLLM won the #ICML2025 Outstanding Paper Award!
We propose a new approach to optimize human-AI collaboration, which is critical for agents. Congratulations to my fantastic co-authors; great job Shirley Wu and Michel Galley driving the project! 👏
Paper: arxiv.org/pdf/2502.00640
We propose a new approach to optimize human-AI collaboration, which is critical for agents. Congratulations to my fantastic co-authors; great job Shirley Wu and Michel Galley driving the project! 👏
Paper: arxiv.org/pdf/2502.00640
High throughput data are goldmines that we often only scratch the surface. Great for AI to systematically analyze! CellVoyager makes Jupyter notebooks for easy replication
📜https://www.biorxiv.org/content/10.1101/2025.06.03.657517v1
💻https://github.com/zou-group/CellVoyager
📜https://www.biorxiv.org/content/10.1101/2025.06.03.657517v1
💻https://github.com/zou-group/CellVoyager
June 5, 2025 at 2:25 PM
High throughput data are goldmines that we often only scratch the surface. Great for AI to systematically analyze! CellVoyager makes Jupyter notebooks for easy replication
📜https://www.biorxiv.org/content/10.1101/2025.06.03.657517v1
💻https://github.com/zou-group/CellVoyager
📜https://www.biorxiv.org/content/10.1101/2025.06.03.657517v1
💻https://github.com/zou-group/CellVoyager
💡IMO one of the best use of AI Scientist is to reanalyze data to find new insights.
Introducing #CellVoyager: AI Compbio Agent that makes new discoveries by autonomously analyzing papers/data, which we then validate🚀
New findings on aging, Covid, scRNAseq etc. Open source!
Introducing #CellVoyager: AI Compbio Agent that makes new discoveries by autonomously analyzing papers/data, which we then validate🚀
New findings on aging, Covid, scRNAseq etc. Open source!
June 5, 2025 at 2:25 PM
💡IMO one of the best use of AI Scientist is to reanalyze data to find new insights.
Introducing #CellVoyager: AI Compbio Agent that makes new discoveries by autonomously analyzing papers/data, which we then validate🚀
New findings on aging, Covid, scRNAseq etc. Open source!
Introducing #CellVoyager: AI Compbio Agent that makes new discoveries by autonomously analyzing papers/data, which we then validate🚀
New findings on aging, Covid, scRNAseq etc. Open source!
Excited that nuclei.io is featured on the cover of Nature BME! AI-clinician collaboration paper rdcu.be/dLgV1
April 22, 2025 at 4:35 PM
Excited that nuclei.io is featured on the cover of Nature BME! AI-clinician collaboration paper rdcu.be/dLgV1
⚡️Really thrilled that #textgrad is published in @nature.com today!⚡️
We present a general method for genAI to self-improve via our new *calculus of text*.
We show how this optimizes agents🤖, molecules🧬, code🖥️, treatments💊, non-differentiable systems🤯 + more!
We present a general method for genAI to self-improve via our new *calculus of text*.
We show how this optimizes agents🤖, molecules🧬, code🖥️, treatments💊, non-differentiable systems🤯 + more!
March 19, 2025 at 4:47 PM
⚡️Really thrilled that #textgrad is published in @nature.com today!⚡️
We present a general method for genAI to self-improve via our new *calculus of text*.
We show how this optimizes agents🤖, molecules🧬, code🖥️, treatments💊, non-differentiable systems🤯 + more!
We present a general method for genAI to self-improve via our new *calculus of text*.
We show how this optimizes agents🤖, molecules🧬, code🖥️, treatments💊, non-differentiable systems🤯 + more!
📢Thrilled to introduce #MedArena medarena.ai 🏥, a platform for clinicians to try frontier #LLMs for free (o3, Gemini, Perplexity + more).
Compare and rank medical chatbots and help shape the future of medical AI! 🏆 Current leaderboard👇
Please share #MedSky
Compare and rank medical chatbots and help shape the future of medical AI! 🏆 Current leaderboard👇
Please share #MedSky
February 25, 2025 at 4:22 PM
📢Thrilled to introduce #MedArena medarena.ai 🏥, a platform for clinicians to try frontier #LLMs for free (o3, Gemini, Perplexity + more).
Compare and rank medical chatbots and help shape the future of medical AI! 🏆 Current leaderboard👇
Please share #MedSky
Compare and rank medical chatbots and help shape the future of medical AI! 🏆 Current leaderboard👇
Please share #MedSky
Incredibly grateful and honored to receive the 2025 Overton Prize ♥️
Surreal to follow the steps of my science heroes🙏 Truly, credit goes to my amazing students, collaborators and mentors who make research so inspiring!
