Gene Network Modules-Based Liner Discriminant Analysis of Microarray Gene Expression Data

Molecular predictor is a new tool for disease diagnosis, which uses gene expression to classify the diagnostic category of a patient. The statistical challenge for constructing such a predictor is that there are thousands of genes to predict for disease category. but only a small number of samples are available. Here we proposed a gene network modules-based linear discriminant analysis (MLDA) approach by integrating 'essential' correlation structure among genes into the predictor in order that the module or cluster structure of genes, which is related to diagnostic classes we look for, can have potential biological interpretation. We evaluated performance of the new method with other established classification methods using three real data sets. Our results show that the new approach has the advantage of computational simplicity and efficiency with lower classification error rates than the compared methods in most cases.