Thesis (Ph. D.)--West Virginia University, 2007. / Title from document title page. Document formatted into pages; contains x, 125 p. : ill. (some col.). Includes abstract. Includes bibliographical references (p. 113-125).

Consensus pattern problem (CPP) aims at finding conserved regions, or motifs, in unaligned sequences. This problem is NP-hard under various scoring schemes. To solve this problem for protein sequences more efficiently,a new scoring scheme and a randomized algorithm based on substitution matrix are proposed here. Any practical solutions to a bioinformatics problem must observe twoprinciples: (1) the problem that it solves accurately describes the real problem; in CPP, this requires the scoring scheme be able to distinguisha real motif from background; (2) it provides an efficient algorithmto solve the mathematical problem. A key question in protein motif-finding is how to determine the motif length. One problem in EM algorithms to solve CPP is how to find good startingpoints to reach the global optimum. These two questions were both well addressed under this scoring scheme,which made the randomized algorithm both fast and accurate in practice. A software, COPIA (COnsensus Pattern Identification and Analysis),has been developed implementing this algorithm. Experiments using sequences from the von Willebrand factor (vWF)familyshowed that it worked well on finding multiple motifs and repeats. COPIA's ability to find repeats makes it also useful in illustrating the internal structures of multidomain proteins. Comparative studies using several groups of protein sequences demonstrated that COPIA performed better than the commonly used motif-finding programs.

Consensus pattern problem (CPP) aims at finding conserved regions, or motifs, in unaligned sequences. This problem is NP-hard under various scoring schemes. To solve this problem for protein sequences more efficiently,a new scoring scheme and a randomized algorithm based on substitution matrix are proposed here. Any practical solutions to a bioinformatics problem must observe twoprinciples: (1) the problem that it solves accurately describes the real problem; in CPP, this requires the scoring scheme be able to distinguisha real motif from background; (2) it provides an efficient algorithmto solve the mathematical problem. A key question in protein motif-finding is how to determine the motif length. One problem in EM algorithms to solve CPP is how to find good startingpoints to reach the global optimum. These two questions were both well addressed under this scoring scheme,which made the randomized algorithm both fast and accurate in practice. A software, COPIA (COnsensus Pattern Identification and Analysis),has been developed implementing this algorithm. Experiments using sequences from the von Willebrand factor (vWF)familyshowed that it worked well on finding multiple motifs and repeats. COPIA's ability to find repeats makes it also useful in illustrating the internal structures of multidomain proteins. Comparative studies using several groups of protein sequences demonstrated that COPIA performed better than the commonly used motif-finding programs.

<div> <div> <div> <p>Proteins are drivers of almost all biological processes in the cell. The functions of a protein are dependent on their three-dimensional structure and elucidating the structure and function of proteins is key to understanding how a biological system operates. In this research, we developed computational methods using machine learning techniques to predicts the structure and function of proteins. Protein 3D structure prediction has advanced significantly in recent years, largely due to deep learning approaches that predict inter-residue contacts and, more recently, distances using multiple sequence alignments (MSAs). The performance of these models depends on the number of similar protein sequences to the query protein, wherein some cases similar sequences are few but dissimilar sequences with local similarities are more and can be helpful. We have developed a novel deep learning-based approach AttentiveDist which further improves over the previous state of art. We added an attention mechanism where dis-similar sequences are also used (increasing number of sequences) and the model itself determines which information from such sequences it should attend to. We showed that the improvement of distance predictions was successfully transferred to achieve better protein tertiary structure modeling. We also show that structure prediction from a predicted distance map can be further enhanced by using predicted inter-residue sidechain center distances and main-chain hydrogen-bonds. Protein function prediction is another avenue we explored where we want to predict the function that a protein will perform. The crux of the approach is to predict the function of protein based on the function of similar sequences. Here, we developed a method where we use dissimilar sequences to extract additional information and improve performance over the previous approaches. We used phylogenetic analysis to determine if a dissimilar sequence can be close to the query sequence and thus can provide functional information. Our method was ranked highly in worldwide protein function prediction competition CAFA3 (2016-2019). Further, we expanded the method with a neural network to predict protein toxicity that can be used as a safety check for human-designed protein sequences.</p></div></div></div>

