#rfdiffusion search results
I am thrilled to release ProteinDJ: a high-performance and modular protein design pipeline. Our open-source workflow incorporates #RFdiffusion, #ProteinMPNN, #FAMPNN, #AlphaFold2 and #Boltz-2. It is a fast, free, and fun way to design proteins (1/5) doi.org/10.1101/2025.0…
One highlight of this paper for me is where we show #RFdiffusion is capable of generating nontrivial backbone features that enable high-affinity interface design with non-idealities such as broken helices, and cross-interface hydrogen bonds as shown in the Bim xtal structure
I gave up last night and just used #RFDiffusion CollabFold to diffuse PDB: 7vve, an engineered PET hydrolase that was featured as the RCSB Molecule of the Month
Playing with RoseTTAFold Diffusion (awesome!) - making binding proteins that target a protein of interest. I find many designs have sidechain clashes between target and binder. I wonder if I'm doing something wrong - are other people seeing this? @sokrypton #RFDiffusion.
Other noteworthy features for v2 include template-guidance for #Boltz2 prediction, auto-contig generation for #RFdiffusion, and models for #HyperMPNN. We have also made bug fixes, improvements to documentation, container updates and more. Details here: github.com/PapenfussLab/p…
BREAKING! 'RFdiffusion', a deep learning wizard, sculpts proteins from molecular blueprints. Navigating challenges from binder design to enzyme scaffolding, it crafts hundreds of proteins, rigorously tested and validated. A new era of protein design unfolds! #RFdiffusion
In the age of chatbots, #RFDiffusion definitely raises the bar. Good times #structuralbiology #proteins , thank you #bakerlab
いま作ってみた2 左: RFDiffusion生成構造、右: ProteinMPNNで配列生成してESMFoldで予測した構造 #RFDiffusion on colaboratory--> #ProteinMPNN ---> #ESMFold
Whenever possible, we employ emerging tools for protein design like #AlphaFold or #RFDiffusion. Still, many challenges are unique to peptides—short half-life, limited oral bioavailability, toxicity—and sampling bias and data scarcity to the #ML modelling process. (2/3)
Playing with the amazing #RFdiffusion Colab notebook (it's just awesome!). Having "issues" with flying peptides, mpnn_results.csv reports RMSD of 10.0Å-30.0Å. Is this something expected for small binders @sokrypton, @_JosephWatson ? Let me know if I could be of any help! 🙏🏻
CellとNatureに掲載された抗体生成AIについて勉強しました！ #MAGE #RFdiffusion 配列ベースMAGE vs 構造ベース拡散モデルRFdiffusion-Ab（RFantibody） hira-labo.com/archives/5099
🔑 Key Scientific Highlights: Rapid Binder Design: Using #RFdiffusion & #ProteinMPNN, we rapidly designed minibinders targeting NY-ESO-1 with high specificity. #AI #CancerResearch
いま作ってみた3 左: RFDiffusion生成構造、右: ProteinMPNNで配列生成してESMFoldで予測した構造 #RFDiffusion on colaboratory--> #ProteinMPNN ---> #ESMFold
いま作ってみた5 左: RFDiffusion生成構造、右: ProteinMPNNで配列生成してESMFoldで予測した構造 半分TIMバレルで半分二重βバレルという胸が熱くなるフォールドが生成されたが、残念ながら目的構造に折りたたむと予測される配列は得られなかった。 #RFDiffusion #ProteinMPNN #ESMFold
いま作ってみた5 左: RFDiffusion生成構造、右: ProteinMPNNで配列生成してESMFoldで予測した構造 これはさすがに巻かないだろうと思ったが、ESMFoldで巻いた構造が予測されてきた。本当に？ ESMFoldは"巻きがち"な感じがするが、この結果もそれかもしれない。 #RFDiffusion #ProteinMPNN #ESMFold
Another early morning start at the @KeystoneSymp conference on "Computational Design and Modelling of Biomolecules". Lots of interesting talks. Lots of #AlphaFold #RoseTTAFold and #RFdiffusion. The photo does poor justice to the real scene. #Banff @BanffNP @FairmontSprings
いま作ってみた4 左: RFDiffusion生成構造、右: ProteinMPNNで配列生成してESMFoldで予測した構造 こんな怪しくて大きめ構造ができるのか？と思ったが一応ESMFoldで予測はされてきた。 #RFDiffusion #ProteinMPNN #ESMFold
From July 14-18, over 70 researchers gathered @Sca_DS #LivingLab for the Leipzig #Rosetta Workshop 2025, organized by the @MeilerLab. The sessions covered #RFDiffusion, #ProteinMPNN, docking methods, and XML scripting, catalysing collaboration and innovation. 📸©️: Julia Belyaeva
Other noteworthy features for v2 include template-guidance for #Boltz2 prediction, auto-contig generation for #RFdiffusion, and models for #HyperMPNN. We have also made bug fixes, improvements to documentation, container updates and more. Details here: github.com/PapenfussLab/p…
CellとNatureに掲載された抗体生成AIについて勉強しました！ #MAGE #RFdiffusion 配列ベースMAGE vs 構造ベース拡散モデルRFdiffusion-Ab（RFantibody） hira-labo.com/archives/5099
I am thrilled to release ProteinDJ: a high-performance and modular protein design pipeline. Our open-source workflow incorporates #RFdiffusion, #ProteinMPNN, #FAMPNN, #AlphaFold2 and #Boltz-2. It is a fast, free, and fun way to design proteins (1/5) doi.org/10.1101/2025.0…
From July 14-18, over 70 researchers gathered @Sca_DS #LivingLab for the Leipzig #Rosetta Workshop 2025, organized by the @MeilerLab. The sessions covered #RFDiffusion, #ProteinMPNN, docking methods, and XML scripting, catalysing collaboration and innovation. 📸©️: Julia Belyaeva
of protein design. By harnessing #AI tools such as #RFdiffusion scientists can now generate entirely new proteins. In a process reminiscent of how creative AI systems like DALL·E produce art, RFdiffusion starts with random noise & gradually “denoises” it until a viable protein 22
