利用生醫知識資料庫探索文獻中的資訊

Abstract

近年來由於生物醫學相關的研究迅速的發展，以及資訊科技發達的影響下， 生物醫學界每天都有大量資訊的電子文件刊登於各種不同的期刊上，然而要從數 量龐大且複雜的生物醫學文獻資料中找出特定且對於研究人員有意義的資訊可 以說是非常重要但卻不容易的事情，倘若能減少研究人員對於這些生醫文獻資料 處理所花費的時間，也就是間接的節省人力、物力以及時間，因此，如何從文獻 中擷取出相關的知識將是一個重要的課題。 對於生物醫學文獻的處理以及知識的擷取，若只依賴傳統的文件探勘技術， 是無法讓此研究有效地運行，因此本研究將導入專家彙整的生醫知識資料庫，包 含了Gene Ontology 資料庫以及BIOBASE TRANSPATH 資料庫，藉由生醫知識 資料庫的輔助，進而從生物醫學文獻中擷取相關的資訊並加以處理與呈現，並且 設計一個圖形化使用者介面系統，讓研究人員透過簡單的操作方式，即可萃取出 存在於單篇文獻或某一主題中的重要資訊。最後並以在Pubmed/MEDLINE 中有 關VEGF 基因的醫學文獻以及VEGF 交互作用網路圖來驗證本系統，驗證結果 確實可行，對於研究人員有所幫助。

Under the influence of the rapid development of biomedical research and information technology in these years, biomedical circles have numerous e-documents published in various periodicals everyday; however, it is very important but difficult to find specific and meaningful information for researchers from numerous and complicated biomedical literatures. Therefore, if the processing time of these literatures by the researchers could be reduced, it is to save human resources, material and time indirectly; thus how to extract relevant knowledge from documents will certainly become the key of the problem. For knowledge and information retrieval process in Biomedical literature, If we make use of traditional data mining techniques without the help of expert knowledge to extract the information in the biomedical literature. It may lead to the study can not be effectively run. Therefore, this study will be imported experts pooled biomedical knowledge database includes the Gene Ontology database and BIOBASE TRANSPATH database. we retrieve relevant information from the biomedical literature by the auxiliary of biomedical knowledge database. Then we process and design a graphical user interface system present these relevant information.This system can help researchers to extract the important information in single literatures or certain topic through easy operation. Finally we verify this system by the biomedical literatures relevant to VEGF gene in PubMed/MEDLINE and VEGF interaction network. The verified results are true and feasible,and helpful to researchers.