Multi-layer sequential network analysis improves protein 3D structural classification.
Multi-layer sequential network analysis improves protein 3D structural classification.
复制标题
DOI：
10.1002/prot.26349
复制
发表时间：
2022-09
影响因子：
2.9
通讯作者：
Milenkovic, Tijana
中科院分区：
文献类型：
--
作者：
Newaz, Khalique;Piland, Jacob;Clark, Patricia L.;Emrich, Scott J.;Li, Jun;Milenkovic, Tijana
蛋白质结构分类（PSC）是将蛋白质分配到预定义结构（例如，CATH或SCOPe）类别。我们最近提出了PSC方法，将蛋白质3D结构建模为蛋白质结构网络（PSN）并分析基于PSN的蛋白质特征，其表现优于或可与最先进的序列或其他基于3D结构的PSC方法相比。然而，现有的基于PSN的PSC方法将蛋白质的整个3D结构建模为静态（即，单层）PSN。因为蛋白质的折叠是一个动态过程，其中一些部分（即，由于蛋白质折叠的3D结构（子结构）先于其他折叠，因此将蛋白质的3D结构建模为捕获子结构的PSN可能进一步有助于改善现有PSC性能。在这里，我们建议将蛋白质的3D结构建模为近似蛋白质的3D子结构的多层顺序PSN，假设这将改进基于单层PSN的当前最先进的PSC方法（并且因此改进现有的最先进的序列和其他3D结构方法）。事实上，我们在72个数据集上证实了这一点，这些数据集涵盖了约44，000个CATH和SCOPe蛋白质结构域。
Protein structural classification (PSC) is a supervised problem of assigning proteins into pre-defined structural (e.g., CATH or SCOPe) classes based on the proteins’ sequence or 3D structural features. We recently proposed PSC approaches that model protein 3D structures as protein structure networks (PSNs) and analyze PSN-based protein features, which performed better than or comparable to state-of-the-art sequence or other 3D structure-based PSC approaches. However, existing PSN-based PSC approaches model the whole 3D structure of a protein as a static (i.e., single-layer) PSN. Because folding of a protein is a dynamic process, where some parts (i.e., sub-structures) of a protein fold before others, modeling the 3D structure of a protein as a PSN that captures the sub-structures might further help improve the existing PSC performance. Here, we propose to model 3D structures of proteins as multi-layer sequential PSNs that approximate 3D sub-structures of proteins, with the hypothesis that this will improve upon the current state-of-the-art PSC approaches that are based on single-layer PSNs (and thus upon the existing state-of-the-art sequence and other 3D structural approaches). Indeed, we confirm this on 72 datasets spanning ~44,000 CATH and SCOPe protein domains.
登录
查看更多内容
影响因子：
3.7
作者：
Milenković T;Filippis I;Lappe M;Przulj N
通讯作者：
Przulj N
影响因子：
3.7
作者：
Aparício D;Ribeiro P;Silva F
通讯作者：
Silva F
影响因子：
3.5
作者：
Figueroa RL;Zeng-Treitler Q;Kandula S;Ngo LH
通讯作者：
Ngo LH
影响因子：
4.6
作者：
Faisal FE;Newaz K;Chaney JL;Li J;Emrich SJ;Clark PL;Milenković T
通讯作者：
Milenković T
影响因子：
5.8
作者：
Aparicio, David;Ribeiro, Pedro;Silva, Fernando
通讯作者：
Silva, Fernando