If one wants to de novo predict protein structures, they must first obtain master level black belt status in virtual python environments! #rfdiffusion
In the age of chatbots, #RFDiffusion definitely raises the bar. Good times #structuralbiology #proteins , thank you #bakerlab
Finally read these 2 x papers from the Baker Lab (@UWproteindesign)🧬 De novo protein design for snake venom neutralisation (binders) 🐍 + multistep reactions (enzymes) 🧪 using #RFDiffusion. nature.com/articles/s4158… science.org/doi/epdf/10.11… #proteindesign #stucturalbiology #PhD
I use @BakerLaboratory’s #RFdiffusion for modeling protein backbones and it WORKS GREAT👌 The model won his group the #NobelPrize , SOOOO… maybe give it a look too, or get TOTALLY LEFT BEHIND… 😂😂🤣
This is interesting as a first large diffusion-based LLM. Most of the LLMs you've been seeing are ~clones as far as the core modeling approach goes. They're all trained "autoregressively", i.e. predicting tokens from left to right. Diffusion is different - it doesn't go left to…
🔑 Key Scientific Highlights: Rapid Binder Design: Using #RFdiffusion & #ProteinMPNN, we rapidly designed minibinders targeting NY-ESO-1 with high specificity. #AI #CancerResearch
Does anybody have an opinion on the benefits (or lack thereof) of the Ada generation (e.g. RTX 6000 Ada instead of RTX A6000) for a GPU workstation for AI tasks like #alphafold2 or #RFdiffusion?
Much attention has been focused on the de novo generation of protein binders using #RFDiffusion, #AlphaFold3 or #AlphaProteo. However, these models still need help with data scarcity, conformational changes, and hallucinations. (1/3) nature.com/articles/d4158…
Whenever possible, we employ emerging tools for protein design like #AlphaFold or #RFDiffusion. Still, many challenges are unique to peptides—short half-life, limited oral bioavailability, toxicity—and sampling bias and data scarcity to the #ML modelling process. (2/3)
Our article is live! We used #RFdiffusion and #FoldSeek to predict protein-protein interactions between rice 🌾 and rice blast fungus. This was part of my work at MaizeGDB, and we’re looking to redo the analysis (and experimental validation) for other host-pathogen systems too!
Application of RFdiffusion to predict interspecies protein-protein interactions between fungal pathogens and cereal crops biorxiv.org/cgi/content/sh… #biorxiv_plants
2⃣ Using AI-powered #RFdiffusion and a new method called #ChemNet, scientists generated and assessed catalytic sites with unprecedented precision. The artificial enzymes showed high efficiency, matching design models within 1Å. #EnzymeDesign #AIinScience #Biochemistry
An impactful proof-of-concept preprint! @UWproteindesign fine-tunes #generativeAI tool #RFdiffusion to create de novo single-domain #antibodies—a big step toward designing complex antibodies that could revolutionize drug development nature.com/articles/d4158…
"#RFdiffusion can help.. ..control a #cell’s responses...chemicals. ; In addit (I offer a mention) - latest discussion, ao, seemed concern on risks chemistry's #AI- 'tools' hav bought, via making it easier to 'design' #biological #weapons (.."by anyone") ; nature.com/articles/d4158…
We tip our diffusion, err... goggles to you 👓 🦠 buff.ly/3TnLZNl #GenAI #RFDiffusion #DrugDiscovery #VisionsOfTheFuture
One highlight of this paper for me is where we show #RFdiffusion is capable of generating nontrivial backbone features that enable high-affinity interface design with non-idealities such as broken helices, and cross-interface hydrogen bonds as shown in the Bim xtal structure
I am thrilled to release ProteinDJ: a high-performance and modular protein design pipeline. Our open-source workflow incorporates #RFdiffusion, #ProteinMPNN, #FAMPNN, #AlphaFold2 and #Boltz-2. It is a fast, free, and fun way to design proteins (1/5) doi.org/10.1101/2025.0…
I gave up last night and just used #RFDiffusion CollabFold to diffuse PDB: 7vve, an engineered PET hydrolase that was featured as the RCSB Molecule of the Month
One highlight of this paper for me is where we show #RFdiffusion is capable of generating nontrivial backbone features that enable high-affinity interface design with non-idealities such as broken helices, and cross-interface hydrogen bonds as shown in the Bim xtal structure
BREAKING! 'RFdiffusion', a deep learning wizard, sculpts proteins from molecular blueprints. Navigating challenges from binder design to enzyme scaffolding, it crafts hundreds of proteins, rigorously tested and validated. A new era of protein design unfolds! #RFdiffusion
Playing with RoseTTAFold Diffusion (awesome!) - making binding proteins that target a protein of interest. I find many designs have sidechain clashes between target and binder. I wonder if I'm doing something wrong - are other people seeing this? @sokrypton #RFDiffusion.
