Document Type


Date of Award

Spring 2017

Degree Name

Doctor of Philosophy in Computing Sciences - (Ph.D.)


Computer Science

First Advisor

Jason T. L. Wang

Second Advisor

James A. McHugh

Third Advisor

David Nassimi

Fourth Advisor

Dimitri Theodoratos

Fifth Advisor

Yi Chen

Sixth Advisor

Katherine Grace Herbert


Big data analytics in computational biology and bioinformatics refers to an array of operations including biological pattern discovery, classification, prediction, inference, clustering as well as data mining in the cloud, among others. This dissertation addresses big data analytics by investigating two important operations, namely pattern discovery and network inference.

The dissertation starts by focusing on biological pattern discovery at a genomic scale. Research reveals that the secondary structure in non-coding RNA (ncRNA) is more conserved during evolution than its primary nucleotide sequence. Using a covariance model approach, the stems and loops of an ncRNA secondary structure are represented as a statistical image against which an entire genome can be efficiently scanned for matching patterns. The covariance model approach is then further extended, in combination with a structural clustering algorithm and a random forests classifier, to perform genome-wide search for similarities in ncRNA tertiary structures.

The dissertation then presents methods for gene network inference. Vast bodies of genomic data containing gene and protein expression patterns are now available for analysis. One challenge is to apply efficient methodologies to uncover more knowledge about the cellular functions. Very little is known concerning how genes regulate cellular activities. A gene regulatory network (GRN) can be represented by a directed graph in which each node is a gene and each edge or link is a regulatory effect that one gene has on another gene. By evaluating gene expression patterns, researchers perform in silico data analyses in systems biology, in particular GRN inference, where the “reverse engineering” is involved in predicting how a system works by looking at the system output alone.

Many algorithmic and statistical approaches have been developed to computationally reverse engineer biological systems. However, there are no known bioin-formatics tools capable of performing perfect GRN inference. Here, extensive experiments are conducted to evaluate and compare recent bioinformatics tools for inferring GRNs from time-series gene expression data. Standard performance metrics for these tools based on both simulated and real data sets are generally low, suggesting that further efforts are needed to develop more reliable GRN inference tools. It is also observed that using multiple tools together can help identify true regulatory interactions between genes, a finding consistent with those reported in the literature. Finally, the dissertation discusses and presents a framework for parallelizing GRN inference methods using Apache Hadoop in a cloud environment.



To view the content in your browser, please download Adobe Reader or, alternately,
you may Download the file to your hard drive.

NOTE: The latest versions of Adobe Reader do not support viewing PDF files within Firefox on Mac OS and if you are using a modern (Intel) Mac, there is no official plugin for viewing PDF files within the browser window.