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.^

What Google Maps can do for Biomedical Data Dissemination: Examples and a Design Study

Background: Biologists often need to assess whether unfamiliar datasets warrant the time investment required for more detailed exploration. Basing such assessments on brief descriptions provided by data publishers is unwieldy for large datasets that contain insights dependent on specific scientific questions. Alternatively, using complex software systems for a preliminary analysis may be deemed as too time consuming in itself, especially for unfamiliar data types and formats. This may lead to wasted analysis time and discarding of potentially useful data. Results: We present an exploration of design opportunities that the Google Maps interface offers to biomedical data visualization. In particular, we focus on synergies between visualization techniques and Google Maps that facilitate the development of biological visualizations which have both low-overhead and sufficient expressivity to support the exploration of data at multiple scales. The methods we explore rely on displaying pre-rendered visualizations of biological data in browsers, with sparse yet powerful interactions, by using the Google Maps API. We structure our discussion around five visualizations: a gene co-regulation visualization, a heatmap viewer, a genome browser, a protein interaction network, and a planar visualization of white matter in the brain. Feedback from collaborative work with domain experts suggests that our Google Maps visualizations offer multiple, scale-dependent perspectives and can be particularly helpful for unfamiliar datasets due to their accessibility. We also find that users, particularly those less experienced with computer use, are attracted by the familiarity of the Google Maps API. Our five implementations introduce design elements that can benefit visualization developers. Conclusions: We describe a low-overhead approach that lets biologists access readily analyzed views of unfamiliar scientific datasets. We rely on pre-computed visualizations prepared by data experts, accompanied by sparse and intuitive interactions, and distributed via the familiar Google Maps framework. Our contributions are an evaluation demonstrating the validity and opportunities of this approach, a set of design guidelines benefiting those wanting to create such visualizations, and five concrete example visualizations.

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.

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. ^

Ranked search on data graphs

Graph-structured databases are widely prevalent, and the problem of effective search and retrieval from such graphs has been receiving much attention recently. For example, the Web can be naturally viewed as a graph. Likewise, a relational database can be viewed as a graph where tuples are modeled as vertices connected via foreign-key relationships. Keyword search querying has emerged as one of the most effective paradigms for information discovery, especially over HTML documents in the World Wide Web. One of the key advantages of keyword search querying is its simplicity—users do not have to learn a complex query language, and can issue queries without any prior knowledge about the structure of the underlying data. The purpose of this dissertation was to develop techniques for user-friendly, high quality and efficient searching of graph structured databases. Several ranked search methods on data graphs have been studied in the recent years. Given a top-k keyword search query on a graph and some ranking criteria, a keyword proximity search finds the top-k answers where each answer is a substructure of the graph containing all query keywords, which illustrates the relationship between the keyword present in the graph. We applied keyword proximity search on the web and the page graph of web documents to find top-k answers that satisfy user’s information need and increase user satisfaction. Another effective ranking mechanism applied on data graphs is the authority flow based ranking mechanism. Given a top- k keyword search query on a graph, an authority-flow based search finds the top-k answers where each answer is a node in the graph ranked according to its relevance and importance to the query. We developed techniques that improved the authority flow based search on data graphs by creating a framework to explain and reformulate them taking in to consideration user preferences and feedback. We also applied the proposed graph search techniques for Information Discovery over biological databases. Our algorithms were experimentally evaluated for performance and quality. The quality of our method was compared to current approaches by using user surveys.

Treefrogs in Forested Swamps at the La Selva Biological Station: Assemblage Variation through Space and Time

Swamp-breeding treefrogs form conspicuous components of many tropical forest sites, yet remain largely understudied. The La Selva Biological Station, a rainforest reserve in Costa Rica, harbors a rich swamp-breeding treefrog fauna that has been studied in only one of the many swamps found at the site. To understand if the species composition of treefrogs at La Selva varies over space or time, frogs were censused in 1982-83, 1994-95, 2005 and 2011 at two ponds located in the reserve. Data on treefrog habitat utilization were also collected. Species composition varied spatially only in 2011. Temporal variation was observed at both ponds for all groups tested. Habitat use varied among species and between swamps. The pattern of variation suggests that temporally dynamic systems such as temporary Neotropical forest swamps will converge and diverge in species composition over time.

An Analytical Workflow for Metagenomic Data and its Application to the Study of Chronic Obstructive Pulmonary Disease (COPD)

Metagenomics is the culture-independent study of genetic material obtained directly from environmental samples. It has become a realistic approach to understanding microbial communities thanks to advances in high-throughput DNA sequencing technologies over the past decade. Current research has shown that different sites of the human body house varied bacterial communities. There is a strong correlation between an individual’s microbial community profile at a given site and disease. Metagenomics is being applied more often as a means of comparing microbial profiles in biomedical studies. The analysis of the data collected using metagenomics can be quite challenging and there exist a plethora of tools for interpreting the results. An automatic analytical workflow for metagenomic analyses has been implemented and tested using synthetic datasets of varying quality. It is able to accurately classify bacteria by taxa and correctly estimate the richness and diversity of each set. The workflow was then applied to the study of the airways microbiome in Chronic Obstructive Pulmonary Disease (COPD). COPD is a progressive lung disease resulting in narrowing of the airways and restricted airflow. Despite being the third leading cause of death in the United States, little is known about the differences in the lung microbial community profiles of healthy individuals and COPD patients. Bronchoalveolar lavage (BAL) samples were collected from COPD patients, active or ex-smokers, and never smokers and sequenced by 454 pyrosequencing. A total of 56 individuals were recruited for the study. Substantial colonization of the lungs was found in all subjects and differentially abundant genera in each group were identified. These discoveries are promising and may further our understanding of how the structure of the lung microbiome is modified as COPD progresses. It is also anticipated that the results will eventually lead to improved treatments for COPD.