Matching Items (15)
Filtering by
- All Subjects: Bioinformatics
- All Subjects: Biology
Description
Sparsity has become an important modeling tool in areas such as genetics, signal and audio processing, medical image processing, etc. Via the penalization of l-1 norm based regularization, the structured sparse learning algorithms can produce highly accurate models while imposing various predefined structures on the data, such as feature groups or graphs. In this thesis, I first propose to solve a sparse learning model with a general group structure, where the predefined groups may overlap with each other. Then, I present three real world applications which can benefit from the group structured sparse learning technique. In the first application, I study the Alzheimer's Disease diagnosis problem using multi-modality neuroimaging data. In this dataset, not every subject has all data sources available, exhibiting an unique and challenging block-wise missing pattern. In the second application, I study the automatic annotation and retrieval of fruit-fly gene expression pattern images. Combined with the spatial information, sparse learning techniques can be used to construct effective representation of the expression images. In the third application, I present a new computational approach to annotate developmental stage for Drosophila embryos in the gene expression images. In addition, it provides a stage score that enables one to more finely annotate each embryo so that they are divided into early and late periods of development within standard stage demarcations. Stage scores help us to illuminate global gene activities and changes much better, and more refined stage annotations improve our ability to better interpret results when expression pattern matches are discovered between genes.
ContributorsYuan, Lei (Author) / Ye, Jieping (Thesis advisor) / Wang, Yalin (Committee member) / Xue, Guoliang (Committee member) / Kumar, Sudhir (Committee member) / Arizona State University (Publisher)
Created2013
Description
In blindness research, the corpus callosum (CC) is the most frequently studied sub-cortical structure, due to its important involvement in visual processing. While most callosal analyses from brain structural magnetic resonance images (MRI) are limited to the 2D mid-sagittal slice, we propose a novel framework to capture a complete set of 3D morphological differences in the corpus callosum between two groups of subjects. The CCs are segmented from whole brain T1-weighted MRI and modeled as 3D tetrahedral meshes. The callosal surface is divided into superior and inferior patches on which we compute a volumetric harmonic field by solving the Laplace's equation with Dirichlet boundary conditions. We adopt a refined tetrahedral mesh to compute the Laplacian operator, so our computation can achieve sub-voxel accuracy. Thickness is estimated by tracing the streamlines in the harmonic field. We combine areal changes found using surface tensor-based morphometry and thickness information into a vector at each vertex to be used as a metric for the statistical analysis. Group differences are assessed on this combined measure through Hotelling's T2 test. The method is applied to statistically compare three groups consisting of: congenitally blind (CB), late blind (LB; onset > 8 years old) and sighted (SC) subjects. Our results reveal significant differences in several regions of the CC between both blind groups and the sighted groups; and to a lesser extent between the LB and CB groups. These results demonstrate the crucial role of visual deprivation during the developmental period in reshaping the structural architecture of the CC.
ContributorsXu, Liang (Author) / Wang, Yalin (Thesis advisor) / Maciejewski, Ross (Committee member) / Ye, Jieping (Committee member) / Arizona State University (Publisher)
Created2013
Description
In many fields one needs to build predictive models for a set of related machine learning tasks, such as information retrieval, computer vision and biomedical informatics. Traditionally these tasks are treated independently and the inference is done separately for each task, which ignores important connections among the tasks. Multi-task learning aims at simultaneously building models for all tasks in order to improve the generalization performance, leveraging inherent relatedness of these tasks. In this thesis, I firstly propose a clustered multi-task learning (CMTL) formulation, which simultaneously learns task models and performs task clustering. I provide theoretical analysis to establish the equivalence between the CMTL formulation and the alternating structure optimization, which learns a shared low-dimensional hypothesis space for different tasks. Then I present two real-world biomedical informatics applications which can benefit from multi-task learning. In the first application, I study the disease progression problem and present multi-task learning formulations for disease progression. In the formulations, the prediction at each point is a regression task and multiple tasks at different time points are learned simultaneously, leveraging the temporal smoothness among the tasks. The proposed formulations have been tested extensively on predicting the progression of the Alzheimer's disease, and experimental results demonstrate the effectiveness of the proposed models. In the second application, I present a novel data-driven framework for densifying the electronic medical records (EMR) to overcome the sparsity problem in predictive modeling using EMR. The densification of each patient is a learning task, and the proposed algorithm simultaneously densify all patients. As such, the densification of one patient leverages useful information from other patients.
