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

I am pleased to announce the release of ProteinDJ v2! This is a major update that integrates BindCraft into the pipeline as an alternative to RFdiffusion for binder generation. You can try it out here: github.com/PapenfussLab/proteindj
#ProteinDJ #BindCraft #ProteinDesign @wehi-research.bsky.social

And thanks to Lyn Deng for creating such a cool ProteinDJ logo!

What started as a BioCommons webinar has helped lead to a new academia–industry collaboration.

ProteinDJ v3 is now free for commercial use, removing a key barrier for biotechnology companies @wehi-research.bsky.social @audaxbio.bsky.social @kmichie.bsky.social

Read more 🔗

ProteinDJ v3.0 is free for commercial use! Built by @joshuamhardy.bsky.social (WEHI), with contributions from @tlitfin.bsky.social and David Ladd (Audax). Commercial deps removed. New: GPU design/relaxation, BoltzGen, AF2/Boltz2 tandem and insulin-receptor binder tutorial. github.com/PapenfussLab...

ProteinDJ was designed for large-scale design campaigns and automatically batches designs over GPUs. It is highly portable and easy to install, with software containers for rapid deployment on HPC and workstation environments using Apptainer and Nextflow. github.com/PapenfussLab... (2/5)

There are multiple ways you can use ProteinDJ for protein design. We have documentation and examples of different protein design applications, including de novo design, fold conditioning, partial diffusion, and motif scaffolding. There are also filters and metrics to help select designs (3/5)

ProteinDJ: a high-performance and modular protein design pipeline https://www.biorxiv.org/content/10.1101/2025.09.24.678028v1

We also created Bindsweeper—a new tool to help you identify the optimal binder design parameters for your target protein. Bindsweeper enables the execution of multiple ProteinDJ runs to test different parameter combinations and reports success rates for each permutation. (4/5)

The BioFGREAT team is always excited about new tools to streamline protein design workflows. Looking forward to checking out ProteinDJ! 🚀🧪

New episode alert! Dive into our discussion on ProteinDJ, an AI-powered pipeline that streamlines synthetic protein design, dramatically improving speed and accessibility for researchers. Tune in to explore this breakthrough! https://tinyurl.com/SciBud-AI

ProteinDJ: a high-performance and modular protein design pipeline

https://www.biorxiv.org/content/10.1101/2025.09.24.678028v1

ProteinDJ: a high-performance and modular protein design pipeline www.biorxiv.org/content/10.1... 🧬🖥️🧪 github.com/PapenfussLab...

ProteinDJ: a high-performance and modular protein design pipeline https://www.biorxiv.org/content/10.1101/2025.09.24.678028v1

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

BindCraft is a standalone binder design pipeline (github.com/martinpacesa/BindCraft), but we have integrated only the first step of the BindCraft workflow (binder hallucination) in ProteinDJ. This is to utilise our existing downstream sequence design/structure prediction packages.

ProteinDJ: a high-performance and modular protein design pipeline [new]
ProteinDJ: modular, scalable protein design pipeline for HPC; parallel deep learning yields high-throughput binders.