Sign in

Martin Steinegger 🇺🇦

@martinsteinegger.bsky.social
4.5K followers 546 following 298 posts

Developing data intensive computational methods • PI @ Seoul National University 🇰🇷 • #FirstGen • he/him • Hauptschüler

PostsRepliesMedia
Martin Steinegger 🇺🇦 @martinsteinegger.bsky.social · 24/09/2026
AlphaFold Database is expanding into pandemic preparedness. Together with NVIDIA, DeepMind, EBI et al. we exhaustively predicted ~1.7 million homo- & heterodimers across 2,812 viral proteomes, resulting in 8,028 high-confidence predictions. 📄 research.nvidia.com/labs/dbr/ass... 🌐 alphafold.ebi.ac.uk
28838
Reposted by Martin Steinegger 🇺🇦
Kieran Didi @kdidi.bsky.social · 18/09/2026
Our wet-lab validation campaign for Proteina-Complexa is now on bioRxiv! It includes some new exciting experimental results, from large protein structures (fully codesigned!) to functional carbohydrate binders. biorxiv.org/content/10.6... Thread with some of the additions 🧵1/n
biorxiv.org
Latent generative search unlocks de novo design of untapped biomolecular interactions at scale
De novo protein design has advanced rapidly, yet designing binders to polar, solvent-exposed epitopes and small, flexible ligands remains challenging. Such hydrated surfaces and flexible molecules, in...
1145
Martin Steinegger 🇺🇦 @martinsteinegger.bsky.social · 19/09/2026
BFVD v3 contains 5.8M viral protein structures, 16× more than v2; 75% high quality, filling a major gap in AFDB coverage. It fully covers 72.6% of reference proteomes and spans 72.7% of ICTV species. Great work by @eunbelivable.bsky.social et al. 📄 www.biorxiv.org/content/10.6... 🌐 bfvd.foldseek.com
18431
Reposted by Martin Steinegger 🇺🇦
Sergey Ovchinnikov @sokrypton.org · 18/09/2026
I do sometimes wonder how much of these improvements are actually coming from us? During my own optimizations with claude in the last year or so, eachtime claude asked if i was willing to share my session transcript, I always said yes.
1193
Reposted by Martin Steinegger 🇺🇦
Sergey Ovchinnikov @sokrypton.org · 17/09/2026
Introducing highly experimental localfold.org Building on @martinsteinegger.bsky.social af2 webgpu port, @milot.bsky.social optimizations & jax ports of af3-like models by @marielle.bsky.social, Choonghwan Lee, Julia Buhmann. WARNING: runs directly on your 💻, may drain 🪫 & eat data📱 & overheat 🔥💻
26826
Reposted by Martin Steinegger 🇺🇦
Milot Mirdita @milot.bsky.social · 16/09/2026
ColabFold 1.6.3 is out! 2.5x faster, pip-installable, ipSAE+pDockQ2 scores. Thanks Choonghwan Lee, Marielle Russo, Gyuri Kim 🐍pip install colabfold[alphafold] CF2 Sneak Peak with AF3/Boltz/Protenix/ESMFold2… 🐍pip install "colabfold[alphafold3]@git+https://github.com/sokrypton/ColabFold@af3-preview"
29736
Reposted by Martin Steinegger 🇺🇦
Janani Durairaj (Jay) @ninjani.bsky.social · 16/09/2026
The PhD and Postdoc application links are now live! Come join me at UNIL to work on deep learning for protein structure, interactions & design. pickybinders.org#open-positions
career5.successfactors.eu
Career Opportunities: PhD student position in deep learning for enzyme structure & catalysis (22980)
03928
Reposted by Martin Steinegger 🇺🇦
Sergey Ovchinnikov @sokrypton.org · 14/09/2026
Finally a more intuitaive way to learn pLDDT/pAE? 😎 sokrypton.github.io/protein_figh... (Character idea from @hannes-stark.bsky.social & Alex Waldherr)
727698
Martin Steinegger 🇺🇦 @martinsteinegger.bsky.social · 13/09/2026
Fold Spacer lets you fly through protein structures (Weekend project #2). It’s my first game: I originally set out to build a racer with structures as the tracks, but was a little too crazy. So it became this instead. You can upload your own structures. 🌐 martin-steinegger.github.io/Fold-Spacer/
215759
Reposted by Martin Steinegger 🇺🇦
Yun S. Song @yun-s-song.bsky.social · 09/09/2026
We are thrilled to share that our GPN-Star manuscript is now published and freely available: doi.org/10.1038/s415... (1/n)
doi.org
Predicting genome-wide functional constraints with GPN-Star - Nature
GPN-Star, a genomic language model with a phylogeny-aware architecture for whole-genome alignment data, is shown to be a scalable and flexible tool for genetic variant effect prediction across species...
