Biomarker extraction in K Pro, our AI Scientist. One prompt on our MOSAIC bladder cohort: split patients into high vs low survival and find the 3 features that best separate them (metastatic-at-diagnosis patients excluded). 🤖 T4 disease ~4× more common in low-OS. ~3 min. 👉 Watch it run

🎙️ Antoine Yver, physician-scientist and Sanofi board member joins our Head of Product Jonas Béal on the Owkin podcast to discuss where AI is genuinely moving the needle in oncology drug development. Watch the podcast here —> youtu.be/wp_raOdBV7I

We gave a group of builders an open brief and two days with K Pro. What they decided was worth building says something about where they thought AI for biology tools fall short. We wrote it up → www.owkin.com/blog/what-was-built-at-the-rewiring-biology-hackathon

🚀 Day 1 of Rewiring Biology is underway in San Francisco. Teams are getting their hands on K Pro and the building has begun. Good luck to all participants, stay tuned for more. www.owkin.com/connect/rewi...

"AI in biology only works when it understands context, learns iteratively, and is built hand-in-hand with the scientists who use it." From our Zurich dinner: why the next frontier is parallel science and data built with the people who use it. Recap → www.owkin.com/blogs-case-s...

Our latest technical blog "A Practical Map of Evaluation for Agentic Systems" talks about agentic eval for K Pro, our AI Scientist, across tool calls, trajectory, and end-to-end intent: www.owkin.com/blogs-case-s...

Following Anthropic’s announcements at The Briefing: AI for Science 2026 event today, including Claude Science, Anthropic’s AI workbench for scientists, we are excited to share that our agentic platform, K Pro, currently reasons through frontier models, including Claude.

Whole-slide images in oncology: incredible data, painful workflow. Download heavy files, switch to separate viewers, switch back to run your models. K Pro's new interactive viewer lets you explore slides in fullscreen, right inside your analysis session. www.owkin.com/k-os/k-pro

One COX2-driven axis suppresses T cells, NK cells, cDC1s, and the myeloid compartment simultaneously, through a single cAMP-dependent mechanism. New Owkin blog: the mechanistic case for triple EP2/EP4/DP1 blockade with OKN4395. www.owkin.com/blogs-case-s...

⏳ 10 days left to apply for Rewiring Biology. Spots going fast. San Francisco, July 11–12. If you've been thinking about it, now's the time. Apply: luma.com/4s2r63rg

🧬 Rewiring Biology Hackathon by Owkin · Luma

Rewiring Biology Hackathon July 11 - July 12, 2026 | San Francisco, California Join us for a two day hackathon where ML engineers, AI scientists, and…

luma.com

🚀 Applications open for Rewiring Biology — Owkin's SF hackathon, July 11–12. 50 spots for frontier builders working on AI tools for biomedical research. Apply: luma.com/4s2r63rg

We spoke with Yann Flereau, Co-founder & CEO of Blossom Lifesciences, about what turns hypotheses into biological truth. The hardest part isn’t generating ideas — it’s finding the right signal and having the data to validate it. That’s where rigorous validation matters most.

Over the past few weeks we shared notes on building target ID into K Pro and testing it on our bladder cancer program: the honest metric (PR-AUC), the bias trap (ERBB2 for everything), the attrition funnel (314 → 1). Here's the full blog tying it together: www.owkin.com/blogs-case-s...

🔬 New preprint: PRDX5, an atypical peroxiredoxin, is upregulated in epithelioid malignant pleural mesothelioma. Using ML to identify cryptic allosteric pockets + a 3.6M-compound virtual screen: 36 non-covalent inhibitors, 8% hit rate, sub-µM potency. www.biorxiv.org/content/10.6...

📢 Announcing our new deal to build AI agents as part of a multi-year K Pro license agreement with @astra-zeneca.bsky.social Read the full press release here - www.owkin.com/newsfeed/owk...

Peer-reviewed in BMC Med Research Methodology: our benchmark of 9 subgroup analysis methods for time-to-event RCTs finds interaction tests best for detecting heterogeneity, ML-based CATE estimators best for identifying good responders. link.springer.com/article/10.1...