ContributorsZhou, Jiayu (Author) / Ye, Jieping (Thesis advisor) / Mittelmann, Hans (Committee member) / Li, Baoxin (Committee member) / Wang, Yalin (Committee member) / Arizona State University (Publisher)
Created2014
Description
Genes have widely different pertinences to the etiology and pathology of diseases. Thus, they can be ranked according to their disease-significance on a genomic scale, which is the subject of gene prioritization. Given a set of genes known to be related to a disease, it is reasonable to use them as a basis to determine the significance of other candidate genes, which will then be ranked based on the association they exhibit with respect to the given set of known genes. Experimental and computational data of various kinds have different reliability and relevance to a disease under study. This work presents a gene prioritization method based on integrated biological networks that incorporates and models the various levels of relevance and reliability of diverse sources. The method is shown to achieve significantly higher performance as compared to two well-known gene prioritization algorithms. Essentially, no bias in the performance was seen as it was applied to diseases of diverse ethnology, e.g., monogenic, polygenic and cancer. The method was highly stable and robust against significant levels of noise in the data. Biological networks are often sparse, which can impede the operation of associationbased gene prioritization algorithms such as the one presented here from a computational perspective. As a potential approach to overcome this limitation, we explore the value that transcription factor binding sites can have in elucidating suitable targets. Transcription factors are needed for the expression of most genes, especially in higher organisms and hence genes can be associated via their genetic regulatory properties. While each transcription factor recognizes specific DNA sequence patterns, such patterns are mostly unknown for many transcription factors. Even those that are known are inconsistently reported in the literature, implying a potentially high level of inaccuracy. We developed computational methods for prediction and improvement of transcription factor binding patterns. Tests performed on the improvement method by employing synthetic patterns under various conditions showed that the method is very robust and the patterns produced invariably converge to nearly identical series of patterns. Preliminary tests were conducted to incorporate knowledge from transcription factor binding sites into our networkbased model for prioritization, with encouraging results. Genes have widely different pertinences to the etiology and pathology of diseases. Thus, they can be ranked according to their disease-significance on a genomic scale, which is the subject of gene prioritization. Given a set of genes known to be related to a disease, it is reasonable to use them as a basis to determine the significance of other candidate genes, which will then be ranked based on the association they exhibit with respect to the given set of known genes. Experimental and computational data of various kinds have different reliability and relevance to a disease under study. This work presents a gene prioritization method based on integrated biological networks that incorporates and models the various levels of relevance and reliability of diverse sources. The method is shown to achieve significantly higher performance as compared to two well-known gene prioritization algorithms. Essentially, no bias in the performance was seen as it was applied to diseases of diverse ethnology, e.g., monogenic, polygenic and cancer. The method was highly stable and robust against significant levels of noise in the data. Biological networks are often sparse, which can impede the operation of associationbased gene prioritization algorithms such as the one presented here from a computational perspective. As a potential approach to overcome this limitation, we explore the value that transcription factor binding sites can have in elucidating suitable targets. Transcription factors are needed for the expression of most genes, especially in higher organisms and hence genes can be associated via their genetic regulatory properties. While each transcription factor recognizes specific DNA sequence patterns, such patterns are mostly unknown for many transcription factors. Even those that are known are inconsistently reported in the literature, implying a potentially high level of inaccuracy. We developed computational methods for prediction and improvement of transcription factor binding patterns. Tests performed on the improvement method by employing synthetic patterns under various conditions showed that the method is very robust and the patterns produced invariably converge to nearly identical series of patterns. Preliminary tests were conducted to incorporate knowledge from transcription factor binding sites into our networkbased model for prioritization, with encouraging results. To validate these approaches in a disease-specific context, we built a schizophreniaspecific network based on the inferred associations and performed a comprehensive prioritization of human genes with respect to the disease. These results are expected to be validated empirically, but computational validation using known targets are very positive.
