Annotating Gene Functions by Spectral Clustering for Combining Gene Expressions and Sequences

Annotating gene functions is a fundamental issue in the post-genomic era. A typical procedure for this issue is first clustering genes and then assigning functions of unknown genes by using known genes in the same cluster. A lot of genomic information are available for this issue, but two major types of data which can be measured for any genes are microarray expressions and sequences, both of which however have their own flaws. Thus a natural and promising approach for gene annotation is to combine these two data sources. We developed an efficient gene annotation method with three steps containing spectral clustering over the integrated clustering cost for each data source. We examined the performance of our proposed method from viewpoints of clustering and annotations. All experimental results indicate our performance advantage over possible clustering/classification-based approaches of gene function annotation, using expressions and/or sequences.