AACR 2026 confirmed AI's central role in cancer research. From foundation models like Apollo to agentic systems, the field is moving from passive tools to active collaborators. Our recap on the three waves of AI in oncology — and where the real bottleneck now lies: www.owkin.com/blogs-case-s...

From foundation models to AI scientists: Inside oncology's AI shift at AACR 2026

owkin.com

🎤 We're at AACR 2026 — stop by booth 4616 to meet the team and try K Pro demos. On Monday April 20, join Dr. Caroline Hoffmann and Jonas Béal for our spotlight: "AI Agent for Pharma R&D: Powering nextgen drug discovery & development". See you there!

90% of ADC trials fail because we've been asking the wrong question. Not "is the target there?" but "WHERE is it, WHAT is it interacting with, and HOW will the TME respond?" Owkin's spatial biology-first approach uses MOSAIC data + K Pro to design next gen ADCs www.owkin.com/blogs-case-s...

Beyond the Magic Bullet: Why the Future of ADCs is Written in Spatial Biology

Discover our blog to see beyond the magic bullet and why the future of ADCs is written in spatial biology.

owkin.com

New preprint: AI agents that learn from experimental feedback for iterative perturbation discovery. Agents receiving results after each round found 166% more gene-phenotype hits than random (29.3 vs 11, p=0.003). 📄 arxiv.org/abs/2603.26177 📄 www.owkin.com/blogs-case-s...

Preprint: CytoSyn, a foundation diffusion model for histopathology. Generates diverse and highly realistic synthetic tissue images using H0-mini’s embeddings as conditioning. Benchmark shows our models reach state-of-the-art FID. Paper: arxiv.org/abs/2603.18089 Model: huggingface.co/Owkin-Biopti...

Preprint on bioRxiv: Multi-modal benchmarking of Ultima UG100 vs Illumina across snRNA-seq, WTS, WES, WGS on FFPE samples. UG100 shows high concordance with Illumina for oncogenic/immune signals, with characteristic indel profile but enhanced precision Preprint: www.biorxiv.org/content/10.6...

Published in Nat Commun: MISO uses local attention transformers to predict spatial gene expression from H&E at near single-cell res. Trained on MOSAIC samples. Outperforms existing methods. In collaboration with FFCD. Paper: www.nature.com/articles/s41... Code: github.com/owkin/miso_c...

We're donating PyDESeq2 to @scverse.bsky.social for long-term maintenance & development. Python reimplementation of DESeq2, ecosystem member since 2023, now in the hands of one of the best open source communities in omics. Good science requires good open source. github.com/scverse/PyDE...

Our new blog explores OwkinZero, a language model fine-tuned on 300,000+ biological Q&A pairs using RLVR. Compact models that outperform larger commercial models on biological inference. Teaching AI to understand mechanisms: www.linkedin.com/posts/owkin_...

Teaching AI to Reason About Biology: Beyond Facts to Mechanisms | OWKIN

How do you teach AI to reason about biology, not just retrieve facts? In 2025, we built the model to do exactly that: 🧠 OwkinZero: a language model fine-tuned specifically for biological reasoning 🔬...

linkedin.com

Spatial omics generates rich multimodal data, but extracting biological insights requires infrastructure at scale. Our new blog covers the 2025 data engine. All building toward BASI. Read more: www.linkedin.com/pulse/buildi...

We introduce IMILIA: interpretable Multiple Instance Learning for IBD inflammation prediction from H&E WSIs. Combines H0-mini, HistoPLUS, and EpiSeg to automatically derive quantitative inflammatory markers. Preprint on arXiv: arxiv.org/abs/2512.13440

Published in Scientific Reports: SarcNet uses federated AI to forecast metastatic relapse in STS, achieving 0.797 AUC. Dive deeper: www.nature.com/articles/s41...

We’re releasing CytoSyn, our new diffusion model for synthetic histopathology image generation. REPA-E architecture. H0-mini conditioning. Model: huggingface.co/Owkin-Biopti... Supporting article: www.owkin.com/blogs-case-s...

Discover OKN4395 at #SITC2025—Poster #1169. A triple inhibitor overcoming tumor immunosuppression by targeting EP2, EP4, DP1. Learn more about OKN4395 at epkin.ai