Knowledge discovery using multiple sources of biological data

The primary aim of this dissertation is to develop data mining tools for knowledge discovery in biomedical data when multiple (homogeneous or heterogeneous) sources of data are available. The central hypothesis is that, when information from multiple sources of data are used appropriately and effectively, knowledge discovery can be better achieved than what is possible from only a single source. ^ Recent advances in high-throughput technology have enabled biomedical researchers to generate large volumes of diverse types of data on a genome-wide scale. These data include DNA sequences, gene expression measurements, and much more; they provide the motivation for building analysis tools to elucidate the modular organization of the cell. The challenges include efficiently and accurately extracting information from the multiple data sources; representing the information effectively, developing analytical tools, and interpreting the results in the context of the domain. ^ The first part considers the application of feature-level integration to design classifiers that discriminate between soil types. The machine learning tools, SVM and KNN, were used to successfully distinguish between several soil samples. ^ The second part considers clustering using multiple heterogeneous data sources. The resulting Multi-Source Clustering (MSC) algorithm was shown to have a better performance than clustering methods that use only a single data source or a simple feature-level integration of heterogeneous data sources. ^ The third part proposes a new approach to effectively incorporate incomplete data into clustering analysis. Adapted from K-means algorithm, the Generalized Constrained Clustering (GCC) algorithm makes use of incomplete data in the form of constraints to perform exploratory analysis. Novel approaches for extracting constraints were proposed. For sufficiently large constraint sets, the GCC algorithm outperformed the MSC algorithm. ^ The last part considers the problem of providing a theme-specific environment for mining multi-source biomedical data. The database called PlasmoTFBM, focusing on gene regulation of Plasmodium falciparum, contains diverse information and has a simple interface to allow biologists to explore the data. It provided a framework for comparing different analytical tools for predicting regulatory elements and for designing useful data mining tools. ^ The conclusion is that the experiments reported in this dissertation strongly support the central hypothesis.^

Statistical analysis and meta-analysis of microarray data

The microarray technology provides a high-throughput technique to study gene expression. Microarrays can help us diagnose different types of cancers, understand biological processes, assess host responses to drugs and pathogens, find markers for specific diseases, and much more. Microarray experiments generate large amounts of data. Thus, effective data processing and analysis are critical for making reliable inferences from the data. ^ The first part of dissertation addresses the problem of finding an optimal set of genes (biomarkers) to classify a set of samples as diseased or normal. Three statistical gene selection methods (GS, GS-NR, and GS-PCA) were developed to identify a set of genes that best differentiate between samples. A comparative study on different classification tools was performed and the best combinations of gene selection and classifiers for multi-class cancer classification were identified. For most of the benchmarking cancer data sets, the gene selection method proposed in this dissertation, GS, outperformed other gene selection methods. The classifiers based on Random Forests, neural network ensembles, and K-nearest neighbor (KNN) showed consistently god performance. A striking commonality among these classifiers is that they all use a committee-based approach, suggesting that ensemble classification methods are superior. ^ The same biological problem may be studied at different research labs and/or performed using different lab protocols or samples. In such situations, it is important to combine results from these efforts. The second part of the dissertation addresses the problem of pooling the results from different independent experiments to obtain improved results. Four statistical pooling techniques (Fisher inverse chi-square method, Logit method. Stouffer's Z transform method, and Liptak-Stouffer weighted Z-method) were investigated in this dissertation. These pooling techniques were applied to the problem of identifying cell cycle-regulated genes in two different yeast species. As a result, improved sets of cell cycle-regulated genes were identified. The last part of dissertation explores the effectiveness of wavelet data transforms for the task of clustering. Discrete wavelet transforms, with an appropriate choice of wavelet bases, were shown to be effective in producing clusters that were biologically more meaningful. ^

Bioinformatic analysis for exploring relationships between genes and gene products

