Interactive learning for classifying microarray gene expression data

Relevance feedback [1], which has been successfully used in content-based image retrieval, is rarely used in the field of bioinformatics. In this paper, we introduce relevance feedback to microarray analysis and implement an interactive learning framework for classifying microarray gene expression data. The aim is to incorporate specialists' feedback to retrain our classifier, which can bridge the gap between the temporal expressions and the associated semantics. Extensive experiments on the Plasmodium falciparum dataset show the effectiveness and promising performance of the scheme.