基于文本挖掘的精子发生各阶段的相关基因蛋白名称提取.pdf

of Researchand Journal Development Computer 基于文本挖掘的精子发生各阶段的相关基因／蛋白名称提取 朱 俊1 殷建平1 赵志一匣1 祝 恩1 班荣军2 1(国防科学技术大学计算机学院长沙410073) 2(南京大学计算机科学与技术系南京 210093) 3(西昌卫星发射中心海南文昌 571300) (cqzhujun@126．corn) Extractionof NamesInvolvedinEach of Gene／Protein Stage onLiterature Based Mining Zhu Enl，andBan Junl～，Yin Rongjun2 Jianpin91，ZhaoZhihen91，Zhu 410073) UniversityofDefenseTechnology，Changsha 1(CollegeofComputer。National 210093) ofComputerScience＆Technology，NanjingUniversity，Nanjing 2(Department Launch 571300) Satellite 3(Xichang Center，Wenchang，Hainan Abstract isan inthelifetimeofmale has importantbioprocess Spermatogenesis effectonmammal’s isa causeofmale major infertility， deep reproduction．Abnormalspermatogenesis howevertreatmentsforthisare the involvedin limited．Characterizinggenes／proteins isfundamentaltOunderstandthemechanisms this andtO underlyingbiologicalprocess develop forthe in mostcrucialinformationof treatments problemsspermatogenesis．However， scattersinvastamountofresearcharticles，SO spermatogenesis—relatedgenes／proteins manually this novel is curationofthese couldbea task．Inpaper，a strategy genes／proteins time—consuming