PhD student at the Institute for Protein Design | Baker Lab | Machine Learning for Protein Design | University of Washington Molecular Engineering || Yale MB&B
Joined September 2025
- Tweets24
- Following77
- Followers97
- Likes1
Rafi Brent retweeted
Designing ligases for pharmaceutically relevant small molecules has evaded us for years. To our amazement, these were some banger enzymes straight out of the computer and a great example of how de novo enzymes can transform synthesis of complex molecules. More to come on ligases!
Rafi Brent retweeted
1/n
Crossover episode! We introduce RFD4-Proteina, our latest design model - and the result of a year-long collaboration between the Baker Lab and NVIDIA GenAIR (the name says it all…). I hope you’ll agree - the results are astonishing. 🌐 Website: rfd4-proteina.org/
Rafi Brent retweeted
Avengers assemble: 1 year BakerLab + NVIDIA GenAIR = 🔥 rfd4-proteina.org
Presenting RFD4-Proteina, our latest protein design model, significantly better and faster than everything we compared against, both in silico and in the lab! 1/30
Rafi Brent retweeted
Great things come from great teams! Super excited to share rfd4-proteina.org, a step-function improvement in generative protein design! A year in the making with @UWproteindesign , NVIDIA GenAIR and the amazing @DidiKieran @nscorley and @RafiBrent! 🧵1/n
Rafi Brent retweeted
RFD4-Proteina, co-developed by @UWproteindesign @UWMedicine & @NVIDIAHealth, debuts today at GTC Berlin. The open-source generative model will use biomolecular reasoning to find new protein solutions for medicine, sustainability, materials & biotech. tinyurl.com/3pw3jn92
ALT Members of the RDF4 modeling team run tests at the UW Medicine Institute for Protein Design. Credit: Sierra Adler/IPD
Rafi Brent retweeted
A step change in protein design: RFD4-Proteina is enables everyone today.
We partenered with @huggingface to make available a free space.
You can solve your hardest biology problem right now. No CS degree required: huggingface.co/blog/nvidia/r…
More to come...
Avengers assemble: 1 year BakerLab + NVIDIA GenAIR = 🔥 rfd4-proteina.org
Presenting RFD4-Proteina, our latest protein design model, significantly better and faster than everything we compared against, both in silico and in the lab! 1/30
Rafi Brent retweeted
It has been incredibly exciting to bring the RFdiffusion and Proteina model families together. An amazing release! 💜💚🔥🎉
And I am just as excited about the applications! 🧬
Massive congrats to @DidiKieran, @nscorley, @RafiBrent, @maxkazman and the many more contributors!
Avengers assemble: 1 year BakerLab + NVIDIA GenAIR = 🔥 rfd4-proteina.org
Presenting RFD4-Proteina, our latest protein design model, significantly better and faster than everything we compared against, both in silico and in the lab! 1/30
Rafi Brent retweeted
🚀 Today at GTC Berlin we introduced RFD4-Proteina! A close one-year collaboration between GenAIR and David Baker's group at @UWproteindesign !
🧬 Design proteins faster and send fewer, better candidates to the lab.
Introducing RFD4-Proteina, a new NVIDIA BioNeMo open model co-developed with @UWproteindesign.
▫️Fast: 13× faster generation than RFdiffusion3 at 200 residues
▫️ Smart: state-of-the-art across 12+ protein design tasks
▫️ Programmable: set your design inputs and use test-time compute on harder problems
Start with our binder-design tutorial nvda.ws/3VK9Uvr
Rafi Brent retweeted
Super excited about this work! We are finally able to not only screen binders for specificity, but design them to be specific 🤯 this will be transformational in the development of pMHC binders and therapeutics in general
Harder specificity challenges: @jBonzaniniSci designed peptide-MHC binders that bind tightly and very specifically, showing the model reasons well about the interactions formed. 20/30
Rafi Brent retweeted
Protein design doesn’t have to stop at the canonical 20 amino acids! After our work on phosphotyrosine binders, RFD4-Proteina adds phosphoserine and phosphothreonine (below) to the repertoire, with binders that distinguish adjacent H3pS10 and H3pT11 sites in the histone H3 tail!
The unified latent space pushes specificity further: with @kinasekid we bind phosphorylated serines and threonines specifically, and even site-selectively when they sit directly next to each other on a target! 22/30
What a wild ride! After a fantastic collaboration between @UWproteindesign and Nvidia GenAIR, we've released the latest in the RFdiffusion and Proteina lineages, namely... RFD4-Proteina! Computationally and in the lab, the results have astonished us🧵 1/n rfd4-proteina.org/
More details to come! For more info:
Website: rfd4-proteina.org/index.html
Paper: rfd4-proteina.org/assets/pap…
Code: github.com/RosettaCommons/RF…
Demo: huggingface.co/spaces/nvidia…
And check out fantastic threads from my coauthors:
nitter.cf/DidiKieran/status/2112…
nitter.cf/nscorley/status/211289…
Avengers assemble: 1 year BakerLab + NVIDIA GenAIR = 🔥 rfd4-proteina.org
Presenting RFD4-Proteina, our latest protein design model, significantly better and faster than everything we compared against, both in silico and in the lab! 1/30
And finally, huge thanks to the fantastic folks at @UWproteindesign and Nvidia who helped make this dream a reality. I've been excited about protein design since high school due to a great TED talk from David Baker. Thanks David for creating such a great place to do science! n/n