从蛋白质相互作用网络和基因本体论进行蛋白质注释。
Protein annotation from protein interaction networks and Gene Ontology.
机构信息
Centre for Diabetes Research, The Western Australian Institute for Medical Research, Australia.
出版信息
J Biomed Inform. 2011 Oct;44(5):824-9. doi: 10.1016/j.jbi.2011.04.010. Epub 2011 May 6.
Abstract
We introduce a novel method for annotating protein function that combines Naïve Bayes and association rules, and takes advantage of the underlying topology in protein interaction networks and the structure of graphs in the Gene Ontology. We apply our method to proteins from the Human Protein Reference Database (HPRD) and show that, in comparison with other approaches, it predicts protein functions with significantly higher recall with no loss of precision. Specifically, it achieves 51% precision and 60% recall versus 45% and 26% for Majority and 24% and 61% for χ²-statistics, respectively.
摘要
我们介绍了一种新的蛋白质功能注释方法，该方法结合了朴素贝叶斯和关联规则，并利用蛋白质相互作用网络中的底层拓扑结构和基因本体论中的图结构。我们将该方法应用于人类蛋白质参考数据库（HPRD）中的蛋白质，并表明与其他方法相比，它可以以更高的召回率预测蛋白质功能，而不会降低精度。具体来说，它的精度为 51%，召回率为 60%，而多数法的精度为 45%，召回率为 26%；χ²统计量的精度为 24%，召回率为 61%。
相似文献
1
Protein annotation from protein interaction networks and Gene Ontology.从蛋白质相互作用网络和基因本体论进行蛋白质注释。
J Biomed Inform. 2011 Oct;44(5):824-9. doi: 10.1016/j.jbi.2011.04.010. Epub 2011 May 6.
2
Detecting Essential Proteins Based on Network Topology, Gene Expression Data, and Gene Ontology Information.基于网络拓扑、基因表达数据和基因本体论信息检测必需蛋白质。
IEEE/ACM Trans Comput Biol Bioinform. 2018 Jan-Feb;15(1):109-116. doi: 10.1109/TCBB.2016.2615931. Epub 2016 Oct 7.
3
Heterogeneous data integration by tree-augmented naïve Bayes for protein-protein interactions prediction.基于树增强朴素贝叶斯的异质数据集成在蛋白质-蛋白质相互作用预测中的应用。
Proteomics. 2013 Jan;13(2):261-8. doi: 10.1002/pmic.201200326. Epub 2012 Dec 3.
4
Predicting Essential Proteins by Integrating Network Topology, Subcellular Localization Information, Gene Expression Profile and GO Annotation Data.通过整合网络拓扑结构、亚细胞定位信息、基因表达谱和 GO 注释数据预测必需蛋白。
IEEE/ACM Trans Comput Biol Bioinform. 2020 Nov-Dec;17(6):2053-2061. doi: 10.1109/TCBB.2019.2916038. Epub 2020 Dec 8.
5
MetaGO: Predicting Gene Ontology of Non-homologous Proteins Through Low-Resolution Protein Structure Prediction and Protein-Protein Network Mapping.MetaGO：通过低分辨率蛋白质结构预测和蛋白质-蛋白质网络映射预测非同源蛋白质的基因本体论。
J Mol Biol. 2018 Jul 20;430(15):2256-2265. doi: 10.1016/j.jmb.2018.03.004. Epub 2018 Mar 10.
6
An Integrated Framework for Functional Annotation of Protein Structural Domains.蛋白质结构域功能注释的综合框架
IEEE/ACM Trans Comput Biol Bioinform. 2015 Jul-Aug;12(4):902-13. doi: 10.1109/TCBB.2015.2389213.
7
Bayesian Markov Random Field analysis for protein function prediction based on network data.基于网络数据的蛋白质功能预测的贝叶斯马尔可夫随机场分析。
PLoS One. 2010 Feb 24;5(2):e9293. doi: 10.1371/journal.pone.0009293.
8
An improved method for scoring protein-protein interactions using semantic similarity within the gene ontology.一种利用基因本体论中的语义相似度来改进蛋白质-蛋白质相互作用评分的方法。
BMC Bioinformatics. 2010 Nov 15;11:562. doi: 10.1186/1471-2105-11-562.
9
Annotating proteins by mining protein interaction networks.通过挖掘蛋白质相互作用网络对蛋白质进行注释。
Bioinformatics. 2006 Jul 15;22(14):e260-70. doi: 10.1093/bioinformatics/btl221.
10
Topology-function conservation in protein-protein interaction networks.蛋白质-蛋白质相互作用网络中的拓扑结构-功能保守性
Bioinformatics. 2015 May 15;31(10):1632-9. doi: 10.1093/bioinformatics/btv026. Epub 2015 Jan 20.
引用本文的文献
1
Diversity and genomics of giant viruses in the North Pacific Subtropical Gyre.北太平洋亚热带环流中巨型病毒的多样性与基因组学
Front Microbiol. 2022 Nov 25;13:1021923. doi: 10.3389/fmicb.2022.1021923. eCollection 2022.