112247
Martin Steinegger 🇺🇦 @martinsteinegger.bsky.social · 02/09/2026
AlphaFold2-WebGPU now supports AlphaFold-Multimer. As in ColabFold, simply use : to separate chains in the sequence input. It is also becoming much more stable: I was able to predict a 491-aa protein in ~4 minutes in M4 Pro. Chrome currently performs better than Firefox for WebGPU, unfortunately.
0296
Reposted by Martin Steinegger 🇺🇦
Lucie Etienne @lucievirevolte.bsky.social · 31/08/2026
Insights into longevity & virus-driven adaptation from Myotis bat genomes International & fantastic collab. with @psudmant.bsky.social @denard.bsky.social Labs ! Major credit to the 2 leading scientists: Juan Vazquez & @lauterbur.bsky.social now with their own labs! You 2 rock! (1/n)
nature.com
Insights into longevity and virus-driven adaptation from Myotis bat genomes - Nature
Comparative and functional analyses of Myotis bats uncover unique patterns of adaptation in virus-interacting proteins and longevity-associated pathways, linking two hallmarks of bat biology.
22812
Martin Steinegger 🇺🇦 @martinsteinegger.bsky.social · 30/08/2026
Run AlphaFold2 locally in your browser via WebGPU, no installation needed, it's just a static webpage using your own GPU or CPU. Short proteins run in seconds. Larger ones are still slow: a 291-aa protein takes ~7 minutes on my M4 Pro. ❗It's just a PoC. 🌐 martin-steinegger.github.io/alphafold2-w...
117841
Reposted by Martin Steinegger 🇺🇦
Pedro Beltrao @pedrobeltrao.bsky.social · 26/08/2026
So many cool results from @katjaluck.bsky.social and @martinsteinegger.bsky.social s lab defining a dictionary of protein interface types. 22 years ago @robrussell.bsky.social and @ptck72.bsky.social guessed there would be 10k types but they were off by a bit :) www.nature.com/articles/nbt...
nature.com
Ten thousand interactions for the molecular biologist - Nature Biotechnology
Nature Biotechnology - Ten thousand interactions for the molecular biologist
1296
Reposted by Martin Steinegger 🇺🇦
Katja Luck @katjaluck.bsky.social · 26/08/2026
In an amazing collaboration with the Steinegger lab we developed Foldseek-Interface and clustered the resolved protein interface universe revealing structural bias, pathogen mimicry and novel interface structures in predicted protein complexes. doi.org/10.64898/202...
doi.org
0255
Martin Steinegger 🇺🇦 @martinsteinegger.bsky.social · 26/08/2026
Foldseek-Interface enables fast search/clustering of the protein interface universe! We clustered 3.1M PDB dimers into 77,167 groups and found new interfaces keep appearing even as fold discovery plateaus. 🧵 📄 www.biorxiv.org/content/10.6... 🔎 search.foldseek.com/interface 🌐 interface.foldseek.com
110941
Martin Steinegger 🇺🇦 @martinsteinegger.bsky.social · 26/08/2026
Is @biorxivpreprint.bsky.social broken? We uploaded a preprint, but for some reason the DOI doi.org/10.64898/202... doesn’t work. Has anyone else run into a similar issue?
doi.org
210
Reposted by Martin Steinegger 🇺🇦
Nature Methods @natmethods.nature.com · 24/08/2026
ProteinDPO: a protein language model for stability prediction and generation of thermostable protein sequences. @brianhie.bsky.social www.nature.com/articles/s41...
nature.com
Aligning protein-generative models to experimental fitness with ProteinDPO - Nature Methods
This Article demonstrates that direct preference optimization (DPO) can be used to effectively align an unsupervised structure-conditioned language model with biophysical information. The aligned mode...
