MMSeqs-GPU + TensorRT-OpenFold make structure prediction fast, all openly available! Excited about running MSA search on large databases without performance hit from swapping thanks to new ARM optimisations. Fun project with great colleagues inside and outside of NVIDIA!

Yes, I peer reviewed DeepSeek-R1 paper for @nature and hope to see more frontier model developers follow their lead of sharing peer-reviewed technical details of their work, and go beyond buzzy blogs and patronizing "yeah, we have done it this way too" post facto claims..🤞

Trust me.

We sought to make proteins both potent and FAST. We used #proteindesign to design precise control over protein interaction lifetimes, enabling us to construct rapid-response circuits, biosensors, and switchable cytokines. Now published nature! Links to paper and tutorial below.

Thrilled to share that today we report our human protein interactome in Science Magazine! Predicting which pairs of proteins in the human proteome is a great challenge due to the shallow eukaryotic evolutionary signals but hugely important to understand. science.org/doi/10.1126/sc…

Phosphorylation on tyrosines control key pathways in immunity, cancer, and metabolism. For the first time, we can now design proteins that specifically recognize individual phosphotyrosines, even in disordered regions. (1/8) Preprint: biorxiv.org/content/10.110…

We are pleased to share our new preprint: “De novo design of RNA and nucleoprotein complexes”. This work extends the principles of de novo protein design to RNA and DNA, enabling the generative design of complex multi-polymer structures! (1/6) doi.org/10.1101/2025.1…

Looks like a scrotum mixed with the hot sauce guy from SpongeBob

This week's issue of #ScienceTranslationalMedicine has arrived! New mRNA vaccines generate self-assembling nanoparticles to enhance immunity, dual-targeting "decoys" prevent metastasis and potentiate immunotherapy against melanoma in mice, and more. scim.ag/43lkZUm

🚨 new paper in Science Translational Medicine 🚨 Here, we describe and evaluate a "best-of-both-worlds" vaccine technology platform that combines the benefits of mRNA vaccines and computationally designed protein nanoparticle immunogens: bit.ly/47s7btG.

How can we computationally design new peptides that activate T cells against cancer and viruses?University of Washington PNASNews "T cell receptor specificity landscape revealed through de novo peptide design" • T cells recognize pathogen-derived peptides presented on MHC molecules through T

Morphed transition of the intermediates in the catalytic cycle of the yeast TRiC chaperone (PDB codes: 6KRD, 6KRE and 6KS6) ChimeraX (bsky: chimerax.ucsf.edu) #molecularart #scivis

🚨new paper alert🚨 Here, we show how recently developed ML tools can be leveraged to design self-assembling protein nanoparticle immunogens in the absence of experimentally determined structures of the oligomeric building blocks. Read more PNASNews: doi.org/10.1073/pnas.2…

Excited to share nature: How does naloxone (Narcan) stop an opioid overdose? We determined the first GDP-bound μ-opioid receptor–G protein (wt) structures and found naloxone traps a novel "latent” state, preventing GDP release and G protein activation. 🧵 nature.com/articles/s4158…

Delighted to share the peer-reviewed version of our article describing a prefusion-stabilized MARV GP vaccine immunogen and a best-in-class MARV neutralizing and protective antibody! Led by Amin Addetia with Vir Biotechnology HHMI nature.com/articles/s4158…

🚨 New Results Alert 🚨 Have you ever wondered what new therapeutic avenues would be enabled if we could program T Cells in the computer to target any desired peptide-MHC neoantigen with a TCR or a TCR-like antibody? What if we could validate these molecules easily in small

New paper “Proteome-wide model for human disease genetics” is now live at Nature Genetics: rdcu.be/eRu7K popEVE (pop.evemodel.org) finds the needles in the haystacks of human genetic variation:

What if we have a big protein but need a smaller version for delivery or engineering? Introducing SCISOR: we shrink proteins by training a diffusion model to find natural substrings! arXiv: arxiv.org/abs/2511.07390 Ethan Baron, Ruben Weitzman, Debora Marks, Andrew Gordon Wilson! 1/7

Excited to share my recent work, CIRPIN 🐍 with Sergey Ovchinnikov and Mazdak Abulnaga on the discovery of thousands of naturally occurring circularly permuted protein domains