Automated and modular protein binder design with BinderFlow

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, BinderFlow’s 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. Competing Interest Statement The authors have declared no competing interest. Footnotes We have added references that were missing.