Association rule mining based on concept lattice in bioinformatics research

Concept lattice represents knowledge with the relationships between the intent and the extent of concepts, and the relations between the generalization and the specialization of concepts, then knowledge can be shown on the Hasse diagram with hierarchical structure, thus it is properly applied to the description of mining association rules in databases. Compared with well-known Apriori and FP-Growth algorithm, mining association rules on concept lattice does not need to scan databases for many times, and shows association rules on the Hasse diagram of concept lattice more visual and concise, moreover, it can be used to mine association rules interactively according to user's subjective interest, then solves the bottleneck of knowledge acquisition effectively, thus it is properly applied to the description of association rule mining in databases. Although the time complexity of building concept lattice algorithm is usually higher than FP-Growth algorithm, less than Apriori algorithm, association rule mining based on concept lattice has its own advantage, which represents the association rules more vivid and concise than Apriori and FP-Growth algorithm, thus, it can be easily applied in molecular biology to manage and analyze biology data. For example, because DNA and protein sequences are essential biological data and exist in huge volumes as well ,it is very important to apply association rule mining to compare and align biology sequences and find biosequence patterns and discovery of disease-causing gene connections and gene-drug interactions as an effective method. ©2010 IEEE.