ProHiFlo: Hierarchical Flow Matching with Functional Guidance for De Novo Protein Generation

ProHiFlo：用于从头蛋白质生成的具有功能引导的分层流匹配模型

Abstract: De novo protein generation has transformative potential in therapeutic design, enzyme engineering, and synthetic biology. While diffusion-based and flow matching approaches have achieved progress, they typically operate at single resolution and lack mechanisms for incorporating functional constraints. 摘要： 从头蛋白质生成在治疗药物设计、酶工程和合成生物学领域具有变革性的潜力。尽管基于扩散模型和流匹配的方法已经取得了进展，但它们通常在单一分辨率下运行，且缺乏整合功能约束的机制。

We introduce ProHiFlo, a hierarchical flow matching framework with three innovations: (1) coarse-to-fine generation that models backbone geometry before refining to all-atom coordinates, reducing computational cost while maintaining accuracy; (2) functional guidance leveraging pretrained predictors to steer generation toward desired properties without retraining; (3) adaptive SE(3)-equivariant architecture for efficient multi-scale processing. 我们引入了 ProHiFlo，这是一个具有三项创新的分层流匹配框架：（1）从粗到细的生成方式，先建模主链几何结构，再细化至全原子坐标，在保持精度的同时降低了计算成本；（2）利用预训练预测器进行功能引导，无需重新训练即可将生成过程导向预期的属性；（3）用于高效多尺度处理的自适应 SE(3) 等变架构。

Experiments on unconditional generation, motif scaffolding, and functional design demonstrate state-of-the-art performance while requiring 4 fewer sampling steps. On enzyme active site scaffolding, ProHiFlo achieves 58.9% success rate compared to 41.2% for RFDiffusion. 在无条件生成、基序支架（motif scaffolding）和功能设计方面的实验表明，该模型实现了最先进的性能，同时采样步骤减少了 4 步。在酶活性位点支架设计任务中，ProHiFlo 的成功率为 58.9%，而 RFDiffusion 为 41.2%。