ContributorsLee, Jang (Author) / Gonzalez, Graciela (Thesis advisor) / Ye, Jieping (Committee member) / Davulcu, Hasan (Committee member) / Gallitano-Mendel, Amelia (Committee member) / Arizona State University (Publisher)
Created2011
Description
Detecting anatomical structures, such as the carina, the pulmonary trunk and the aortic arch, is an important step in designing a CAD system of detection Pulmonary Embolism. The presented CAD system gets rid of the high-level prior defined knowledge to become a system which can easily extend to detect other anatomic structures. The system is based on a machine learning algorithm --- AdaBoost and a general feature --- Haar. This study emphasizes on off-line and on-line AdaBoost learning. And in on-line AdaBoost, the thesis further deals with extremely imbalanced condition. The thesis first reviews several knowledge-based detection methods, which are relied on human being's understanding of the relationship between anatomic structures. Then the thesis introduces a classic off-line AdaBoost learning. The thesis applies different cascading scheme, namely multi-exit cascading scheme. The comparison between the two methods will be provided and discussed. Both of the off-line AdaBoost methods have problems in memory usage and time consuming. Off-line AdaBoost methods need to store all the training samples and the dataset need to be set before training. The dataset cannot be enlarged dynamically. Different training dataset requires retraining the whole process. The retraining is very time consuming and even not realistic. To deal with the shortcomings of off-line learning, the study exploited on-line AdaBoost learning approach. The thesis proposed a novel pool based on-line method with Kalman filters and histogram to better represent the distribution of the samples' weight. Analysis of the performance, the stability and the computational complexity will be provided in the thesis. Furthermore, the original on-line AdaBoost performs badly in imbalanced conditions, which occur frequently in medical image processing. In image dataset, positive samples are limited and negative samples are countless. A novel Self-Adaptive Asymmetric On-line Boosting method is presented. The method utilized a new asymmetric loss criterion with self-adaptability according to the ratio of exposed positive and negative samples and it has an advanced rule to update sample's importance weight taking account of both classification result and sample's label. Compared to traditional on-line AdaBoost Learning method, the new method can achieve far more accuracy in imbalanced conditions.
ContributorsWu, Hong (Author) / Liang, Jianming (Thesis advisor) / Farin, Gerald (Committee member) / Ye, Jieping (Committee member) / Arizona State University (Publisher)
Created2011
Description
Rapid advance in sensor and information technology has resulted in both spatially and temporally data-rich environment, which creates a pressing need for us to develop novel statistical methods and the associated computational tools to extract intelligent knowledge and informative patterns from these massive datasets. The statistical challenges for addressing these massive datasets lay in their complex structures, such as high-dimensionality, hierarchy, multi-modality, heterogeneity and data uncertainty. Besides the statistical challenges, the associated computational approaches are also considered essential in achieving efficiency, effectiveness, as well as the numerical stability in practice. On the other hand, some recent developments in statistics and machine learning, such as sparse learning, transfer learning, and some traditional methodologies which still hold potential, such as multi-level models, all shed lights on addressing these complex datasets in a statistically powerful and computationally efficient way. In this dissertation, we identify four kinds of general complex datasets, including "high-dimensional datasets", "hierarchically-structured datasets", "multimodality datasets" and "data uncertainties", which are ubiquitous in many domains, such as biology, medicine, neuroscience, health care delivery, manufacturing, etc. We depict the development of novel statistical models to analyze complex datasets which fall under these four categories, and we show how these models can be applied to some real-world applications, such as Alzheimer's disease research, nursing care process, and manufacturing.
