Research Of Protein Secondary Structure Prediction Based On Genetic Algorithm

With the approach of post-genome era, proteomics is becoming an important research domain in the life science.Protein Secondary Structure Prediction (PSSP), with a long historic task, is still a challenge in the research of proteomics at present. Any new breakthrough in this area will be helpful to knowing better the function of protein and the human healthy or paroxysm cell constitutes. What is more, it will be an important assistant to some relevant industries such as medical engineering, agriculture, agbiotech, etc.Some works on the study of PSSP using the methods of data mining and the theory of bioinformatics are done in this thesis. Firstly, starting with the analysis of current bioinformatics in the field of PSSP and development status, we try to find out the difficulties faced and determine the direction of this study. Secondly, according to the hydrophobic nature of pro-amino acids, we use the very representative data from the current protein databases known, to create an effective model. By researching and analysising data mining techniques, such as Association Rules(AR), Genetic Algorithms(GA) and Simulated Annealing(SA), etc. we use Simple Genetic Algorithm(SGA) with AR to achieve the model rules mining and PSSP. At the same time, using the Simulated Annealing Genetic Algorithm(SAGA) into the PSSP model rules mining, can overcome this SGA most serious "premature convergence", and solve SA slow convergence and easy into local convergence.Finally, we design experiments to compare SGA model rules mining with SAGA model rules mining in PSSP, verifying algorithm to improve the effectiveness and accuracy.