Statistical Applications in Genetics and Molecular Biology最新文献

Genome-wide association studies (GWAS) are susceptible to bias due to population stratification (PS). The most widely used method to correct bias due to PS is principal components (PCs) analysis (PCA), but there is no objective method to guide which PCs to include as covariates. Often, the ten PCs with the highest eigenvalues are included to adjust for PS. This selection is arbitrary, and patterns of local linkage disequilibrium may affect PCA corrections. To address these limitations, we estimate genomic propensity scores based on all statistically significant PCs selected by the Tracy-Widom (TW) statistic. We compare a principal components and propensity scores (PCAPS) approach to PCA and EMMAX using simulated GWAS data under no, moderate, and severe PS. PCAPS reduced spurious genetic associations regardless of the degree of PS, resulting in odds ratio (OR) estimates closer to the true OR. We illustrate our PCAPS method using GWAS data from a study of testicular germ cell tumors. PCAPS provided a more conservative adjustment than PCA. Advantages of the PCAPS approach include reduction of bias compared to PCA, consistent selection of propensity scores to adjust for PS, the potential ability to handle outliers, and ease of implementation using existing software packages.

In recent years, a large number of time series microbial community data has been produced in molecular biological studies, especially in metagenomics. Among the statistical methods for time series, local similarity analysis is used in a wide range of environments to capture potential local and time-shifted associations that cannot be distinguished by traditional correlation analysis. Initially, the permutation test is popularly applied to obtain the statistical significance of local similarity analysis. More recently, a theoretical method has also been developed to achieve this aim. However, all these methods require the assumption that the time series are independent and identically distributed. In this paper, we propose a new approach based on moving block bootstrap to approximate the statistical significance of local similarity scores for dependent time series. Simulations show that our method can control the type I error rate reasonably, while theoretical approximation and the permutation test perform less well. Finally, our method is applied to human and marine microbial community datasets, indicating that it can identify potential relationship among operational taxonomic units (OTUs) and significantly decrease the rate of false positives.

Arrays based on single nucleotide polymorphisms (SNPs) have been successful for the large scale discovery of copy number variants (CNVs). However, current CNV calling algorithms still have limitations in detecting CNVs with high specificity and sensitivity, especially in case of small (<100 kb) CNVs. Therefore, this study presents a simple statistical analysis to evaluate CNV calls from SNP arrays in order to improve the noise-robustness of existing CNV calling algorithms. The proposed approach estimates local noise of log R ratios and returns the probability that a certain observation is different from this log R ratio noise level. This probability can be triggered at different thresholds to tailor specificity and/or sensitivity in a flexible way. Moreover, a comparison based on qPCR experiments showed that the proposed noise-robust CNV calls outperformed original ones for multiple threshold values.

Zhang, Z. and Zheng, L. (2015): "A mutual information estimator with exponentially decaying bias," Stat. Appl. Genet. Mol. Biol., 14, 243-252, proposed a nonparametric estimator of mutual information developed in entropic perspective, and demonstrated that it has much smaller bias than the plugin estimator yet with the same asymptotic normality under certain conditions. However it is incorrectly suggested in their article that the asymptotic normality could be used for testing independence between two random elements on a joint alphabet. When two random elements are independent, the asymptotic distribution of $sqrt{n}$n-normed estimator degenerates and therefore the claimed normality does not hold. This article complements Zhang and Zheng by establishing a new chi-square test using the same entropic statistics for mutual information being zero. The three examples in Zhang and Zheng are re-worked using the new test. The results turn out to be much more sensible and further illustrate the advantage of the entropic perspective in statistical inference on alphabets. More specifically in Example 2, when a positive mutual information is known to exist, the new test detects it but the log likelihood ratio test fails to do so.

Unraveling interactions among variables such as genetic, clinical, demographic and environmental factors is essential to understand the development of common and complex diseases. To increase the power to detect such variables interactions associated with clinical time-to-events outcomes, we borrowed established concepts from random survival forest (RSF) models. We introduce a novel RSF-based pairwise interaction estimator and derive a randomization method with bootstrap confidence intervals for inferring interaction significance. Using various linear and nonlinear time-to-events survival models in simulation studies, we first show the efficiency of our approach: true pairwise interaction-effects between variables are uncovered, while they may not be accompanied with their corresponding main-effects, and may not be detected by standard semi-parametric regression modeling and test statistics used in survival analysis. Moreover, using a RSF-based cross-validation scheme for generating prediction estimators, we show that informative predictors may be inferred. We applied our approach to an HIV cohort study recording key host gene polymorphisms and their association with HIV change of tropism or AIDS progression. Altogether, this shows how linear or nonlinear pairwise statistical interactions of variables may be efficiently detected with a predictive value in observational studies with time-to-event outcomes.

Gene-environment (G×E) interaction plays a pivotal role in understanding the genetic basis of complex disease. When environmental factors are measured continuously, one can assess the genetic sensitivity over different environmental conditions on a disease trait. Motivated by the increasing awareness of gene set based association analysis over single variant based approaches, we proposed an additive varying-coefficient model to jointly model variants in a genetic system. The model allows us to examine how variants in a gene set are moderated by an environment factor to affect a disease phenotype. We approached the problem from a variable selection perspective. In particular, we select variants with varying, constant and zero coefficients, which correspond to cases of G×E interaction, no G×E interaction and no genetic effect, respectively. The procedure was implemented through a two-stage iterative estimation algorithm via the smoothly clipped absolute deviation penalty function. Under certain regularity conditions, we established the consistency property in variable selection as well as effect separation of the two stage iterative estimators, and showed the optimal convergence rates of the estimates for varying effects. In addition, we showed that the estimate of non-zero constant coefficients enjoy the oracle property. The utility of our procedure was demonstrated through simulation studies and real data analysis.

Longitudinal gene expression profiles of subjects are collected in some clinical studies to monitor disease progression and understand disease etiology. The identification of gene sets that have coordinated changes with relevant clinical outcomes over time from these data could provide significant insights into the molecular basis of disease progression and lead to better treatments. In this article, we propose a Distance-Correlation based Gene Set Analysis (dcGSA) method for longitudinal gene expression data. dcGSA is a non-parametric approach, statistically robust, and can capture both linear and nonlinear relationships between gene sets and clinical outcomes. In addition, dcGSA is able to identify related gene sets in cases where the effects of gene sets on clinical outcomes differ across subjects due to the subject heterogeneity, remove the confounding effects of some unobserved time-invariant covariates, and allow the assessment of associations between gene sets and multiple related outcomes simultaneously. Through extensive simulation studies, we demonstrate that dcGSA is more powerful of detecting relevant genes than other commonly used gene set analysis methods. When dcGSA is applied to a real dataset on systemic lupus erythematosus, we are able to identify more disease related gene sets than other methods.

In biomedical research, multiple endpoints are commonly analyzed in "omics" fields like genomics, proteomics and metabolomics. Traditional methods designed for low-dimensional data either perform poorly or are not applicable when analyzing high-dimensional data whose dimension is generally similar to, or even much larger than, the number of subjects. The complex biochemical interplay between hundreds (or thousands) of endpoints is reflected by complex dependence relations. The aim of the paper is to propose tests that are very suitable for analyzing omics data because they do not require the normality assumption, are powerful also for small sample sizes, in the presence of complex dependence relations among endpoints, and when the number of endpoints is much larger than the number of subjects. Unbiasedness and consistency of the tests are proved and their size and power are assessed numerically. It is shown that the proposed approach based on the nonparametric combination of dependent interpoint distance tests is very effective. Applications to genomics and metabolomics are discussed.