Mining Data with Feature Interactions

156963-Thumbnail Image.png
Description
Models using feature interactions have been applied successfully in many areas such as biomedical analysis, recommender systems. The popularity of using feature interactions mainly lies in (1) they are able to capture the nonlinearity of the data compared with linear…

Models using feature interactions have been applied successfully in many areas such as biomedical analysis, recommender systems. The popularity of using feature interactions mainly lies in (1) they are able to capture the nonlinearity of the data compared with linear effects and (2) they enjoy great interpretability. In this thesis, I propose a series of formulations using feature interactions for real world problems and develop efficient algorithms for solving them.

Specifically, I first propose to directly solve the non-convex formulation of the weak hierarchical Lasso which imposes weak hierarchy on individual features and interactions but can only be approximately solved by a convex relaxation in existing studies. I further propose to use the non-convex weak hierarchical Lasso formulation for hypothesis testing on the interaction features with hierarchical assumptions. Secondly, I propose a type of bi-linear models that take advantage of interactions of features for drug discovery problems where specific drug-drug pairs or drug-disease pairs are of interest. These models are learned by maximizing the number of positive data pairs that rank above the average score of unlabeled data pairs. Then I generalize the method to the case of using the top-ranked unlabeled data pairs for representative construction and derive an efficient algorithm for the extended formulation. Last but not least, motivated by a special form of bi-linear models, I propose a framework that enables simultaneously subgrouping data points and building specific models on the subgroups for learning on massive and heterogeneous datasets. Experiments on synthetic and real datasets are conducted to demonstrate the effectiveness or efficiency of the proposed methods.
Date Created
2018
Agent

Analysis of Twitter's Effect on Stock Prices

137174-Thumbnail Image.png
Description
Twitter has become a very popular social media site that is used daily by many people and organizations. This paper will focus on the financial aspect of Twitter, as a process will be shown to be able to mine data…

Twitter has become a very popular social media site that is used daily by many people and organizations. This paper will focus on the financial aspect of Twitter, as a process will be shown to be able to mine data about specific companies' stock prices. This was done by writing a program to grab tweets about the stocks of the thirty companies in the Dow Jones.
Date Created
2014-05
Agent

Network Reconstruction Based on Evolutionary-Game Data Via Compressive Sensing

128004-Thumbnail Image.png
Description

Evolutionary games model a common type of interactions in a variety of complex, networked, natural systems and social systems. Given such a system, uncovering the interacting structure of the underlying network is key to understanding its collective dynamics. Based on…

Evolutionary games model a common type of interactions in a variety of complex, networked, natural systems and social systems. Given such a system, uncovering the interacting structure of the underlying network is key to understanding its collective dynamics. Based on compressive sensing, we develop an efficient approach to reconstructing complex networks under game-based interactions from small amounts of data. The method is validated by using a variety of model networks and by conducting an actual experiment to reconstruct a social network. While most existing methods in this area assume oscillator networks that generate continuous-time data, our work successfully demonstrates that the extremely challenging problem of reverse engineering of complex networks can also be addressed even when the underlying dynamical processes are governed by realistic, evolutionary-game type of interactions in discrete time.

Date Created
2011-12-21
Agent

Comparison of Nine Tractography Algorithms for Detecting Abnormal Structural Brain Networks in Alzheimer’s Disease

128110-Thumbnail Image.png
Description

Alzheimer’s disease (AD) involves a gradual breakdown of brain connectivity, and network analyses offer a promising new approach to track and understand disease progression. Even so, our ability to detect degenerative changes in brain networks depends on the methods used.…

Alzheimer’s disease (AD) involves a gradual breakdown of brain connectivity, and network analyses offer a promising new approach to track and understand disease progression. Even so, our ability to detect degenerative changes in brain networks depends on the methods used. Here we compared several tractography and feature extraction methods to see which ones gave best diagnostic classification for 202 people with AD, mild cognitive impairment or normal cognition, scanned with 41-gradient diffusion-weighted magnetic resonance imaging as part of the Alzheimer’s Disease Neuroimaging Initiative (ADNI) project. We computed brain networks based on whole brain tractography with nine different methods – four of them tensor-based deterministic (FACT, RK2, SL, and TL), two orientation distribution function (ODF)-based deterministic (FACT, RK2), two ODF-based probabilistic approaches (Hough and PICo), and one “ball-and-stick” approach (Probtrackx). Brain networks derived from different tractography algorithms did not differ in terms of classification performance on ADNI, but performing principal components analysis on networks helped classification in some cases. Small differences may still be detectable in a truly vast cohort, but these experiments help assess the relative advantages of different tractography algorithms, and different post-processing choices, when used for classification.

