Research Of Promoter Recognition Using The Rough Set Theory

The application of rough set theory to the field of bioinformatics has been the hot area for researchers since the end of last century. The rough set theory is just provided with the problem,and it is applied into bioinformatics extensively more and more,it is applied into many fields extensively, such as artificial intelligence, discovery of knowledge and data,identify and class of mode, fault detecting and so on, it can analyze imprecise,inconsistent, incomplete and any other various imperfect informations. recognition is an important research subject in the field of bioinformatics. Promoter is a DNA area which is very important to control and adjust transcribing. The research of its configuration to the gene expression model, the gene adjustable network and the cell variance is extremely valuable.So,how to identify promoter and find information contained by these promoter accurately and quickly from gene group will become tremendously significative.The thesis analysised and researched the basic concept related to rough set theory and the currrent research situation of the computer promoter recognition technology. Then the thesis went on to figutre out the method of applying rough set theory to promoter recognition technology, researched the improvement of current promoter recognition technology using rough set theory, from the perspective of knowledge dependence, calculated the dependence of transcription factor binding sites using konwledge dependence, laid the foundation for promoter recognition technology in the future.Then the thesis analysised and researched the transcription factor binding sites sequence, analysised the methods using rough set theory of treating incomplete information system firstly, then pretreated the sequences using attribute importance, provided facilitation of promoter recognition using rough set theory for the future.On the basis of the sequence pretreating and the calculating of sites dependence, proposed a promoter recognition method based on rough set theory, resolved the problem of current promoter recognition technology that considered the transcription factor binding sites individually.By collecting the promoter sequences, then this thesis verificated the method using experiment, tested the effectiveness of the method using related datas. The result of the experiment proved that the method this thesis proposed can recognised promoter well.