Back

Automated and modular protein binder design with BinderFlow

Chacon-Sanchez, C.; Gonzalez-Rodriguez, N.; Llorca, O.; Fernandez-Leiro, R.

2025-09-16 bioinformatics
10.1101/2025.09.10.675490 bioRxiv
Show abstract

Deep learning has revolutionised de novo protein design, with new models achieving unprecedented success in creating novel proteins with specific functions, including artificial protein binders. However, current methods remain computationally demanding and challenging to operate without specialised infrastructure and expertise. To overcome these limitations, we developed BinderFlow, a structured and parallelised pipeline for protein binder design. Its batch-basednature enables live monitoring of design campaigns, seamless coexistence with other GPU-intensive processes, and reduces human intervention. Furthermore, BinderFlows modular structure enables straightforward modifications to the design pipeline to incorporate new models and tools or to implement alternative design strategies. Complementing this, we developed BFmonitor, a web-based dashboard that simplifies campaign monitoring, design evaluation, and hit selection. Together, these tools lower the entry barrier for non-specialised users and streamline expert workflows, making generative protein design more accessible, scalable and practical for both exploratory and production-level research.

Matching journals

The top 3 journals account for 50% of the predicted probability mass.

50% of probability mass above

"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.