English  |  正體中文  |  简体中文  |  Items with full text/Total items : 90074/105197 (86%)
Visitors : 7153343      Online Users : 34
RC Version 6.0 © Powered By DSPACE, MIT. Enhanced by NTU Library IR team.
Scope Tips:
  • please add "double quotation mark" for query phrases to get precise results
  • please goto advance search for comprehansive author search
  • Adv. Search
    HomeLoginUploadHelpAboutAdminister Goto mobile version


    Please use this identifier to cite or link to this item: http://asiair.asia.edu.tw/ir/handle/310904400/9631


    Title: 疾病相關基因探勘與預測
    Authors: 陳士農
    Contributors: 資訊學院
    資訊傳播學系
    Keywords: 疾病相關基因;選擇性剪接;資料探勘;智慧型代理人;樣式選擇;樣式權重;資訊擷取
    disease-related gene;alternative splicing;data mining;intelligent agent;pattern selection;pattern weighting;information retrieval;An Integrated System for
    Date: 2007
    Issue Date: 2010-05-13 15:11:47 (UTC+8)
    Abstract: 在人類基因體計畫(Human Genome Project)完成定序後,越來越多的人投入生物資訊(Bioinformatics)的研究行列,不管是在序列的預測、藥物的研發或是疾病的治療等,都是重要的研究課題。本計畫提出一個疾病相關基因探勘與預測之整合系統,提供收集文獻資料並且提供查詢疾病相關基因的選擇性剪接(alternative splicing)資訊。本方法能提供生物醫學研究人員在生物實驗驗證時的相關資訊,縮短生物實驗驗證的時間。使用者可以輸入基因名稱(gene name)、去氧核醣核酸序列(DNA sequence),並選擇疾病相關基因的權重矩陣(weight matrix),經由系統分析與預測後,輸出疾病相關資訊,像是完整的基因序列、mRNA、內子(intron)、外子(exon)、選擇性剪接、摘要報告等,並以圖形介面輸出。
    利用關鍵字搜尋文獻的時候,有些人往往遭遇到對要找尋的內容不熟悉而無法給予重要的字詞作為關鍵字來搜尋的困境。在這個計畫中,我們提出一個『利用文件查詢』的方法,來幫助那些因為事先沒有概念去給定關鍵字來做文件搜尋的使用者。為了得到可信賴的搜尋結果,並且在短的回覆時間內完成查詢,所有的文件都事先根據具有適當權重的樣式來轉成向量,根據這些向量之間的距離來判斷相似度的大小,並且將相似度大於某個給定閥值的文件,依照相似度的大小排列出來。我們計畫選擇相關生物資訊的字辭,如基因或蛋白質的名稱,來做為代表性的樣式,並且根據這些樣式在原始文獻中的出現頻率分佈來調整其權重。
    After the Human Genome Project is completed, more and more researchers involve in the research of bioinformatics. No matter the prediction of sequence, research and development of medicine or treatment of the disease etc. are all important research subjects. This proposal proposes an integrated system for disease-related genes mining and prediction from biomedical literatures. This system can collect the biomedical literatures and query the alternative splicing information of disease-related genes. This research can provide the relevant information to the biologists and shorten the time for the verification of biological experiment. The user can input gene name, DNA sequence, any compound words, or documents, then select the weight matrix. After it is analyzed and predicted by the system, it can output the disease-related information, such as complete disease gene sequence, mRNA, intron, exon, alternative splicing, summary report, etc., and showed by the graphic interface.
    To use keywords search for literatures, someone might suffer from the difficulty that user must be somewhat familiar with the topics user concerning with such that user could specify the patterns (or terms) with highlight as keywords. In this proposal, we proposed document query to search literatures for the users who have no prior knowledge to specify keywords, but only with one document they is interesting. To achieve this goal with reliable search results and short response time for query processes, all of the documents are transformed as vectors according to selected patterns with proper weighting in advance. The similarities are evaluated by measuring the distance between the vectors. The documents will be ranked orderly according to the values of the similarities between them and the query document if the similarities are greater than a given threshold. We plan to select the related bioinformatics terms, such as genes or proteins names, as representative patterns and to tune their weighting according the statistics of frequency distribution of these patterns in the source literatures.
    Appears in Collections:[資訊傳播學系] 科技部研究計畫

    Files in This Item:

    File Description SizeFormat
    96 陳士農1.doc24KbMicrosoft Word766View/Open
    96 陳士農2.doc25KbMicrosoft Word435View/Open
    index.html0KbHTML221View/Open


    All items in ASIAIR are protected by copyright, with all rights reserved.


    DSpace Software Copyright © 2002-2004  MIT &  Hewlett-Packard  /   Enhanced by   NTU Library IR team Copyright ©   - Feedback