Plate VI · News
New papers, tools and news, as posted by @fabian_theis. Replies and reposts are left out.
🔬 pertpy: a unified, scalable framework for single-cell perturbation analysis, now out in Nature Methods Designed for modern perturbation data - CRISPR, drug screens, patient treatments - scaling to millions of cells and 1000s of conditions. 👉 nature.com/articles/s4159…
Thanks to team for wonderful lab xmas party yesterday! 🎄🎅🏼 Besides Feuerzangenbowle (=mulled wine^2) we had this funny guess-the-paper from Santa's crazy review. Not sure you can guess the paper 📝, but I loved ~summary "Benchmarking the benchmark of benchmarking benchmarks."😅
🎄 We’re hiring in Health AI at @HelmholtzMunich! 🔹 PIs in Health AI/AI Foundations 🔹 Health AI Fellows (independent postdocs) 🔹 Clinical AI Consultants (with TUM, LMU, M1) Apply👇 PIs: jobs.helmholtz-muenchen.de/jobposting/83f… Fellows: jobs.helmholtz-muenchen.de/jobposting/754… Consult: jobs.helmholtz-muenchen.de/jobposting/c7b…
View on X: post of 19 Dec 2025🚀 New preprint! The Human Cytokine Dictionary - 9.7M cells, 12 donors, 90 cytokines - our largest human single-cell perturbation atlas yet. Users can map cytokine activity in their own data. Huge thanks to Lukas, Sören, Larsen, Parse Bio & Seelig lab! 🔗 biorxiv.org/content/10.648…
Nature Methods names AI agents a “Method to Watch”! We've started building active-learning loops with perturbation models, where AI proposes experiments & data closes loop. Supplying such models to agents could transform exp design into theory search. nature.com/articles/s4159…
View on X: post of 12 Dec 2025Excited to share new preprint led by Sergio Salas on “unassigned RNAs” in imaging-based spatial transcriptomics. Across technologies, 30-40% of transcripts fall outside segmentation, & many show structured, biologically meaningful extrasomatic patterns. 📄 biorxiv.org/content/10.648…
🚀 Excited to share our preprint scConcept: a contrastive pretraining framework for technology-agnostic single-cell representations. We move beyond reconstruction to learn rich, cell-level embeddings for diverse omics. 📘 biorxiv.org/content/10.110…
View on X: post of 13 Nov 2025Breaking down walls in #PrecisionHealth at #FallingWalls 2025! Great exchange with Frank Laukien, Caroline Gubser-Keller, Eicke Latz & Steve Quake on how AI & molecular analytics reshape medicine. Our goal: virtual twin cells, tissues & patients. #AIinMedicine #HelmholtzMunich
🚀 Prophet v3 is out! AI that predicts how cells respond to genetic & chemical perturbations across readouts. Now scales to 1.9 M molecules + in vitro validation of melanoma-specific hits 🧬💊 📄 biorxiv.org/content/10.110… #AI #Biology #DeepLearning
EU commissioner Henna Virkkunen officially launching EU‘s RAISE project - its Resource for AI Science in Europe at AIS25 in Copenhagen. includes training programs, data hubs, funding and compute. Exciting & important for Europe and beyond. 🇪🇺
Munich is now the #2 AI ecosystem in Europe (after Paris) and #11 globally, per Dealroom’s Global Tech Ecosystem Index 2025! 🇩🇪🤖🇫🇷 Proud of the growing strength of the Bavarian AI ecosystem 👉 baiosphere.org 🔗 dealroom.co/tech-ecosystem… #AI #Munich #baiosphere
View on X: post of 3 Nov 2025🎃 Happy Halloween from our Lab! 👻🧬 No bad computational tricks — only treats! 🧫💻✨
Looking for a PhD/postdoc position in Cambridge UK in comp bio? Check out Hana Aliee's new lab at CRUK: cruk.cam.ac.uk/research-group…
View on X: post of 30 Oct 2025🧬 Excited to share Nicheformer out now in Nature Methods! A transformer foundation model linking single-cell & spatial omics, learning spatial context from gene expression to map tissue organization. Led by Ale Tejada & Anna Schaar 👏 👉 nature.com/articles/s4159…
At the Staatskanzlei Munich for the State Reception celebrating Bavaria’s Excellence Clusters — great to see so much scientific excellence and innovation recognized and supported across disciplines. 🚀🇩🇪 #Wissenschaft #Innovation #Bayern
Björn Schuller from TUM and Imperial talking about deep learning on mobile sensor data at scale. Wonder how and when we get all these scales together. #BavarianAcademy #MedicalAIConference
Eric Topol giving evening keynote at our Bavarian Conference on AI in medicine, amongst other on AI for prevention and super aging. A true visionary and communicator! see eg erictopol.substack.com/p/dawn-of-a-ne… @eriktopol
Inspiring evening w/ Eric Topol, Matthias Tschöp & Markus Schwaiger. Key message: unite scientists and data across institutions to make AI medicine real — starting with prevention. 🧬🤝 Excited for the Bavarian AI in Medicine Conference tomorrow.
