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.^

Herbivore and nutrient impact on primary producer assemblages in a tropical marine environment

Globally, human populations are increasing and coastal ecosystems are becoming increasingly impacted by anthropogenic stressors. As eutrophication and exploitation of coastal resources increases, primary producer response to these drivers becomes a key indicator of ecosystem stability. Despite the importance of monitoring primary producers such as seagrasses and macroalgae, detailed studies on the response of these benthic habitat components to drivers remain relatively sparse. Utilizing a multi-faceted examination of turtle-seagrass and sea urchin-macroalgae consumer and nutrient dynamics, I elucidate the impact of these drivers in Akumal, Quintana Roo, Mexico. In Yal Ku Lagoon, macroalgae bioindicators signified high nutrient availability, which is important for further studies, but did not consistently follow published trends reflecting decreased δ 15N content with distance from suspected source. In Akumal Bay, eutrophication and grazing by turtles and fishes combine to structure patches within the seagrass beds. Grazed seagrass patches had higher structural complexity and productivity than patches continually grazed by turtles and fishes. Results from this study indicate that patch abandonment may follow giving-up density theory, the first to be recorded in the marine environment. As Diadema antillarum populations recover after their massive mortality thirty years ago, the role these echinoids will have in reducing macroalgae cover and altering ecosystem state remains to be clear. Although Diadema antillarum densities within the coral reef ecosystem were comparable to other regions within the Caribbean, the echinoid population in Akumal Bay was an insufficient driver to prevent dominance of a turf-algal-sediment (TAS) state. After a four year study, declining coral cover coupled with increased algal cover suggests that the TAS-dominated state is likely to persist over time despite echinoid recovery. Studies on macroalgal diversity and nutrients within this same region of echinoids indicated diversity and nutrient content of macroalgae increased, which may further increase the persistence of the algal-dominated state. This study provides valuable insight into the variable effects of herbivores and nutrients on primary producers within a tropical coastal ecosystem. Results from this work challenge many of the currently accepted theories on primary producer response to nutrients and herbivory while providing a framework for further studies into these dynamics.