Now online: We developed novel oligomers and turned them into FGFR agonists via binder induced receptor clustering. #denovo_proteins sciencedirect.com/science/articl…

Luisa Bisceglia explains into how understanding the expression patterns of G-protein-coupled receptors (GPCRs) and their influence on drug sensitivity can lead to more precise and effective cancer therapies. #Bioinformatics #CancerTherapy #BITS2024 Luisa Bisceglia

Great resource by Natalia De Oliveira Rosa🌹 , with fundamental contributions by talented Scuola Normale's allievi PierGiorgio Ferronato and Pasquale Miglionico . Check it out at atlantis.bioinfolab.sns.it Feedback welcome!!!

Chakit Arora talks about the role of G-protein-coupled receptor (GPCR) signaling in cancer, utilizing omics analysis to uncover new insights and opportunities for precision medicine in oncology. #Bioinformatics #CancerResearch #PrecisionMedicine #BITS2024

A couple of days left to apply!

ESM3 is out from EvolutionaryScale! 98B params (~GPT3 scale). Multimodal over sequence, structure, and function with cool design applications. Trained on variable masking ratios and decodes proteins iteratively. Some work on alignment too. Looks exciting! evolutionaryscale.ai/blog/esm3-rele…

We have trained ESM3 and we're excited to introduce EvolutionaryScale. ESM3 is a generative language model for programming biology. In experiments, we found ESM3 can simulate 500M years of evolution to generate new fluorescent proteins. Read more: evolutionaryscale.ai/blog/esm3-rele…

Our new BFMD database makes predicted multimer structures searchable with Foldseek-Multimer. It includes the Homomer Atlas @elevyLab, Predictomes Johannes Walter, ProtVar Pedro Beltrao, and ModelArchive @torstenschwede. Thanks for open-sourcing these! 1/3 🌐search.foldseek.com

L’invasione nel campo della medicina e della salute pubblica da parte della politica e del Senatore Claudio Borghi A. e’ inaccettabile. Voler abolire o modificare la legge sui vaccini, per guadagnare il consenso politico del movimento no vax, ci riporta ai momenti più bui del

Looking for a PhD at the frontier of Human-centered Artificial Intelligence? 19 newly added open positions at Italy's National Phd on AI! linkedin.com/pulse/looking-…

FoldMason progressively aligns thousands of protein structures in seconds, enabling remote MSA for distant phylogeny. Highlights: structural flexible MSA, LDDT conservation score, friendly webserver🧵 💾github.com/steineggerlab/… 🌐search.foldseek.com/foldmason 📄biorxiv.org/content/10.110…

Introducing the 😱OMG dataset and 🤖gLM2! OMG is a massive Open MetaGenomic corpus totaling 3.1Tbp of data and 3.3B proteins. We train gLM2, the first mixed-modality genomic language model, on OMG. 1/🧵 #BioML #AI4Science

Science does not advance by regression to the mean (tending to the average). Like evolution there is an outlier that harbors a solution to new challenges. Defend the outlier, despite the pressure of the statistics. That... over time... leads to progress.

Using single-cell and spatial transcriptomics data, FlowSig provides a unified signaling modeling framework by connecting intercellular communication mediated by ligand-receptor interactions and intracellular gene expression modules. nature.com/articles/s4159…

Check out my new work with Frank Noe where we answer if the structure of different protein conformations really can be predicted. nature.com/articles/s4146… Also try the Colab to see if your protein has different conformations: colab.research.google.com/github/patrick…

The Big Fantastic Virus Database (BFVD) contains ColabFold predicted protein structures of all UniRef30 viral proteins. It's the largest DB of viral structures spanning major viral clades.🧵 🌐bfvd.steineggerlab.workers.dev 🌐search.foldseek.com 📄biorxiv.org/cgi/content/sh…

Excited to see PocketVec published in Nature Communications!, with many significant changes wrt the bioRxiv preprint. nature.com/articles/s4146…

Mesoscale Explorer molstar.org/me/ Paper out !! Excellent work with Alexander Rose David S. Goodsell 🏳️‍🌈  and David Sehnal doi.org/10.1002/pro.51…