ContributorsHuang, Shuai (Author) / Li, Jing (Thesis advisor) / Askin, Ronald (Committee member) / Ye, Jieping (Committee member) / Runger, George C. (Committee member) / Arizona State University (Publisher)
Created2012
Description
Mammary gland development in humans during puberty involves the enlargement of breast tissue, but this is not true in non-human primates. To identify potential causes of this difference, I examined variation in substitution rates across genes related to mammary development. Genes undergoing purifying selection show slower-than-average substitution rates, while genes undergoing positive selection show faster rates. These may be related to the difference between humans and other primates. Three genes were found to be accelerated were FOXF1, IGFBP5, and ATP2B2, but only the latter one was found in humans and it seems unlikely that it would be related to the differences between mammary gland development at puberty between humans and non-human primates.
ContributorsArroyo, Diana (Author) / Cartwright, Reed (Thesis director) / Wilson Sayres, Melissa (Committee member) / Schwartz, Rachel (Committee member) / School of Life Sciences (Contributor) / Barrett, The Honors College (Contributor)
Created2016-05
Description
The modern web presents an opportunity for educators and researchers to create tools that are highly accessible. Because of the near-ubiquity of modern web browsers, developers who hope to create educational and analytical tools can reach a large au- dience by creating web applications. Using JavaScript, HTML, and other modern web development technologies, Genie was developed as a simulator to help educators in biology, genetics, and evolution classrooms teach their students about population genetics. Because Genie was designed for the modern web, it is highly accessible to both educators and students, who can access the web application using any modern web browser on virtually any device. Genie demonstrates the efficacy of web devel- opment technologies for demonstrating and simulating complex processes, and it will be a unique educational tool for educators who teach population genetics.
ContributorsRoos, Benjamin Hirsch (Author) / Cartwright, Reed (Thesis director) / Wilson Sayres, Melissa (Committee member) / Mayron, Liam (Committee member) / Barrett, The Honors College (Contributor) / Computer Science and Engineering Program (Contributor)
Created2015-05
Description
With the rising data output and falling costs of Next Generation Sequencing technologies, research into data compression is crucial to maintaining storage efficiency and costs. High throughput sequencers such as the HiSeqX Ten can produce up to 1.8 terabases of data per run, and such large storage demands are even more important to consider for institutions that rely on their own servers rather than large data centers (cloud storage)1. Compression algorithms aim to reduce the amount of space taken up by large genomic datasets by encoding the most frequently occurring symbols with the shortest bit codewords and by changing the order of the data to make it easier to encode. Depending on the probability distribution of the symbols in the dataset or the structure of the data, choosing the wrong algorithm could result in a compressed file larger than the original or a poorly compressed file that results in a waste of time and space2. To test efficiency among compression algorithms for each file type, 37 open-source compression algorithms were used to compress six types of genomic datasets (FASTA, VCF, BCF, GFF, GTF, and SAM) and evaluated on compression speed, decompression speed, compression ratio, and file size using the benchmark test lzbench. Compressors that outpreformed the popular bioinformatics compressor Gzip (zlib -6) were evaluated against one another by ratio and speed for each file type and across the geometric means of all file types. Compressors that exhibited fast compression and decompression speeds were also evaluated by transmission time through variable speed internet pipes in scenarios where the file was compressed only once or compressed multiple times.
ContributorsHowell, Abigail (Author) / Cartwright, Reed (Thesis director) / Wilson Sayres, Melissa (Committee member) / Taylor, Jay (Committee member) / Barrett, The Honors College (Contributor)
Created2017-05
Description
Lactase persistence is the ability of adults to digest lactose in milk (Segurel & Bon, 2017). Mammals are generally distinguished by their mammary glands which gives females the ability to produce milk and feed their newborn children. The new born therefore requires the ability to breakdown the lactose in the milk to ensure its proper digestion (Segurel & Bon, 2017). Generally, humans lose the expression of lactase after weaning, which prevents them being able to breakdown lactose from dairy (Flatz, 1987).
