Physical Sciences and Mathematics Commons^™

Representation Learning With Autoencoders For Electronic Health Records, Najibesadat Sadatijafarkalaei

Wayne State University Theses

Increasing volume of Electronic Health Records (EHR) in recent years provides great opportunities for data scientists to collaborate on different aspects of healthcare research by applying advanced analytics to these EHR clinical data. A key requirement however

is obtaining meaningful insights from high dimensional, sparse and complex clinical data. Data science approaches typically address this challenge by performing feature learning in order to build more reliable and informative feature representations from clinical data followed by supervised learning. In this research, we propose a predictive modeling approach based on deep feature representations and word embedding techniques. Our method uses different deep …

Qualitative Change Detection Approach For Preventive Therapies, Cristina Mitrea

Wayne State University Dissertations

Currently, most diseases are diagnosed only after disease-associated changes have occurred. In this PhD dissertation, we propose a paradigm shift from treating the disease to maintaining the healthy state. The proposed approach is able to identify when systemic qualitative changes in biological systems happen, thus opening the possibility of therapeutic interventions before the occurrence of symptoms. The change detection method exploits knowledge from biological networks and longitudinal data using a system impact analysis approach. This approach is validated on eight datasets, for seven different model organisms and eight biological phenomena. On these data, our proposed method performs well, consistently identifying …

Horizontal And Vertical Integration Of Bio-Molecular Data, Tin Chi Nguyen

Wayne State University Dissertations

Modern biomedical research lies at the crossroads of data gathering, interpretation, and hypothesis testing. Due to noise, study bias, or too small changes in biological signals between disease and healthy, individual studies often fail to identify the true phenomenon. Data integration is the key to obtaining the power needed to pinpoint the biological mechanisms of disease states. Given this, we tried to make important contributions in both horizontal and vertical integration of high-throughput data; the former is meta-analysis of independent studies, while the latter is the integration of multi-omics data.

For horizontal meta-analysis, we developed two frameworks: DANUBE and the …

Efficient Synergistic De Novo Co-Assembly Of Bacterial Genomes From Single Cells Using Colored De Bruijn Graph, Narjes Sadat Movahedi Tabrizi

Wayne State University Dissertations

Recent progress in DNA amplification techniques, particularly multiple displacement

amplification (MDA), has made it possible to sequence and assemble bacterial

genomes from a single cell. However, the quality of single cell genome assembly has

not yet reached the quality of normal multi-cell genome assembly due to the coverage

bias (including uneven depth of coverage and region blackout) and errors caused by

MDA. Computational methods try to mitigates the amplification bias. In this document

we introduce a de novo co-assembly method using colored de Bruijn graph,

which can overcome the problem of blackout regions due to amplification bias. The

algorithm is …

Applications Of Machine Learning In Biology And Medicine, Saied Haidarian Shahri

Wayne State University Dissertations

Machine learning as a field is defined to be the set of computational algorithms that improve their performance by assimilating data.

As such, the field as a whole has found applications in many diverse disciplines from robotics and communication in engineering to economics and finance, and also biology and medicine.

It should not come as a surprise that many popular methods in use today have completely different origins.

Despite this heterogeneity, different methods can be divided into standard tasks, such as supervised, unsupervised, semi-supervised and reinforcement learning.

Although machine learning as a field can be formalized as methods trying to …

Algorithms And Tools For Computational Analysis Of Human Transcriptome Using Rna-Seq, Nan Deng

Wayne State University Dissertations

Alternative splicing plays a key role in regulating gene expression, and more than 90% of human genes are alternatively spliced through different types of alternative splicing. Dysregulated alternative splicing events have been linked to a number of human diseases. Recently, high-throughput RNA-Seq technologies have provided unprecedented opportunities to better characterize and understand transcriptomes, in particular useful for the detection of splicing variants between healthy and diseased human transcriptomes.

We have developed two novel algorithms and tools and a computational workflow to interrogate human transcriptomes between healthy and diseased conditions. The first is a read count-based Expectation-Maximization (EM) algorithm and tool, …

The Rna Newton Polytope And Learnability Of Energy Parameters, Elmirasadat Forouzmand

Wayne State University Theses

Computational RNA secondary structure prediction has been a topic of much research interest for several decades now. Despite all the progress made in the field, even the state-of-the-art algorithms do not provide satisfying results, and the accuracy of output is limited for all the existent tools. Very complex energy models, different parameter estimation methods, and recent machine learning approaches had not been the answer for this problem. We believe that the first step to achieve results with high quality is to use the energy model with the potential for predicting accurate output. Hence, it is necessary to have a systematic …

