Towards precise classification of cancers based on robust gene functional expression profiles

Abstract

BackgroundDevelopment of robust and efficient methods for analyzing and interpreting high dimension gene expression profiles continues to be a focus in computational biology. The accumulated experiment evidence supports the assumption that genes express and perform their functions in modular fashions in cells. Therefore, there is an open space for development of the timely and relevant computational algorithms that use robust functional expression profiles towards precise classification of complex human diseases at the modular level.ResultsInspired by the insight that genes act as a module to carry out a highly integrated cellular function, we thus define a low dimension functional expression profile for data reduction. After annotating each individual gene to functional categories defined in a proper gene function classification system such as Gene Ontology applied in this study, we identify those functional categories enriched with differentially expressed genes. For each functional category or functional module, we compute a summary measure (s) for the raw expression values of the annotated genes to capture the overall activity level of the module. In this way, we can treat the gene expressions within a functional module as an integrative data point to replace the multiple values of individual genes. We compare the classification performance of decision trees based on functional expression profiles with the conventional gene expression profiles using four publicly available datasets, which indicates that precise classification of tumour types and improved interpretation can be achieved with the reduced functional expression profiles.ConclusionThis modular approach is demonstrated to be a powerful alternative approach to analyzing high dimension microarray data and is robust to high measurement noise and intrinsic biological variance inherent in microarray data. Furthermore, efficient integration with current biological knowledge has facilitated the interpretation of the underlying molecular mechanisms for complex human diseases at the modular level.

Peeling Off the Hidden Genetic Heterogeneities of Cancers Based on Disease-Relevant Functional Modules

“…In addition, our previous study (15) for classifying cancers using 1-dimensional (BP) characterization of modules demonstrated that the modular approach to using the derived modular functional expression profiles is a powerful and robust alternative approach to analyzing high-dimensional gene profiles of cancers. Although both 1-and 2-dimensional modular categorization can perform equally well, we recommend using 2-dimensional (BP and CC) characterization of modules to achieve more compact and detailed knowledge in both functionality and cellular location, data that are more useful and revealing for further experimental investigation (for example, by molecular trafficking techniques).…”

“…Segal et al (14) defined "modules" as biologically meaningful gene sets that are conditionally activated or repressed across a wide variety of cancer types, and identified some modules deregulated in cancer. Our recent study demonstrated that cancer types can be precisely and robustly classified based on functional modules enriched with differentially expressed genes (15). Nevertheless, nothing in the literature exists for fully exploiting the power and value of the modular approaches to systematically dissecting the molecular heterogeneities of human diseases.…”

Network-Assisted Disease Classification and Biomarker Discovery

“…One of the fi rst studies, in which a pathway activity score is calculated from GO functional modules was published by Guo et al [ 66 ]. To discriminate between different tumor types, the authors defi ned the pathway activity score as the mean or median expression value of genes which are part of GO modules enriched with differentially expressed genes.…”

Pathway-based microarray analysis for robust disease classification

“…Pathway-based analysis using expression profiles has been shown by Guo et al [8] to provide more accurate disease classification than using individual genes. Subsequently, different methods for inferring pathway activity (PAC) have been proposed [9,10].…”

“…Nonetheless, there are several limitations to these previous pathway activity inference methods. For example, Guo et al [8] proposed methods to estimate the pathway activity by taking the mean or median of the gene expression values of all member genes in a pathway. However, such methods would not be able to find the coherent gene expression patterns that may be present within a pathway effectively.…”