English  |  正體中文  |  简体中文  |  Items with full text/Total items : 28588/40619
Visitors : 4200559      Online Users : 62
RC Version 4.0 © Powered By DSPACE, MIT. Enhanced by NTU Library IR team.
Scope Adv. Search

Please use this identifier to cite or link to this item: http://ntour.ntou.edu.tw:8080/ir/handle/987654321/18169

Title: 基於支持向量機及物理化學性質為基礎的線性抗原預測系統
Linear Epitope Prediction Based on Support Vector Machine and Propensity Scale Method
Authors: Ya-Chi Lin
Contributors: NTOU:Department of Computer Science and Engineering
Keywords: 線性抗原決定基;物理化學性質;胺基酸片段;支持向量機
Linear Epitope;physico-chemical property;amino acid pair;SVM
Date: 2010
Issue Date: 2011-07-04
Abstract: B細胞抗原決定基在設計開發疫苗和誘生抗體反應的研究上扮演相當重要的角色。以生物實驗直接辨識蛋白質分子中抗原決定基的位置相當耗時且需要大量的實驗資源,所以透過資訊技術開發具有高度正確預測率的工具,可加速提高生物實驗的成功機率,但是至今卻仍然具有相當的挑戰性。本論文提出一套有效改善機制,針對僅以物理化學特性為基礎的線性抗原決定基預測系統,額外使用長度從2到4個經實驗確認具有抗原特性的胺基酸片段做為支持向量機(Support Vector Machine)的特徵值,以提升對線性抗原決定基預測的正確率。本論文使用常見的抗原決定基資料集來進行驗證,並同時與其他方法的預測結果進行比較。依據實驗結果顯示,本論文所提出的方法與原來僅使用抗原特徵的預測系統相比,對與HIV抗原相關測試資料集的平均預測正確率提升11.6%,平均馬修相關係數也提升15.1%;對Pellequer測試資料集而言,整體的平均預測正確率改善3%,平均馬修相關係數提升4.1%;對AntiJen測試資料集而言,整體的平均預測正確率改善19.6%,平均馬修相關係數提升9.2%。本研究亦針對近年來所發表的論文蒐錄一組新的測試資料集,對該資料集而言,整體的平均預測正確率改善12.7%,平均馬修相關係數提升10.1%。若與其他知名的線性抗原決定基預測系統比較,對上述不同的抗原決定基資料集進行預測,本系統在平均識別度、平均正確率、平均陽性預測值及平均馬修相關係數的表現都分別優於其他系統。
B-cell epitopes play an important role for developing synthetic peptide vaccines and inducing antibody responses. Applying biological experiments for epitope identification is time consuming and demands a lot of experimental resources. Therefore, it is useful yet challenging design for a linear epitope prediction system with high prediction rates through computational approaches. In this thesis, a combinatorial mechanism based on physico-chemical properties and SVM (Support Vector Machine) techniques for linear epitope prediction is proposed. A collected set of verified epitope and non-epitope segments ranging from 2 to 4 amino acids were trained and applied as the features of SVM. The proposed methodology was evaluated by released epitope databases and compared with other existing linear epitope prediction methods. As the result, for the HIV related antigens, the average prediction accuracy of the proposed method is 67.1% and the average Matthews correlation coefficient is 0.282. For the Pellequer related antigens, the average prediction accuracy is 60.1% and the average Matthews correlation coefficient is 0.216. For the AntiJen related antigens, the average prediction accuracy is 67.6% and the average Matthews correlation coefficient by 0.113. Furthermore, several recent published epitope related papers were collected as a new testing dataset, and for this dataset, the average prediction accuracy of the proposed method is 60.9%, and the average Matthews correlation coefficient is 0.106. In comparison with four well-known prediction systems, the experimental results have shown that our proposed method mostly outperform all other systems in terms of specificity, accuracy, positive predictive value, and Matthews correlation coefficient for all different datasets.
URI: http://ethesys.lib.ntou.edu.tw/cdrfb3/record/#G0M98570005
Appears in Collections:[資訊工程學系] 博碩士論文

Files in This Item:

File Description SizeFormat

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


著作權政策宣告: 本網站之內容為國立臺灣海洋大學所收錄之機構典藏,無償提供學術研究與公眾教育等公益性使用,請合理使用本網站之內容,以尊重著作權人之權益。
網站維護: 海大圖資處 圖書系統組
DSpace Software Copyright © 2002-2004  MIT &  Hewlett-Packard  /   Enhanced by   NTU Library IR team Copyright ©   - Feedback