PPDiff：在蛋白质-蛋白质复合物设计的混合序列-结构空间中进行扩散
PPDiff: Diffusing in Hybrid Sequence-Structure Space for Protein-Protein Complex Design
AI总结：
提出非自回归扩散模型 PPDiff，联合设计任意蛋白靶点的结合蛋白序列与结构，在数据集 PPBench 预训练及两项实际应用微调中成功率超越基线。
摘要：
设计具有高亲和力的蛋白质结合蛋白在生物医学研究和生物技术中至关重要。尽管在针对特定蛋白质方面取得了最新进展，但无需大量湿实验测试即可按需为任意蛋白质靶点创建高亲和力结合蛋白的能力，仍然是一个重大挑战。在此，我们提出了 PPDiff，这是一种以非自回归方式联合设计任意蛋白质靶点结合蛋白序列和结构的扩散模型。PPDiff 基于我们开发的带有因果注意力层的序列结构交织网络（SSINC），该网络集成了交织的自注意力层以捕获全局氨基酸相关性，k近邻（kNN）等变图层以模拟三维（3D）空间中的局部相互作用，以及因果注意力层以简化蛋白质序列内复杂的相互依赖关系。为了评估 PPDiff，我们整理了 PPBench，这是一个通用的蛋白质-蛋白质复合物数据集，包含来自蛋白质数据库（PDB）的 706,360 个复合物。该模型在 PPBench 上进行预训练，并在两个实际应用上进行微调：靶蛋白微型结合蛋白复合物设计和抗原-抗体复合物设计。PPDiff 始终超越基线方法，在预训练任务和两个下游应用中分别实现了 50.00%、23.16% 和 16.89% 的成功率。代码、数据和模型可在 https://github.com/JocelynSong/PPDiff 获取。
英文摘要：
Designing protein-binding proteins with high affinity is critical in biomedical research and biotechnology. Despite recent advancements targeting specific proteins, the ability to create high-affinity binders for arbitrary protein targets on demand, without extensive rounds of wet-lab testing, remains a significant challenge. Here, we introduce PPDiff, a diffusion model to jointly design the sequence and structure of binders for arbitrary protein targets in a non-autoregressive manner. PPDiffbuilds upon our developed Sequence Structure Interleaving Network with Causal attention layers (SSINC), which integrates interleaved self-attention layers to capture global amino acid correlations, k-nearest neighbor (kNN) equivariant graph layers to model local interactions in three-dimensional (3D) space, and causal attention layers to simplify the intricate interdependencies within the protein sequence. To assess PPDiff, we curate PPBench, a general protein-protein complex dataset comprising 706,360 complexes from the Protein Data Bank (PDB). The model is pretrained on PPBenchand finetuned on two real-world applications: target-protein mini-binder complex design and antigen-antibody complex design. PPDiffconsistently surpasses baseline methods, achieving success rates of 50.00%, 23.16%, and 16.89% for the pretraining task and the two downstream applications, respectively. The code, data and models are available at https://github.com/JocelynSong/PPDiff.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
