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

Abstract

Background: Development 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.

Results: Inspired 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.

Conclusion: This 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.

Figure 1

Training classification rules for four cancer types based on functional expression profiles of 114 modules. A – Decision tree trained with the NCI60 FEP median measure. The internal nodes of the tree are denoted with the functional modules from Gene Ontology. The leaf nodes give the classification results for the cancer types. The numbers in the leaf nodes are the total number of samples contained over the number of the incorrectly predicted samples. B – Functional expression profiles of the three identified modules. For the identified GO modules from decision analysis, their functional expression profiles are demonstrated with a colouring spectrum of their medians. Each GO module corresponds to a row, and the column denotes the functional expression for each cell line. At the top are names of cell lines (renal cancer (RE), colon cancer (CO), leukaemia (LE), melanoma (ME)). Samples with a missing value or the null value are coded with black colour, a positive with red colour and a negative with green colour. C – numbers of genes annotated and differentially expressed in the three identified modules.

Figure 2

Comparison of different gene expression measures for classification of cancer types in terms of accuracy (A), precision (B) and recall (C).

Figure 3

Training classification rules for lymphoma subtypes based on functional expression profiles of 44 GO modules. A – Decision tree trained with the lymphoma FEP median measure. The internal nodes of the tree are denoted with the functional modules from Gene Ontology. The leaf nodes give the classification results for the lymphoma subtypes. The numbers in the leaf nodes are the total number of samples contained over the number of the incorrectly predicted samples. B – Functional expression profiles of the three identified modules. For the identified GO modules from decision analysis, their functional expression profiles are demonstrated with a colouring spectrum of their medians. Each GO module corresponds to a row, and the column denotes the functional expression for each cell line. At the top are names of cell lines (diffuse large B-cell lymphoma (DLBCL), follicular lymphoma (FL), chronic lymphocyte leukaemia (CLL), and the healthy sources (NORMAL)). Samples with a missing value or the null value are coded with black colour, a positive with red colour and a negative with green colour. C – Numbers of genes annotated and differentially expressed in the three identified modules.

Figure 4

Comparison of different gene expression measures for classification of lymphoma tissues in terms of accuracy (A), precision (B) and recall (C).