Article
Multidisciplinary Sciences
Xiaoyu Liang, Xuewei Cao, Qiuying Sha, Shuanglin Zhang
Summary: The article introduces a novel multivariate method for phenome-wide association studies (PheWAS) and demonstrates its superiority through extensive simulation studies and real-life application. The proposed method involves hierarchical clustering, clustering linear combination, and false discovery rate control steps.
Article
Computer Science, Interdisciplinary Applications
Xinyue Wang, Xiaoqian Jiang, Jaideep Vaidya
Summary: The paper proposes two algorithms for generating synthetic SNPs that are indistinguishable from real SNPs. Through game theoretic analysis, it demonstrates the possibility of incentivizing honest behavior by the server. Extensive experiments show that the proposed method can ensure efficient and trustworthy outsourcing of logistic regression for GWAS.
JOURNAL OF BIOMEDICAL INFORMATICS
(2021)
Review
Biochemistry & Molecular Biology
Frederick J. Boehm, Xiang Zhou
Summary: Genome-wide association studies have provided numerous associations for common diseases and complex traits. Mendelian randomization methods, utilizing SNP associations, help uncover causal relationships between complex traits. The availability of GWAS summary statistics has motivated the development of new Mendelian randomization methods with relaxed causality assumptions, offering opportunities for robust biological discoveries.
COMPUTATIONAL AND STRUCTURAL BIOTECHNOLOGY JOURNAL
(2022)
Article
Cell Biology
Yingjie Guo, Chenxi Wu, Zhian Yuan, Yansu Wang, Zhen Liang, Yang Wang, Yi Zhang, Lei Xu
Summary: This article introduces a gene-based method to detect gene-gene interactions by adding additive constraints to the model, and experimental results show that this method outperforms previous experiments in detecting gene-gene interactions.
FRONTIERS IN CELL AND DEVELOPMENTAL BIOLOGY
(2021)
Article
Biochemical Research Methods
Jean-Tristan Brandenburg, Lindsay Clark, Gerrit Botha, Sumir Panji, Shakuntala Baichoo, Christopher Fields, Scott Hazelhurst
Summary: The H3AGWAS workflow is a powerful and scalable tool for genome-wide association studies, capable of handling large datasets and facilitating parameter adjustments and result analysis.
BMC BIOINFORMATICS
(2022)
Article
Genetics & Heredity
Jin Zhang, Min Chen, Yangjun Wen, Yin Zhang, Yunan Lu, Shengmeng Wang, Juncong Chen
Summary: The newly developed FastRR algorithm under the MLM framework shows superior power in detecting and estimating the effects of multiple genetic markers on traits, providing a more accurate and stable approach for both large and small QTN detection. Compared with existing methods, FastRR algorithm also offers the advantage of high computing speed in high dimensional genomic datasets.
FRONTIERS IN GENETICS
(2021)
Article
Multidisciplinary Sciences
Qingqin S. Li, Randall L. Morrison, Gustavo Turecki, Wayne C. Drevets
Summary: Epigenetic mechanisms play a significant role in the etiology of major depressive disorder (MDD), as indicated by a meta-analysis study. The study identified differentially methylated positions (DMPs) and differentially methylated regions (DMRs) associated with MDD, highlighting the involvement of pathways related to neuronal synaptic plasticity, calcium signaling, and inflammation.
SCIENTIFIC REPORTS
(2022)
Article
Genetics & Heredity
Jing Xiao, Yang Zhou, Shu He, Wen-Long Ren
Summary: The newly proposed method ScoreEB combines score test and Empirical Bayes, improving computational efficiency in multi-locus GWAS. Applied to quantitative trait analysis in plants and animals, ScoreEB can detect new genes and accurately control false positive rate.
FRONTIERS IN GENETICS
(2021)
Article
Multidisciplinary Sciences
Abbas Saad Alatrany, Wasiq Khan, Abir Hussain, Dhiya Al-Jumeily
Summary: The increasing incidence of Alzheimer's disease (AD) poses socioeconomic challenges. In this study, a hybrid feature selection approach and neural network models are used to predict AD. The approach outperformed existing methods with 99% accuracy and f1-score, providing impactful outcomes for other chronic diseases.
