原子级机器学习蛋白质 - 甘氨酸相互作用和在糖生物学中的交叉奇拉识别
Eric J Carpenter1, Chuanhao Peng1, Simatsidk Haregu1
1Department of Chemistry, University of Alberta, Edmonton, Alberta T6G 2G2, Canada.
Science advances
|December 5, 2025
概括
一个新的机器学习模型,MCNet,预测了糖甘蛋白相互作用,包括罕见的l-糖甘. 这有助于对当前和潜在的镜像生命形式中的生物分子相互作用的理解.
科学领域:
- 葡萄糖生物学 葡萄糖生物学
- 机器学习 机器学习
- 计算生物学 计算生物学
背景情况:
- 预测甘氨酸与蛋白质的相互作用对于理解生物过程至关重要.
- 现有的机器学习模型很难预测新型甘氨酸结构的特性,例如反体.
- 常见的甘氨酸的镜像形式的l-甘氨酸很少见,但与天体生物学和合成生物学有关.
研究的目的:
- 开发一种机器学习模型 (MCNet),能够预测糖结合蛋白 (GBPs) 和糖 (包括反体) 之间的定量相互作用.
- 通过利用原子级 glycan 描述,实现超出传统训练数据集范围的预测.
- 探索机器学习在预测与镜像生命形式相关的相互作用方面的潜力.
主要方法:
- 开发了MCNet,这是一个机器学习模型,利用原子级 glycan 描述.
- 经过训练的MCNet数据从糖甘微阵列和亲和度测量,通过一个"分数绑定"参数统一.
- 使用独立的甘氨酸和莱克阵列实验验验证的MCNet预测.
主要成果:
- MCNet准确地预测了GBP和常见的糖甘反体之间的定量相互作用,这些反体在培训数据中并不存在.
- 该模型发现了l-葡萄糖与糖结合的GBPs的意想不到的结合,这在实验中得到了证实.
- MCNet 证明了它能够推断出新型甘氨酸结构的特性.
结论:
- 在预测甘氨酸与蛋白质相互作用方面,MCNet代表了重大进步,克服了当前模型的局限性.
- 该模型能够预测与l-glycans的相互作用,为研究镜像生命形式开辟了新的途径.
- 像MCNet这样的机器学习方法准备扩大糖生物学和生物分子相互作用预测的边界.
相关概念视频
Protein Glycosylation
9.2K
Glycosylation, the most common post-translational modification for proteins, serves diverse functions. Adding sugars to proteins makes the proteins more resistant to proteolytic digestion. Glycosylated proteins can act as markers and receptors to promote cell-cell adhesion. Additionally, they have many essential quality control functions in the cell, such as correct protein folding and facilitating transport of misfolded proteins to the cytosol, which can be degraded.
Glycosylation occurs in...
Glycosylation occurs in...
9.2K
Oligosaccharide Assembly
3.5K
Protein glycosylation starts in the ER lumen and continues in the Golgi apparatus. Glycosyltransferases catalyze the addition of sugar molecules or glycosylation of proteins. Usually, these enzymes add sugars to the hydroxyl groups of selected serine or threonine residues to form O-linked glycans or the amino groups of asparagine residues to form N-linked glycans. Different positions on the same polypeptide chain can contain differently linked glycans.
Multiple sugar molecules that may or may...
Multiple sugar molecules that may or may...
3.5K
Protein-protein Interfaces
14.4K
Many proteins form complexes to carry out their functions, making protein-protein interactions (PPIs) essential for an organism's survival. Most PPIs are stabilized by numerous weak noncovalent chemical forces. The physical shape of the interfaces determines the way two proteins interact. Many globular proteins have closely-matching shapes on their surfaces, which form a large number of weak bonds. Additionally, many PPIs occur between two helices or between a surface cleft and a...
14.4K


