Biomedical Text Mining and Its Applications 英文参考文献.docVIP

Education BiomedicalTextMiningandItsApplications RaulRodriguez-Esteban* PfizerResearchTechnologyCenter,Cambridge,Massachusetts,UnitedStatesofAmerica hu-berlin.de/,hakenber/links/benchmarks. MainConcepts html;/ccp/corpora/ obtaining.shtml). Before beginning a text mining task, it is advisable to limit the scopeofthetasktoacorpusmadeofaset ofdocumentsaroundthetopicofinterest. Inourcase,aPMLcorpuscouldcomprise alltheMedlineabstractsthatmentionthe term‘‘progressivemultifocalleukoenceph- alopathy,’’becausethisisanunambiguous term.Anotherrelevantcorpustoconsider could be the ImmunoTome [9], which is focusedonimmunology. Terms A term is a name used in a specific domain,andaterminologyisacollectionof terms. Terms abound in biomedical text, where they constitute important building blocks. Some examples of terms are the names of cell types, proteins, medical devices,diseases,genemutations,chemical names, and protein domains [7]. Due to theirimportance,textminershaveworked to design algorithms that recognize terms (see examples in Figure 1). The task of recognizingtermsisalsocallednamedentity recognition in the text mining literature, althoughthisNLPtaskisbroaderandgoes beyondrecognitionofterms.Althoughthe concept of term is intuitive (or, perhaps, because it is intuitive), terms are hard to defineprecisely[8].Forexample,thetext ‘‘earlyprogressivemultifocalleukoenceph- alopathy’’couldpossiblyrefertoany,orall, of these disease terms: ‘‘early progressive Introduction This tutorial is intended for biologists andcomputationalbiologistsinterestedin addingtextminingtoolstotheirbioinfor- maticstoolbox.Asanillustrativeexample, the tutorial examines the relationship between progressive multifocal leukoen- cephalopathy (PML) and antibodies. Re- centcasesofPMLhavebeenassociatedto the administration of some monoclonal antibodies such as efalizumab [1]. Those interestedinafurtherintroductiontotext mining may also want to read other reviews[2–4]. Textminersareinterested interminol- o