Clustering Of Gene Expression Data Based On Shape Similarity

摘要

A method for gene clustering from expression profiles using shape information is presented. The conventional clustering approaches such as K-means assume that genes with similar functions have similar expression levels and hence allocate genes with similar expression levels into the same cluster. However, we observed that genes with similar function often exhibit similarity in signal shape even though the expression magnitude can be far apart. As a result, we aim to cluster according to signal shape similarity. This shape information is captured in the form of normalized and time-scaled forward first differences, which then are subject to a variational Bayes clustering. We discuss the problem and our proposed method of solution. Initial results are given and show the method has promise in being able to cluster large sets of time-series data over many genes.