期刊文献+
任意字段
题名或关键词
题名
关键词
文摘
作者
第一作者
机构
刊名
分类号
参考文献
作者简介
基金资助
栏目信息

基于多特征与多分类器融合的PPIE方法 被引量：1

Protein-protein Interaction Extraction Method Based on Multiple Features and Multiple Classifiers Fusion
下载PDF
导出
摘要 从生物医学文献中自动地抽取蛋白质相互作用(PPI)关系是文本挖掘的一项重要任务。考虑到特征和分类器的选择对于PPI任务的重要性,提出一种基于丰富特征和多分类器融合的蛋白质关系抽取方法。选取15种词法、句法及语义特征,融合3种分类器,采用文档级别的10倍交叉验证方法,在5个公开的PPI基准语料上进行评估实验,结果表明,该方法在AIMed语料上取得的F值和AUC值分别为63.7%和87.8%,具有良好的抽取性能。 Automatically extracting Protein-protein Interaction（PPI） from biomedical literature is a significant task in text mining. Considering the choice of features and the selection of classifier is of great importance for Protein-protein Interaction Extraction（PPIE） task, this paper proposes a method to combine various features and multiple classifiers, Fifteen lexical, syntactic and semantic features, three kinds of classifiers and the standard ten-fold document level crossvalidation evaluation method are used to evaluate on the five public PPI corpuses, and results show that the method achieves the preferable F-score（63.7% ） and AUC-score（ 87. 8% ） on the AIMed corpus which is on the top of the PPI extraction task, and it has better extraction performance.
作者 王健 刘敏捷 林鸿飞
机构地区 大连理工大学计算机科学与技术学院
出处 《计算机工程》 CAS CSCD 北大核心 2015年第11期207-212,共6页 Computer Engineering
基金 国家自然科学基金资助项目(61340020)
关键词 蛋白质相互作用关系抽取 丰富特征 支持向量机 最大熵 图核 Protein-protein Interaction Extraction （ PPIE ） rich features Support Vector Machine （ SVM ） maximum entropy graph kernel
分类号 TP391 [自动化与计算机技术—计算机应用技术]
  • 相关文献

参考文献17

  • 1Pyysalo S, Ginter F, Heimonen J, et al. Biolnfer: A Corpus for Information Extraction in the Biomedical Domain [ J ]. BMC Bioinformatics, 2007,8 ( 1 ) : 50.
  • 2Bunescu R, Ge R, Kate R J, et al. Comparative Experiments on Learning Information Extractors for Proteins and Their Interactions [J]. Artificial Intelligence in Medicine, 2005,33 ( 2 ) : 139-155.
  • 3Ding J,Berleant D, Nettleton D, et al. Mining Medline: Abstracts, Sentences, or Phrases [ C ]//Proceedings of IEEE Symposium on Biocomputing. Washington D. C. , USA : IEEE Press, 2002 : 326-337.
  • 4Fundel K, Kiiffner R, Zimmer R. RelEx-relation Extra- ction Using Dependency Parse Trees [J]. Bioinformatics,2007,23 (3) :365-371.
  • 5Nadellec C. Learning Language in Logic-genic Inter- action Extraction Challenge[ C ]//Proceedings of the 4th IEEE Learning Language in Logic Workshop. Washington D. C. , USA : IEEE Press ,2005:216-222.
  • 6Bunescu R,Mooney R, Ramani A, et al. Integrating Coo- ccurrence Statistics with Information Extraction for Robust Retrieval of Protein Interactions from Medline[C]//Pro- ceedings of Workshop on Linking Natural Language Pro- cessing and Biology. [ S. 1. ]:Association for Comput- ational Linguistics ,2006:49-56.
  • 7Fundel K, Ktiffner R, Zimmer R. RelEx Relation Extraction Using Dependency Parse Trees [J]. Bioinformatics ,2007,23 ( 3 ) :365-371.
  • 8Qian L, Zhou G. Tree Kernel-based Protein-protein Interaction Extraction from Biomedical Literature [ J ]. Journal of Biomedical Informatics, 2012, .45 ( 3 ) : 535 -543.
  • 9Qian W, Fu C, Cheng H. Semi-supervised Method for Extraction of Protein-protein Interactions Using Hybrid Model [ C ]//Proceedings of ISDEA '13. Washington D. C. , USA :IEEE Press ,2013 : 1268-1271.
  • 10Airola A, Pyysalo S, Bjarne J, et al. All-paths Graph Kernel for Protein-protein Interaction Extraction with Evaluation of Cross-corpus Learning [ J ]. BMC Bioinformatics ,2008,9 ( 11 ).

二级参考文献13

  • 1ZANZONI A,MONTECCHI-PALAZZI L,QUONDAM M,et al.MINT:A molecular INTeraction database[J].FEBS Letters,2002,513(1):135-140.
  • 2BADER G,BETEL D,HOGUE C.Bind—the biomolecular interac-tion network database[J].Nucleic Acids Research,2003,31(1):248-250.
  • 3XENARIOS I,RICH D W,SALWINSKI L,et al.DIP:The data-base of interacting proteins[J].Nucleic Acids Research,2000,28(1):289-291.
  • 4BUNESCU R,MOONEY R,RAMANI A.Integrating co-occurrencestatistics with information extraction for robust retrieval of protein in-teractions from Medline[C]//BioNLP'06:Proceedings of the Work-shop on Linking Natural Language Processing and Biology:TowardsDeeper Biological Literature Analysis.Stroudsburg:Association forComputational Linguistics,2006:49-56.
  • 5FUNDEL K,KUFFER R,ZIMMER R.RelEx-relation extraction u-sing dependency parse trees[J].Bioinformatics,2006,23(3):365–371.
  • 6NIELSEN L A.Extracting protein-protein interactions using simplecontextual features[C]//BioNLP'06:Proceedings of the Workshopon Linking Natural Language Processing and Biology:Towards Dee-per Biological Literature Analysis.Stroudsburg:Association forComputational Linguistics,2006:120-121.
  • 7MIYAO Y,SAETRE R,SAGAE K,et al.Task-oriented evaluationof syntactic parsers and their representations[EB/OL].[2011-05-01].http://www.aclweb.org/anthology-new/P/P08/P08-1006.pdf.
  • 8BUNESCU R C,MOONEY R J.A shortest path dependency kernelfor relation extraction[C]//HLT'05:Proceedings of the Conferenceon Human Language Technology and Empirical Methods in NaturalLanguage Processing.Stroudsburg:Association for ComputationalLinguistics,2005:724-731.
  • 9AIROLA A,PYYSALO S,BJRNE J,et al.All-paths graph ker-nel for protein-protein interaction extraction with evaluation of cross-corpus learning[J].BMC Bioinformatics,2008,9(Suppl 11):S2.
  • 10MIWA M,STRE R,MIYAO Y,et al.Protein-protein interactionextraction by leveraging multiple kernels and parsers[J].Interna-tional Journal of Medical Informatics,2009,78(12):39-46.

共引文献1

同被引文献4

引证文献1

二级引证文献3

计算机工程
2015年 第11期

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部