🔥The 9th Round of Easy Loan, Earn $40 Reward is in progress❗️ ⏰ Promotion Period: January 15th - Feburary 15th, 2025 👉 Register now and check more details at gate.io/campaigns/358

Is it possible to design soluble analogs of integral membrane proteins using deep learning? The answer is yes! In our latest study we've successfully created novel soluble proteins with claudin, rhomboid protease, and GPCR-like topologies. Read more here biorxiv.org/content/10.110…

"Computational design of soluble analogues of integral membrane protein structures" Solubilizing membrane proteins (e.g., GPCRs) by inverting AlphaFold2 and redesigning AAs w/ a version of ProteinMPNN trained exclusively on soluble proteins. biorxiv.org/content/10.110…

Very happy to share the new manuscript from Bruno Correia lab! With Casper Goverde we de novo designed several complex natural folds, including soluble analogues of integral membrane proteins! biorxiv.org/content/10.110…

ARE YOU SICK OF AI?! BECAUSE WE DID IT AGAIN IN AN EVEN MORE OBSCURE SPACE THAN TEXT OR IMAGES. BUCKLE UP BECAUSE THIS WONT MAKE ANY SENSE UNLESS YOU LIKE PROTEINS 💃💃🧬🧵

We developed a new method for designing proteins which lets us model the entire structure, including sidechains. This involves co-designing protein structure and sequence biorxiv.org/content/10.110…

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!

Now out in slightly shorter form :) nature.com/articles/s4158… Kotaro Tsuboyama Justas Dauparas Elodie Laine Sergey Ovchinnikov

We found that when designing new self-assembling proteins, ProteinMPNN designs more polar interfaces than Rosetta, which improves solution properties. Details here: biorxiv.org/cgi/content/sh… Great work by Rob de Haas and team when Justas Dauparas was developing #ProteinMPNN.

We've added a lot more MSAs to OpenProteinSet since the original release last year and so we wrote up a standalone manuscript. To our knowledge, it's the largest and most accurate database of MSAs in the open. arxiv.org/abs/2308.05326

Online at Science Magazine now: my paper with Florian Praetorius at Institute for Protein Design We made tiny protein hinges that behave similarly to the hinges you encounter in the macroscopic world (gif credit Ian Haydon , protein credit yours truly) science.org/doi/full/10.11…

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…

Stability issues bringing you down? Try ProteinMPNN! Our preprint describing sequence redesign of natural proteins with ProteinMPNN for improved properties is up. Check it out: biorxiv.org/content/10.110…

Very excited to share RoseTTAFold All-Atom and RFdiffusion All-Atom, methods for structure prediction and design of biomolecular assemblies! biorxiv.org/content/10.110… 1/n

Sharing an early preprint of my Microsoft AI4Science summer internship project. We developed SE(3) flow matching for protein backbone generation. Compared to SE(3) diffusion, we find our method achieves higher designability, faster sampling, with a way simpler implementation. 1/8

Our paper using ProteinMPNN redesign for improved properties is up on JACS! Huge thanks to Reyes, Indrek Kalvet, Sam, and many others for their work. Shout out to Justas Dauparas for developing such a groundbreaking (and versatile!) tool. Institute for Protein Design pubs.acs.org/doi/full/10.10…

LigandMPNN preprint: biorxiv.org/content/10.110… LigandMPNN inference code + model weights (including ProteinMPNN, SolubleMPNN etc): github.com/dauparas/Ligan…

That's my designed protein on the cover of Science! Achievement unlocked!

Today in nature we present the results of our exploration of the soluble protein universe and the design of functional soluble membrane proteins with Casper Goverde Nico Goldbach Bruno Correia 1/6 nature.com/articles/s4158…

Check out how we use ML-assisted method to design small molecule binders (binder to polar and flexible ligands as well!) and turn binding to sensing via CID and nanopore. Institute for Protein Design Art credit to Ian Haydon | Science dlvr.it/T9mdkM

Here is the link to the Colab, let us know if you have any problems or you have a hard target our pipeline cannot design against! We want to keep improving it and community feedback is very important 🙏🏻💻 colab.research.google.com/github/martinp…