A study on predicting patterns over the protein sequence datasets using association rule mining

Data Mining has recently increased its popularity of solving crucial problems in the field of biological science. Nowadays a large quantity of data and information about biological issues and its environments has been accessed by individual, organization, business, family or institution. A critical problem in biological data analysis is to classify the biological sequences and structures based on their critical features and functions. Protein is one among the important factor and acts as the constituents of all living organisms. Protein plays the most predominant role for causing viral diseases like viral fever, fluid diseases, poliomyelitis, hepatitis, swine flu, tumor, etc. The proposed system focus onto discover the most dominating amino acids which causes the chromaffin tumor. Finally the dominating patterns were predicted from a clustered protein sequence Succinate dehydrogenase - DHSB_HUMAN protein chain with 100% confidence threshold and the results were quite promising in the field of bio-medicine