My research is focused on the people of Turkana, a human pastoral population inhabiting Northwest Kenya. The people of Turkana are Nilotic people that are native to the Turkana district. There are currently no conclusive studies done on evidence for genetic lactase persistence in Turkana. Therefore, my research will be on the evolution of lactase persistence in the people of Turkana. The goal of this project is to investigate the evolutionary history of two genes with known involvement in lactase persistence, LCT and MCM6, in the Turkana. Variants in these genes have previously been identified to result in the ability to digest lactose post-weaning age. Furthermore, an additional study found that a closely related population to the Turkana, the Massai, showed stronger signals of recent selection for lactase persistence than Europeans in these genes. My goal is to characterize known variants associated with lactase persistence by calculating their allele frequencies in the Turkana and conduct selection scans to determine if LCT/MCM6 show signatures of positive selection. In doing this, we conducted a pilot study consisting of 10 female Turkana individuals and 10 females from four different populations from the 1000 genomes project namely: the Yoruba in Ibadan, Nigeria (YRI); Luhya in Webuye, Kenya; Utah Residents with Northern and Western European Ancestry (CEU); and the Southern Han Chinese. The allele frequency calculation suggested that the CEU (Utah Residents with Northern and Western European Ancestry) population had a higher lactase persistence associated allele frequency than all the other populations analyzed here, including the Turkana population. Our Tajima’s D calculations and analysis suggested that both the Turkana population and the four haplotype map populations shows signatures of positive selection in the same region. The iHS selection scans we conducted to detect signatures of positive selection on all five populations showed that the Southern Han Chinese (CHS), the LWK (Luhya in Webuye, Kenya) and the YRI (Yoruba in Ibadan, Nigeria) populations had stronger signatures of positive selection than the Turkana population. The LWK (Luhya in Webuye, Kenya) and the YRI (Yoruba in Ibadan, Nigeria) populations showed the strongest signatures of positive selection in this region. This project serves as a first step in the investigation of lactase persistence in the Turkana population and its evolution over time.
My research is focused on the people of Turkana, a human pastoral population inhabiting Northwest Kenya. The people of Turkana are Nilotic people that are native to the Turkana district. There are currently no conclusive studies done on evidence for genetic lactase persistence in Turkana. Therefore, my research will be on the evolution of lactase persistence in the people of Turkana. The goal of this project is to investigate the evolutionary history of two genes with known involvement in lactase persistence, LCT and MCM6, in the Turkana. Variants in these genes have previously been identified to result in the ability to digest lactose post-weaning age. Furthermore, an additional study found that a closely related population to the Turkana, the Massai, showed stronger signals of recent selection for lactase persistence than Europeans in these genes. My goal is to characterize known variants associated with lactase persistence by calculating their allele frequencies in the Turkana and conduct selection scans to determine if LCT/MCM6 show signatures of positive selection. In doing this, we conducted a pilot study consisting of 10 female Turkana individuals and 10 females from four different populations from the 1000 genomes project namely: the Yoruba in Ibadan, Nigeria (YRI); Luhya in Webuye, Kenya; Utah Residents with Northern and Western European Ancestry (CEU); and the Southern Han Chinese. The allele frequency calculation suggested that the CEU (Utah Residents with Northern and Western European Ancestry) population had a higher lactase persistence associated allele frequency than all the other populations analyzed here, including the Turkana population. Our Tajima’s D calculations and analysis suggested that both the Turkana population and the four haplotype map populations shows signatures of positive selection in the same region. The iHS selection scans we conducted to detect signatures of positive selection on all five populations showed that the Southern Han Chinese (CHS), the LWK (Luhya in Webuye, Kenya) and the YRI (Yoruba in Ibadan, Nigeria) populations had stronger signatures of positive selection than the Turkana population. The LWK (Luhya in Webuye, Kenya) and the YRI (Yoruba in Ibadan, Nigeria) populations showed the strongest signatures of positive selection in this region. This project serves as a first step in the investigation of lactase persistence in the Turkana population and its evolution over time.
ContributorsJobe, Ndey Bassin (Author) / Wilson Sayres, Melissa (Thesis director) / Paaijmans, Krijn (Committee member) / Taravella, Angela (Committee member) / School of Earth and Space Exploration (Contributor) / School of Life Sciences (Contributor) / Barrett, The Honors College (Contributor)
Created2019-05