Also underscores the value of open academic environment that make this possible
Surreal to follow the steps of my science heroes🙏 Truly, credit goes to my amazing students, collaborators and mentors who make research so inspiring!
Also underscores the value of open academic environment that make this possible
February 20, 2025 at 4:39 PM
Incredibly grateful and honored to receive the 2025 Overton Prize ♥️
Surreal to follow the steps of my science heroes🙏 Truly, credit goes to my amazing students, collaborators and mentors who make research so inspiring!
Also underscores the value of open academic environment that make this possible
Surreal to follow the steps of my science heroes🙏 Truly, credit goes to my amazing students, collaborators and mentors who make research so inspiring!
Also underscores the value of open academic environment that make this possible
The shift from AI as tools to AI as agents has tremendous implications for medicine and healthcare.
@erictopol.bsky.social and I share our perspective on new possibilities and how to prepare for this shift in @thelancet.bsky.social
thelancet.com/journals/lan...
@erictopol.bsky.social and I share our perspective on new possibilities and how to prepare for this shift in @thelancet.bsky.social
thelancet.com/journals/lan...
February 7, 2025 at 5:30 PM
The shift from AI as tools to AI as agents has tremendous implications for medicine and healthcare.
@erictopol.bsky.social and I share our perspective on new possibilities and how to prepare for this shift in @thelancet.bsky.social
thelancet.com/journals/lan...
@erictopol.bsky.social and I share our perspective on new possibilities and how to prepare for this shift in @thelancet.bsky.social
thelancet.com/journals/lan...
Our new paper in Circulation shows how #ADMET-AI predicts cardiotoxicity of drugs and generates interpretable insights www.ahajournals.org/doi/abs/10.1...
January 29, 2025 at 5:57 PM
Our new paper in Circulation shows how #ADMET-AI predicts cardiotoxicity of drugs and generates interpretable insights www.ahajournals.org/doi/abs/10.1...
Excited to share our new study of #genomics🧬, #EHR📈 + treatment outcomes of 78K patients across 20 #cancers!
We identified >700 mutations predicting which drugs💊 are effective for individual patients. Our #ML model predicts who responds well to immunotherapies. #precisioncancer
We identified >700 mutations predicting which drugs💊 are effective for individual patients. Our #ML model predicts who responds well to immunotherapies. #precisioncancer
January 8, 2025 at 3:45 PM
Excited to share our new study of #genomics🧬, #EHR📈 + treatment outcomes of 78K patients across 20 #cancers!
We identified >700 mutations predicting which drugs💊 are effective for individual patients. Our #ML model predicts who responds well to immunotherapies. #precisioncancer
We identified >700 mutations predicting which drugs💊 are effective for individual patients. Our #ML model predicts who responds well to immunotherapies. #precisioncancer
Interestingly, we find that neural stem cells rejuvenate their neighbors and T cells accelerate aging of nearby cells. See paper for insights into mechanisms.
We also quantify the effects of exercise, reprogramming + diseases on brain aging. All our code and data are public!
We also quantify the effects of exercise, reprogramming + diseases on brain aging. All our code and data are public!
December 18, 2024 at 10:19 PM
Interestingly, we find that neural stem cells rejuvenate their neighbors and T cells accelerate aging of nearby cells. See paper for insights into mechanisms.
We also quantify the effects of exercise, reprogramming + diseases on brain aging. All our code and data are public!
We also quantify the effects of exercise, reprogramming + diseases on brain aging. All our code and data are public!
We measured spatial transcriptomics of >4M cells across mouse brains over 20 ages 🐭
We used this to train clocks that quantify the biological age of each cell. Our graph neural network models the effects of cell-cell interaction on cellular age. 2/3
We used this to train clocks that quantify the biological age of each cell. Our graph neural network models the effects of cell-cell interaction on cellular age. 2/3
December 18, 2024 at 10:19 PM
We measured spatial transcriptomics of >4M cells across mouse brains over 20 ages 🐭
We used this to train clocks that quantify the biological age of each cell. Our graph neural network models the effects of cell-cell interaction on cellular age. 2/3
We used this to train clocks that quantify the biological age of each cell. Our graph neural network models the effects of cell-cell interaction on cellular age. 2/3
🎆4 years in the making! Thrilled to share the 1st spatial single cell aging clock ⏰ www.nature.com/articles/s41...
