Gene selection approach based on improved swarm intelligent optimisation algorithm for tumour classification

• Published in: IET systems biology 2016-06, Vol.10 (3), p.107-115
• Main Authors: Jin, Cong, Jin, Shu-Wei
• Format: Article
• Language: English
• Subjects: Algorithms; Animals; Biology; Classification; Classifiers; ensemble classifiers; gene datasets; Gene expression; gene expression profiles; Gene Expression Profiling - methods; gene selection approach; gene space; Genes; genetics; Humans; informative genes; medical computing; Neoplasm Proteins - metabolism; Neoplasms - classification; Neoplasms - diagnosis; Neoplasms - metabolism; Optimization; particle swarm optimisation; pattern classification; Pattern Recognition, Automated - methods; Reproducibility of Results; Sensitivity and Specificity; swarm intelligence; swarm intelligent optimisation algorithm; Tumors; tumour classification; tumour classifiers; tumours
• ISSN: 1751-8849; 1751-8857
• DOI: 10.1049/iet-syb.2015.0064

A number of different gene selection approaches based on gene expression profiles (GEP) have been developed for tumour classification. A gene selection approach selects the most informative genes from the whole gene space, which is an important process for tumour classification using GEP. This study presents an improved swarm intelligent optimisation algorithm to select genes for maintaining the diversity of the population. The most essential characteristic of the proposed approach is that it can automatically determine the number of the selected genes. On the basis of the gene selection, the authors construct a variety of the tumour classifiers, including the ensemble classifiers. Four gene datasets are used to evaluate the performance of the proposed approach. The experimental results confirm that the proposed classifiers for tumour classification are indeed effective.