부산대학교 도서관

One of the first computational steps in exploration and analysis of the gene expression data is clustering. However, most of the standard clustering methods do not take prior biological information into account. Here, we propose a new approach for gene expression clustering analysis. The approach benefits from a new deep learning architecture, Robust Autoencode, and from incorporating prior system-wide biological information into the clustering process. We tested our approach on two gene expression datasets. Our approach outperformed all other clustering methods on the labelled yeast gene expression dataset. Furthermore, we showed that it is better in identifying the functionally common clusters on the unlabelled human gene expression dataset. The results demonstrate that our new deep learning architecture can generalise well the specific properties of gene expression profiles. Furthermore, the results confirm our hypothesis that the prior biological network knowledge is helpful in the gene expression clustering.