Come and set up your own group to bring your ambitious research vision to fruition in our fantastic Structural Studies division at @mrclmb.ac.uk ! 😍

MRC Laboratory of Molecular Biology@mrclmb.ac.uk · 3w ago

Lead the next discovery at the LMB. We’re recruiting Group Leaders to join our Structural Studies and @cellbiol-mrclmb.bsky.social Divisions. Benefit from long-term support, access to outstanding core-facilities and a collaborative environment where science thrives. ➡️ mrclmb.ac.uk/research-lea...

(Please repost) 💻 💊 I’m hiring a postdoc at the University of Arizona to work with me on a new NIH-funded project on how sex hormones change cell metabolism. The primary focus for the postdoc will be predicting drug side effects (off-target drug effects).

LoL-align: a probabilistic, distance-based protein structure alignment algorithm that shows higher sensitivity for remote homologs and better alignment quality than previous methods. @martinsteinegger.bsky.social www.nature.com/articles/s41...

LoL-align: sensitive and fast probabilistic protein structure alignment - Nature Methods

LoL-align is a probabilistic, distance-based protein structure alignment algorithm that iteratively optimizes a local log-odds score, achieving higher sensitivity for remote homologs and better alignm...

nature.com

Are you a postdoc in Cambridge? Consider applying to be a Research Fellow at Clare Hall! @clarehallcambridge.bsky.social www.clarehall.cam.ac.uk/rf/

LoL-align is out in @natmethods.nature.com! It aligns protein structures without superposition. More sensitive than TM-align and DALI, producing better alignments 5–20× faster. Now available in Foldseek! 📄 www.nature.com/articles/s41... 💾 github.com/steineggerlab/foldseek 🌐 search.foldseek.com

Systematic exploration of predicted quaternary structures within pandemic-relevant viral proteomes www.biorxiv.org/content/10.6...

Systematic exploration of predicted quaternary structures within pandemic-relevant viral proteomes

Mechanistic understanding of viral protein-protein interactions enables global health security and pandemic preparedness, yet experimental characterisation remains difficult, costly, and often restric...

biorxiv.org

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

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 · 3mo 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 · 3mo 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 · 3mo 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 · 3mo 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 · 3mo 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 · 4mo 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 · 4mo 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 · 4mo 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