To carry out their specific roles in the cell, genes and gene products often work together in groups, forming many relationships among themselves and with other molecules. Such relationships include physical protein-protein interaction relationships, regulatory relationships, metabolic relationships, genetic relationships, and much more. With advances in science and technology, some high throughput technologies have been developed to simultaneously detect tens of thousands of pairwise protein-protein interactions and protein-DNA interactions. However, the data generated by high throughput methods are prone to noise. Furthermore, the technology itself has its limitations, and cannot detect all kinds of relationships between genes and their products. Thus there is a pressing need to investigate all kinds of relationships and their roles in a living system using bioinformatic approaches, and is a central challenge in Computational Biology and Systems Biology. This dissertation focuses on exploring relationships between genes and gene products using bioinformatic approaches. Specifically, we consider problems related to regulatory relationships, protein-protein interactions, and semantic relationships between genes. A regulatory element is an important pattern or "signal", often located in the promoter of a gene, which is used in the process of turning a gene "on" or "off". Predicting regulatory elements is a key step in exploring the regulatory relationships between genes and gene products. In this dissertation, we consider the problem of improving the prediction of regulatory elements by using comparative genomics data. With regard to protein-protein interactions, we have developed bioinformatics techniques to estimate support for the data on these interactions. While protein-protein interactions and regulatory relationships can be detected by high throughput biological techniques, there is another type of relationship called semantic relationship that cannot be detected by a single technique, but can be inferred using multiple sources of biological data. The contributions of this thesis involved the development and application of a set of bioinformatic approaches that address the challenges mentioned above. These included (i) an EM-based algorithm that improves the prediction of regulatory elements using comparative genomics data, (ii) an approach for estimating the support of protein-protein interaction data, with application to functional annotation of genes, (iii) a novel method for inferring functional network of genes, and (iv) techniques for clustering genes using multi-source data.

Theoretical study of chloroperoxidase catalyzed chlorination of beta-cyclopentanedione and role of water in the chlorination mechanism

Chloroperoxidase (CPO) is a potential biocatalyst for use in asymmetric synthesis. The mechanisms of CPO catalysis are therefore of interest. The halogenation reaction, one of several chemical reactions that CPO catalyzes, is not fully understood and is the subject of this dissertation. The mechanism by which CPO catalyzes halogenation is disputed. It has been postulated that halogenation of substrates occurs at the active site. Alternatively, it has been proposed that hypochlorous acid, produced at the active site via oxidation of chloride, is released prior to reaction, so that halogenation occurs in solution. The free-solution mechanism is supported by the observation that halogenation of most substrates often occurs non-stereospecifically. On the other hand, the enzyme-bound mechanism is supported by the observation that some large substrates undergo halogenation stereospecifically. The major purpose of this research is to compare chlorination of the substrate β-cyclopentanedione in the two environments. One study was of the reaction with limited hydration because such a level of hydration is typical of the active site. For this work, a purely quantum mechanical approach was used. To model the aqueous environment, the limited hydration environment approach is not appropriate. Instead, reaction precursor conformations were obtained from a solvated molecular dynamics simulation, and reaction of potentially reactive molecular encounters was modeled with a hybrid quantum mechanical/molecular mechanical approach. Extensive work developing parameters for small molecules was pre-requisite for the molecular dynamics simulation. It is observed that a limited and optimized (active-site-like) hydration environment leads to a lower energetic barrier than the fully solvated model representative of the aqueous environment at room temperature, suggesting that the stable water network near the active site is likely to facilitate the chlorination mechanism. The influence of the solvent environment on the reaction barrier is critical. It is observed that stabilization of the catalytic water by other solvent molecules lowers the barrier for keto-enol tautomerization. Placement of water molecules is more important than the number of water molecules in such studies. The fully-solvated model demonstrates that reaction proceeds when the instantaneous dynamical water environment is close to optimal for stabilizing the transition state.

The potential role of environmental exposures and genomic signaling in development of central nervous system tumors

