Using Binary Variation Method for Predicting Protein SubChloroplast Locations Based on Evolution Information

• Main Authors: Ching-Hui Chiu, 裘靖慧
• Other Authors: Eric Y. T. Juan
• Format: Others
• Language: zh-TW
• Published: 2010
• Online Access: http://ndltd.ncl.edu.tw/handle/05977524757776607832

碩士 === 國立臺灣海洋大學 === 資訊工程學系 === 98 === Photosynthesis plays a critical role in carbon cycle and oxygen cycle on earth. Photosynthesis which occurs in plants, algae, and some species of bacteria is a complex set of processes converting carbon dioxide and water into organic compounds, especially sugars, using the energy from sunlight. Chloroplasts are organelles in plant cells and eukaryotic organisms that conduct photosynthesis and amino acid biosynthesis. Thus, it is significantly valuable for understanding the function of chloroplast proteins. Since the function of chloroplast proteins and their chloroplast locations are closely correlated, the knowledge of protein chloroplast locations can be very helpful in understanding their role in the biological processes. In this paper, we present a novel protein description method, binary variation method based on evolution information, to represent protein sequential evolution information. A prediction system for protein chloroplast locations is constructed based on the binary variation method and Support Vector Machines. The experimental results showed that the system is more reliable and stable and an effectively improves the prediction performance. The system may be beneficial to the chloroplast proteome study.