Qizhai Li

Qizhai Li

Auto-generated profile, based on publicly available information

Qizhai Li

State Key Laboratory of Mathematical Sciences, Academy of Mathematics and Systems Science, Chinese Academy of Sciences , Beijing 100190

Research Focus & Metrics

Academic Career Length

14Years (2013-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
25 June 2018 in Journal of the Royal Statistical Society Series B: Statistical Methodology
Verified
Journal Article
Open access
PDF file
FLFaming Liang
Faming Liang
BJBochao Jia
Bochao Jia
JXJingnan Xue
Jingnan Xue
QLQizhai Li
Qizhai Li
YLYe Luo
Ye Luo
Summary: Missing data are frequently encountered in high dimensional problems, but they are usually difficult to deal with by using standard algorithms, such as the expectation–maximization algorithm and its variants. To tackle this difficulty, some problem-specific algorithms have been developed in the literature, but there still lacks a general algorithm. This work is to fill the gap: we propose a general algorithm for high dimensional missing data problems. The algorithm works by iterating between an imputation step and a regularized optimization step. At the imputation step, the missing data are imputed conditionally on the observed data and the current estimates of parameters and, at the regularized optimization step, a consistent estimate is found via the regularization approach for the minimizer of a Kullback–Leibler divergence defined on the pseudocomplete data. For high dimensional problems, the consistent estimate can be found under sparsity constraints. The consistency of the averaged estimate for the true parameter can be established under quite general conditions. The algorithm is illustrated by using high dimensional Gaussian graphical models, high dimensional variable selection and a random-coefficient model.

1 June 2018 in The American Journal of Clinical Nutrition
Verified
Journal Article
Closed access
PLPeiqin Li
Peiqin Li
JZJing Zhao
Jing Zhao
KKKumar Kothapalli
Kumar Kothapalli
XLXiang Li
Xiang Li
HLHui Li
Hui Li
YGYing Gao
Ying Gao
Arachidonic acid (AA) is the major polyunsaturated fatty acid (PUFA) substrate for potent eicosanoid signaling to modulate inflammation and thrombosis and is controlled in part by tissue abundance. Fatty acid desaturase 1 (FADS1) catalyzes synthesis of omega-6 (n-3) AA and n-3 eicosapentaenoic acid (EPA). The rs66698963 polymorphism, a 22-base pair (bp) insertion-deletion 137 bp downstream of a sterol regulatory element in FADS2 intron 1, mediates expression of FADS1 in vitro, as well as exerting positive selection in several human populations. The associations between the polymorphism rs66698963 and plasma PUFAs as well as disease phenotypes are unclear. This study aimed to evaluate the relation between rs66698963 genotypes and plasma PUFA concentrations and blood lipid profiles. Plasma fatty acids were measured from a single sample obtained at baseline in 1504 healthy Chinese adults aged between 35 and 59 y with the use of gas chromatography. Blood lipids were measured at baseline and a second time at the 18-mo follow-up. The rs66698963 genotype was determined by using agarose gel electrophoresis. Linear regression and logistic regression analyses were performed to assess the association between genotype and plasma PUFAs and blood lipids. A shift from the precursors linoleic acid and α-linolenic acid to produce AA and EPA, respectively, was observed, consistent with FADS1 activity increasing in the order of genotypes D/D to I/D to I/I. For I/I compared with D/D carriers, plasma concentrations of n-6 AA and the ratio of AA to n-3 EPA plus docosahexaenoic acid (DHA) were 57% and 32% higher, respectively. Carriers of the deletion (D) allele of rs66698963 tended to have higher triglycerides (β = 0.018; SE: 0.009; P = 0.05) and lower HDL cholesterol (β = -0.008; SE: 0.004; P = 0.02) than carriers of the insertion (I) allele. The rs66698963 genotype is significantly associated with AA concentrations and AA to EPA+DHA ratio, reflecting basal risk of inflammatory and related chronic disease phenotypes, and is correlated with the risk of dyslipidemia. This trial was registered at chictr.org.cn as ChiCTR-EOC-17012759.

