Gunnar Rätsch

All indexes can be downloaded from S3 (see metagraph.ethz.ch/indexes for details). Code available on github: github.com/ratschlab/me...

We recently published Metagraph [1] & polished the website to made it usable/stable/efficient for more users. Check out AI summary/tax. id feature [2]. Search in 17PB indexed sequences takes ≈3min on single server. Try!

[1] www.nature.com/articles/s41...
[2] metagraph.ethz.ch/results?sear...

Efficient and accurate search in petabase-scale sequence repositories - Nature MetaGraph enables scalable indexing of large sets of DNA, RNA or protein sequences using annotated de Bruijn graphs.

The Metagraph paper is out in Nature; it showed up in my feeds today! Congratulations to Mikhail Karasikov, @gxxxr.bsky.social, @akkah21.bsky.social and all of the other authors (whom I'd love to follow on Bluesky if I can find you ;P) www.nature.com/articles/s41...

Efficient and accurate search in petabase-scale sequence repositories - Nature MetaGraph enables scalable indexing of large sets of DNA, RNA or protein sequences using annotated de Bruijn graphs.

After years of research and continuous refinement, we’re thrilled to share that our paper on the MetaGraph framework — enabling Petabase-scale search across sequencing data — has been published today in Nature (www.nature.com/articles/s41...)

Splicing neoepitope prediction is sensitive to methodological differences Motivation: Cancer-specific neoepitopes may arise from abnormal splicing in the transcriptomic landscape (alternative splicing neoepitopes, ASNs), leading to divergent proteins with high potential imm...

This manuscript on the reproducibility of splicing neoepitope prediction took us a while. We find that subtle choices in how one exactly generates and filters neoepitope candidates, creates major differences in the number and identity of the neoepitopes.
www.biorxiv.org/content/10.1...

🔬 Toward histopathology 2.0: spatial transcriptomes inferred from routine diagnostic H&E images + a chat interface for cell-resolution histopathology through English language. (1/6)

Just presented our new multimodal histopathology method "SpotWhisperer" at ICML, one of the largest AI conference.

SpotWhisperer enables spatially resolved annotation of histopathology images using natural language. We achieved this by "transferring" annotations from transcriptomic data. More soon!

Congrats, great work!

Can you please send a link that works? This one appears broken.

🎉 Yesterday, @alizeepace.bsky.social, our first PhD Fellow of the @eth-ai-center.bsky.social, graduated! She was supervised by ETH AI Center Faculty members Prof. Rätsch @gxxxr.bsky.social and Prof. Schölkopf. Congrats, Dr. Pace! Next, she will join Google DeepMind in Zurich as a Research Scientist.

Preference Elicitation for Offline Reinforcement Learning Applying reinforcement learning (RL) to real-world problems is often made challenging by the inability to interact with the environment and the difficulty of designing reward functions. Offline RL...

This is joint work with Bernhard Schölkopf, @gxxxr.bsky.social, and @gioramponi.bsky.social, which we will also be presenting at ICLR 2025 🎉
Link: arxiv.org/abs/2406.18450

Invited speakers: @evamarianovoa.bsky.social .social
@fabiantheis.bsky.social @rivaselenarivas.bsky.social
Sterling Churchman, Barbara Treutlein, Rahul Satijia, Rhiju Das, Silvi Rouskin, Karla Neugebauer, Yoseph Barash, Jernej Ule, Julien Gagneur, and Oliver Stegle.

I'm excited about a meeting on RNA + AI together with @quaidmorris.bsky.social and @hagentilgner.bsky.social in Ascona, Ticino on May 4-8. We have a great line-up of speakers and room for you to present your work. Please join us if you are into RNA & AI. Registration open www.rna-ai.org.

Great to see ELLIS and EMBL getting closer and working together!

Also invited speakers: Rhiju Das, Silvi Rouskin, Karla Neugebauer, Yoseph Barash, Jernej Ule, Julien Gagneur, Oliver Stegle

Where RNA Science Meets AI, May 4–8, 2025, Ascona. Invited speakers: @evamarianovoa.bsky.social @fabiantheis.bsky.social @rivaselenarivas.bsky.social, Sterling Churchman, Barbara Treutlein, Rahul Satijia,
Registration open www.rna-ai.org
@hagentilgner.bsky.social @quaidmorris.bsky.social

Very honored to have been elected an @ellis.eu Scholar in the program for Robust Machine Learning: ellis.eu/programs/rob...

What better way to celebrate it than to speak at the ELLIS UnConference in Bad Teinach?

My group is hiring postdoc(s) and I will be at #NeurIPS2024 if you want to talk - send me a DM or find me on Whova!

UK-based, 2 year position. We work on AI/ML for health, specifically building and *understanding/explaining* deep (multimodal) models on healthcare data, especially medical imaging.

Nerd humor 🤓 #statisticshumor #cardiosky #medsky

Generative AI’s environmental costs are soaring — and mostly secret First-of-its-kind US bill would address the environmental costs of the technology, but there’s a long way to go.

Generative AI’s environmental costs are soaring — and mostly secret