A5021108739- Statistical Methods and Inference
- Gene expression and cancer classification
- Genetic Mapping and Diversity in Plants and Animals
- Metabolomics and Mass Spectrometry Studies
- Bioinformatics and Genomic Networks
- Gene Regulatory Network Analysis
- Genetic and phenotypic traits in livestock
- Advanced Statistical Methods and Models
- Optimal Experimental Design Methods
- Spectroscopy and Chemometric Analyses
- Financial Risk and Volatility Modeling
- Bayesian Modeling and Causal Inference
- Statistical Methods and Bayesian Inference
- Genetic Associations and Epidemiology
- Face and Expression Recognition
- Cancer, Lipids, and Metabolism
- Image and Signal Denoising Methods
- Hydrology and Drought Analysis
- Mental Health Research Topics
- Genetics and Plant Breeding
- Receptor Mechanisms and Signaling
- Molecular Biology Techniques and Applications
- Neural Networks and Applications
- Systemic Lupus Erythematosus Research
- Multisensory perception and integration
University of California, Irvine
2023-2025
Purdue University West Lafayette
2015-2024
China Jiliang University
2024
Beijing University of Technology
2024
Capital Medical University
2012-2016
Chulalongkorn University
2015
Google (United States)
2012
Henan Radio and Television University
2012
University of Rochester
2007
University of Rochester Medical Center
2004-2005
The coefficient of determination, a.k.a. R2, is well-defined in linear regression models, and measures the proportion variation dependent variable explained by predictors included model. To extend it for generalized we use variance function to define total variable, as well remaining after modeling predictive effects independent variables. Unlike other definitions that demand complete specification likelihood function, our definition R2 only needs know mean functions, so applicable more...
A two-dimensional (2-D) correlation optimized warping (COW) algorithm has been developed to align 2-D gas chromatography coupled with time-of-flight mass spectrometry (GC x GC/TOF-MS) data. By partitioning raw chromatographic profiles and the grid points simultaneously along first second dimensions on basis of applying a one-dimensional COW characteristic vectors, nongrid can be interpolatively warped. This was directly applied total ion counts (TIC) homogeneous chemical samples, i.e.,...
Abstract Despite the efficacy of highly active antiretroviral therapy in reducing viral burden, neurologic disease associated with HIV-1 infection CNS has not decreased prevalence. does induce by direct neurons, although extensive data suggest that intra-CNS burden correlates both severity virally induced disease, and generation neurotoxic metabolites. Many these molecules are capable inducing neuronal apoptosis vitro, but vivo correlate dysfunction, thus prompting us to investigate cellular...
Purpose The present study examines the impact of typical aging and Parkinson’s disease (PD) on relationship among breath pausing, syntax, punctuation. Method Thirty young adults, 25 typically older 15 individuals with PD participated. Fifteen participants were age- sex-matched to PD. Participants read a passage aloud 2 times. Utterance length, location pauses relative punctuation number disfluencies mazes measured. Results Older adults produced shorter utterances, smaller percentage breaths...
ABSTRACT Current literature on transfer learning has been focused improving the predictive performance corresponding to a small dataset by transferring information it from larger but possibly biassed dataset. However, methods currently available do not allow computation of prediction intervals, and hence, one rely using either alone or combining with obtain intervals traditional linear regression methods. In this article, we propose an E mpirical B ayes approach for P rediction I nterval T...
An Ag-20 vol.% V 2 AlC composite material was prepared using the spark plasma sintering method. The influence of number arc discharge on electrical contact performance Ag-V composites systematically investigated. For first time, we observed that ablation mechanism evolves with increasing cycles. During single ablation, preferentially discharges Ag phase owing to its lower work function. This process creates a relatively flat region where reinforcement and matrix remain distinct. acts as...
Identifying quantitative trait loci (QTL) for both additive and epistatic effects raises the statistical issue of selecting variables from a large number candidates using small observations. Missing and/or marker values prevent one directly applying classical model selection criteria such as Akaike's information criterion (AIC) Bayesian (BIC). We propose two-step variable method which deals with sparse parameter space sample size issues. The regression coefficient priors are flexible enough...
Despite the fact that colorectal cancer (CRC) is one of most prevalent and deadly cancers in world, development improved robust biomarkers to enable screening, surveillance, therapy monitoring CRC continues be evasive. In particular, patients with colon polyps are at higher risk developing cancer; however, noninvasive methods identify these suffer from poor performance. consideration challenges involved identifying metabolite individuals high for cancer, we have investigated NMR-based...