21 March 2014 in International Journal of Food Properties
Verified
Journal Article
Open access
LWLi Wang
Li Wang
HLHongzhi Liu
Hongzhi Liu
LLLi Liu
Li Liu
Qiang WangQiang Wang
Qiang Wang
QLQizhai Li
Qizhai Li
JZJianshu Zhang
Jianshu Zhang
The objective of this work was to study the contribution of different peanut varieties with regard to their arachin and conarachin fractions, and their respective subunits to protein gel properties. It was found that the proteins of various cultivars could be classified into two groups according to the lack of the 35.5 kDa acidic subunit of the arachin. Two peanut cultivars, Yueyou7 and Qinglan8, had the highest content of arachin (62.3%) and conarachin (53.5%), respectively. Three indexes, namely, hardness, springiness, and cohesiveness, were used to describe the protein gel properties. An efficient approach was developed to characterize the three gel properties into one index. The correlation coefficients between the newly depicted index and the original ones were 0.87, 0.41, and 0.47, which corresponded to hardness, springiness, and cohesiveness, respectively. Principal component analysis, linear discriminant analysis, and cluster analysis were used as classification techniques. About 40 varieties were classified into three groups by principal component analysis and all group members determined by principal component analysis are in the predicted group that 100.0% of original grouped cases correctly classified by linear discriminant analysis. The result of cluster analysis had some similarities with the principal component analysis.

5 June 2013 in Genetic Epidemiology
Verified
Journal Article
Closed access
PDF file
TYTing Yan
Ting Yan
QLQizhai Li
Qizhai Li
YLYuanzhang Li
Yuanzhang Li
ZLZhaohai Li
Zhaohai Li
GZGang Zheng
Gang Zheng

1 July 2025 in Bioinformatics
Verified
Journal Article
Open access
NRNicholas Rios
Nicholas Rios
YSYuke Shi
Yuke Shi
JCJun Chen
Jun Chen
XZXiang Zhan
Xiang Zhan
LXLingzhou Xue
Lingzhou Xue
QLQizhai Li
Qizhai Li
Motivation: Compositional data are frequently encountered in many disciplines, such as in next-generation sequencing experiments widely used in biomedical studies. Regression analysis with compositional data as either responses or predictors has been well studied. However, when both responses and predictors are compositional, the inventory of analysis tools is surprisingly limited, especially in the high-dimensional setting. Among the few existing methods, most of them rely on a log-ratio transformation to move compositional data from the simplex to real numbers. Yet, a serious weakness of these methods is their failure to handle the substantial fraction of zeroes observed in data collected from next-generation sequencing experiments. Results: To investigate associations between two high-dimensional multi-omics compositions, we propose a composition-on-composition (COC) regression analysis method which does not require log-ratio transformations and hence can handle zeroes in the data. To account for high dimensionality, we estimate regression coefficients using a penalized estimation equation approach. Finally, inference procedures for COC regression are also proposed. Superior performance of COC is demonstrated through both comprehensive numerical simulations and case studies. Availability and implementation: Source R codes to implement COC method is available at https://github.com/nrios4/COC.

2 June 2025 in Bioinformatics
Verified
Journal Article
Open access
JYJingxin Yan
Jingxin Yan
XZXiaoyu Zhang
Xiaoyu Zhang
SWShuying Wang
Shuying Wang
JWJinjuan Wang
Jinjuan Wang
QLQizhai Li
Qizhai Li
Motivation: The Sequence Kernel Association Test (SKAT) and its extensions are the most popular methods for studying the association between phenotypes and a set of single nucleotide polymorphisms. Their practical application is very wide, but most of these methods are designed for continuous and binary phenotypes. Ordered categorical phenotypes are also very common in practice, so there is an urgent need to develop SKAT-type tests for proportional odds model. Results: To accommodate ordered categorical phenotypes, we propose a test named the Sequence Kernel Association Test for the Proportional Odds Model (POM-SKAT). It constructs a score test for the variance of the coefficients of interest using a quasi-likelihood and the P-value is evaluated by approximating the asymptotic distribution of the test statistic with the Pearson Type III distribution. Simulation studies demonstrate that our method performs well and achieves high power in detecting gene-phenotype associations. We apply POM-SKAT to rheumatoid arthritis data provided by Genetic Analysis Workshop 16, identifying multiple relevant gene variants. Availability and implementation: Code is available at GitHub (https://github.com/amss-stat/POM-SKAT).