1103
Reposted by Martin Steinegger 🇺🇦
MDRepo @mdrepo.bsky.social · 17/08/2026
mdrepo.org now has its own account (that's me!) Follow the account for updates on content and functionality.
0115
Reposted by Martin Steinegger 🇺🇦
Adam Phillippy @aphillippy.bsky.social · 06/08/2026
For the past 30 years, “whole-genome sequencing” has been a misnomer. Today the T2T Consortium publishes a dozen papers heralding a future of truly complete genomes for humans and nearly any vertebrate 👨‍🔬🐒🐦🐀🦒🐎🫏🐹🐟 (sorry, no salamanders): www.cell.com/consortium/t... 🧵[1/15]
3202106
Martin Steinegger 🇺🇦 @martinsteinegger.bsky.social · 07/08/2026
The ratio between abstracts accessed and PDFs downloaded @biorxivpreprint.bsky.social was around 2:1, since the abstract page led to the PDF. Now it’s close to 1:2. Does this mean we shift to an LLM based paper exploration? For Riboseek the ratio is even 1:10 (www.biorxiv.org/content/10.6...)
biorxiv.org
Fast remote nucleotide sequence alignment with Riboseek
Structure prediction has reached RNA, where generating deep alignments is now the bottleneck. We developed Riboseek, a search and alignment tool for RNA and DNA that represents sequences as overlappin...
2122
Reposted by Martin Steinegger 🇺🇦
Manny Ares 👀 @mannyares.bsky.social · 02/08/2026
Awesome new tool from the Steinegger lab 🚨 A real time saver if you want to find phylogenetic variants of an RNA of interest! Check it out!
0113
Martin Steinegger 🇺🇦 @martinsteinegger.bsky.social · 03/08/2026
Riboseek has now a WIP Marv Logo!
0335
Martin Steinegger 🇺🇦 @martinsteinegger.bsky.social · 01/08/2026
Riboseek is a fast RNA/DNA search. More sensitive than nhmmer at 250x speed. Structure-aware realignment produces MSAs approaching rMSA quality. Plus 1.7M precomputed RNA MSAs, and an API to search your own 📄 www.biorxiv.org/content/10.6... 💾 github.com/steineggerla... 🌐 search.foldseek.com/riboseek
217975
Reposted by Martin Steinegger 🇺🇦
Joe Greener @jgreener64.bsky.social · 28/07/2026
Now out as a perspective in PLOS Biology. Where next for structural bioinformatics? journals.plos.org/plosbiology/...
journals.plos.org
Where next for structural bioinformatics?
Structural bioinformatics aims to answer biological questions by considering biomolecular structures at scale. This Perspective argues that now that we have accurate predictions, we need to ask what w...
0258
Reposted by Martin Steinegger 🇺🇦
Stephen Turner @stephenturner.us · 27/07/2026
Impressive demos. www.kimi.com/blog/kimi-k3
kimi.com
Kimi K3 Tech Blog: Open Frontier Intelligence
Kimi K3 is the world's first open 3T-class model — frontier performance across coding, knowledge work, and reasoning, with native multimodality and 1M context.
151
Reposted by Martin Steinegger 🇺🇦
Yo Akiyama @yoakiyama.bsky.social · 21/07/2026
Excited to share our now published paper @cp-cell.bsky.social highlighting advances in modeling the evolution of protein-protein interactions with MSA Pairformer. Big thanks to Zhidian Zhang, Olivia Tang, @eunbelivable.bsky.social @milot.bsky.social @martinsteinegger.bsky.social and @sokrypton.org!
cell.com
Expanding the scope of protein language modeling to protein-protein interactions with MSA Pairformer
Protein language models have excelled at modeling individual proteins, but extending these capabilities to protein complexes remains a major challenge. MSA Pairformer, a parameter-efficient protein la...
