The Baker Lab has a new #openaccess paper in Nature Communications showing that dramatic improvements can be achieved when deep learning software is used to design protein-binding proteins. Full paper ➡️ nature.com/articles/s4146… Short summary ⬇️ bakerlab.org/2023/05/08/dee…

.Nate Bennett and colleagues show how deep learning can be used to improve the hit-rate of de novo protein binder design 10-fold. Institute for Protein Design #DeepLearning #proteindesign #BiotechNatureComms nature.com/articles/s4146…

Introducing RoseTTAFold2: Protein structure prediction AI that combines the best of AlphaFold2 and RoseTTAFold. Even without IPA and triangle attention, RF2 achieves comparable performance to AlphaFold2. biorxiv.org/content/10.110…

Geometrically standardized features give LEGO blocks their ability to be intuitively assembled into structures. Here we show that designed proteins can be made to a similar standard, enabling useful features in nanomaterials such as scalable size: biorxiv.org/content/10.110…

Digital art techniques can now devise custom, working biomolecules on demand. These proteins could form the basis for vaccines, therapeutics and biomaterials. Read the full story: nature.com/articles/d4158…

It's so great to see our RFdiffusion paper now live nature. This article from Ewen Callaway gives a great overview of RFdiffusion and protein diffusion models more broadly, and also highlights some of the ways people are already using it in their own research!

Phil Leung and I are excited to see our work on multistate design of hinge proteins finally published as a peer-reviewed paper science.org/doi/full/10.11…

We’re really happy to share our preprint demonstrating the atomically-accurate design of single-domain antibodies (VHHs) with RFdiffusion!

Impressive work from Institute for Protein Design, Nate Bennett Joseph Watson @RobertRagotte Andrew Borst, DeJenae See, Phil Leung & team: “Atomically accurate de novo design of single-domain antibodies” Thanks for choosing Twist DNA to support this work 🧬 bit.ly/4a9mwyk

Want a quick primer on the science behind why Xaira just launched with a $1B+ seed round? The wonders of peer view and publishing have very conveniently decided to just publish our review on how generative AI is transforming de novo protein design! sciencedirect.com/science/articl…

Love this article by Charlotte Schubert GeekWire on what we're trying to do here in #Seattle at XairaTherapeutics Justas Dauparas Nate Bennett geekwire.com/2024/inside-th…