| Popis: |
The Sequential Pattern Mining (SPM) is a fundamental task in data mining. The SPM mines subsequences from given sequence which can be used for various analyses. This paper aims to propose an efficient method for mining frequent sequential patterns in biological data. It also includes the k-mer for decomposing the sequence according to the user defined threshold value. The input data used is breast cancer gene BRCA2 normal and mutated BRCA2 gene. The parameters used for analyses are suffix, candidate pattern and frequent pattern. The suffix value is increased for mono-,di and tri-nucleotide in mutated gene and in frequent pattern tri-nucleotide has increased nucleotide in mutated gene. So this abnormal increase in pattern may leads to cancer in the human |
