In a series of 3 papers and preprints, we’re thrilled to share with you the working laser phase plate. In collaboration with research led by Holger Müller at UC Berkeley, this is a huge innovation in imaging to make small and faint objects inside cells visible.
Antibody therapies now make up ~25% of all new FDA approvals. ESMFold2 is especially strong at modeling antibody-antigen interactions — hit rates of 15–29% for scFvs across five targets. No target-specific tuning. bit.ly/4vmGX52
🚨 New preprint: We reprocessed 77k zebrafish RNA-seq datasets from across the global research community and found hidden viruses in 10% of them—including a fish virus whose proteins are 91% identical to human Influenza B—then built a generalizable pipeline.
Introducing RNAquarium 🐟: a discovery engine built to scale across any species with public data, extracting multi-scale and multi-organism biology from sequences that already exist and underscoring the value of bulk RNA-seq data for modeling 🧬
ESMC learned protein biology from 2.8 billion sequences — the full evolutionary record of what works in nature. That's what a world model of protein biology looks like.
Download: bit.ly/4ebUoxY
Update: ESMFold2-pipeline is now live on @AriaxBio.
Design nanobodies, scFvs , and miniproteins with structural templates, hotspot targeting, and Protenix v2 validation.
ariax.bio/resources/esmf…
I've been really impressed with ESMFold2's design capabilities.
To make it easier to run locally, as well as to support structural templates, multichain targets, hotspots, Protenix-v2 validation, and automated MSA handling, I created this project:
github.com/cytokineking/e…
Design nanobodies, antibodies, and miniproteins with ESMFold2, the latest state-of-the-art model from the ESM team.
ESMFold2-pipeline is now live on Ariax Bio, the only hosted platform for the complete design workflow.
Read our announcement:
What if we could see proteins inside living cells that have never been visible before? The laser phase plate is helping make that possible.
Learn more: bit.ly/4vIPC1U
State of the art on antibody-antigen and protein-protein interaction prediction. No target-specific tuning. No MSA required.
Explore our new folding model: bit.ly/4vmGX52
This is a little late, but happy to share our work with @DonnaFarber3 on transcriptional control of tissue adapation and effector function in infant T cells that appeared recently in @NatImmunol. Thanks to @hipcProject and @biohub for their support.
Congrats to @biohub on ESMFold2 - a new protein structure model trained end-to-end on 256 NVIDIA H100 Tensor Core GPUs.
The full NVIDIA CUDA-X stack made it possible:
⚡ cuEquivariance fused kernels for triangle multiplication - reduced compute overhead at the core of the
Proteins are the machinery of life. Scientists have cataloged billions of protein sequences—but their biology is still mostly unknown.
ESM Atlas is a new way in. bit.ly/4dJcF6G
7.5 million people in the U.S. live with psoriasis. Many still struggle—despite existing treatments.
Our team combined AI analysis with CRISPR experiments to identify overlooked biological pathways, then tested an existing asthma drug as a potential treatment. And it worked.
Designing a protein binder used to mean years of lab experiments. ESMFold2 lets researchers run hundreds of thousands of designs computationally—then take only the most promising into the lab. We tested it across 5 targets in oncology and immunology. It worked.
Download and
1/📢 New preprint! Do you actually need a biology-specific foundation model to predict how cells respond to perturbations? Surprising answer: a general-purpose tabular model - never trained on a single cell - matches or beats the specialists!
📄 doi.org/10.64898/2026.…@biohub