2
Gene Ontology Capsule GAN: an improved architecture for protein function prediction.基因本体胶囊生成对抗网络：一种用于蛋白质功能预测的改进架构。
PeerJ Comput Sci. 2022 Aug 15;8:e1014. doi: 10.7717/peerj-cs.1014. eCollection 2022.
3
SIN-3 functions through multi-protein interaction to regulate apoptosis, autophagy, and longevity in Caenorhabditis elegans.SIN-3 通过多蛋白相互作用调节秀丽隐杆线虫的细胞凋亡、自噬和寿命。
Sci Rep. 2022 Jun 22;12(1):10560. doi: 10.1038/s41598-022-13864-0.
4
SDN2GO: An Integrated Deep Learning Model for Protein Function Prediction.SDN2GO：一种用于蛋白质功能预测的集成深度学习模型。
Front Bioeng Biotechnol. 2020 Apr 29;8:391. doi: 10.3389/fbioe.2020.00391. eCollection 2020.
5
Characterizing Cancer Drug Response and Biological Correlates: A Geometric Network Approach.表征癌症药物反应和生物学相关性：一种几何网络方法。
Sci Rep. 2018 Apr 23;8(1):6402. doi: 10.1038/s41598-018-24679-3.
6
Insights from the protein-protein interaction network analysis of Mycobacterium tuberculosis toxin-antitoxin systems.结核分枝杆菌毒素-抗毒素系统的蛋白质-蛋白质相互作用网络分析见解
Bioinformation. 2017 Nov 30;13(11):380-387. doi: 10.6026/97320630013380. eCollection 2017.
7
DeepGO: predicting protein functions from sequence and interactions using a deep ontology-aware classifier.DeepGO：使用深度本体感知分类器从序列和相互作用预测蛋白质功能。
Bioinformatics. 2018 Feb 15;34(4):660-668. doi: 10.1093/bioinformatics/btx624.
8
Improving protein function prediction using domain and protein complexes in PPI networks.利用蛋白质-蛋白质相互作用网络中的结构域和蛋白质复合物改进蛋白质功能预测
BMC Syst Biol. 2014 Mar 24;8:35. doi: 10.1186/1752-0509-8-35.
本文引用的文献
1
GOPred: GO molecular function prediction by combined classifiers.GOPred：基于组合分类器的 GO 分子功能预测。
PLoS One. 2010 Aug 31;5(8):e12382. doi: 10.1371/journal.pone.0012382.
2
Predicting protein functions by relaxation labelling protein interaction network.通过弛豫标记蛋白质相互作用网络预测蛋白质功能。
BMC Bioinformatics. 2010 Jan 18;11 Suppl 1(Suppl 1):S64. doi: 10.1186/1471-2105-11-S1-S64.
3
A hub-attachment based method to detect functional modules from confidence-scored protein interactions and expression profiles.基于枢纽附着的方法，从置信评分的蛋白质相互作用和表达谱中检测功能模块。
BMC Bioinformatics. 2010 Jan 18;11 Suppl 1(Suppl 1):S25. doi: 10.1186/1471-2105-11-S1-S25.
4
The IntAct molecular interaction database in 2010.2010 年的 IntAct 分子相互作用数据库。
Nucleic Acids Res. 2010 Jan;38(Database issue):D525-31. doi: 10.1093/nar/gkp878. Epub 2009 Oct 22.
5
Structural relationships among proteins with different global topologies and their implications for function annotation strategies.具有不同整体拓扑结构的蛋白质之间的结构关系及其对功能注释策略的影响。
Proc Natl Acad Sci U S A. 2009 Oct 13;106(41):17377-82. doi: 10.1073/pnas.0907971106. Epub 2009 Sep 24.
6
How and when should interactome-derived clusters be used to predict functional modules and protein function?应当如何以及何时使用互作组学衍生的聚类来预测功能模块和蛋白质功能？
Bioinformatics. 2009 Dec 1;25(23):3143-50. doi: 10.1093/bioinformatics/btp551. Epub 2009 Sep 21.
7
Predicting protein function by frequent functional association pattern mining in protein interaction networks.通过蛋白质相互作用网络中的频繁功能关联模式挖掘预测蛋白质功能。
IEEE Trans Inf Technol Biomed. 2010 Jan;14(1):30-6. doi: 10.1109/TITB.2009.2028234. Epub 2009 Sep 1.
8
Global functional atlas of Escherichia coli encompassing previously uncharacterized proteins.包含此前未被鉴定蛋白质的大肠杆菌全功能图谱。
PLoS Biol. 2009 Apr 28;7(4):e96. doi: 10.1371/journal.pbio.1000096.
9
High-quality binary protein interaction map of the yeast interactome network.酵母相互作用组网络的高质量二元蛋白质相互作用图谱。
Science. 2008 Oct 3;322(5898):104-10. doi: 10.1126/science.1158684. Epub 2008 Aug 21.
10
ClusFCM: an algorithm for predicting protein functions using homologies and protein interactions.ClusFCM：一种利用同源性和蛋白质相互作用预测蛋白质功能的算法。
J Bioinform Comput Biol. 2008 Feb;6(1):203-22. doi: 10.1142/s0219720008003333.
Zotero 插件