an exploratory data analysis method to reveal modular latent structures in high-throughput data一个探索性数据分析方法揭示模块化的潜在结构在高通量数据.pdfVIP

Yu BMC Bioinformatics 2010, 11:440 /1471-2105/11/440 METHODOLOGY ARTICLE Open Access An exploratory data analysis method to reveal modular latent structures in high-throughput data Tianwei Yu Abstract Background: Modular structures are ubiquitous across various types of biological networks. The study of network modularity can help reveal regulatory mechanisms in systems biology, evolutionary biology and developmental biology. Identifying putative modular latent structures from high-throughput data using exploratory analysis can help better interpret the data and generate new hypotheses. Unsupervised learning methods designed for global dimension reduction or clustering fall short of identifying modules with factors acting in linear combinations. Results: We present an exploratory data analysis method named MLSA (Modular Latent Structure Analysis) to estimate modular latent structures, which can find co-regulative modules that involve non-coexpressive genes. Conclusions: Through simulations and real-data analyses, we show that the method can recover modular latent structures effectively. In addition, the method also performed very well on data generated from sparse global latent factor models. The R code is available at /~tyu8/MLSA/. Background incorporate TF-gene linkage databases with gene expres- Modularity refers to the organization of biological units sion data showed that multiple TFs can act on a gene, (genes, proteins etc.) into quasi-autonomous groups [1]. and the expressions of the genes within a module regu- It is an abstract concept that may take different forms lated by the same set of TFs can be modeled reasonably in different networks. In systems biology, the most com- well by linear functio