The etiology of central nervous system tumors (CNSTs) is mainly unknown. Aside from extremely rare genetic conditions, such as neurofibromatosis and tuberous sclerosis, the only unequivocally identified risk factor is exposure to ionizing radiation, and this explains only a very small fraction of cases. Using meta-analysis, gene networking and bioinformatics methods, this dissertation explored the hypothesis that environmental exposures produce genetic and epigenetic alterations that may be involved in the etiology of CNSTs. A meta-analysis of epidemiological studies of pesticides and pediatric brain tumors revealed a significantly increased risk of brain tumors among children whose mothers had farm-related exposures during pregnancy. A dose response was recognized when this risk estimate was compared to those for risk of brain tumors from maternal exposure to non-agricultural pesticides during pregnancy, and risk of brain tumors among children exposed to agricultural activities. Through meta-analysis of several microarray studies which compared normal tissue to astrocytomas, we were able to identify a list of 554 genes which were differentially expressed in the majority of astrocytomas. Many of these genes have in fact been implicated in development of astrocytoma, including EGFR, HIF-1α, c-Myc, WNT5A, and IDH3A. Reverse engineering of these 554 genes using Bayesian network analysis produced a gene network for each grade of astrocytoma (Grade I-IV), and ‘key genes’ within each grade were identified. Genes found to be most influential to development of the highest grade of astrocytoma, Glioblastoma multiforme (GBM) were: COL4A1, EGFR, BTF3, MPP2, RAB31, CDK4, CD99, ANXA2, TOP2A, and SERBP1. Lastly, bioinformatics analysis of environmental databases and curated published results on GBM was able to identify numerous potential pathways and geneenvironment interactions that may play key roles in astrocytoma development. Findings from this research have strong potential to advance our understanding of the etiology and susceptibility to CNSTs. Validation of our ‘key genes’ and pathways could potentially lead to useful tools for early detection and novel therapeutic options for these tumors.

Phylogenetic analysis of within -host serially-sampled viral data

The primary goal of this dissertation is the study of patterns of viral evolution inferred from serially-sampled sequence data, i.e., sequence data obtained from strains isolated at consecutive time points from a single patient or host. RNA viral populations have an extremely high genetic variability, largely due to their astronomical population sizes within host systems, high replication rate, and short generation time. It is this aspect of their evolution that demands special attention and a different approach when studying the evolutionary relationships of serially-sampled sequence data. New methods that analyze serially-sampled data were developed shortly after a groundbreaking HIV-1 study of several patients from which viruses were isolated at recurring intervals over a period of 10 or more years. These methods assume a tree-like evolutionary model, while many RNA viruses have the capacity to exchange genetic material with one another using a process called recombination. ^ A genealogy involving recombination is best described by a network structure. A more general approach was implemented in a new computational tool, Sliding MinPD, one that is mindful of the sampling times of the input sequences and that reconstructs the viral evolutionary relationships in the form of a network structure with implicit representations of recombination events. The underlying network organization reveals unique patterns of viral evolution and could help explain the emergence of disease-associated mutants and drug-resistant strains, with implications for patient prognosis and treatment strategies. In order to comprehensively test the developed methods and to carry out comparison studies with other methods, synthetic data sets are critical. Therefore, appropriate sequence generators were also developed to simulate the evolution of serially-sampled recombinant viruses, new and more through evaluation criteria for recombination detection methods were established, and three major comparison studies were performed. The newly developed tools were also applied to "real" HIV-1 sequence data and it was shown that the results represented within an evolutionary network structure can be interpreted in biologically meaningful ways. ^

Towards the prediction of mutations in genomic sequences

Bio-systems are inherently complex information processing systems. Furthermore, physiological complexities of biological systems limit the formation of a hypothesis in terms of behavior and the ability to test hypothesis. More importantly the identification and classification of mutation in patients are centric topics in today's cancer research. Next generation sequencing (NGS) technologies can provide genome-wide coverage at a single nucleotide resolution and at reasonable speed and cost. The unprecedented molecular characterization provided by NGS offers the potential for an individualized approach to treatment. These advances in cancer genomics have enabled scientists to interrogate cancer-specific genomic variants and compare them with the normal variants in the same patient. Analysis of this data provides a catalog of somatic variants, present in tumor genome but not in the normal tissue DNA. In this dissertation, we present a new computational framework to the problem of predicting the number of mutations on a chromosome for a certain patient, which is a fundamental problem in clinical and research fields. We begin this dissertation with the development of a framework system that is capable of utilizing published data from a longitudinal study of patients with acute myeloid leukemia (AML), who's DNA from both normal as well as malignant tissues was subjected to NGS analysis at various points in time. By processing the sequencing data at the time of cancer diagnosis using the components of our framework, we tested it by predicting the genomic regions to be mutated at the time of relapse and, later, by comparing our results with the actual regions that showed mutations (discovered at relapse time). We demonstrate that this coupling of the algorithm pipeline can drastically improve the predictive abilities of searching a reliable molecular signature. Arguably, the most important result of our research is its superior performance to other methods like Radial Basis Function Network, Sequential Minimal Optimization, and Gaussian Process. In the final part of this dissertation, we present a detailed significance, stability and statistical analysis of our model. A performance comparison of the results are presented. This work clearly lays a good foundation for future research for other types of cancer.^