Cancer Classification Based on the Features of Itemset Sequence Pattern of TP53 Protein Code Using Deep Miden - KNN

Cancer is a disease that still difficult to identify up today. One of the causes cancer genetic modification because mutations in p53 gene. Healthy cells have wild type protein (normal) able manage DNA separation. If mutates, it will be detect composition has changed. Bioinformatics combination biology and information engineering (TI) utilized data. applications data mining bioinformatics development pharmaceutical medical industries. Data classification can use variety methods including K-Nearest Neighbor (KNN), C45, ID3, several other methods. most reliable KNN. In this study, used two algorithms. The first was with k-fold method, which divided into training test data, test-1 test-2 were made slices. second by method for selecting an itemset sequence pattern had largest Gain Information, either 2 itemsets, 3 so on (Deep Miden). best accuracy result 96.00% obtained through process computation testing server based variations terms number patterns Deep Miden sequences k values KNN method.