De Novo Co-Assembly Of Bacterial Genomes From Multiple Single Cells, Narjes Sadat Movahedi Tabrizi

Wayne State University Theses

Recent progress in DNA amplication techniques, particularly multiple displacement amplication (MDA), has made it possible to sequence and assemble bacterial genomes from a single cell. However, the quality of single cell genome assembly has not yet reached the quality of normal multicell genome assembly due to the coverage bias and errors caused by MDA. Using a template of more than one cell for MDA or combining separate MDA products has been shown to improve the result of genome assembly from few single cells, but providing identical single cells, as a necessary step for these approaches, is a challenge. As a …

Teak: A Novel Computational And Gui Software Pipeline For Reconstructing Biological Networks, Detecting Activated Biological Subnetworks, And Querying Biological Networks., Thair Judeh

Wayne State University Dissertations

As high-throughput gene expression data becomes cheaper and cheaper, researchers are faced with a deluge of data from which biological insights need to be extracted and mined since the rate of data accumulation far exceeds the rate of data analysis. There is a need for computational frameworks to bridge the gap and assist researchers in their tasks. The Topology Enrichment Analysis frameworK (TEAK) is an open source GUI and software pipeline that seeks to be one of many tools that fills in this gap and consists of three major modules. The first module, the Gene Set Cultural Algorithm, de novo …

Towards Personalized Medicine Using Systems Biology And Machine Learning, Calin Voichita

Wayne State University Dissertations

The rate of acquiring biological data has greatly surpassed our ability to interpret it. At the same time, we have started to understand that evolution of many diseases such as cancer, are the results of the interplay between the disease itself and the immune system of the host. It is now well accepted that cancer is not a single disease, but a “complex collection of distinct genetic diseases united by common hallmarks”. Understanding the differences between such disease subtypes is key not only in providing adequate treatments for known subtypes but also identifying new ones. These unforeseen disease subtypes are …

Computational Approaches To Anti-Toxin Therapies And Biomarker Identification, Rebecca Jane Swett

Wayne State University Dissertations

This work describes the fundamental study of two bacterial toxins with computational methods, the rational design of a potent inhibitor using molecular dynamics, as well as the development of two bioinformatic methods for mining genomic data.

Clostridium difficile is an opportunistic bacillus which produces two large glucosylating toxins. These toxins, TcdA and TcdB cause severe intestinal damage. As Clostridium difficile harbors considerable antibiotic resistance, one treatment strategy is to prevent the tissue damage that the toxins cause. The catalytic glucosyltransferase domain of TcdA and TcdB was studied using molecular dynamics in the presence of both a protein-protein binding partner and …

Hierarchical Multi-Label Classification For Protein Function Prediction Going Beyond Traditional Approaches, Noor Al Aydie

Wayne State University Dissertations

Hierarchical multi-label classification is a variant of traditional classification in which the

instances can belong to several labels, that are in turn organized in a hierarchy. Functional classification of genes is a challenging problem in functional genomics due to several reasons. First, each gene participates in multiple biological activities. Hence, prediction models should support multi-label classification. Second, the genes are organized and classified according to a hierarchical classification scheme that represents the relationships between the functions of the genes. These relationships should be maintained by the prediction models. In addition, various bimolecular data sources, such as gene expression data and …

Differential Modeling For Cancer Microarray Data, Omar Odibat

Wayne State University Dissertations

Capturing the changes between two biological phenotypes is a crucial task in understanding the mechanisms of various diseases. Most of the existing computational approaches depend on testing the changes in the expression levels of each single gene individually. In this work, we proposed novel computational approaches to identify the differential genes between two phenotypes. These approaches aim to quantitatively characterize the differences between two phenotypes and can provide better insights and understanding of various diseases. The purpose of this thesis is three-fold. Firstly, we review the state-of-the-art approaches for differential analysis of gene expression data.

Secondly, we propose a novel …

Detecting Phenotype-Specific Interactions Between Biological Processes From Microarray Data And Annotations, Nadeem Ahmed Ansari

Wayne State University Dissertations

The development of high throughput technologies such as DNA microarrays has enabled researchers to measure expression levels on a genomic scale. Correct and efficient biological interpretation of the voluminous data generated by these technologies, however, remains a challenging problem. A commonly used approach in interpreting the results of such high throughput experiments is to map the list of differentially expressed (DE) genes to gene ontology (GO) terms, which provides a list of biological processes, biochemical functions, and cellular locations associated with the DE genes. A previously unexplored aspect is the identifications of unusual associations between biological processes. Such associations may …