用于蛋白质适应度预测的多尺度表征学习
Multi-Scale Representation Learning for Protein Fitness Prediction
AI总结：
本文提出S3F多尺度多模态框架，融合蛋白质语言模型序列表征与编码主链、表面拓扑的GVP网络，在ProteinGym的217个DMS实验上达到SOTA适应度预测。
摘要：
设计新型功能蛋白质关键取决于准确建模其适应度景观。鉴于湿实验获得的功能注释有限，以往方法主要依赖在大量无标注蛋白质序列或结构数据集上训练的自监督模型。早期蛋白质表征学习研究仅关注序列或结构特征，而近期混合架构试图融合这些模态以利用各自优势。然而，与领先的纯序列方法相比，这些序列-结构模型迄今仅取得渐进式改进，凸显了有效协同利用这些模态方面尚未解决的挑战。此外，某些蛋白质的功能高度依赖其表面拓扑的细粒度特征，而这些特征此前被模型忽视。为应对这些局限，我们提出 Sequence-Structure-Surface Fitness（S3F）模型——一个整合多个尺度蛋白质特征的新型多模态表征学习框架。我们的方法将蛋白质语言模型得到的序列表征，与编码蛋白质主链及精细表面拓扑的 Geometric Vector Perceptron 网络相结合。所提方法在包含217个替换深度突变扫描实验的 ProteinGym 基准上取得最先进的适应度预测性能，并为理解决定蛋白质功能的因素提供洞见。代码位于 https://github.com/DeepGraphLearning/S3F。
英文摘要：
Designing novel functional proteins crucially depends on accurately modeling their fitness landscape. Given the limited availability of functional annotations from wet-lab experiments, previous methods have primarily relied on self-supervised models trained on vast, unlabeled protein sequence or structure datasets. While initial protein representation learning studies solely focused on either sequence or structural features, recent hybrid architectures have sought to merge these modalities to harness their respective strengths. However, these sequence-structure models have so far achieved only incremental improvements when compared to the leading sequence-only approaches, highlighting unresolved challenges effectively leveraging these modalities together. Moreover, the function of certain proteins is highly dependent on the granular aspects of their surface topology, which have been overlooked by prior models. To address these limitations, we introduce the Sequence-Structure-Surface Fitness (S3F) model - a novel multimodal representation learning framework that integrates protein features across several scales. Our approach combines sequence representations from a protein language model with Geometric Vector Perceptron networks encoding protein backbone and detailed surface topology. The proposed method achieves state-of-the-art fitness prediction on the ProteinGym benchmark encompassing 217 substitution deep mutational scanning assays, and provides insights into the determinants of protein function. Our code is at https://github.com/DeepGraphLearning/S3F.
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。