Looking fwd to Bavarian Conference on AI in Medicine (Oct 27–28) in Munich: events.hifis.net/event/2048with Eric Topol, Mihaela van der Schaar, & Islem Rekik. Plus prologue with @erictopol at Helmholtz Munich on monday morning. Let’s discuss where AI can really impact medicine. 💡
View on X: post of 25 Oct 2025🚀 Our new Science paper is out (w/ B DeMeo, D Burkhardt, A Shalek, M Cortes): science.org/doi/10.1126/sc… We show that active learning + transcriptomic perturbations can guide which exps to run next, boosting phenotypic hit rates >13x. AI not just predicting bio, but designing it.🔁
Our lab together with the Lücken lab is in the mountains for our annual hackathon & retreat ⛰️💻 A great mix of science and community: new project ideas, evening coding, creative drawing, and a group hike. Inspiring energy & fresh thinking, truly grateful for this awesome team!
🚀 Excited to share scPortrait! Led by Sophia Mädler & Niklas Schmacke w/ the Mann lab — a new @scverse tool for standardized single-cell image data. Enables ML-ready extraction, >1B cell processing, cross-omics, & cancer macrophage insights. 🔗 biorxiv.org/content/10.110…
Excited to speak today at the EC’s R&I Community event on RAISE – Building the Resource for AI Science in Europe. We’ll discuss how pooling compute, data, talent & funding can supercharge AI-driven discovery across life sciences & health. 👉 stream: …rch-innovation-community.ec.europa.eu
View on X: post of 17 Sept 20252nd day of our DLD Baiosphere conference starting out w aim to ‘put on some fairy dust’ (Yossi Vardi’s words) - w supermotivating Bohemian Rhapsody flashmob vid, watch it will make your day ☺️ youtu.be/jO2R_35HhiY
View on X: post of 11 Sept 2025Excited that our DLD Baiosphere conference on AI is starting now - with major political presence from Bavaria & great talks/panels from science and industry! MP Söder with strong commitment on academic freedom & local strength in AI to attract talents. 🚀dld-conference.com
New paper in @ScienceMagazine with Schoof & Porse labs: We chart early human hematopoiesis using single-cell proteomics, and amongst others developed a dynamic model linking RNA to protein levels, explaining more proteomic variation. 📄 science.org/doi/10.1126/sc…
Back from the SolvAI Retreat 2025 in Nice — amazing discussions on AI in science. Key themes: LMs alone won’t get us to scientific discovery, what makes a theory, and how AI can help us build them. Thanks to Eric Xing & Yann LeCun for organizing!
🚀 NSF just announced a $100M investment in National AI Research Institutes, with medicine & health applications listed first among priority areas, highlighting how biomedical impact continues to lead innovation and real-world benefit! nsf.gov/news/nsf-annou… 👩⚕️🔬 #AI #Health
View on X: post of 31 Jul 2025🚀 Exciting opportunity for scientists in the Bavarian AI ecosystem @bAIosphere! Host your funded retreat or workshop at the beautiful, remote Speinshart Scientific Center for AI & SuperTech🤖. 👉 baiosphere.org/baiosphere-spe… 👉 speinshart.ai #AI #Bavaria #ScienceCommunity
Great to host @ericxing, President & University Professor at MBZUAI, together with Dekyi Liang, Chief of Staff @mbzuai, at our Helmholtz Computational Health Center last Friday 🤖. Inspiring talk on “AI-driven Digital Organism” and engaging discussions with colleagues & PIs 🧬.
