Gunnar Rätsch
@gxr
Followers
3K
Following
1K
Media
40
Statuses
1K
I love large biomedical data. @gxxxr.bsky.social
Zurich, Switzerland
Joined April 2009
All indexes can be downloaded from S3 (see https://t.co/G1Km9Rn9Hh for details). Code available here:
github.com
Scalable annotated de Bruijn graphs for DNA indexing, alignment, and assembly - ratschlab/metagraph
0
0
0
We recently published Metagraph [1] & polished the website to made it usable/stable/efficient for more users. Check out AI summary/tax. id feature [3]. Search in 17PB indexed sequences takes ≈3min on single server. Try! [1] https://t.co/WdYoxCiLip [2] https://t.co/vhERUgnv9j
1
0
1
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 ( https://t.co/WQgDjIYDZL).
nature.com
Nature - MetaGraph enables scalable indexing of large sets of DNA, RNA or protein sequences using annotated de Bruijn graphs.
1
25
63
Early-career scientists: here’s your chance to lead independent research!🌟Max Planck Research Groups offer 6+ years, up to €2.7M in funding, open-topic freedom, team support & tenure-track opportunities. Intrigued? 😃Apply by Oct 14, 2025! https://t.co/cHxPLyRQZ5👉
5
79
183
Thanks for organizing! Such challenges are very important to have in order to distill whats "good sales" and whats good "performance". However, most performance measures have limitations & the real test is to use the method for scientific discovery or translational applications.
Our Autoimmune Disease ML Challenge drew in ~1,000 participants from 62 countries to solve the problem of predicting gene expression from pathology images. We’re thrilled to present the top performers of Crunches 1 and 2 – learn more: https://t.co/ggttJFAD0W
@broadinstitute
0
1
7
📣 SOPHiA GENETICS has joined #NAIPO – Switzerland’s national #AI initiative for precision oncology, selected by @Innosuisse. Together with @EPFL, @ETH & leading hospitals, we’re building a secure infrastructure to make cancer care more effective & equitable for every patient.
0
2
8
I'm looking forward to help shape and participate in this InnoSuisse AI Oncology initiative under the leadership of the EPFL AI Center and ETH AI Center. We aim to bring AI methodology closer to the clinical practice. @ETH_AI_Center @EPFL_AI_Center
linkedin.com
Introducing… NAIPO — the National AI Initiative for Precision Oncology — selected as a Flagship Initiative by Innosuisse. 🔬 🤖 Rolling out over the next four years, the initiative aims to transf...
0
1
5
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.
biorxiv.org
Motivation Cancer-specific neoepitopes may arise from abnormal splicing in the transcriptomic landscape (alternative splicing neoepitopes, ASNs), leading to divergent proteins with high potential...
1
3
17
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 by "transferring" annotations from transcriptomic data.
🔬 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)
0
2
7
🔬 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)
1
11
35
I just read this WSJ article on why Europe's tech scene is so much smaller than the US's and China's. I'm afraid that, like most articles on this topic, it largely misses the mark. Which in itself illustrates a key reason why Europe is lagging behind: when you fail to
696
1K
7K
RL for real-world applications = offline learning + reward learning. How do we make this work? Find out more at ICLR poster #377 at 10am today! @gio_ramponi and I will be presenting our latest work on offline preference-based RL (joint w/ @gxr, @bschoelkopf).
2
7
53
🥳🔥Our study is out in @GenomeBiology! Conventional filtering out high-mtRNA cells depletes key malignant populations in cancer single-cell studies. Read it here 👉 https://t.co/sPeaqDzyAu Thanks to the dream team: @JoYatesResearch @KraftAgnieszka
genomebiology.biomedcentral.com
Background Single-cell transcriptomics has transformed our understanding of cellular diversity, yet noise from technical artifacts and low-quality cells can obscure key biological signals. A common...
5
29
131
Congratulations to @nonchevk from @ETH @CSatETH, the winner of the Autoimmune Disease Machine Learning Challenge #1
The first @Schmidt_Center Crunch has officially wrapped, and Crunchers have made tangible progress for IBD patients through real-world, data-driven impact. Here’s a quick recap of the Eric and Wendy Schmidt Center at Broad Institute’s autoimmune disease challenge 👇
2
4
10
For #CHIL2025, we're gathering top literature from 2024 in AI & healthcare. "Top" can mean an exciting topic, a method you found extremely useful, or a game-changing dataset. Drop your recommendations (and why you chose them) in the coments below! 👇
1
3
8
🎉 Yesterday, @AlizeePace, our very first PhD Fellow of the @ETH_AI_Center, graduated! She was supervised by ETH AI Center Faculty members Prof. Gunnar Rätsch @gxr and Prof. @bschoelkopf. Congrats, Dr. Pace! Next, she will join @GoogleDeepMind in Zurich as a Research Scientist.
6
2
68
Where RNA Science Meets AI, May 4–8, 2025, Ascona. Invited speakers: @OliverStegle @fabian_theis @fiddle @EvaMariaNovoa @BTreutlein @satijalab @RivasElenaRivas @RouskinLab @YosephBarash @gagneurlab, Rhiju Das, Karla Neugebauer, Jernej Ule Registration open,
1
9
36
Where RNA Science Meets AI, May 4–8, 2025, Ascona. Invited speakers: @OliverStegle @fabian_theis @fiddle @EvaMariaNovoa @BTreutlein @satijalab @RivasElenaRivas @RouskinLab @YosephBarash @gagneurlab, Rhiju Das, Karla Neugebauer, Jernej Ule Registration open,
1
9
36
Can't make it to the oral session? Checkout our preprint:
arxiv.org
Notable progress has been made in generalist medical large language models across various healthcare areas. However, large-scale modeling of in-hospital time series data - such as vital signs, lab...
0
1
1