26027
Martin Steinegger 🇺🇦 @martinsteinegger.bsky.social · 16/07/2026
@wheelerlab.org is talking about his effort to build a resource for protein dynamics (PDB for MD). MDRepo is a repository to store simulation data. This is really needed to push the needle in design, function and more. Please help make it successful by sharing your MD data. #ismb2026 🌐 mdrepo.org
02110
Martin Steinegger 🇺🇦 @martinsteinegger.bsky.social · 16/07/2026
My student @yewonhan.bsky.social will talk today at 3DSIG about our work on expanding the AlphaFold database to complexes (31M predictions). It starts at 14.20 in the International Ballroom East. Please join. We also brought Marv stickers with us. #ISMB2026
0201
Martin Steinegger 🇺🇦 @martinsteinegger.bsky.social · 16/07/2026
@rolanddunbrack.bsky.social is talking about kinases and interface scoring (ipSAE). AF’s ipTM score avg. PAE over the full area not just the interface, so disorder and extra domains drag it down. ipSAE uses a PAE cutoff to avoid low scores, therefor only consider good interface contacts. #ismb2026
0114
Martin Steinegger 🇺🇦 @martinsteinegger.bsky.social · 13/07/2026
Christopher E. Mason’s keynote at the HitSeq at #ISMB2026 felt like watching an episode of „Sendung ohne Namen“ (does anybody know it?). A crazy amount of ideas, facts, and sci-fi. From environmental metagenomics to space genomics.
010
Martin Steinegger 🇺🇦 @martinsteinegger.bsky.social · 13/07/2026
@yewonhan.bsky.social build a website to explore the #ISMB2026 program. Check it out here: yewon-han-bioinfo.github.io/ISMB2026-tal...
yewon-han-bioinfo.github.io
ISMB 2026 · Talks Explorer
161
Martin Steinegger 🇺🇦 @martinsteinegger.bsky.social · 13/07/2026
Richard Durbin starts the #ISMB2026 with his keynote about BWT for genomic search. A walk-through from BWA to his most recent work on pan-genomes GBWT. www.biorxiv.org/content/10.6.... Congratulations on the accomplishments by a Senior Scientist Award.
0281
Martin Steinegger 🇺🇦 @martinsteinegger.bsky.social · 12/07/2026
I’m at #ISMB2026 in Washington, DC. Please let me know if you’d like to catch up over coffee.
070
Martin Steinegger 🇺🇦 @martinsteinegger.bsky.social · 22/06/2026
It seems @anthropic.com or OpenAI are unusable for biological work now. I was considering buying a Teams account, but I am worried it will be useless in the end. Has anybody experience with other LLMs?
5120
Martin Steinegger 🇺🇦 @martinsteinegger.bsky.social · 19/06/2026
ICML is happening in Seoul this year, and I’ve been getting several messages about lab visits. Who else will be in town and would like to meet? @milot.bsky.social lab and mine are planning a dinner on July 7th, after the reception. Let me know if you’re interested!
0269
Reposted by Martin Steinegger 🇺🇦
Igor Martayan @imartayan.bsky.social · 15/06/2026
Just submitted my PhD thesis on algorithms for fast, large-scale k-mer-based sequence analysis. It's now available to read at phd.martayan.org Take a look and feel free to share! #Bioinformatics #PhDone
phd.martayan.org
Algorithm design and implementation for the scale of sequencing data
26822
Martin Steinegger 🇺🇦 @martinsteinegger.bsky.social · 10/06/2026
Korea reduces the immigration barriers for foreign researcher www.koreatimes.co.kr/southkorea/2... Happy to see this happening.
koreatimes.co.kr
Korea expands ‘top-tier' visa to woo global scientists - The Korea Times
Korea is expanding its elite "top-tier" visa program to encompass foreign professors and researchers as part of an aggressive push to secure global...
1309
Reposted by Martin Steinegger 🇺🇦
Pedro Beltrao @pedrobeltrao.bsky.social · 08/06/2026
Why AI-assisted research might have a lower impact that some estimate? I tried to look back at the rise of the internet and its impact on scientific research as a comparison point. I should stop spending time on this but condensing this info also helps me think www.evocellnet.com/2026/06/look...
evocellnet.com
Looking back at the rise of the internet to gauge the impact of AI-assisted scientific research
There is a lot of debate and some hyperbole around the impact of AI-assisted scientific research. When considering the future impact of gene...
