Comparisons of Different Feature Sets for Predicting Carbohydrate-Binding Proteins From Amino Acid Sequences Using Support Vector Machine

under my guidance and supervision and be accepted in partial fulfillment of the requirements for the degree of Master of Computer Science & Engineering. The research results presented in the thesis have not been included in any other paper submitted for any degree to any other University or Institute. It is understood that by this approval the undersigned do not necessarily endorse or approve any statement made, opinion expressed or conclusion drawn therein but approve the thesis only for the purpose for which it has been submitted. All information have been obtained and presented in accordance with academic rules and ethical conduct. I also declare that, as required by these rules and conduct, I have fully cited and referenced all materials and results that are not original to this work. Acknowledgement The main objective of this project is to predict the carbohydrate-binding proteins using efficient machine learning methods. During the period I have come to know various databases of proteins, tools and techniques for classification and related works. I would like to express my gratitude to Prof. Mita Nasipuri, for her valuable guidance, advice and supervision that have served as a pillar of strength and confidence throughout my M.E Thesis work. I am privileged to witness her enthusiastic and dedicated interest towards advanced research that motivates me and enriches my growth as a student and a researcher. I am indebted to her for her unflinching support and the innovative ideas and extraordinary experiences that she have shared with me during the course of this research. It is an honor for me to thank heartily to Prof Mahantapas Kundu of the Computer science and engineering Department, Jadavpur University whose truly scientific intuition and crucial contribution have paved the way towards successful execution of this research work. for his unsolicited help for any type of software related problems. I would also like to thank Smt. Piyali Chatterjee for her effective advices, during data collection process. I would like to extend my appreciation to my friends and seniors without whose support and cooperation, this thesis would never been possible. Last but not the least I would like to thank all my family members for giving me constant encouragement and mental support during my project work.