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

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...

biorxiv.org

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

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.

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 🔥💻

Martin Steinegger 🇺🇦@martinsteinegger.bsky.social · 3w ago

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...

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"

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

Janani Durairaj (Jay)@ninjani.bsky.social · 4w ago

Some exciting news: I'm joining the University of Lausanne @unil.bsky.social @dbc-unil.bsky.social as an Assistant Professor next month 🎉 My group will work on context-aware deep learning for protein structure, interaction & design. Postdoc and PhD openings coming soon - keep an eye out!

Finally a more intuitaive way to learn pLDDT/pAE? 😎 sokrypton.github.io/protein_figh... (Character idea from @hannes-stark.bsky.social & Alex Waldherr)

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/

We are thrilled to share that our GPN-Star manuscript is now published and freely available: doi.org/10.1038/s415... (1/n)

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...

doi.org

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.

Martin Steinegger 🇺🇦@martinsteinegger.bsky.social · 3w ago

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...

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)

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.

nature.com

CIRI Lyon@ciri-lyon.bsky.social · 4w ago

Félicitations à Lucie Etienne et son équipe, soutenue par le CNRS IRP RAPIDvBAT, le CNRS IRC Univ. Arizona et le CNRS MITI, pour leurs travaux sur la longévité et l’adaptation induite par les virus à partir des génomes de chauves-souris Myotis. 💡: www.nature.com/articles/s41....

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...

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...

Ten thousand interactions for the molecular biologist - Nature Biotechnology

Nature Biotechnology - Ten thousand interactions for the molecular biologist

nature.com

Martin Steinegger 🇺🇦@martinsteinegger.bsky.social · 4w ago

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

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...

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

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?

ProteinDPO: a protein language model for stability prediction and generation of thermostable protein sequences. @brianhie.bsky.social www.nature.com/articles/s41...

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...

nature.com

mdrepo.org now has its own account (that's me!) Follow the account for updates on content and functionality.

Martin Steinegger 🇺🇦@martinsteinegger.bsky.social · 2mo ago

@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

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]

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...)

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...

biorxiv.org

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!

Martin Steinegger 🇺🇦@martinsteinegger.bsky.social · 2mo ago

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

Riboseek has now a WIP Marv Logo!

Martin Steinegger 🇺🇦@martinsteinegger.bsky.social · 2mo ago

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

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

Now out as a perspective in PLOS Biology. Where next for structural bioinformatics? journals.plos.org/plosbiology/...

Joe Greener@jgreener64.bsky.social · 11mo ago

I wrote a blog post about the future of structural bioinformatics. Where to go after AlphaFold? How do we avoid the field becoming a load of half-baked LLMs? Let me know what you think. jgreener64.github.io/posts/struct...

Impressive demos. www.kimi.com/blog/kimi-k3

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!

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...

cell.com

@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

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

@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

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.