Autism Spectrum Disorder (ASD) is part of the developmental disabilities. There are numerous symptoms for ASD patients, including lack of abilities in social interaction, communication obstacle and repeatable behaviors. Meanwhile, the rate of ASD prevalence has kept rising by the past 20 years from 1 out of 150 in 2000 to 1 out of 54 in 2016. In addition, the ASD population is quite large. Specifically, 3.5 million Americans live with ASD in the year of 2014, which will cost U.S. citizens $236-$262 billion dollars annually for autism services. So, it is critical to make an accurate diagnosis for preschool age children with ASD, in order to give them a better life. Instead of using traditional ASD behavioral tests, such as ADI-R, ADOS, and DSM-IV, we applied brain MRI images as input to make diagnosis. We revised 3D-ResNet structure to fit 110 preschool children's brain MRI data, along with Convolution 3D and VGG model. The prediction accuracy with raw data is 65.22%. The accuracy is significantly improved to 82.61% by removing the noise around the brain. We also showed the speed of ML prediction is 308 times faster than behavior tests.

<p>Data science uses the latest techniques in statistics and machine learning to extract insights from data. With the increasing amount of protein data, a number of novel research approaches have become feasible.</p><p>Micropeptides are an emerging field in the protein universe. They are small proteins with <= 100 amino acid residues (aa) and are translated from small open reading frames (sORFs) of <= 303 base pairs (bp). Traditionally, their existence was ignored because of the technical difficulties in isolating them. With technological advances, a growing number of micropeptides have been characterized and shown to play vital roles in many biological processes. Yet, we lack bioinformatics methods for predicting them directly from DNA sequences, which could substantially facilitate research in this field with minimal cost. With the increasing amount of data, developing new methods to address this need becomes possible. We therefore developed MiPepid, a machine-learning-based method specifically designed for predicting micropeptides from DNA sequences by curating a high-quality dataset and by training MiPepid using logistic regression with 4-mer features. MiPepid performed exceptionally well on holdout test sets and performed much better than existing methods. MiPepid is available for downloading, easy to use, and runs sufficiently fast.</p><p>Long noncoding RNAs (LncRNAs) are transcripts of > 200 bp and does not encode a protein. Contrary to their “noncoding” definition, an increasing number of lncRNAs have been found to be translated into functional micropeptides. Therefore, whether most lncRNAs are translated is an open question of great significance. To address this question, by harnessing the availability of large-scale human variation data, we have explored the relationships between lncRNAs, micropeptides, and canonical regular proteins (> 100 aa) from the perspective of genetic variation, which has long been used to study natural selection to infer functional relevance. Through rigorous statistical analyses, we find that lncRNAs share a similar genetic variation profile with proteins regarding single nucleotide polymorphism (SNP) density, SNP spectrum, enrichment of rare SNPs, etc., suggesting lncRNAs are under similar negative selection strength with proteins. Our study revealed similarities between micropeptides, lncRNAs, and canonical proteins and is the first attempt to explore the relationships between the three groups from a genetic variation perspective.</p><p>Deep learning has been tremendously successful in 2D image recognition. Protein binding ligand prediction is fundamental topic in protein research as most proteins bind ligands to function. Proteins are 3D structures and can be considered as 3D images. Prediction of binding ligands of proteins can then be converted to a 3D image classification problem. In addition, a large number of protein structure data are available now. We therefore utilized deep learning to predict protein binding ligands by designing a 3D convolutional neural network from scratch and by building a large 3D image dataset of protein structures. The trained model achieved an average F1 score of over 0.8 across 151 classes on the holdout test set. Compared to existing methods, our model performed better. In summary, we showed the feasibility of deploying deep learning in protein structure research.</p><p>In conclusion, by exploring various edges of the protein universe from the perspective of data science, we showed that the increasing amount of data and the advancement of data science methods made it possible to address a wide variety of pressing biological questions. We showed that for a successful data science study, the three components – goal, data, method – all of them are indispensable. We provided three successful data science studies: the careful data cleaning and selection of machine learning algorithm lead to the development of MiPepid that fits the urgent need of a micropeptide prediction method; identifying the question and exploring it from a different angle lead to the key insight that lncRNAs resemble micropeptides; applying deep learning to protein structure data lead to a new approach to the long-standing question of protein-ligand binding. The three studies serve as excellent examples in solving a wide range of data science problems with a variety of issues.</p>