Blood metabolite levels are affected by numerous factors, including preanalytical factors such as collection methods and geographical sites. These perturbations have caused deleterious consequences for many metabolomics studies represent a major challenge in the field. It is important to understand these develop models reduce their perturbations. However, date, lack of suitable mathematical blood under homeostasis has hindered progress. In this study, we quantitative healthy adults based on...
We propose to explore high-dimensional data with categorical outcomes by generalizing the penalized orthogonal-components regression method (POCRE), a supervised dimension reduction initially proposed for linear regression. This generalized POCRE, i.e., gPOCRE, sequentially builds up orthogonal components selecting predictors which maximally explain variation of response variables. Therefore, gPOCRE simultaneously selects significant and reduces dimensions constructing these selected model....
We developed a classification approach to multiple quantitative trait loci (QTL) mapping built upon Bayesian framework that incorporates the important prior information most genotypic markers are not cotransmitted with QTL or their effects negligible. The genetic effect of each marker is modeled using three-component mixture class for having negligible and separate classes positive negative on trait. posterior probability marker's provides natural statistic evaluating credibility identified...
Many genetic variants have been linked to familial or sporadic Parkinson's disease (PD), among which those identified in PARK16, BST1, SNCA, LRRK2, GBA and MAPT genes demonstrated be the most common risk factors worldwide. Moreover, complex gene-gene gene-environment interactions highlighted PD pathogenesis. Compared studies focusing on predisposing effects of genes, there is a relative lack research investigating how these their influence clinical profiles PD. In cohort consisting 2,011...
We propose a penalized orthogonal-components regression (POCRE) for large p small n data. Orthogonal components are sequentially constructed to maximize, upon standardization, their correlation the response residuals. A new penalization framework, implemented via empirical Bayes thresholding, is presented effectively identify sparse predictors of each component. POCRE computationally efficient owing its sequential construction leading principal components. In addition, such offers other...
We propose a two-stage penalized least squares method to build large systems of structural equations based on the instrumental variables view classical method. show that, with numbers endogenous and exogenous variables, system can be constructed via consistent estimation set conditional expectations at first stage, selection regulatory effects second stage. While stage obtained ridge regression, adaptive lasso is employed achieve selection. The resultant estimates enjoy oracle properties....
Constructing gene regulatory networks is crucial to unraveling the genetic architecture of complex traits and understanding mechanisms diseases. On basis expression single nucleotide polymorphism data in yeast, Saccharomyces cerevisiae, we constructed using a two-stage penalized least squares method. A large system structural equations via optimal prediction set surrogate variables was established at first stage, followed by consistent selection effects second stage. Using this approach,...
Association analysis for ionomic concentrations of 20 elements identified independent genetic factors underlying the root and shoot ionomes rice, providing a platform selecting dissecting causal variants. Understanding basis mineral nutrient acquisition is key to fully describing how terrestrial organisms interact with non-living environment. Rice (Oryza sativa L.) serves both as model organism studies an important component global food system. Studies in rice ionomics have primarily focused...
We compute the value-at-risk of financial losses by fitting a generalized Pareto distribution to exceedances over threshold. Following common practice setting threshold as high sample quantiles, we show that, for both independent observations and time-series data, asymptotic variance maximum likelihood estimation depends on choice threshold, unlike existing study using divergent also propose random weighted bootstrap method interval VaR, with critical values computed empirical absolute...
Currently, genome-wide association studies (GWAS) are conducted by collecting a massive number of SNPs (i.e., large p) for relatively small individuals n) and associations made between clinical phenotypes genetic variation one single-nucleotide polymorphism (SNP) at time. Univariate approaches like this ignore the linkage disequilibrium in regions low recombination. This results reliability candidate gene identification. Here we propose to improve case-control GWAS approach implementing...
Genome-wide associations between single-nucleotide polymorphisms and clinical traits were simultaneously conducted using penalized orthogonal-components regression. This method was developed to identify the genetic variants controlling phenotypes from a massive number of candidate variants. By investigating association all phenotype antibodies against cyclic citrullinated peptide rheumatoid arthritis data provided by Genetic Analysis Workshop 16, we identified regions which may contribute...