標題: Prediction of Non-classical Secreted Proteins Using Informative Physicochemical Properties
作者: Hung, Chiung-Hui
Huang, Hui-Ling
Hsu, Kai-Ti
Ho, Shinn-Jang
Ho, Shinn-Ying
生物科技學系
生物資訊及系統生物研究所
Department of Biological Science and Technology
Institude of Bioinformatics and Systems Biology
關鍵字: amino acid index;non-classical secreted protein;SVM prediction
公開日期: 1-九月-2010
摘要: The prediction of non-classical secreted proteins is a significant problem for drug discovery and development of disease diagnosis. The characteristic of non-classical secreted proteins is they are leaderless proteins without signal peptides in N-terminal. This characteristic makes the prediction of non-classical proteins more difficult and complicated than the classical secreted proteins. We identify a set of informative physicochemical properties of amino acid indices cooperated with support vector machine (SVM) to find discrimination between secreted and non-secreted proteins and to predict non-classical secreted proteins. When the sequence identity of dataset was reduced to 25%, the prediction accuracy on training dataset is 85% which is much better than the traditional sequence similarity-based BLAST or PSI-BLAST tool. The accuracy of independent test is 82%. The most effective features of prediction revealed the fundamental differences of physicochemical properties between secreted and non-secreted proteins. The interpretable and valuable information could be beneficial for drug discovery or the development of new blood biochemical examinations.
URI: http://dx.doi.org/10.1007/s12539-010-0023-z
http://hdl.handle.net/11536/21951
ISSN: 1913-2751
DOI: 10.1007/s12539-010-0023-z
期刊: INTERDISCIPLINARY SCIENCES-COMPUTATIONAL LIFE SCIENCES
Volume: 2
Issue: 3
起始頁: 263
結束頁: 270
顯示於類別:期刊論文


文件中的檔案:

  1. 000208709200007.pdf

若為 zip 檔案,請下載檔案解壓縮後,用瀏覽器開啟資料夾中的 index.html 瀏覽全文。