Brewing since 2020, Why and how does this family of enzymes, the GNAT polyamine acetyltransferares, carry out the same function using these dramatically different oligomeric states? authors.elsevier.com/c/1nfiF3SNvc... Read it in Structure, an amazing work by Joel Roca, CATH and SFSU

TEDLH is out! 🎉 A library of 900K+ HMMs for sensitive protein domain searches, built from TED and mapped to CATH (@cathgene3d.bsky.social). Give it a look! #Bioinformatics #ProteinDomains Paper: doi.org/10.1093/bioi... Library: doi.org/10.6084/m9.f...

TEDLH: domain HMMs for sensitive detection of remote homologues

AbstractMotivation. The Encyclopedia of Domains (TED) provides domain annotations for proteins in the AlphaFold Protein Structure Database (AFDB) using a c

doi.org

Had a great time at the #ML4NGP Training school in Sevilla! Back to Italy tomorrow (normally it would be back to London but things change!) P.S. Signed my TT contract with @unipd.bsky.social , starting March 23rd. Exciting!

To advance the family-based modelling approach, we are releasing the entire framework open source: ProFam Atlas: A curated, large-scale training corpus containing nearly 40 million protein families. Code & Weights: github.com/alex-hh/prof... Data: zenodo.org/records/1771...

ProFam: Open-Source Protein Family Language Modelling for Fitness Prediction and Design

Protein language models have become essential tools for engineering novel functional proteins. The emerging paradigm of family-based language models makes use of homologous sequences to steer protein ...

biorxiv.org

For design, ProFam-1 excels at homology-guided generation. It produces diverse sequences with low sequence identity to natural proteins while preserving predicted structural similarity and conservation patterns of the natural family, even when conditioning on just a single example sequence.

Built by CATH, TÜM and NVIDIA, ProFam-1 is our new open-source protein family language model (pfLM) designed to generate functional protein variants and predict fitness using in-context example sequences.

Going full circle! 😊 The University of Padua was home for both my Bachelor’s and Master’s degrees. After 7 amazing years at UCL in the Orengo Group, I’m really happy to share that I’ve won a Tenure-Track Assistant Professorship in Biochemistry at my Alma Mater!

From Sameer Velankar & colleagues in @narjournal.bsky.social #NARDatabaseIssue | #AlphaFold #Protein #Structure #Database 2025: a redesigned interface and updated structural coverage | #Bioinformatics #Proteomics #OpenScience #AFDB 🧪🔓 CC/ @ebi.embl.org ⬇️ academic.oup.com/nar/advance-...

AlphaFold Protein Structure Database 2025: a redesigned interface and updated structural coverage

Abstract. The AlphaFold Protein Structure Database (AFDB; https://alphafold.ebi.ac.uk), developed by EMBL–EBI and Google DeepMind, provides open access to

academic.oup.com

We are looking for a computational postdoc to work with us on new optimisation algorithms to make #RELION even better. Join our bubbly team at the @mrclmb.bsky.social in Cambridge, UK. 🤗 RTs appreciated. mrc.tal.net/vx/appcentre...

It was lovely to speak at the CATH 30 symposium, celebrating 30 years of the @cathgene3d.bsky.social protein structure classification database. I was presenting recent work on our new generative protein-family language model: preprint coming soon.

Packing for our first flight with our kid tomorrow. Wish us luck! We went from 9kg of checked luggage for 2 months in Thailand to 3 checked suitcases and a pram. Send help!

We have a stellar lineup of speakers! Christine Orengo Burkhard Rost Janet Thornton David Jones Gonzalo Parra @gonzaparra.bsky.social Sameer Velankar Alex Bateman Maria Martin Rob Finn Gerardo Tauriello Alexey Murzin

There will be talks from world leaders in structural bioinfomatics on various themes including pioneering protein language models and key international resources including: PDBe, InterPro, UniProt, MGnify, SWISS-MODEL, FrustraEvo and CATH.

CATH turns 30 years old this year! We are organising a 1-day symposium on September 16th at UCL, highlighting recent AI-based developments to enhance protein family classifications, annotations and analyses. www.eventbrite.co.uk/e/protein-an...

Protein Annotations in the age of AI

A not-for-profit symposium hosted at UCL - more details about speakers and venue below.

eventbrite.co.uk

Today I became a British citizen! 🇬🇧

#ISMBECCB2025 is over! Back to London tomorrow after a science feast, a talk, and a selfie with John Jumper. Not too bad!

