I’ve spent the past decade building bio AI models—until now, training them meant years, huge cost, and teams spanning AI, biology, and infra. Not anymore. Introducing a new capability at Biomni Lab: now any scientist can create, fine-tune, pre-train, and optimize bio foundation models on their own datasets, just by describing what they want. This is powered by a new feature called GPU-as-a-tool where we let AI agents launch and orchestrate GPU sandboxes. In the video, we show that you can use prompt to: - Fine-tune Borzoi for MPRA regulatory activity prediction - Fine-tune scGPT on a H1 hESC perturb-seq data - Fine-tune ESM2 for protein subcellular localization prediction - Pre-train a protein language model from scratch on UniRef - Build a novel multi-task ADMET model across 22 endpoints Another big challenge once you’ve trained or have access to a model is actually using it productively. As it is embedded within Biomni Lab, it bridges that gap, letting you “ask the model” to identify and prioritize relevant biological insights directly. Another exciting direction is lab-in-the-loop: scientists can design models, generate predictions, interpret results, and send them to the wet lab—all within one integrated biology environment. This is a preview capability and we’re looking for beta testers. Sign up here for early access: forms.gle/1yhCP6Vrc12DaS4q6 Learn more about opportunities and limitations in our blog: phylo.bio/blog/ai-agents-bui… @phylo_bio

Biomni Lab lets biologists collaborate with AI agents to finish complex tasks end-to-end. Here are 15 popular use cases, each link is a full replay so you can watch the agent work through every step: 1. Spatial transcriptomics analysis: map gene expression across tissue architecture from spatial transcriptomics data, with spatial clustering and neighborhood analysis. biomni.phylo.bio/replay/shar… 2. Binder design: design de novo protein binders against a target structure using computational protein design tools. biomni.phylo.bio/replay/shar… 3. Biomarker panel design: identify and optimize a multi-marker diagnostic or prognostic panel from omics data. biomni.phylo.bio/replay/shar… 4. Clinical trial landscaping: search and summarize the trial landscape for a disease area, mapping phase, endpoints, and sponsor activity. biomni.phylo.bio/replay/shar… 5. Survival analysis: pull clinical and expression data, fit Cox models, generate Kaplan-Meier curves, and identify prognostic markers. biomni.phylo.bio/replay/shar… 6. scRNA-seq processing and annotation: from raw counts to UMAP clustering, marker gene detection, and automated cell type labeling. biomni.phylo.bio/replay/shar… 7. Cell-cell communication: infer ligand-receptor interactions between cell types from single-cell data and map intercellular signaling networks. biomni.phylo.bio/replay/shar… 8. Primer design for novel Cas13: analyze a putative Cas13 protein from a metagenomic screen—verify the ORF, identify HEPN domains, and design cloning primers with restriction sites and a FLAG biomni.phylo.bio/replay/shar… 9. Proteomics differential expression: normalize mass spec data, run statistical tests, and visualize differentially abundant proteins. biomni.phylo.bio/replay/shar… 10. Gene regulatory network inference: reconstruct transcription factor-target gene networks from expression data and identify key regulators. biomni.phylo.bio/replay/shar… 11. Gene co-expression network analysis: build weighted co-expression networks, identify gene modules, and correlate them with phenotypic traits. biomni.phylo.bio/replay/shar… 12. Microbiome analysis: process 16S/metagenomic sequencing data to profile microbial communities, diversity, and differential abundance. biomni.phylo.bio/replay/shar… 13. Polygenic risk scores: compute and evaluate PRS from GWAS summary statistics against a target cohort. biomni.phylo.bio/replay/shar… 14. Variant annotation: annotate genetic variants with functional predictions, allele frequencies, and clinical significance. biomni.phylo.bio/replay/shar… 15. Fine-mapping: narrow GWAS loci to credible causal variants using statistical fine-mapping methods. biomni.phylo.bio/replay/shar… Each of these would normally take days to weeks of scripting, debugging, and iteration. In Biomni Lab, the agent handles the full execution while you steer the science. Learn more: phylo.bio/use-cases

We’re excited to release Phylo’s first research blog on evaluating biology agents. We discussed issues in existing evals and built BiomniBench to address them. Interesting to see that Biomni Lab now matches large pharma scientists on the data analysis benchmark. Read more:

Building better evaluation for biology is hard, but at Phylo (@phylo_bio) we think it's one of the most important problems to solve right now. The community has made real progress building benchmarks for biology agents. But most check only the final answer, which tells you little about where agents struggle or whether the process was sound. Today we're introducing BiomniBench, the first trace-based real-world evaluation for AI agents in biology. Instead of just checking the final output, it also evaluates the analytical process step by step: data handling, method selection, statistical rigor, and biological interpretation. This is how biologists actually evaluate each other's work, and we think it should be how we evaluate agents too. We share preliminary results on BiomniBench-DataAnalysis-v0, where we compare Biomni Lab against other general-purpose and domain-specific agents, as well as two groups of human scientists from the pharmaceutical industry. Biomni Lab leads all agents and performs comparably to senior pharmaceutical scientists. We also evaluated on BixBench, where Biomni Lab leads ahead of all other agents. We learned quite a lot from this exercise, including building a verified subset, which we discuss in detail in the blog post. It's not perfect, but we believe it's a meaningful step toward evaluation that helps us diagnose and improve agent capabilities, and better represent the real progress AI agents are making in empowering biologists' day-to-day work. We will be open-sourcing BiomniBench and looking for biologists, research institutions, pharma companies, and agent developers to contribute. Stay tuned. Blog post: phylo.bio/blog/evaluating-ai…

Early access participantとして使用していたが、ほんとにすごい。例えば「○○タンパク質に結合するバインダーペプチドを設計して」と指示するだけでアミノ酸配列、立体構造（PDBになかったら予測も）、ポケット予測、ペプチド設計（修飾も）を一気に実行する。30分で。 @ProjectBiomni @phylo_bio

Excited to announce our inaugural blog post - with @Ginkgo to analyze complex cell painting analysis - the agents are now capable of tackling more specialized tasks!

