Abstract
BackgroundUnsupervised analyses such as clustering are the essential tools required to interpret time-series expression data from microarrays. Several clustering algorithms have been developed to analyze gene expression data. Early methods such as k-means, hierarchical clustering, and self-organizing maps are popular for their simplicity. However, because of noise and uncertainty of measurement, these common algorithms have low accuracy. Moreover, because gene expression is a temporal process, the relationship between successive time points should be considered in the analyses. In addition, biological processes are generally continuous; therefore, the datasets collected from time series experiments are often found to have an insufficient number of data points and, as a result, compensation for missing data can also be an issue.ResultsAn affinity propagation-based clustering algorithm for time-series gene expression data is proposed. The algorithm explores the relationship between genes using a sliding-window mechanism to extract a large number of features. In addition, the time-course datasets are resampled with spline interpolation to predict the unobserved values. Finally, a consensus process is applied to enhance the robustness of the method. Some real gene expression datasets were analyzed to demonstrate the accuracy and efficiency of the algorithm.ConclusionThe proposed algorithm has benefitted from the use of cubic B-splines interpolation, sliding-window, affinity propagation, gene relativity graph, and a consensus process, and, as a result, provides both appropriate and effective clustering of time-series gene expression data. The proposed method was tested with gene expression data from the Yeast galactose dataset, the Yeast cell-cycle dataset (Y5), and the Yeast sporulation dataset, and the results illustrated the relationships between the expressed genes, which may give some insights into the biological processes involved.
Highlights
Unsupervised analyses such as clustering are the essential tools required to interpret time-series expression data from microarrays
Here, the proposed algorithm based on B-splines interpolation [10], affinity propagation [12], and consensus clustering [14] is described
The time-course gene expression clustering problem was formulated as follows: for a set of genes G = {G1, G2, . . . , Gn} where n is the number of genes, and each gene Gi includes τ time points for the gene expression values, the n genes are grouped into K disjoint clusters C1, C2, . . . , CK
Summary
Unsupervised analyses such as clustering are the essential tools required to interpret time-series expression data from microarrays. Several clustering algorithms have been developed to analyze gene expression data. Methods such as k-means, hierarchical clustering, and self-organizing maps are popular for their simplicity. High-throughput data of time-series gene expression are recorded to explore the complex dynamics of biological systems. Analyses of microarray data are essential in several time-series expression experiments such as biological systems, infectious diseases, and genetic interactions [1]. Pattern recognition techniques are helpful [2] to explore and exploit high-throughput screening data from microarrays By using these techniques, similar expression patterns can be organized into a group. Some of the older methods such as k-means, hierarchical clustering, and
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
