基于 RVM 集成学习的异质数据人类功能基因网络预测。
Prediction of human functional genetic networks from heterogeneous data using RVM-based ensemble learning.
机构信息
Department of Biomedical Engineering, University of Southern California, Los Angeles, 90089, USA.
出版信息
Bioinformatics. 2010 Mar 15;26(6):807-13. doi: 10.1093/bioinformatics/btq044. Epub 2010 Feb 4.
Abstract
MOTIVATION
Three major problems confront the construction of a human genetic network from heterogeneous genomics data using kernel-based approaches: definition of a robust gold-standard negative set, large-scale learning and massive missing data values.
RESULTS
The proposed graph-based approach generates a robust GSN for the training process of genetic network construction. The RVM-based ensemble model that combines AdaBoost and reduced-feature yields improved performance on large-scale learning problems with massive missing values in comparison to Naïve Bayes.
CONTACT
SUPPLEMENTARY INFORMATION
Supplementary material is available at Bioinformatics online.
摘要
动机
使用基于内核的方法从异构基因组学数据构建人类遗传网络时，面临三个主要问题：稳健的黄金标准负集的定义、大规模学习和大量缺失数据值。
结果
所提出的基于图的方法为遗传网络构建的训练过程生成了一个稳健的 GSN。与朴素贝叶斯相比，基于 RVM 的集成模型（结合了 AdaBoost 和降维特征）在具有大量缺失值的大规模学习问题上具有更好的性能。
联系人
补充信息
补充材料可在 Bioinformatics 在线获得。
相似文献
1
Prediction of human functional genetic networks from heterogeneous data using RVM-based ensemble learning.基于 RVM 集成学习的异质数据人类功能基因网络预测。
Bioinformatics. 2010 Mar 15;26(6):807-13. doi: 10.1093/bioinformatics/btq044. Epub 2010 Feb 4.
2
forgeNet: a graph deep neural network model using tree-based ensemble classifiers for feature graph construction.forgeNet：一种基于图的深度神经网络模型，使用基于树的集成分类器进行特征图构建。
Bioinformatics. 2020 Jun 1;36(11):3507-3515. doi: 10.1093/bioinformatics/btaa164.
3
MetaKTSP: a meta-analytic top scoring pair method for robust cross-study validation of omics prediction analysis.MetaKTSP：一种用于组学预测分析的稳健跨研究验证的元分析最高得分对方法。
Bioinformatics. 2016 Jul 1;32(13):1966-73. doi: 10.1093/bioinformatics/btw115. Epub 2016 Mar 2.
4
mRMRe: an R package for parallelized mRMR ensemble feature selection.mRMRe：一个用于并行化 mRMR 集成特征选择的 R 包。
Bioinformatics. 2013 Sep 15;29(18):2365-8. doi: 10.1093/bioinformatics/btt383. Epub 2013 Jul 3.
5
Semi-supervised multi-label collective classification ensemble for functional genomics.用于功能基因组学的半监督多标签集体分类集成方法
BMC Genomics. 2014;15 Suppl 9(Suppl 9):S17. doi: 10.1186/1471-2164-15-S9-S17. Epub 2014 Dec 8.
6
Modeling gene-wise dependencies improves the identification of drug response biomarkers in cancer studies.对基因层面的依赖性进行建模可改善癌症研究中药物反应生物标志物的识别。
Bioinformatics. 2017 May 1;33(9):1362-1369. doi: 10.1093/bioinformatics/btw836.
7
DrugE-Rank: improving drug-target interaction prediction of new candidate drugs or targets by ensemble learning to rank.DrugE-Rank：通过集成学习排序改进新候选药物或靶点的药物-靶点相互作用预测。
Bioinformatics. 2016 Jun 15;32(12):i18-i27. doi: 10.1093/bioinformatics/btw244.
8
LEARNING PARSIMONIOUS ENSEMBLES FOR UNBALANCED COMPUTATIONAL GENOMICS PROBLEMS.学习用于不平衡计算基因组学问题的简约集成方法。
Pac Symp Biocomput. 2017;22:288-299. doi: 10.1142/9789813207813_0028.
9
Positive-unlabeled ensemble learning for kinase substrate prediction from dynamic phosphoproteomics data.基于动态磷酸化蛋白质组学数据的激酶底物预测的正例-未标记样本集成学习
Bioinformatics. 2016 Jan 15;32(2):252-9. doi: 10.1093/bioinformatics/btv550. Epub 2015 Sep 22.
10
Network inference with ensembles of bi-clustering trees.基于二部聚类树集成的网络推断。
BMC Bioinformatics. 2019 Oct 28;20(1):525. doi: 10.1186/s12859-019-3104-y.
引用本文的文献
1
MoNETA: MultiOmics Network Embedding for SubType Analysis.MoNETA：用于亚型分析的多组学网络嵌入
NAR Genom Bioinform. 2024 Oct 16;6(4):lqae141. doi: 10.1093/nargab/lqae141. eCollection 2024 Sep.
2
Development and verification of a combined diagnostic model for primary Sjögren's syndrome by integrated bioinformatics analysis and machine learning.基于集成生物信息学分析和机器学习的原发性干燥综合征联合诊断模型的建立与验证。
Sci Rep. 2023 May 27;13(1):8641. doi: 10.1038/s41598-023-35864-4.