1179
Reposted by Martin Steinegger 🇺🇦
Janani Durairaj (Jay) @ninjani.bsky.social · 08/06/2026
Search with TEA 🍵 Against Many! → On the web: pickybinders.org/tea/steam → Locally: github.com/PickyBinders... Feedback welcome!
pickybinders.org
STEAM - Search with TEA against Many
Generated by create next app
0174
Reposted by Martin Steinegger 🇺🇦
Sasha Gusev @sashagusevposts.bsky.social · 07/06/2026
I wrote about AI in academia. "PhD-level thinking", LLM bias, grunt work, alignment, AGI, data center water use, AI politics -- something for everyone.
open.substack.com
Thoughts on AI in academia
PhD-level thinking, LLM bias, alignment, AGI, data centers, and AI politics
59336
Reposted by Martin Steinegger 🇺🇦
hbkgenomics.bsky.social @hbkgenomics.bsky.social · 06/06/2026
Does your designed active site already exist in nature? Is an uncharacterized protein hiding a catalytic site or a pocket? Folddisco answers both, searching millions of structures for a 3D motif in seconds. @natbiotech.nature.com 🧬 📄 www.nature.com/articles/s41... 🧵1/7👇
nature.com
Structural motif search across the protein universe with Folddisco - Nature Biotechnology
Folddisco enables protein structural motif search in million scale databases.
14715
Martin Steinegger 🇺🇦 @martinsteinegger.bsky.social · 06/06/2026
Folddisco is now published @natbiotech.nature.com. It’s a fast motif search for similar 3D DISCOntinuous residues like catalytic sites or zinc fingers across the entire protein universe. 📄 www.nature.com/articles/s41... 💾 folddisco.foldseek.com​​​​​​​​​​​​​​​​ 🌐 search.foldseek.com/folddisco
nature.com
Structural motif search across the protein universe with Folddisco - Nature Biotechnology
Folddisco enables protein structural motif search in million scale databases.
213455
Reposted by Martin Steinegger 🇺🇦
Elisa Fadda @elisafadda.bsky.social · 05/06/2026
Very cool! 😎⤵️ Folddisco 🪩 a motif search algorithm that supports querying both short motif queries (Fig. 1d) and long, discontinuous segments (Fig. 1e) in seconds against 53 million structures 🥳🥳 www.nature.com/articles/s41...
nature.com
Structural motif search across the protein universe with Folddisco - Nature Biotechnology
Folddisco enables protein structural motif search in million scale databases.
1123
Reposted by Martin Steinegger 🇺🇦
Nature Biotechnology @natbiotech.nature.com · 05/06/2026
Structural motif search across the protein universe with Folddisco - @martinsteinegger.bsky.social go.nature.com/4g8lCb0
go.nature.com
Structural motif search across the protein universe with Folddisco - Nature Biotechnology
Folddisco enables protein structural motif search in million scale databases.
13922
Martin Steinegger 🇺🇦 @martinsteinegger.bsky.social · 28/05/2026
hetro-di-mers are released now.
0206
Reposted by Martin Steinegger 🇺🇦
Kenneth Loi @kenjmloi.bsky.social · 27/04/2026
Excited to share our discovery of a new programmable RNA-guided DNA-targeting system hiding inside bacteriophages that predates CRISPR. We call it VIPR (Viral Interference Programmable Repeat), and it uses an entirely new logic to find its targets. Thread + link below.
7448197
Reposted by Martin Steinegger 🇺🇦
Minji Lee @m1nj2.bsky.social · 21/04/2026
We introduce ConforNets, a mechanism for conformational control in AlphaFold3 models - SoTA at producing diverse conformations on every multistate benchmark (N=104) - Novel capability: transfer state from one protein to another Outperforms BioEmu, ConforMix and AFsample3 🧵1/8
1419
Reposted by Martin Steinegger 🇺🇦
Torsten Schwede @torstenschwede.bsky.social · 21/04/2026
The CASP experiment is about to start - and is still short on challenging prediction targets. Ligand complexes, RNA, …
12016
Reposted by Martin Steinegger 🇺🇦
Sebastian Deorowicz @sdeorowicz.bsky.social · 14/04/2026
10 years after the first FAMSA paper, its successor is now published in Nat Biotech! We believe that FAMSA2 can enable analyses of large protein collections that were previously unattainable. Thank you, Andrzej and Cedric, for great collaboration www.nature.com/articles/s41...
nature.com
Fast and accurate multiple-protein-sequence alignment at scale with FAMSA2 - Nature Biotechnology
FAMSA2 accurately aligns millions of protein sequences at high speed.
35923