Date of Award
Doctor of Philosophy (PhD)
Computational Analysis and Modeling
One of the major challenges in the field of bioinformatics is the elucidation of protein folding for the functional annotation of proteins. The factors that govern protein folding include the chemical, physical, and environmental conditions of the protein's surroundings, which can be measured and exploited for computational discovery purposes. These conditions enable the protein to transform from a sequence of amino acids to a globular three-dimensional structure. Information concerning the folded state of a protein has significant potential to explain biochemical pathways and their involvement in disorders and diseases. This information impacts the ways in which genetic diseases are characterized and cured and in which designer drugs are created. With the exponential growth of protein databases and the limitations of experimental protein structure determination, sophisticated computational methods have been developed and applied to search for, detect, and compare protein homology. Most computational tools developed for protein structure prediction are primarily based on sequence similarity searches. These approaches have improved the prediction accuracy of high sequence similarity proteins but have failed to perform well with proteins of low sequence similarity. Data mining offers unique algorithmic computational approaches that have been used widely in the development of automatic protein structure classification and prediction.
In this dissertation, we present a novel approach for the integration of physico-chemical properties and effective feature extraction techniques for the classification of proteins. Our approaches overcome one of the major obstacles of data mining in protein databases, the encapsulation of different hydrophobicity residue properties into a much reduced feature space that possess high degrees of specificity and sensitivity in protein structure classification. We have developed three unique computational algorithms for coherent feature extraction on selected scale properties of the protein sequence. When plagued by the problem of the unequal cardinality of proteins, our proposed integration scheme effectively handles the varied sizes of proteins and scales well with increasing dimensionality of these sequences. We also detail a two-fold methodology for protein functional annotation. First, we exhibit our success in creating an algorithm that provides a means to integrate multiple physico-chemical properties in the form of a multi-layered abstract feature space, with each layer corresponding to a physico-chemical property. Second, we discuss a wavelet-based segmentation approach that efficiently detects regions of property conservation across all layers of the created feature space.
Finally, we present a unique graph-theory based algorithmic framework for the identification of conserved hydrophobic residue interaction patterns using identified scales of hydrophobicity. We report that these discriminatory features are specific to a family of proteins, which consist of conserved hydrophobic residues that are then used for structural classification. We also present our rigorously tested validation schemes, which report significant degrees of accuracy to show that homologous proteins exhibit the conservation of physico-chemical properties along the protein backbone. We conclude our discussion by summarizing our results and contributions and by listing our goals for future research.
Chowriappa, Pradeep, "" (2008). Dissertation. 467.