Date Created
2015-04-14
Agent

Boosting Brain Connectome Classification Accuracy in Alzheimer's Disease Using Higher-Order Singular Value Decomposition

128112-Thumbnail Image.png
Description

Alzheimer's disease (AD) is a progressive brain disease. Accurate detection of AD and its prodromal stage, mild cognitive impairment (MCI), are crucial. There is also a growing interest in identifying brain imaging biomarkers that help to automatically differentiate stages of…

Alzheimer's disease (AD) is a progressive brain disease. Accurate detection of AD and its prodromal stage, mild cognitive impairment (MCI), are crucial. There is also a growing interest in identifying brain imaging biomarkers that help to automatically differentiate stages of Alzheimer's disease. Here, we focused on brain structural networks computed from diffusion MRI and proposed a new feature extraction and classification framework based on higher order singular value decomposition and sparse logistic regression. In tests on publicly available data from the Alzheimer's Disease Neuroimaging Initiative, our proposed framework showed promise in detecting brain network differences that help in classifying different stages of Alzheimer's disease.

Date Created
2015-07-24
Agent

FlyExpress 7: An Integrated Discovery Platform To Study Coexpressed Genes Using in Situ Hybridization Images in Drosophila

130273-Thumbnail Image.png
Description
Gene expression patterns assayed across development can offer key clues about a gene’s function and regulatory role. Drosophila melanogaster is ideal for such investigations as multiple individual and high-throughput efforts have captured the spatiotemporal patterns of thousands of embryonic expressed…

Gene expression patterns assayed across development can offer key clues about a gene’s function and regulatory role. Drosophila melanogaster is ideal for such investigations as multiple individual and high-throughput efforts have captured the spatiotemporal patterns of thousands of embryonic expressed genes in the form of in situ images. FlyExpress (www.flyexpress.net), a knowledgebase based on a massive and unique digital library of standardized images and a simple search engine to find coexpressed genes, was created to facilitate the analytical and visual mining of these patterns. Here, we introduce the next generation of FlyExpress resources to facilitate the integrative analysis of sequence data and spatiotemporal patterns of expression from images. FlyExpress 7 now includes over 100,000 standardized in situ images and implements a more efficient, user-defined search algorithm to identify coexpressed genes via Genomewide Expression Maps (GEMs). Shared motifs found in the upstream 5′ regions of any pair of coexpressed genes can be visualized in an interactive dotplot. Additional webtools and link-outs to assist in the downstream validation of candidate motifs are also provided. Together, FlyExpress 7 represents our largest effort yet to accelerate discovery via the development and dispersal of new webtools that allow researchers to perform data-driven analyses of coexpression (image) and genomic (sequence) data.
Date Created
2017-06-30
Agent

Evolution-Informed Modeling Improves Outcome Prediction for Cancers

128373-Thumbnail Image.png
Description

Despite wide applications of high-throughput biotechnologies in cancer research, many biomarkers discovered by exploring large-scale omics data do not provide satisfactory performance when used to predict cancer treatment outcomes. This problem is partly due to the overlooking of functional implications…

Despite wide applications of high-throughput biotechnologies in cancer research, many biomarkers discovered by exploring large-scale omics data do not provide satisfactory performance when used to predict cancer treatment outcomes. This problem is partly due to the overlooking of functional implications of molecular markers. Here, we present a novel computational method that uses evolutionary conservation as prior knowledge to discover bona fide biomarkers. Evolutionary selection at the molecular level is nature's test on functional consequences of genetic elements. By prioritizing genes that show significant statistical association and high functional impact, our new method reduces the chances of including spurious markers in the predictive model. When applied to predicting therapeutic responses for patients with acute myeloid leukemia and to predicting metastasis for patients with prostate cancers, the new method gave rise to evolution-informed models that enjoyed low complexity and high accuracy. The identified genetic markers also have significant implications in tumor progression and embrace potential drug targets. Because evolutionary conservation can be estimated as a gene-specific, position-specific, or allele-specific parameter on the nucleotide level and on the protein level, this new method can be extended to apply to miscellaneous “omics” data to accelerate biomarker discoveries.

Date Created
2016-10-21
Agent

Machine Learning Methods for Diagnosis, Prognosis and Prediction of Long-term Treatment Outcome of Major Depression

Description
Major Depression, clinically called Major Depressive Disorder, is a mood disorder that affects about one eighth of population in US and is projected to be the second leading cause of disability in the world by the…

Major Depression, clinically called Major Depressive Disorder, is a mood disorder that affects about one eighth of population in US and is projected to be the second leading cause of disability in the world by the year 2020. Recent advances in biotechnology have enabled us to collect a great variety of data which could potentially offer us a deeper understanding of the disorder as well as advancing personalized medicine.

