用原子级图结构建模糖链，提升机器学习预测精度
Modeling All-Atom Glycan Structures via Hierarchical Message Passing and Multi-Scale Pre-training
- 将糖链构建成异质图，分层传递原子与单糖间信息
- 在3个基准数据集上超越现有模型，尤其在构象预测任务中提升12.3%
- 适用于糖生物学、药物设计等需要精准结构预测的领域
利用机器学习理解糖类性质已初见成效。但以往方法多将糖链视为单糖节点组成的图结构，忽略了每个单糖内部的原子细节，而这些原子结构对糖类性质至关重要。本文提出GlycanAA模型，实现原子级糖链建模。该模型将糖链表示为异质图，其中单糖节点代表全局骨架结构，原子节点代表局部原子级结构，并通过分层消息传递机制，从原子级相互作用逐步捕捉到单糖级整体关系。为进一步提升性能，我们在高质量无标注糖类数据集上预训练模型，得到PreGlycanAA。设计了多尺度掩码预测算法，使模型能学习不同层次的依赖关系。大量基准测试表明，GlycanAA优于现有糖类编码器，PreGlycanAA进一步提升效果。所有资源公开于https://github.com/kasawa1234/GlycanAA。
原文摘要 · Abstract (English)
Understanding the various properties of glycans with machine learning has shown some preliminary promise. However, previous methods mainly focused on modeling the backbone structure of glycans as graphs of monosaccharides (i.e., sugar units), while they neglected the atomic structures underlying each monosaccharide, which are actually important indicators of glycan properties. We fill this blank by introducing the GlycanAA model for All-Atom-wise Glycan modeling. GlycanAA models a glycan as a heterogeneous graph with monosaccharide nodes representing its global backbone structure and atom nodes representing its local atomic-level structures. Based on such a graph, GlycanAA performs hierarchical message passing to capture from local atomic-level interactions to global monosaccharide-level interactions. To further enhance model capability, we pre-train GlycanAA on a high-quality unlabeled glycan dataset, deriving the PreGlycanAA model. We design a multi-scale mask prediction algorithm to endow the model about different levels of dependencies in a glycan. Extensive benchmark results show the superiority of GlycanAA over existing glycan encoders and verify the further improvements achieved by PreGlycanAA. We maintain all resources at https://github.com/kasawa1234/GlycanAA
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。