Protein-based agonists generated from our de novo protein minibinder pipeline bind to human #TLR3 with nanomolar affinities. This collaborative project was led by recently graduated Dr. Chloe Adams and is out now on bioRxiv: biorxiv.org/content/10.110…

Why does cancer incidence increase with age? Is it the accumulation of mutations? Is it declining immune system? Is it other factors? This PNAS article emphasizes the role of immune system decline over mutation accumulation. 1/2

YAbS: The Antibody Society’s Antibody Therapeutics Database 1/ YAbS provides an extensive and dynamic resource tracking over 2,900 antibody therapeutics, including approved, investigational, and in-development antibody candidates, offering a valuable tool for researchers,

.Vertex Pharmaceuticals's opioid-free drug for acute pain wins FDA approval nature.com/articles/s4158…

Sam Altman Don’t trust the votes, people don’t know what they’re talking about. Local models are interesting but only so useful. Go for the best open source model possible.

Everyone vote for o3-mini type model to be open-sourced please 🥺🥺🥺 We can distill or quantize a phone sized model dw the open-source community will work its magic!!

Excited to share our joint work with Richard Shuai, Full-Atom MPNN (FAMPNN), a protein sequence design method that explicitly models both sequence and side-chain structure! 🧵 1/N

AI provides a universal framework that leverages data and compute at scale to uncover higher-order patterns Today, Arc Institute in collaboration with NVIDIA releases Evo 2—a fully open source biological foundation model trained on genomes spanning the entire tree of life 🧵

Today, the NVIDIA healthcare and life sciences team launched Evo 2 -- a powerful foundation model for DNA across all domains of life, developed in collaboration with Arc Institute and Stanford University. Announced today as the largest publicly available AI model for genomic data, Evo 2

Researchers have developed a deep learning protein language model, ESM3, that enables programmable protein design. Learn more in this week's issue of Science: scim.ag/4b5IlQu

At Science Magazine today, an important new way we can make major headway into immunologic and infectious diseases. Sequencing the lymphocyte B and T cell receptors and A.I. to accurately make the diagnosis! A seminal study Maxim Zaslavsky Scott_Boyd_Lab_Stanford Anshul Kundaje (anshulkundaje@bluesky) and colleagues

Structural biology is in an era of dynamics & assemblies but turning raw experimental data into atomic models at scale remains challenging. Minhuan Li and I present ROCKET🚀: an AlphaFold augmentation that integrates crystallographic and cryoEM/ET data with room for more! 1/14.

Historic day for builders in bio: We’ve open-sourced Vevo Therapeutics’s #Tahoe100M, largest single-cell atlas ever—by a wide margin—as the inaugural contribution to Arc Institute’s Virtual Cell Atlas, ready for download today. A leap forward for AI models of cells & drug discovery. 🧵

Patent protection for therapeutic monoclonal antibodies requires a fundamental shift in strategy following Amgen v. Sanofi, which invalidated broad functional claims for antibody genera in the USA go.nature.com/4gYpZ5i rdcu.be/ebaZZ

Proteins power life, but their complexity makes them hard to understand or design. We’re introducing ProtBFN, a 650M parameter Bayesian Flow Networks capable of generating natural, diverse and novel protein sequences. Here's Tom Barrett (Tom Barrett), Staff Scientist at

We introduce 🌿 MINT (Multimer Interaction Transformer) – a Protein Language Model (PLM) trained on 96M protein-protein interactions (PPIs) to predict binding affinity, mutational impacts, & antibody interactions better than existing PLMs. 🔗Code: github.com/VarunUllanat/m… 🧵👇

🚀 Introducing TxAgent: a first of its kind AI agent for therapeutic reasoning across a universe of 211 tools, with a comparison against DeepSeek-R1 671B NVIDIA AI TxAgent is an AI agent that redefines how AI can reason, retrieve, and integrate biomedical knowledge for precision

ABCFold: Easier Running and Comparison of AlphaFold 3, Boltz-1, and Chai-1 - Structural biology has seen a revolution with deep learning-based protein structure predictors like AlphaFold 3, Boltz-1, and Chai-1. However, running and comparing these models efficiently remains a

Published in Nature (2023), Kruse et al. (Tüting lab) demonstrate that adoptively transferred CD4+ T cells alone—but not CD8+ T cells—can eradicate melanoma tumors completely lacking both MHC class I and II expression. These findings challenge the current paradigm of cancer

Happy Sunday to all! This morning, we are excited to share Chase’s work developing a simple, scalable method to assemble 100s-1000s of custom genes from oligo pools using standard lab tools! (Small 🧵 below)