蛋白质二级结构特征分析与相互作用预测计算机科学与技术专业论文.docxVIP

哈尔滨工业大学工学硕士学位论文 哈尔滨工业大学工学硕士学位论文 II II Abstract With the completion of the Human Genome Project, biology has now entered post genomics era marked by functional genomics. As an important research branch of post genomics era, proteomics plays a very important role since all kinds of biological processes or events need the participation of proteins or their interactions. With the advancement of protein sequencing technology, x-ray crystallography and function analysis method, a huge number of protein sequential, structural and functional data are generated. This provides us a new chance to use data -driven technology, such as machine learning and data mining, to predict protein structure and function automatically. This paper makes deep research into several key issues in proteomics by using methods of machine learning. The main content of this thesis includes the following parts: First, this paper analyzes the characteristic properties of protein sequences that will be used in prediction, including the physical and chemical characteristics of amino acids as well as the composition and location features of amino acids, constructs a protein pattern dictionary similar to human la nguage dictionary for each species by using pattern discovery algorithm, assigns related secondary structure information to each word in protein pattern dictionary, and makes segmentation for protein sequences that will be predicted by using least sub -word idea and word gridding technology according to the words in pattern dictionary. Secondly, a prediction method based on protein pattern dictionary is proposed for solving the protein secondary structure prediction (PSSP) problem. And in accordance with the physical and chemical characteristics of amino acids this paper builds physical and chemical characteristics template to cover the unknown word in dictionary, and then uses Maximum Entropy model to find the best secondary structure sequence for each protein sequence. Thi