A Brief Review of Data Mining Application Involving Protein Sequence Classification

摘要

Data mining techniques have been used by researchers for analyzing protein sequences. In protein analysis, especially in protein sequence classification, selection of feature is most important. Popular protein sequence classification techniques involve extraction of specific features from the sequences. Researchers apply some well-known classification techniques like neural networks, Genetic algorithm, Fuzzy ARTMAP, Rough Set Classifier etc for accurate classification. This paper presents a review is with three different classification models such as neural network model, fuzzy ARTMAP model and Rough set classifier model. A new technique for classifying protein sequences have been proposed in the end. The proposed technique tries to reduce the computational overheads encountered by earlier approaches and increase the accuracy of classification.