3
Machine learning: its challenges and opportunities in plant system biology.机器学习：在植物系统生物学中的挑战与机遇。
Appl Microbiol Biotechnol. 2022 May;106(9-10):3507-3530. doi: 10.1007/s00253-022-11963-6. Epub 2022 May 16.
4
Machine Learning for Integrating Data in Biology and Medicine: Principles, Practice, and Opportunities.用于整合生物学和医学数据的机器学习：原理、实践与机遇
Inf Fusion. 2019 Oct;50:71-91. doi: 10.1016/j.inffus.2018.09.012. Epub 2018 Sep 21.
5
Synstable Fusion: A Network-Based Algorithm for Estimating Driver Genes in Fusion Structures.Synstable 融合：一种用于估计融合结构中驱动基因的基于网络的算法。
Molecules. 2018 Aug 16;23(8):2055. doi: 10.3390/molecules23082055.
6
FusionPathway: Prediction of pathways and therapeutic targets associated with gene fusions in cancer.FusionPathway：预测癌症中基因融合相关的通路和治疗靶点。
PLoS Comput Biol. 2018 Jul 24;14(7):e1006266. doi: 10.1371/journal.pcbi.1006266. eCollection 2018 Jul.
7
A comparison of graph- and kernel-based -omics data integration algorithms for classifying complex traits.用于复杂性状分类的基于图和核的组学数据整合算法比较。
BMC Bioinformatics. 2017 Dec 6;18(1):539. doi: 10.1186/s12859-017-1982-4.
8
Identification of functional modules by integration of multiple data sources using a Bayesian network classifier.使用贝叶斯网络分类器整合多个数据源来识别功能模块。
Circ Cardiovasc Genet. 2014 Apr;7(2):206-17. doi: 10.1161/CIRCGENETICS.113.000087.
9
Identification of cancer fusion drivers using network fusion centrality.利用网络融合中心度识别癌症融合驱动因子。
Bioinformatics. 2013 May 1;29(9):1174-81. doi: 10.1093/bioinformatics/btt131. Epub 2013 Mar 16.
10
Systems genetics in "-omics" era: current and future development.“组学”时代的系统遗传学：现状与未来发展
Theory Biosci. 2013 Mar;132(1):1-16. doi: 10.1007/s12064-012-0168-x. Epub 2012 Nov 9.
本文引用的文献
1
Human Protein Reference Database--2009 update.人类蛋白质参考数据库——2009年更新版
Nucleic Acids Res. 2009 Jan;37(Database issue):D767-72. doi: 10.1093/nar/gkn892. Epub 2008 Nov 6.
2
Predicting co-complexed protein pairs from heterogeneous data.从异构数据中预测共复合蛋白质对。
PLoS Comput Biol. 2008 Apr 18;4(4):e1000054. doi: 10.1371/journal.pcbi.1000054.
3
NetworKIN: a resource for exploring cellular phosphorylation networks.NetworKIN：一个用于探索细胞磷酸化网络的资源。
Nucleic Acids Res. 2008 Jan;36(Database issue):D695-9. doi: 10.1093/nar/gkm902. Epub 2007 Nov 2.
4
COXPRESdb: a database of coexpressed gene networks in mammals.COXPRESdb：一个哺乳动物中共表达基因网络的数据库。
Nucleic Acids Res. 2008 Jan;36(Database issue):D77-82. doi: 10.1093/nar/gkm840. Epub 2007 Oct 11.
5
External validation of mathematical models to distinguish between benign and malignant adnexal tumors: a multicenter study by the International Ovarian Tumor Analysis Group.区分良性和恶性附件肿瘤的数学模型的外部验证：国际卵巢肿瘤分析小组的多中心研究
Clin Cancer Res. 2007 Aug 1;13(15 Pt 1):4440-7. doi: 10.1158/1078-0432.CCR-06-2958.
6
Reactome: a knowledge base of biologic pathways and processes.Reactome：生物通路和过程的知识库。
Genome Biol. 2007;8(3):R39. doi: 10.1186/gb-2007-8-3-r39.
7
Inferring genome-wide functional linkages in E. coli by combining improved genome context methods: comparison with high-throughput experimental data.通过结合改进的基因组上下文方法推断大肠杆菌全基因组功能联系：与高通量实验数据的比较
Genome Res. 2007 Apr;17(4):527-35. doi: 10.1101/gr.5900607. Epub 2007 Mar 5.
8
High-throughput electronic biology: mining information for drug discovery.高通量电子生物学：挖掘药物发现信息。
Nat Rev Drug Discov. 2007 Mar;6(3):220-30. doi: 10.1038/nrd2265.
9
PReMod: a database of genome-wide mammalian cis-regulatory module predictions.PReMod：一个全基因组哺乳动物顺式调控模块预测数据库。
Nucleic Acids Res. 2007 Jan;35(Database issue):D122-6. doi: 10.1093/nar/gkl879. Epub 2006 Dec 5.
10
Choosing negative examples for the prediction of protein-protein interactions.选择用于预测蛋白质-蛋白质相互作用的负样本。
BMC Bioinformatics. 2006 Mar 20;7 Suppl 1(Suppl 1):S2. doi: 10.1186/1471-2105-7-S1-S2.
Zotero 插件