Classification of microarrays to nearest centroids
Bioinformatics
Accurate Cancer Classification Using Expressions of Very Few Genes
IEEE/ACM Transactions on Computational Biology and Bioinformatics (TCBB)
Bioinformatics
Robust Classification Method of Tumor Subtype by Using Correlation Filters
IEEE/ACM Transactions on Computational Biology and Bioinformatics (TCBB)
| Hi-index | 0.00 |
Gene expression profiles consisting of thousands of genes can describe the characteristics of specific cancer subtype. By efficiently using the overall scheme of gene expression, accurate tumor diagnosis can be performed well in clinical medicine. However, faced many problems such as too much noise and the curse of dimensionality that the number of genes far exceeds the size of samples in tumor dataset, tumor classification by selecting a small set of gene subset from the thousands of genes becomes a challenging task. This paper proposed a novel high accuracy method, which utilized the global scheme of differentially expressed genes corresponding to each tumor subtype which is determined by tumor-related genes, to classify tumor samples by using Minimum Average Correlation Energy (MACE) filter method to computing the similarity degree between a test sample with unknown label in test set and the template constructed with training set. The experimental results obtained on two actual tumor datasets indicate that the proposed method is very effective and robust in classification performance.