Interested in learning more about how UniProt uses #MachineLearning to annotate proteins. Read about our collaboration with Google AI - an interview with machine learning engineer Andreea Gane in our latest blog insideuniprot.blogspot.com

Thank you #ResearchBytes for the opportunity to talk about our ongoing work on ProtNLM and to the amazing collaborators including Elena Speretta, Maria Martin, UniProt, Max Bileschi, David Dohan, Amelie H , Laetitia Papaxanthos, Eugene Brevdo, Ankur Parikh, Lucy Colwell

1/10 Looking for a tool to map cells across time and space? We introduce moscot-tools.org, a scalable framework for #optimaltransport (#OT) applications in single-cell genomics! bit.ly/3MiICFc

A special InterPro release is live: 100.0 🥳 ✨Update to Pfam 37.0 ✨Update of Pfam-N 582 new signatures have been integrated from the NCBIfam (26), Pfam (545), PANTHER (3) and CDD (8) databases. Have a look: ebi.ac.uk/interpro/

A new release of Pfam: Pfam 37.0 is available! Head to the InterPro website to access its content

Really excited about our new work (led by Pete Shaw) on ProtEx: A Retrieval Augmented Approach to Protein Function Prediction. Gives SOTA results on several tasks (especially for rare classes and sequences far from training set) to help better characterize the protein universe!

Pfam-N annotations have been updated, using a new deep learning method, have a look at our blog post to learn more: xfam.wordpress.com/2024/05/31/pfa…

Thanks to CellRank 2's interface with moscot Dominik Klein Giovanni Palla Zoe Piran @CuturiMarco , you can apply it to large-scale multi-modal time series data to study fate decisions and their molecular drivers - also in spatio-temporal data! biorxiv.org/content/10.110…

Did you know that you can search for proteins with similar structures using Foldseek ? We have added a link to the Foldseek server on the InterPro protein pages under "External links" and on AlphaFold subpages, have a look: ebi.ac.uk/interpro/prote…

InterPro release 101.0 is out! ✨Update to NCBIfam 15.0 ✨Update of Pfam-N (using Pfam 37.0 data for training) 753 new entries, including 767 signatures from the NCBIfam (318), Pfam (446), PANTHER (2) and CDD (1) databases. Have a look: lnkd.in/eATC6Vyp

The Pfam protein families database: embracing AI/ML Nucleic Acids Res 1. The latest updates to the Pfam database highlight a substantial shift towards AI integration, with Pfam-N using deep learning to increase family coverage by 8.8% in UniProtKB, offering a more expansive

We are pleased to announce the publication of a new Pfam paper: The Pfam protein families database: embracing AI/ML Nucleic Acids Res academic.oup.com/nar/advance-ar…

Good to see moscot finally published in nature! Check out the paper (tinyurl.com/33zuwsep), the research briefing (tinyurl.com/mrvpbkpj), and moscot-tools.org to learn more about it!

Today we introduce an AI co-scientist system, designed to go beyond deep research tools to aid scientists in generating novel hypotheses & research strategies. Learn more, including how to join the Trusted Tester Program, at goo.gle/417wJrA

We are looking a PhD Student Researcher at Google DeepMind for 2025 summer! Strong publication record and technical skills on machine learning and genomics preferred. Need to be 80% for a few months. Team in London. Looking forward to hear from you!