Noise-Robust Soft Clustering of Gene Expression Time-Course Data

Abstract

Clustering is an important tool in microarray data analysis. This unsupervised learning technique is commonly used to reveal structures hidden in large gene expression data sets. The vast majority of clustering algorithms applied so far produce hard partitions of the data, i.e. each gene is assigned exactly to one cluster. Hard clustering is favourable if clusters are well separated. However, this is generally not the case for microarray time-course data, where gene clusters frequently overlap. Additionally, hard clustering algorithms are often highly sensitive to noise. To overcome the limitations of hard clustering, we applied soft clustering which offers several advantages for researchers. First, it generates accessible internal cluster structures, i.e. it indicates how well corresponding clusters represent genes. This can be used for the more targeted search for regulatory elements. Second, the overall relation between clusters, and thus a global clustering structure, can be defined. Additionally, soft clustering is more noise robust and a priori pre-filtering of genes can be avoided. This prevents the exclusion of biologically relevant genes from the data analysis. Soft clustering was implemented here using the fuzzy c-means algorithm. Procedures to find optimal clustering parameters were developed. A software package for soft clustering has been developed based on the open-source statistical language R. The package called Mfuzz is freely available.

A Differentiation-Based MicroRNA Signature Identifies Leiomyosarcoma as a Mesenchymal Stem Cell-Related Malignancy

“…To identify differentially expressed miRNAs among samples of ULMS, ULM, and MM (defined as the 'classifier list') we used the analysis of variance algorithm as implemented in the R package 20 with Benjamini-Hochberg correction for false positives and a P value cutoff of 0.01 or 0.05. Phylogenetic trees were then generated by applying the Weighted Least Squares (WLS) 21 algorithm as implemented in the Phylip package version 3.67 22 to the Pearson correlation distance of subsets of differentially expressed miRNAs (the 'classifier list').…”

“…Expression profile clusters were calculated using the mfuzz algorithm, 20 a fuzzy c-means R package commonly used for clustering profiles of timeseries. The number of clusters was set to 10 with a fuzzification parameter of 1.1.…”

Interleukin 32 promotes hematopoietic progenitor expansion and attenuates bone marrow cytotoxicity

“…genes with a corresponding z-score 43 in all time points [56]. Detected gene clusters were examined for enrichment of functional categories based on GO annotation.…”

Network Analyses Reveal Shifts in Transcript Profiles and Metabolites That Accompany the Expression of SUN and an Elongated Tomato Fruit

“…Expression profiles for wild-type fruit were clustered using fuzzy C means by using the Mfuzz package (Futschik and Carlisle, 2005) in R, with a C value of 100 to maximize dynamic differential clustering identification and core clustered at 0.70 membership probability. Dynamically regulated gene clusters were identified by inspecting plots of the normalized expression profiles of each cluster, which led to the identification of 10 clusters that showed a dynamic range of expression in one tissue over another as well as six ontogeny and spatially specific clusters.…”