This dissertation focuses on developing methods for three different aspects of predictive analytics related to the disorder: automatic diagnosis, prognosis, and prediction of long-term treatment outcome. The data used for each task have their specific characteristics and demonstrate unique problems. Automatic diagnosis of melancholic depression is made on the basis of metabolic profiles and micro-array gene expression profiles where the presence of missing values and strong empirical correlation between the variables is not unusual. To deal with these problems, a method of generating a representative set of features is proposed. Prognosis is made on data collected from rating scales and questionnaires which consist mainly of categorical and ordinal variables and thus favor decision tree based predictive models. Decision tree models are known for the notorious problem of overfitting. A decision tree pruning method that overcomes the shortcomings of a greedy nature and reliance on heuristics inherent in traditional decision tree pruning approaches is proposed. The method is further extended to prune Gradient Boosting Decision Tree and tested on the task of prognosis of treatment outcome. Follow-up studies evaluating the long-term effect of the treatments on patients usually measure patients' depressive symptom severity monthly, resulting in the actual time of relapse upper bounded by the observed time of relapse. To resolve such uncertainty in response, a general loss function where the hypothesis could take different forms is proposed to predict the risk of relapse in situations where only an interval for time of relapse can be derived from the observed data.
Date Created
2017
Agent

Scaling Up Large-scale Sparse Learning and Its Application to Medical Imaging

155389-Thumbnail Image.png
Description
Large-scale $\ell_1$-regularized loss minimization problems arise in high-dimensional applications such as compressed sensing and high-dimensional supervised learning, including classification and regression problems. In many applications, it remains challenging to apply the sparse learning model to large-scale problems that have massive…

Large-scale $\ell_1$-regularized loss minimization problems arise in high-dimensional applications such as compressed sensing and high-dimensional supervised learning, including classification and regression problems. In many applications, it remains challenging to apply the sparse learning model to large-scale problems that have massive data samples with high-dimensional features. One popular and promising strategy is to scaling up the optimization problem in parallel. Parallel solvers run multiple cores on a shared memory system or a distributed environment to speed up the computation, while the practical usage is limited by the huge dimension in the feature space and synchronization problems.

In this dissertation, I carry out the research along the direction with particular focuses on scaling up the optimization of sparse learning for supervised and unsupervised learning problems. For the supervised learning, I firstly propose an asynchronous parallel solver to optimize the large-scale sparse learning model in a multithreading environment. Moreover, I propose a distributed framework to conduct the learning process when the dataset is distributed stored among different machines. Then the proposed model is further extended to the studies of risk genetic factors for Alzheimer's Disease (AD) among different research institutions, integrating a group feature selection framework to rank the top risk SNPs for AD. For the unsupervised learning problem, I propose a highly efficient solver, termed Stochastic Coordinate Coding (SCC), scaling up the optimization of dictionary learning and sparse coding problems. The common issue for the medical imaging research is that the longitudinal features of patients among different time points are beneficial to study together. To further improve the dictionary learning model, I propose a multi-task dictionary learning method, learning the different task simultaneously and utilizing shared and individual dictionary to encode both consistent and changing imaging features.
Date Created
2017
Agent

Domain Adaptive Computational Models for Computer Vision

155339-Thumbnail Image.png
Description
The widespread adoption of computer vision models is often constrained by the issue of domain mismatch. Models that are trained with data belonging to one distribution, perform poorly when tested with data from a different distribution. Variations in vision based…

The widespread adoption of computer vision models is often constrained by the issue of domain mismatch. Models that are trained with data belonging to one distribution, perform poorly when tested with data from a different distribution. Variations in vision based data can be attributed to the following reasons, viz., differences in image quality (resolution, brightness, occlusion and color), changes in camera perspective, dissimilar backgrounds and an inherent diversity of the samples themselves. Machine learning techniques like transfer learning are employed to adapt computational models across distributions. Domain adaptation is a special case of transfer learning, where knowledge from a source domain is transferred to a target domain in the form of learned models and efficient feature representations.

The dissertation outlines novel domain adaptation approaches across different feature spaces; (i) a linear Support Vector Machine model for domain alignment; (ii) a nonlinear kernel based approach that embeds domain-aligned data for enhanced classification; (iii) a hierarchical model implemented using deep learning, that estimates domain-aligned hash values for the source and target data, and (iv) a proposal for a feature selection technique to reduce cross-domain disparity. These adaptation procedures are tested and validated across a range of computer vision applications like object classification, facial expression recognition, digit recognition, and activity recognition. The dissertation also provides a unique perspective of domain adaptation literature from the point-of-view of linear, nonlinear and hierarchical feature spaces. The dissertation concludes with a discussion on the future directions for research that highlight the role of domain adaptation in an era of rapid advancements in artificial intelligence.
Date Created
2017
Agent
Subscribe to Ye, Jieping