文章题目：Powerful and robust non-parametric association testing for microbiome data via a zero-inflated quantile approach (ZINQ)
发表杂志：Microbiome
发表时间：2021-9-2
通讯作者：Wodan Ling
原文链接：https://pubmed.ncbi.nlm.nih.gov/34474689/
软件链接：https://github.com/wdl2459/ZINQ-v2
Identification of bacterial taxa associated with diseases, exposures, and other variables of interest offers a more comprehensive understanding of the role of microbes in many conditions.
However, despite considerable(相当多) research in(用于) statistical methods for association testing with microbiome data, (然而)approaches that are generally applicable(适用) remain elusive(难捉摸的).
association testing
Classical tests often do not accommodate(不能适应) the realities of microbiome data, leading to(导致) power loss.
Approaches tailored(定制的) for microbiome data depend highly upon(高度依赖于) the normalization strategies used to(用于) handle(处理) differential read depth and other data characteristics, and they often have unacceptably(令人无法接受的) high false positive rates, generally due to unsatisfied(不满意) distributional assumptions.
On the other hand, many non-parametric tests suffer from loss(损失) of power and may also present(存在) difficulties in adjusting for potential covariates.
Most extant(现存的) approaches also fail in the presence(存在) of heterogeneous effects.
The field(领域) needs new non-parametric approaches that are tailored(量身定制的) to microbiome data, robust to distributional assumptions, and powerful under heterogeneous effects, while permitting(允许) adjustment for covariates.
As an alternative(代替) to existing approaches, we propose(提出) a zero-inflated quantile approach (ZINQ), which uses a two-part quantile regression model to accommodate(适应) the zero inflation in microbiome data.
For a given taxon, ZINQ consists of(包括) a valid test in logistic regression to model the zero counts, followed by(然后) a series of quantile rank-score(分位数等级分数) based tests on multiple quantiles of the non-zero part with adjustment for the zero inflation.
As a regression and quantile-based(基于分位数) approach, the method is non-parametric and robust to(对..。具有稳健性) irregular(不规则的) distributions, while providing an allowance(空余) for covariate adjustment.
Since no distributional assumptions are made, ZINQ can be applied to data that has been processed under any normalization strategy.