Article
Biochemical Research Methods
Min Yuan, Xu Steven Xu, Yaning Yang, Yinsheng Zhou, Yi Li, Jinfeng Xu, Jose Pinheiro
Summary: This study found bias in existing EBE-based GWAS methods and proposed a fast and unbiased method, SCEBE, for large-scale GWAS analysis, significantly improving computational efficiency.
BRIEFINGS IN BIOINFORMATICS
(2021)
Article
Biochemical Research Methods
Itziar Irigoien, Bru Cormand, Maria Soler-Artigas, Cristina Sanchez-Mora, Josep-Antoni Ramos-Quiroga, Concepcion Arenas
Summary: With the rise of GWAS, the analysis of large-scale SNP data has become crucial in biomedical research. This paper proposes a new method based on genetic distances between individuals to identify disease-related SNPs in case-control studies. By considering population substructure and avoiding multiple testing issues, the method provides ordered lists of SNPs and serves as a useful tool for researchers to focus their attention in the initial stage.
IEEE-ACM TRANSACTIONS ON COMPUTATIONAL BIOLOGY AND BIOINFORMATICS
(2022)
Article
Biochemical Research Methods
Xinyue Wang, Leonard Dervishi, Wentao Li, Erman Ayday, Xiaoqian Jiang, Jaideep Vaidya
Summary: This work introduces an efficient framework for conducting collaborative GWAS on distributed datasets, maintaining data privacy without compromising the accuracy of the results. The proposed method reduces communication and computational overheads using a two-step strategy and iterative and sampling techniques. Logistic regression is used as the statistical method in this approach. The empirical evaluation showcases the efficiency and applicability of this method in different study heterogeneity and skewed phenotype distributions.
Article
Biochemical Research Methods
Maura John, Markus J. Ankenbrand, Carolin Artmann, Jan A. Freudenthal, Arthur Korte, Dominik G. Grimm
Summary: GWAS is an important tool for studying complex genotype-phenotype relationships, with LMMs commonly used to detect associations. However, actual data often violates key LMM assumptions. The proposed permGWAS method offers more efficient computation and can improve the interpretation of GWAS results by providing realistic significance thresholds based on permutations.
Article
Plant Sciences
Huilong Hong, Mei Li, Yijie Chen, Haorang Wang, Jun Wang, Bingfu Guo, Huawei Gao, Honglei Ren, Ming Yuan, Yingpeng Han, Lijuan Qiu
Summary: This study analyzed the phenotypic diversity and genetic basis of epicotyl length (EL) in soybean using 951 cultivars and landraces from different regions. The study identified 180 QTNs and QEIs associated with EL, and predicted 10 candidate genes that may be involved in seed germination and seedling development.
FRONTIERS IN PLANT SCIENCE
(2022)
Article
Agriculture, Dairy & Animal Science
Md Azizul Haque, Mohammad Zahangir Alam, Asif Iqbal, Yun-Mi Lee, Chang-Gwon Dang, Jong-Joo Kim
Summary: Holstein has been the most widely used dairy cattle breed in the Korean Peninsula since its introduction in 1885. A genome-wide association study (GWAS) was conducted to identify the genes associated with body conformation traits in the Korean Holstein population, and 24 significant SNPs were identified. The study provides insights into the genetic basis of body conformation traits and paves the way for future breeding strategies in dairy cattle.
Article
Economics
Tao Zou, Wei Lan, Runze Li, Chih-Ling Tsai
Summary: In this article, a covariance-mean regression model with heterogeneous similarity matrices is introduced. The article addresses two statistical inference challenges in this new model setting and proposes corresponding solutions. Extensive simulations and an empirical study demonstrate the effectiveness of the proposed methods.
JOURNAL OF ECONOMETRICS
(2022)
Article
Statistics & Probability
Runze Li, Kai Xu, Yeqing Zhou, Liping Zhu
Summary: In this article, we propose a novel test based on an aggregation of the marginal cumulative covariances to accommodate heteroscedasticity and high dimensionality in high-dimensional data. Our proposed test statistic is scale-invariance, tuning-free, and easy to implement, with established asymptotic normality under the null hypothesis. We find that our proposed test is much more powerful than existing competitors for covariates with heterogeneous variances, even under high-dimensional linear models, while maintaining high efficiency for homoscedastic covariates.
