ProHiFlo: Hierarchical Flow Matching with Functional Guidance for De Novo Protein Generation
Researchers have developed ProHiFlo, a new hierarchical flow matching framework for de novo protein generation. This method improves efficiency and accuracy by modeling backbone geometry before refining to all-atom coordinates. ProHiFlo also incorporates functional guidance using pretrained predictors to steer generation toward desired properties without retraining. Experiments show state-of-the-art performance, including a higher success rate in enzyme active site scaffolding compared to existing methods. AI
IMPACT Introduces a more efficient and targeted approach to protein design, potentially accelerating therapeutic and enzyme engineering.