Release ProteinDJ v2.0.0 - Major Update · PapenfussLab/proteindj This update introduces support for BindCraft and HyperMPNN to the ProteinDJ pipeline, template-guided structure prediction with Boltz-2, and improves container definitions for better compatibility....

Other features for v2 include template-guidance for #Boltz-2 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/proteindj/releases/tag/v2.0.0

Atomically accurate de novo design of antibodies with RFdiffusion #antibody #design #modeling #rfdiffusion

ProteinDJ logo

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/10.1101/2025.09.24.678028 #proteindesign

Thanks to @biancabroske.bsky.social , @scbinder.bsky.social , @tim-kempchen.bsky.social and all the other authors for a fantastic collaboration. A big thank you goes to the developers of #RFdiffusion, #Chroma, #Bindcraft and others to make these amazing algorithms available.

When we saw the first tweats about #RFdiffusion and #Chroma, we wanted to try if we can apply these tools to our own research.
Have a look at our preprint and learn what worked out of the box and what didn't.

De novo designed proteins neutralize lethal snake venom toxins - Nature Deep learning methods have been used to design proteins that can neutralize the effects of three-finger toxins found in snake venom, which could lead to the development of safer and more accessible an...

Finally read these 2 x papers from the Baker Lab (@uwproteindesign.bsky.social)🧬 De novo protein design for snake venom neutralisation (binders) 🐍 + multistep reactions (enzymes) 🧪 using #RFDiffusion.
nature.com/articles/s41...
science.org/doi/epdf/10.... #proteindesign #stucturalbiology #PhD

Synthetic Protein Interaction Project Recent machine learning-based methods - including RFdiffusion, FoldFlow-2 and BindCraft - now enable the de novo design of synthetic proteins that interact with any specific protein, nucleic acid, ...

@biogrid.bsky.social is happy to release of our new themed curation project on #SyntheticProtein interactions using proteins generated with #rfdiffusion, #foldflow, and #bindcraft. Our page linked below contains all interactions and download files will be available very soon 🧪 #AI #MachineLearning

SciTech Chronicles. . . . . . . . .Feb 14th, 2025 When you ask for clarity, be ready for disappointment Vol II No 40 343 links Curated The recycled solar cell has the same efficiency as the ...

SciTech Chronicles. . . . . . . . .Feb 14th, 2025

bit.ly/stc021425

#perovskite #water first-generation #end-of-life #Titan #dissipation #rotation #circular #influenza #vaccine #H1N1 #H3N2 #proteins #enzymes #structure #RFdiffusion #buried #extremophiles #subglacial #hydrothermal

Cas activity assay. 3 strongest inhibitors characterised. Mimic RNAs. Xtallised one. Two others wouldn't xtallise, CD agrees with prediction; also checked folding/stability. Nice candidates for regulation of Cas. Functional in bacteria. Rescue phage infection as designed. As a crispr off switch - 8 weeks from AI design to targeted inhibitor.

Session 9 Cyntia Taveneau: De novo design of crispr-cas inhibitors. CRISPR system degrades DNA from phage; phage escape with antiCRISPR. Can we design them?? AIcrs designed to block active site of Cas13. #RFdiffusion Scoring top 96. Expr and purify. Biolayer interferometry. #LorneProteins2025

Toward video generative models of the molecular world As the capabilities of generative AI models have grown, you've probably seen how they can transform simple text prompts into hyperrealistic images and even extended video clips.

Toward #video #generative_models of the #molecular world

#AI #RFdiffusion #MDGen

phys.org/news/2025-01...

Antagonist antibodies can have unwanted agonist activities. It is now possible to generate pure antagonist protein-binding proteins with high affinity using RosettaFold | #Antibodies #TNFR #OX40 #4-1BB #RFdiffusion | David Baker uofwa.bsky.social | Science @science.org | tinyurl.com/yc34m5jt

I would appreciate any advice on analyzing a protein structure using #AlphaFold, Colab, or #RFDiffusion models to identify new interactors. If anyone is interested, I would love to connect via Teams and collaborate. 🧬🖥️ #deeplearning

I would appreciate any advice on analyzing a protein structure using #AlphaFold, Colab, or #RFDiffusion models to identify new interactors. If anyone is interested, I would love to connect via Teams and collaborate. 🧬🖥️ #deeplearning

We are open to various forms of collaboration and would value fluent feedback with expert groups in #AlphaFold Multimer and #RFDiffusion. Let’s connect! DM if you are interested!

We are exploring the structure of a protein using #AlphaFold and #RFDiffusion models to later identify potential interactors. Interested in collaborating? Please send a direct message. #AI #ML

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?

Five protein-design questions that still challenge AI Nature - Tools such as Rosetta and AlphaFold have redefined the protein-engineering landscape. But some problems remain out of reach — for now.

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

Exploring AI-Based Protein Sequence Generation with EvoDiff from Microsoft Research EvoDiff is a new, state-of-the-art protein sequence generation system from Microsoft Research. How well does it work?

Protein Sequence Generation with EvoDiff: colbyford.medium.com/exploring-ai...

#proteins #diffusion #ai #computationalbiology #bioinformatics #rfdiffusion #alphafold #colabfold