DCFold用单次前向传播实现AlphaFold3级精度，提速15倍。
DCFold: Efficient Protein Structure Generation with Single Forward Pass
- 采用双一致性训练与时间测地线匹配调度器，实现单步生成。
- 推理速度提升15倍，结构预测与结合剂设计任务均达AlphaFold3水平。
- 适合需要快速生成的药物筛选与蛋白质设计场景。
AlphaFold3引入基于扩散的架构，将蛋白质结构预测提升至全原子分辨率并显著提高精度，已成为多样生成与设计任务的基础模型。然而其迭代设计导致推理时间大幅增加，限制了在虚拟筛选和蛋白质设计等下游任务中的实际应用。我们提出DCFold，一种单步生成模型，在保持AlphaFold3级精度的同时实现高效推理。其提出的双一致性训练框架结合新型时间测地线匹配（TGM）调度器，使推理速度提升15倍，且在结构预测与结合剂设计基准测试中验证了有效性。
原文摘要 · Abstract (English)
AlphaFold3 introduces a diffusion-based architecture that elevates protein structure prediction to all-atom resolution with improved accuracy. This state-of-the-art performance has established AlphaFold3 as a foundation model for diverse generation and design tasks. However, its iterative design substantially increases inference time, limiting practical deployment in downstream settings such as virtual screening and protein design. We propose DCFold, a single-step generative model that attains AlphaFold3-level accuracy. Our Dual Consistency training framework, which incorporates a novel Temporal Geodesic Matching (TGM) scheduler, enables DCFold to achieve a 15x acceleration in inference while maintaining predictive fidelity. We validate its effectiveness across both structure prediction and binder design benchmarks.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。