点击次数：

论文类型： 期刊论文

发表时间： 2018-01-01

发表刊物： INTERNATIONAL JOURNAL OF DATA MINING AND BIOINFORMATICS

收录刊物： SCIE

卷号： 20

期号： 3

页面范围： 213-229

ISSN号： 1748-5673

关键字： ensemble classification; microarray data; MapReduce programming model; parallel information fusion

摘要： Analysis of large-scale gene expression data is a research hotspot in the field of bioinformatics, which can be used to study abnormal phenomenon in plant growth process. This paper proposes a biological knowledge integration method based on parallel clustering to select gene subsets effectively. Gene ontology is utilised to obtain the biological functional similarity, and combined with gene expression data. Parallelised affinity propagation algorithm is used to cluster data since it can not only obtain more biologically meaningful subsets, but also avoid the loss of some potential value in genes from simple gene primary selection. The algorithm is verified with four typical plant datasets and compared with other well-known integration methods. Experimental results on plant stress response datasets demonstrate that the proposed method can select genes with stronger classification ability.