Today at 2 PM at 3DSIG #ISMBECCB2025, @nbordin.bsky.social presents our joint work on metagenomic-scale clustering and novel domain discovery in predicted structures! 📄 www.biorxiv.org/content/10.1... Also check out poster: B-50 lolalign Sensitive structural alignments by Lasse B-123 BFVD by Rachel

Metagenomic-scale analysis of the predicted protein structure universe

Protein structure prediction breakthroughs, notably AlphaFold2 and ESMfold, have led to an unprecedented influx of computationally derived structures. The AlphaFold Protein Structure Database now prov...

biorxiv.org

Off to Liverpool for #ISMBECCB2025! Looking forward to some awesome science and friends!

"in 2025 we will have flying cars" 😂😂😂

Science Magazine@science.org · last yr.

Exclusive: An international scientific competition widely credited with spurring the development of artificial intelligence for biology appears to be on its deathbed. scim.ag/44ukS90

We've updated our AFESM website to now include biome filtering, allowing exploration of protein structures adapted to specific environments. 🌐 afesm.foldseek.com Read more about the work in the skeetorial 🦋 bsky.app/profile/mart... or our preprint 📄 www.biorxiv.org/content/10.1...

Martin Steinegger 🇺🇦@martinsteinegger.bsky.social · last yr.

AFESM: a metagenomic guide through the protein structure universe! We clustered 821M structures (AFDB&ESMatlas) into 5.12M groups; revealing biome-specific groups, only 1 new fold even after AlphaFold2 re-prediction & many novel domain combos. 🧵 🌐 afesm.foldseek.com 📄 www.biorxiv.org/content/10.1...

Our latest preprint is out on bioRxiv! A collaboration between the groups of @martinsteinegger.bsky.social , David Jones and Christine Orengo, we clustered AlphaFold Database and ESMatlas, a whopping 821 million proteins! We reveal biome-specific groups & over 11k novel domain combinations.

Metagenomic-scale analysis of the predicted protein structure universe

Protein structure prediction breakthroughs, notably AlphaFold2 and ESMfold, have led to an unprecedented influx of computationally derived structures. The AlphaFold Protein Structure Database now prov...

biorxiv.org

I dropped off the radar for a bit, as Aria, our daughter, was born two months earlier than expected! My wife was discharged from the hospital a week later after being stabilised. Aria has spent the last 40 days in the Neonatal Unit at Hillingdon Hospital, with wonderful care from the NHS.

See you in Liverpool at ISMB/ECCB 2025!

First time sitting on the “attack” end of a PhD viva! Really enjoyed the experience!

AlphaFold DB now has TED integrated! This is a special one for me — my first project where I took ownership from start to finish, bringing together different teams to integrate domain annotations into #AlphaFold DB. A huge learning experience, and I’m excited to finally see it live! 🧵(1/6)

EMBL-EBI@ebi.embl.org · 2y ago

🚀 #AlphaFold Database update AlphaFold DB now integrates The Encyclopedia of Domains (TED) – a resource designed to systematically identify & classify structural domains within AlphaFold-predicted protein structures. www.ebi.ac.uk/about/news/u... @pdbeurope.bsky.social

🚀 #AlphaFold Database update AlphaFold DB now integrates The Encyclopedia of Domains (TED) – a resource designed to systematically identify & classify structural domains within AlphaFold-predicted protein structures. www.ebi.ac.uk/about/news/u... @pdbeurope.bsky.social

Excited to share PoET-2, our next breakthrough in protein language modeling. It represents a fundamental shift in how AI learns from evolutionary sequences. 🧵 1/13

Just booked flights and accommodation for the ML4NGP symposium followed by 3DBioinfo in Barcelona in March! Looking forward to see friends and collaborators! Straight to Italy for sitting on a PhD viva panel, busy weeks!

Foldseek 10 with 4-27x (1-8 GPUs) faster search through MMseqs2-GPU. Faster ProstT5 protein search w/o structure prediction through multi-GPU/Apple Metal, new BFVD/BFMD databases and multimer clustering (preview). 💾 github.com/steineggerla... 📄 www.biorxiv.org/content/10.1... 🐍 available in bioconda