抽象的

The classification of multiclass tumor gene expression data based on two-layer particle swarm optimization

Yajie Liu, Xinling Shi, Changxin Gou, Baolei Li, Lian Gao

The classification of gene expression data to determine different type of tumor samples is significantly important to research tumors in molecular biology level formaking further treatment plan of the patient. Particle swarm optimization (PSO) has employed as a solution for classification and clustering in bioinformatics. In this study, a classifier based on the two layer particle swarm optimization (TLPSO) algorithm is established to classify the uncertain training sample sets obtained from gene expression data of breast, prostate, lung and colon tumor samples. Compared with PSO and K-means algorithm in validation, the classification stability and accuracy based on the proposedTLPSOalgorithmis improved significantly, which may provide more information to clinicians for choosing more appropriate treatment.