Kexin Huang

EvE Bio's pharmome-mapping online data has just been adopted by yet another biomedical reasoning model; in this case @KexinHuang5's Biomni at Stanford U. The snowballing adoption of our data is very exciting.

🤝Excited to partner with Tamarind @kavi_deniz to build towards an agentic AI protein designer. 🔁 Agentic protein optimization — Starting from a sequence, Biomni iteratively improves thermostability by orchestrating AlphaFold-2, ThermoMPNN, and reasoning over predictions and…

👋 Biomni v0.0.4 is now released! In one week of open-sourcing, we have seen amazing contributions from the community: - Multimodal LLM ChatNT @instadeepai as a tool to let Biomni talk with raw DNA/RNA/protein sequence - Added biomedical knowledge graph PrimeKG with millions of…

🧪Designing a CRISPR screen take days—finding gene targets, controls, and creating experimental protocols. Biomni curates target genes in minutes using advanced web search, literature mining, and pathway analysis. ⚡️ ✨Try it at biomni.stanford.edu

Happy to share that our work on POPPER — an AI agent for autonomous scientific hypothesis validation — has been accepted to #ICML2025! I’ll be presenting during the poster session this Thursday at 4:30pm — come say hi if you’re around! ⬇️

🚀 Excited to open-source our general-purpose biomedical AI agent Biomni. Biomni A1 (agent) + E1 (env) with 150 specialized tools, 59 databases, and 105 software! With just a few lines of code, you can now automate complex biomedical research with AI agent! E1 only scratches…

🧬 Excited to open-source Biomni! With just a few lines of code, you can now automate biomedical research with AI agent! We are releasing Biomni A1 (agent) + E1 (env) with 150 specialized tools, 59 databases, and 105 software. E1 is our first attempt at curating the bio-agent…

💊 90% of drugs fail trials—often from poor ADME/tox. AI models can accurately predict ADMET, but they aren’t widely accessible to scientists. Paste a SMILES into Biomni agent → get 17 endpoints via GNNs, RDKit & literature in minutes. 👉 biomni.stanford.edu

This is super cool! Looks like a tremendous resource for biologists who'd want to leverage the power of AI to accelerate their workflows.

🤝Excited to announce @ProjectBiomni × @AnthropicAI! AI agents are set to transform how biologists do everyday research. Thanks to this partnership, the platform is now free for scientists worldwide: biomni.stanford.edu Learn more: anthropic.com/customers/biom…

🧬Uncovering how a genetic variant leads to disease can take hours of deep reasoning—digging through RegulomeDB, ENCODE, ClinVar, PubMed, and more. Biomni automates these steps and delivers a structured report in minutes. Try it at biomni.stanford.edu

One-month update of Biomni⬇️ Excited to see how Biomni has automated 15K+ research tasks for biologists!

Are AI scientists already better than human researchers? We recruited 43 PhD students to spend 3 months executing research ideas proposed by an LLM agent vs human experts. Main finding: LLM ideas result in worse projects than human ideas.

How close are we to widespread adoption of industrialized AI agents in biotech & drug discovery? Progress has accelerated in the last 6 mo: - @ProjectBiomni, general purpose scientific AI agent automating literature reviews, hypothesis generation, protocol design,…

Cells are dynamic, messy and context dependent. Scaling models across diverse states needs flexibility to capture heterogeneity Introducing State, a transformer that predicts perturbation effects by training over sets of cells Team effort led by the unstoppable @abhinadduri

🧬 scRNA-seq annotation is fundamental, but it can take weeks! ⬇️ Biomni is an AI agent that gets it done in minutes by writing scanpy/umap code, searching literature/databases, and applying biological reasoning. Try it free on your scRNA dataset at biomni.stanford.edu ⚡

Save the date! Machine Learning for Drug Discovery (MLDD) is happening soon on Monday 30 June, 2025. MLDD aims to bring together ML for drug discovery experts, innovators, and enthusiasts from the machine learning, biotechnology and drug discovery domains in London, UK to…

@sara_mostafavi (@genentech ) & I (@Stanford) r excited to announce co-advised postdoc positions for candidates with deep expertise in ML for bio (especially sequence to function models, causal perturbational models & single cell models). See details below. Pls RT 1/

Even the smartest LLMs can fail at basic multiturn communication Ask for grocery help → without asking where you live 🤦‍♀️ Ask to write articles → assumes your preferences 🤷🏻‍♀️ ⭐️CollabLLM (top 1%; oral @icmlconf) transforms LLMs from passive responders into active collaborators.…