JOURNAL OF THE AMERICAN STATISTICAL ASSOCIATION
(2023)
Article
Statistics & Probability
Xu Guo, Haojie Ren, Changliang Zou, Runze Li
Summary: The hard thresholding rule is commonly used in feature screening for ultrahigh-dimensional data. However, choosing the right threshold can be challenging. This study introduces a data-adaptive threshold selection procedure with error rate control, which is able to control the false discovery rate and per family error rate while retaining all important predictors.
JOURNAL OF THE AMERICAN STATISTICAL ASSOCIATION
(2023)
Article
Economics
Xu Guo, Runze Li, Jingyuan Liu, Mudong Zeng
Summary: This paper proposes new statistical inference procedures for high dimensional mediation models, where both the outcome model and the mediator model are linear with high dimensional mediators. Traditional procedures for mediation analysis cannot be used due to high-dimensionality of the mediators. The paper introduces estimation procedures, penalized Wald test, and F-type test for indirect and direct effects, and applies them to study the mediation effects of financial metrics on stock reaction to COVID-19 pandemic.
JOURNAL OF ECONOMETRICS
(2023)
Article
Biology
Ying An, Runze Li, Xianlai Chen
Summary: In this paper, a Multi-graph attEntive Representation learning framework integrating Group information from similar patiEnts(MERGE) is proposed for medical prediction. The framework improves the accuracy of patient representation by capturing individual temporal characteristics and learning group representations of similar patients.
COMPUTERS IN BIOLOGY AND MEDICINE
(2022)
Article
Economics
Xu Guo, Runze Li, Jingyuan Liu, Mudong Zeng
Summary: Motivated by an empirical analysis of stock reaction to COVID-19 pandemic, the study proposes a generalized mediation model with high-dimensional potential mediators to investigate the mediation effects of financial metrics that bridge company's sector and stock value. The estimation procedure for the direct effect is established using a partial penalized maximum likelihood method, and its theoretical properties are presented. Tests for the indirect and direct effects are developed, with the former having a chi 2 limiting null distribution and the latter asymptotically following a chi 2-distribution. Simulation studies and empirical analysis of stock reaction to COVID-19 pandemic are conducted to validate the proposed procedures and explore the underlying mechanism of the relationship between companies' sectors and their stock values.
JOURNAL OF BUSINESS & ECONOMIC STATISTICS
(2023)
Article
Statistics & Probability
Changcheng Li, Runze Li, Jiawei Wen, Songshan Yang, Xiang Zhan
Summary: In this article, we propose the regularized linear programming discriminant rule with folded concave penalty for ultrahigh-dimensional data. We use the local linear approximation algorithm to transform the model with folded concave penalty into a weighted l(1) model. Additionally, we present efficient and parallelizable algorithms based on feature space split to address the computational challenges posed by ultrahigh dimensionality.
JOURNAL OF COMPUTATIONAL AND GRAPHICAL STATISTICS
(2023)
Article
Statistics & Probability
Wei Zhong, Chen Qian, Wanjun Liu, Liping Zhu, Runze Li
Summary: It is important to analyze the relationship between posted salary and job requirements in online labor markets using the online job advertisements data. The challenge lies in dealing with interval-valued salaries and selecting significant predictor skill words. To address this, a new feature screening method, ADD-SIS, is proposed, which utilizes nonparametric maximum likelihood estimation and interval information. This article also explores the important skill words for salaries in job advertisements for data scientists and data analysts in China. The importance of this article is 9 out of 10.
JOURNAL OF THE AMERICAN STATISTICAL ASSOCIATION
(2023)
Article
Mathematics, Interdisciplinary Applications
Donna L. Coffman, John J. Dziak, Kaylee Litson, Yajnaseni Chakraborti, Megan E. Piper, Runze Li
Summary: The increase in the use of mobile and wearable devices allows for dense assessment of mediating processes. This study presents a method for estimating and testing the indirect effect of a randomized treatment on a distal binary variable as mediated by a nonparametric trajectory. The study also provides an empirical example and an R package for practical application of this technique.
