Could one envision a synthetic receptor technology that is fully programmable, able to detect diverse extracellular antigens – both soluble and cell-attached – and convert that recognition into a wide range of intracellular responses, from transgene expression and real-time

Introducing ESM Cambrian. Unsupervised learning can invert biology at scale to reveal the hidden structure of the natural world. We’ve scaled up compute and data to train a new generation of protein language models. ESM C defines a new state of the art for protein

Super excited to preprint our work on developing a Biomolecular Emulator (BioEmu): Scalable emulation of protein equilibrium ensembles with generative deep learning from Microsoft Research AI for Science. #ML #AI #NeuralNetworks #Biology #AI4Science biorxiv.org/content/10.110…

🚨NEW PUBLICATION ALERT🚨: In a paper out today in Science Magazine we describe a way to build synthetic phosphorylation circuits with customizable sense-and-response functions in human cells. Check it out at science.org/doi/10.1126/sc…. 🧵1/n

Can we learn protein biology from a language model? In new work led by Liam Bai and me, we explore how sparse autoencoders can help us understand biology—going from mechanistic interpretability to mechanistic biology.

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 🧵

The BioEmu-1 model and inference code are now public under MIT license!!! Please go ahead, play with it and let us know if there are issues. github.com/microsoft/bioe…

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.

Protein function often depends on protein dynamics. To design proteins that function like natural ones, how do we predict their dynamics? Hannah Wayment-Steele and I are thrilled to share the first big, experimental datasets on protein dynamics and our new model: Dyna-1! 🧵

We are excited to announce the launch of our new series of talks for early career scientists, including assistant professors, newly appointed principal investigators, and researchers preparing for faculty positions.

1/4 🚀 Announcing the 2025 Protein Engineering Tournament. This year’s challenge: design PETase enzymes, which degrade the type of plastic in bottles. Can AI-guided protein design help solve the climate crisis? Let’s find out! ⬇️ #AIforBiology #ClimateTech #ProteinEngineering

Today in the journal Science: BioEmu from Microsoft Research AI for Science. This generative deep learning method emulates protein equilibrium ensembles – key for understanding protein function at scale. msft.it/6010S7T8n

Awesome to see this epic piece of work, led by Cecilia Clementi, finally appear in Nature Chemistry. The development of a general coarse-grained protein forcefield to describe folding, binding and conformation changes without solvent and all-atom, has been long anticipated!

In 1965, Margaret Dayhoff published the Atlas of Protein Sequence and Structure, which collated the 65 proteins whose amino acid sequences were then known. Inspired by that Atlas, today we are releasing the Dayhoff Atlas of protein sequence data and protein language models.

The MLSB workshop will be in San Diego, CA (co-located with NeurIPS) this year for its 6th edition in December 🧬🔬 Stay tuned MLSB (in San Diego) as we share details about the stellar lineup of speakers, the official call for papers, and other announcements!🌟

Excited to share work with Zhidian Zhang, Milot Mirdita, Martin Steinegger, and Sergey Ovchinnikov biorxiv.org/content/10.110… TLDR: We introduce MSA Pairformer, a 111M parameter protein language model that challenges the scaling paradigm in self-supervised protein language modeling 🧵

Can protein LMs reveal scientific knowledge? We start by asking how pLMs turn sequences into structure signals. We map a contact prediction circuit: early motif features gate later domain features. Spurious or science? We can now test. 🧵(1 of N)

First time at #MLCB! I'll be speaking tomorrow about my development of an ML predictor of domain–peptide interaction affinity to model proteome-scale signaling networks. It'll be livestreamed too.