Excited to share the next phase of Biomni project! Try out today at biomni.phylo.bio

Today we’re launching Phylo, a research lab studying agentic biology, backed by a $13.5M seed round co-led by @a16z and @MenloVentures / Anthology Fund @AnthropicAI. We’re also introducing a research preview of Biomni Lab, the first Integrated Biology Environment (IBE), where we’re imagining a new way biologists work. Biomni Lab uses agents to orchestrate hundreds of biological databases, software tools, molecular AI models, expert workflows, and even external research services in one workspace, supporting research end-to-end from question to experiment to result. Agents handle the mechanics, while you define the question, then review, steer, and decide. Scientists end up spending more time on science: asking questions, understanding mechanisms, and eliminating diseases. Phylo (@phylo_bio) is a spin-out of @ProjectBiomni, where we will maintain the open-source community and push open-science research. I’m grateful to continue building with my co-founders @YuanhaoQ @jure @lecong and the dream founding team @serena2z @TianweiShe @huangzixin20151 @gm2123 @margaretwhua @malayhgandhi. We’re also fortunate to be advised by leading scientists @zhangf, Carolyn Bertozzi, and @fabian_theis, and supported by an amazing group of investors including @JorgeCondeBio @zakdoric Matt Kraning @ZettaVentures @dreidco @conviction @saranormous @svangel @valkyrie_vc and others. Biomni Lab is available for free today: biomni.phylo.bio/ Learn more in our launch post: phylo.bio/blog/company-fundr… We are also hosting launch events - join us at South San Francisco: luma.com/n8k8qb0n Virtual: luma.com/l5ryjaij We’re also hiring! phylo.bio/careers

Excited to share the launch of @phylo_bio 🚀 — a research lab studying agentic biology, spun out of our open-source AI scientist @ProjectBiomni. As scientific cofounder, I’m proud of what this team has built: Biomni Lab, the first Integrated Biology Environment where agents handle the mechanics and scientists focus on questions, mechanisms, and discovery. Onward 🚀 🔬 Try it free: biomni.phylo.bio/ 📢 We’re hiring: phylo.bio/careers

Biomni is highlighted at "Methods to Watch" from Nature Methods 🙌 nature.com/articles/s41592-0…

So much of biomedical research rests on tacit knowledge—unwritten and invisible to LLMs—causing agents to underperform. The Biomni Open Know-How Catalogue bridges that gap: a curated library of human expertise that Biomni agents use intelligently on the fly, with dramatic gains. Build together: biomni.stanford.edu/blog/bio…

This is one of the most effective ways to make your @ProjectBiomni agent super good! Teach your Biomni agent by adding your know-how. agent can intelligently follow your expertise on all related tasks. See our example about designing CRISPR sgRNAs: biomni.stanford.edu/blog/bio…

Excited to have @ProjectBiomni be part of Laude Slingshots program!

Biomni v0.0.8 is live! 🎉 🌟NEW: Gradio UI - Interactive web interface for Biomni agents, now open source! 🌟 Other features: 🧪ChEMBL, UniChem, QuickGO & DailyMed database integrations 📜Transcripformer & Arc State embeddings 🔎GPT-5 model support 👉Try it here: github.com/snap-stanford/Bio…

Super exciting to be partnering with Nebius on our recent AI agents and benchmark work, building next generation infra in AI4Science, and wonderful to share progress on CRISPR-GPT, drug screening agent, and more next week. Join me with Artem from Nebius and talented student Yuanhao (Jerry), who led many of these work in our group. #ai #CRISPR #Genomics #GPU #Infrastructure

🙌Biomni-R0-32B, the first RL agent model trained end-to-end for biology research, is now open-weight on @huggingface! To benchmark progress, we’re also releasing Biomni-Eval1 — 443 data points across 10 biomedical research tasks! 🔗 Data: huggingface.co/datasets/biom… 🔗 Model: huggingface.co/biomni/Biomni…

🧪Announcing @ProjectBiomni × @pylabrobot — a step toward an AI biologist that can think, design, and execute wet-lab experiments end-to-end. See Biomni in action below 👇 Super fun collab with @RetroBio_ @rickwierenga @serena2z! Learn more: biomni.stanford.edu/blog/pyl…

🚀 Biomni v0.0.7 is live! New features: 📜 PDF export for agent chats 🦠 SOTA cell type transfer algorithms 🔬LazySlide pathology support 🔍Claude web search 🌟Bioimaging pipeline tools 🧬Gene conversion & ESM embeddings 🪴Glycoengineering capabilities Plus improved commercial licensing & data handling! 👉 Try it here: github.com/snap-stanford/Bio…

this guys calenders gotta be crazy