いま作ってみた2 左: RFDiffusion生成構造、右: ProteinMPNNで配列生成してESMFoldで予測した構造 #RFDiffusion on colaboratory--> #ProteinMPNN ---> #ESMFold
Another early morning start at the @KeystoneSymp conference on "Computational Design and Modelling of Biomolecules". Lots of interesting talks. Lots of #AlphaFold #RoseTTAFold and #RFdiffusion. The photo does poor justice to the real scene. #Banff @BanffNP @FairmontSprings
いま作ってみた3 左: RFDiffusion生成構造、右: ProteinMPNNで配列生成してESMFoldで予測した構造 #RFDiffusion on colaboratory--> #ProteinMPNN ---> #ESMFold
🔑 Key Scientific Highlights: Rapid Binder Design: Using #RFdiffusion & #ProteinMPNN, we rapidly designed minibinders targeting NY-ESO-1 with high specificity. #AI #CancerResearch
Whenever possible, we employ emerging tools for protein design like #AlphaFold or #RFDiffusion. Still, many challenges are unique to peptides—short half-life, limited oral bioavailability, toxicity—and sampling bias and data scarcity to the #ML modelling process. (2/3)
いま作ってみた5 左: RFDiffusion生成構造、右: ProteinMPNNで配列生成してESMFoldで予測した構造 半分TIMバレルで半分二重βバレルという胸が熱くなるフォールドが生成されたが、残念ながら目的構造に折りたたむと予測される配列は得られなかった。 #RFDiffusion #ProteinMPNN #ESMFold
From July 14-18, over 70 researchers gathered @Sca_DS #LivingLab for the Leipzig #Rosetta Workshop 2025, organized by the @MeilerLab. The sessions covered #RFDiffusion, #ProteinMPNN, docking methods, and XML scripting, catalysing collaboration and innovation. 📸©️: Julia Belyaeva
いま作ってみた4 左: RFDiffusion生成構造、右: ProteinMPNNで配列生成してESMFoldで予測した構造 こんな怪しくて大きめ構造ができるのか？と思ったが一応ESMFoldで予測はされてきた。 #RFDiffusion #ProteinMPNN #ESMFold
いま作ってみた5 左: RFDiffusion生成構造、右: ProteinMPNNで配列生成してESMFoldで予測した構造 これはさすがに巻かないだろうと思ったが、ESMFoldで巻いた構造が予測されてきた。本当に？ ESMFoldは"巻きがち"な感じがするが、この結果もそれかもしれない。 #RFDiffusion #ProteinMPNN #ESMFold
Playing with the amazing #RFdiffusion Colab notebook (it's just awesome!). Having "issues" with flying peptides, mpnn_results.csv reports RMSD of 10.0Å-30.0Å. Is this something expected for small binders @sokrypton, @_JosephWatson ? Let me know if I could be of any help! 🙏🏻
In the age of chatbots, #RFDiffusion definitely raises the bar. Good times #structuralbiology #proteins , thank you #bakerlab
An impactful proof-of-concept preprint! @UWproteindesign fine-tunes #generativeAI tool #RFdiffusion to create de novo single-domain #antibodies—a big step toward designing complex antibodies that could revolutionize drug development nature.com/articles/d4158…
#RFdiffusion is now #opensource: it is a method for structure generation, with or without conditional information. It can perform a whole range of #protein design challenges such as binder design, unconditional protein generation and others. bakerlab.org/2023/03/30/rf-… #Python #AI
Something went wrong.
Something went wrong.
United States Trends
- 1. #DWTS 34.8K posts
- 2. Alix 9,949 posts
- 3. Robert 100K posts
- 4. Elaine 34.2K posts
- 5. Carrie Ann 3,292 posts
- 6. Anthony Black 2,171 posts
- 7. Dylan 32.3K posts
- 8. Drummond 2,262 posts
- 9. #WWENXT 6,590 posts
- 10. Suggs 2,196 posts
- 11. Jalen Johnson 3,709 posts
- 12. Ezra 11K posts
- 13. CJ McCollum 1,481 posts
- 14. Wizards 8,676 posts
- 15. #DancingWithTheStars 1,043 posts
- 16. Godzilla 31.2K posts
- 17. #NXTGoldRush 5,376 posts
- 18. Bruce Pearl N/A
- 19. Daniella 2,615 posts
- 20. Brown 164K posts