DOI: 10.21276/sjet

Pages: 335-339

Sequential rule mining is a fundamental technique of data mining which has many application one of which is in the area of bioinformatics. Bioinformatics is an application of information technology to store gigantic biological data in an organised way so that the data can easily be analysed. These biological data is in form of sequences of proteins and sequence analysis is one of the major research areas in bioinformatics. These Bioinformatics data are incremental datasets and at the present era of cheap information technology these bioinformatics data has become big data. Efficient mining of big data require parallel as well as iterative techniques. Here we propose a technique to analyse these sequential data and extract sequential rule using map reduce Framework of Hadoop mounted over genetic algorithm. Map reduce is responsible for parallelizing of mining technique where as genetic algorithm would work in an iterative manner to generate sequential rules from DNA sequences.