Computational biologist @biozentrum.bsky.social. Likes protein structures.
https://ninjani.github.io/
Janani Durairaj (Jay)
Loading...
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
🌐 https://search.foldseek.com/folddisco
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...
@lorenzopantolini.bsky.social and I are headed to @iclr-conf.bsky.social at Rio soon, with talks about this work at @gembioworkshop.bsky.social and LMRL workshops. Reach out to chat about representation learning for de novo protein design! 🫖
Stoic 🦾 from our shared student @daniil-litvinov.bsky.social predicts protein complex stoichiometry. A fun collab with @ninjani.bsky.social @torstenschwede.bsky.social - this #AI adventure beyond our core #CryoET methods was made possible by the @biozentrum.unibas.ch PhD Fellowship Program! 🧪 🧶🧬
It's finally out!
Search with TEA 🍵 Against Many!
→ On the web: pickybinders.org/tea/steam
→ Locally: github.com/PickyBinders...
Feedback welcome!
Equivariance is dead! 😢
Or is it? 😈
Genie 3 is out! Our latest protein design model achieves SoTA results for binder design and motif scaffolding, greatly improving on BindCraft and Proteina-Complexa.
It does so using all-atom SE(3)-equivariance based on a branched polymer representation👇
There is a lot of debate and some hyperbole around the impact of AI-assisted scientific research. When considering the future impact of gene...
Starting from an #AlphaFold-Multimer prediction, we used #ROCKET to build a model of ZPD, a homopolymeric zona pellucida (#ZP) protein, into an initial #cryo-EM map at only ~9 Å resolution. A subsequently obtained 4.6 Å map highlighted how superior the ROCKET model was over the initial prediction:
Martin Steinegger 🇺🇦
Very happy to have had a chance to attack an initially very low-resolution #cryo-EM map with #ROCKET! Thank you again @alisiafadini.bsky.social and all other co-authors of this important work, which truly shows the power of combining experimental structural biology and #AI inference.
rdcu.be/fa9YH
Folddisco enables protein structural motif search in million scale databases.
www.nature.com
ROCKET 🚀 inference-time optimization of AlphaFold to fit structural data is published! rdcu.be/fa9YH
Since our preprint, we’ve pushed it to regimes where other methods break: low resolution, weak signal, real experimental edge cases. Here’s what we learned: 1/15
Janani Durairaj (Jay)
Pedro Beltrao
Janani Durairaj (Jay)
Folddisco finds similar (dis)continuous 3D motifs in large protein structure databases. Its efficient index enables fast uncharacterized active site annotation, protein conformational state analysis and PPI interface comparison. 1/9🧶🧬
📄 www.biorxiv.org/content/10.1...
🌐 search.foldseek.com/folddisco
Ben Engel
Nature Methods - ROCKET improves experimental structure elucidation by integrating implicit structural knowledge from OpenFold, a trainable reimplementation of AlphaFold2, with X-ray...
ROCKET 🚀 inference-time optimization of AlphaFold to fit structural data is published! rdcu.be/fa9YH
Since our preprint, we’ve pushed it to regimes where other methods break: low resolution, weak signal, real experimental edge cases. Here’s what we learned: 1/15
Luca Jovine
A fun little idea that worked surprisingly well, using a structure-informed yet structure-independent alphabet for de novo protein design: www.biorxiv.org/content/10.6...
🧵(1/n)
Martin Steinegger 🇺🇦
Now published in NSMB!
Paper: doi.org/10.1038/s415...
Full PDF: rdcu.be/fhBtI
Overview of additions since the preprint👇 (1/5)
Nature Methods - ROCKET improves experimental structure elucidation by integrating implicit structural knowledge from OpenFold, a trainable reimplementation of AlphaFold2, with X-ray...
Introducing Genie 3, a generative protein model that substantially advances the state-of-the-art for binder design, increasing in silico success rates by up to 20x on hard multimeric targets. It also debuts a form of inference-time scaling unobserved in other design models. 🧵1/8
Fresh from bioRxiv our latest work introducing The Embedded Alphabet (TEA), a powerful new representation for protein sequences obtained by discretising ESM2 embeddings into 20 characters.
Pre-print: www.biorxiv.org/content/10.1...
🧵👇(1/n)
Alisia Fadini
Janani Durairaj (Jay)
Meet Stoic from @daniil-litvinov.bsky.social and @ninjani.bsky.social: embeddings to predict stoichiometry of protein complexes from sequence fast and accurately 🧬🧩💻🤩
www.biorxiv.org/content/10.6...
Video
This work introduces the Runs N’ Poses dataset for benchmarking deep learning methods on the protein–ligand complex prediction task. It shows that current methods rely on memorization, challenging the...
Detecting remote homology with speed and sensitivity is crucial for tasks like function annotation and structure prediction. We introduce a novel approach using contrastive learning to convert protein...
Excited to share our latest preprint evaluating AlphaFold3, Boltz-1, Chai-1 and Protenix for predicting protein-ligand interactions, featuring our newly introduced benchmark dataset 🌹Runs N’ Poses🌹!
www.biorxiv.org/content/10.1...
🧵👇 (1/n)
Deep learning has driven major breakthroughs in protein structure prediction, however the next critical advance is accurately predicting how proteins interact with other molecules, especially small mo...
