Module-based Analysis of Biological Data for Network Inference and Biomarker Discovery

Systems biology comprises the global, integrated analysis of large-scale data encoding different levels of biological information with the aim to obtain global insight into the cellular networks. Several studies have unveiled the modular and hierarchical organization inherent in these networks. In this dissertation, we propose and develop innovative systems approaches to integrate multi-source biological data in a modular manner for network inference and biomarker discovery in complex diseases such as breast cancer.

The first part of the dissertation is focused on gene module identification in gene expression data. As the most popular way to identify gene modules, many cluster algorithms have been applied to the gene expression data analysis. For the purpose of evaluating clustering algorithms from a biological point of view, we propose a figure of merit based on Kullback-Leibler divergence between cluster membership and known gene ontology attributes. Several benchmark expression-based gene clustering algorithms are compared using the proposed method with different parameter settings. Applications to diverse public time course gene expression data demonstrated that fuzzy c-means clustering is superior to other clustering methods with regard to the enrichment of clusters for biological functions. These results contribute to the evaluation of clustering outcomes and the estimations of optimal clustering partitions.

The second part of the dissertation presents a hybrid computational intelligence method to infer gene regulatory modules. We explore the combined advantages of the nonlinear and dynamic properties of neural networks, and the global search capabilities of the hybrid genetic algorithm and particle swarm optimization method to infer network interactions at modular level.

The proposed computational framework is tested in two biological processes: yeast cell cycle, and human Hela cancer cell cycle. The identified gene regulatory modules were evaluated using several validation strategies: 1) gene set enrichment analysis to evaluate the gene modules derived from clustering results; (2) binding site enrichment analysis to determine enrichment of the gene modules for the cognate binding sites of their predicted transcription factors; (3) comparison with previously reported results in the literatures to confirm the inferred regulations.

The proposed framework could be beneficial to biologists for predicting the components of gene regulatory modules in which any candidate gene is involved. Such predictions can then be used to design a more streamlined experimental approach for biological validation. Understanding the dynamics of these gene regulatory modules will shed light on the related regulatory processes. Driven by the fact that complex diseases such as cancer are “diseases of pathways”, we extended the module concept to biomarker discovery in cancer research. In the third part of the dissertation, we explore the combined advantages of molecular interaction network and gene expression profiles to identify biomarkers in cancer research. The reliability of conventional gene biomarkers has been challenged because of the biological heterogeneity and noise within and across patients. In this dissertation, we present a module-based biomarker discovery approach that integrates interaction network topology and high-throughput gene expression data to identify markers not as individual genes but as modules. To select reliable biomarker sets across different studies, a hybrid method combining group feature selection with ensemble feature selection is proposed. First, a group feature selection method is used to extract the modules (subnetworks) with discriminative power between disease groups. Then, an ensemble feature selection method is used to select the optimal biomarker sets, in which a double-validation strategy is applied. The ensemble method allows combining features selected from multiple classifications with various data subsampling to increase the reliability and classification accuracy of the final selected biomarker set. The results from four breast cancer studies demonstrated the superiority of the module biomarkers identified by the proposed approach: they can achieve higher accuracies, and are more reliable in datasets with same clinical design. Based on the experimental results above, we believe that the proposed systems approaches provide meaningful solutions to discover the cellular regulatory processes and improve the understanding about disease mechanisms. These computational approaches are primarily developed for analysis of high-throughput genomic data. Nevertheless, the proposed methods can also be extended to analyze high-throughput data in proteomics and metablomics areas.