MULTIVARIATE BEHAVIORAL RESEARCH
(2023)
Article
Construction & Building Technology
Xiaoniu Yu, Xiaohua Pan
Summary: Seawater-based soybean-induced carbonate precipitation (SSICP) method was used for sandy soil improvement. Comparative bio-cementation tests showed that SSICP had better sand improvement performance compared to deionized water-based soybean-induced carbonate precipitation (SICP). The compressive strength of bio-cemented Ottawa sand blocks using SSICP reached 401.67 kPa, twice the strength of SICP bio-cemented blocks (191.62 kPa). The improved sand strength in SSICP can be attributed to the mixture of calcium carbonate and calcite magnesium produced by the SSICP process, which is more effective than calcite produced by the SICP process. The performance of carbonate precipitation and bio-cementation was better on Ottawa sand than on sea sand.
JOURNAL OF SUSTAINABLE CEMENT-BASED MATERIALS
(2023)
Article
Statistics & Probability
Ben Sheng, Changcheng Li, Le Bao, Runze Li
Summary: Accurate estimation of HIV incidence is crucial for monitoring the epidemic, targeting interventions, and evaluating existing prevention and treatment programs. This article proposes a semisupervised logistic regression model that combines data from multiple sources to estimate individual level HIV recency status. Applied to Malawi PHIA data, the model outperforms the current practice for individual level estimation and is more suitable for estimating HIV recency rates at aggregated levels.
ANNALS OF APPLIED STATISTICS
(2023)
Article
Substance Abuse
Joon Kyung Nam, Megan E. Piper, Zhaoxue Tong, Runze Li, James J. Yang, Douglas E. Jorenby, Anne Buu
Summary: This study fills the knowledge gap by examining the impact of e-cigarette use, dependence, cessation motivation/goals, and environmental restriction on speed of progression to smoking and vaping cessation. The findings show that dual use of e-cigarettes with cigarettes, lower primary dependence motives of smoking, higher secondary dependence motives of smoking, higher motivation to quit smoking, more ambitious future goals to quit smoking, and more restrictive environment for smoking all contribute to quicker progression to smoking cessation. Dual users with higher secondary dependence motives of smoking or with lower primary dependence motives of vaping progress faster to vaping cessation. The results suggest that nicotine dependence is product-specific with two distinct constructs.
DRUG AND ALCOHOL DEPENDENCE
(2023)
Article
Statistics & Probability
Jia Wang, Xizhen Cai, Xiaoyue Niu, Runze Li
Summary: This article introduces a class of network models where the likelihood of connection is influenced by high-dimensional nodal covariates and node-specific popularity. A Bayesian method is proposed for feature selection, with implementation via Gibbs sampling. To address computational challenges in large sparse networks, a working model is developed for parameter updates based on dense sub-graphs. Model selection consistency is proven for both models, even when dimension grows exponentially. Monte Carlo studies and real world examples illustrate the performance of the proposed models and estimation procedures. Supplementary materials are available online.
JOURNAL OF THE AMERICAN STATISTICAL ASSOCIATION
(2023)
Article
Mechanics
Xian-dong Li, Tian-fei Xiao, Ming-yan Lan, Peng Zheng, Run-ze Li, Zhi-li Zhou, Le-teng Gong, Jian Li
Summary: The dynamic evolution behavior of subsonic streamers and their voltage polarity effects were investigated. The streamer development process can be divided into two stages: bottom-up period characterized by root spherical expansion and OH emission line, and top-down period characterized by head burst expansion and emission lines of H-beta, H-alpha, and O. The magnetic pinch effect on the internal plasma distribution determines the expansion mode of the streamer, while the low capture energy of the solvated electron and local space charge accumulation contribute to the faster propagation of positive streamers at low voltage levels.
Article
Substance Abuse
Anne Buu, Zhaoxue Tong, Zhanrui Cai, Runze Li, James Yang, Douglas E. Jorenby, Megan E. Piper
Summary: This study utilized 13 waves of data from 227 dual users to identify subtypes of dual users based on the dynamic interactions between cigarette and e-cigarette consumption. The subtypes were characterized by their product-specific trajectories of dependence and were compared in terms of use contexts.
NICOTINE & TOBACCO RESEARCH
(2023)