<div>With the rapid development in high-throughput technologies and the next generation sequencing (NGS) during the past decades, the bottleneck for advances in computational biology and bioinformatics research has shifted from data collection to data analysis. As one of the central goals in precision health, understanding and interpreting high-dimensional biomedical data is of major interest in computational biology and bioinformatics domains. Since significant effort has been committed to harnessing biomedical data for multiple analyses, this thesis is aiming for developing new machine learning approaches to help discover and interpret the complex mechanisms and interactions behind the high dimensional features in biomedical data. Moreover, this thesis also studies the prediction of post-treatment response given histopathologic images with machine learning.</div><div><br></div><div>Capturing the important features behind the biomedical data can be achieved in many ways such as network and correlation analyses, dimensionality reduction, image processing, etc. In this thesis, we accomplish the computation through co-expression analysis, survival analysis, and matrix decomposition in supervised and unsupervised learning manners. We use co-expression analysis as upfront feature engineering, implement survival regression in deep learning to predict patient survival and discover associated factors. By integrating Cox proportional hazards regression into non-negative matrix factorization algorithm, the latent clusters of human genes are uncovered. Using machine learning and automatic feature extraction workflow, we extract thirty-six image features from histopathologic images, and use them to predict post-treatment response. In addition, a web portal written by R language is built in order to bring convenience to future biomedical studies and analyses.</div><div><br></div><div>In conclusion, driven by machine learning algorithms, this thesis focuses on the integrative analysis given multimodal biomedical data, especially the supervised cancer patient survival prognosis, the recognition of latent gene clusters, and the application of predicting post-treatment response from histopathologic images. The proposed computational algorithms present its superiority comparing to other state-of-the-art models, provide new insights toward the biomedical and cancer studies in the future.</div>

<p>The goal of this thesis is to algorithmically identify candidate modifiers for <i>retinitis pigmentosa</i> (RP) to help improve therapy and predictions for this genetic disorder that may lead to a complete loss of vision. A current research by (Chow et al., 2016) focused on the genetic contributors to RP by trying to recognize a correlation between genetic modifiers and phenotypic variation in female <i>Drosophila melanogaster</i>, or fruit flies. In comparison to the genome-wide association analysis carried out in Chow et al.’s research, this study proposes using a K-Means clustering algorithm on RNA expression data to better understand which genes best exhibit characteristics of the RP degenerative model. Validating this algorithm’s effectiveness in identifying suspected genes takes priority over their classification.</p><p>This study investigates the linear relationship between <i>Drosophila </i>eye size and genetic expression to gather statistically significant, strongly correlated genes from the clusters with abnormally high or low eye sizes. The clustering algorithm is implemented in the R scripting language, and supplemental information details the steps of this computational process. Running the mean eye size and genetic expression data of 18,140 female <i>Drosophila</i> genes and 171 strains through the proposed algorithm in its four variations helped identify 140 suspected candidate modifiers for retinal degeneration. Although none of the top candidate genes found in this study matched Chow’s candidates, they were all statistically significant and strongly correlated, with several showing links to RP. These results may continue to improve as more of the 140 suspected genes are annotated using identical or comparative approaches.</p>