We use #AI + spatial transcriptomics to discover what makes some cells age faster/slower in the brain 🧠
Led by Eric Sun and awesome collaboration w/ @brunetlab.bsky.social🧵
We use #AI + spatial transcriptomics to discover what makes some cells age faster/slower in the brain 🧠
Led by Eric Sun and awesome collaboration w/ @brunetlab.bsky.social🧵
December 18, 2024 at 10:19 PM
🎆4 years in the making! Thrilled to share the 1st spatial single cell aging clock ⏰ www.nature.com/articles/s41...
We use #AI + spatial transcriptomics to discover what makes some cells age faster/slower in the brain 🧠
Led by Eric Sun and awesome collaboration w/ @brunetlab.bsky.social🧵
We use #AI + spatial transcriptomics to discover what makes some cells age faster/slower in the brain 🧠
Led by Eric Sun and awesome collaboration w/ @brunetlab.bsky.social🧵
Excited to share several works w/ fantastic students + collaborators at #NeurIPS2024 this week! ✈️
Look forward to meeting old and new friends in Vancouver; let me know if you'd like to chat!
Look forward to meeting old and new friends in Vancouver; let me know if you'd like to chat!
December 10, 2024 at 10:36 PM
Excited to share several works w/ fantastic students + collaborators at #NeurIPS2024 this week! ✈️
Look forward to meeting old and new friends in Vancouver; let me know if you'd like to chat!
Look forward to meeting old and new friends in Vancouver; let me know if you'd like to chat!
📢 Excited that #unitox is selected as a #NeurIPS2024 spotlight!💡
We created #LLM agent to analyze >100K pages of FDA docs from all approved drugs ➡️ new database annotating 8 toxicity types for 2400 drugs. Validated by clinicians. openreview.net/pdf?id=Vb1vV...
We created #LLM agent to analyze >100K pages of FDA docs from all approved drugs ➡️ new database annotating 8 toxicity types for 2400 drugs. Validated by clinicians. openreview.net/pdf?id=Vb1vV...
December 9, 2024 at 4:56 PM
📢 Excited that #unitox is selected as a #NeurIPS2024 spotlight!💡
We created #LLM agent to analyze >100K pages of FDA docs from all approved drugs ➡️ new database annotating 8 toxicity types for 2400 drugs. Validated by clinicians. openreview.net/pdf?id=Vb1vV...
We created #LLM agent to analyze >100K pages of FDA docs from all approved drugs ➡️ new database annotating 8 toxicity types for 2400 drugs. Validated by clinicians. openreview.net/pdf?id=Vb1vV...
🎉Thrilled that #GenePT is published!
We show how to create #ChatGPT embeddings of genes and #singlecell --> improve gene function prediction + cell annotation/analyses🧬
📰 www.nature.com/articles/s41...
🌐 github.com/yiqunchen/Ge...
Great job Yiqun Chen! #LLM for bio.
We show how to create #ChatGPT embeddings of genes and #singlecell --> improve gene function prediction + cell annotation/analyses🧬
📰 www.nature.com/articles/s41...
🌐 github.com/yiqunchen/Ge...
Great job Yiqun Chen! #LLM for bio.
December 6, 2024 at 3:08 PM
🎉Thrilled that #GenePT is published!
We show how to create #ChatGPT embeddings of genes and #singlecell --> improve gene function prediction + cell annotation/analyses🧬
📰 www.nature.com/articles/s41...
🌐 github.com/yiqunchen/Ge...
Great job Yiqun Chen! #LLM for bio.
We show how to create #ChatGPT embeddings of genes and #singlecell --> improve gene function prediction + cell annotation/analyses🧬
📰 www.nature.com/articles/s41...
🌐 github.com/yiqunchen/Ge...
Great job Yiqun Chen! #LLM for bio.
If you use SHAP, LIME or Data Shapley, you might be interested in our new #neurips2024 paper. We introduce stochastic amortization to speed up feature + data attribution by 10x-100x 🚀 #XML
Surprisingly we can "learn to attribute" cheaply from noisy explanations! arxiv.org/abs/2401.15866
Surprisingly we can "learn to attribute" cheaply from noisy explanations! arxiv.org/abs/2401.15866
December 2, 2024 at 5:35 PM
If you use SHAP, LIME or Data Shapley, you might be interested in our new #neurips2024 paper. We introduce stochastic amortization to speed up feature + data attribution by 10x-100x 🚀 #XML
Surprisingly we can "learn to attribute" cheaply from noisy explanations! arxiv.org/abs/2401.15866
Surprisingly we can "learn to attribute" cheaply from noisy explanations! arxiv.org/abs/2401.15866