English  |  正體中文  |  简体中文  |  Items with full text/Total items : 26988/38789
Visitors : 2347615      Online Users : 31
RC Version 4.0 © Powered By DSPACE, MIT. Enhanced by NTU Library IR team.
Scope Adv. Search
LoginUploadHelpAboutAdminister

Please use this identifier to cite or link to this item: http://ntour.ntou.edu.tw:8080/ir/handle/987654321/49300

Title: 從序列預測蛋白質-蛋白質相互作用使用氨基酸的主要理化性質
Prediction of Protein-Protein Interactions from Sequence Using Principal Physicochemical Properties of Amino Acids
Authors: Chang, Chih-Kai
張智凱
Contributors: NTOU:Department of Computer Science and Engineering
國立臺灣海洋大學:資訊工程學系
Keywords: 蛋白質相互作用;蛋白質描述方法;胺基酸理化性質
protein-protein interaction prediction;protein description method;physicochemical properties of amino acids
Date: 2015
Issue Date: 2018-08-22T06:56:26Z
Abstract: 蛋白質相互作用在生物的生化功能上扮演極為重要的角色,幾乎主宰了所有活體細胞的生化反應。利用計算機預測蛋白質的相互作用在近幾年已是生物資訊學的熱門議題,原因在於透過實驗分析蛋白質相互作用過於昂貴以及耗時,計算機能夠快速的分析蛋白質間的相互作用。 胺基酸是蛋白質的基本組成單位,其理化性質影響著蛋白質的結構以及生物學的功能。因此在蛋白質相互作用的預測中考慮胺基酸的理化性質將有助於提高蛋白質相互作用的預測準確率。 在本篇論文中,我們提出了蛋白質相互作用預測系統,利用胺基酸的19種理化性質把蛋白質序列轉化成數值陣列,並且結合不同的蛋白質描述方法,將蛋白質相互作用對的數值陣列轉換成特徵向量,最後我們使用機器學習方法進行蛋白質間相互作用的分類預測。
Protein–protein interactions (PPIs), which play an important role in many biological processes, almost dominate the biochemical reactions in all living cells. The use of computer to predict PPIs can provide fast analysis and has become a hot topic of biological in recent years because the experimental analysis of PPIs is expensive and time consuming. The physicochemical properties of amino acids, which are the basic components of proteins, affect protein structure and biological function. Considering the physicochemical properties of amino acids in PPI prediction can help improve the prediction accuracy of PPIs. In this paper, we propose a PPI prediction system. We use 19 kinds of physicochemical properties of amino acids to transform the PPI pairs into numeric arrays. In addition, we combine difference protein description method to transform the numeric arrays into feature vectors. Finally, we use machine learning methods to classify protein-protein interactions.
URI: http://ethesys.lib.ntou.edu.tw/cgi-bin/gs32/gsweb.cgi?o=dstdcdr&s=G0010157049.id
http://ntour.ntou.edu.tw:8080/ir/handle/987654321/49300
Appears in Collections:[資訊工程學系] 博碩士論文

Files in This Item:

There are no files associated with this item.



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