English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Biological sequencing data consist of read counts, e.g. of specified taxa andoften exhibit sparsity (zero-count inflation) and overdispersion (extra-Poissonvariability). As most sequencing techniques provide an arbitrary total count,taxon-specific counts should ideally be treated as proportions under thecompositional data-analytic framework. There is increasing interest in the roleof the gut microbiome composition in mediating the effects of differentexposures on health outcomes. Most previous approaches to compositionalmediation have addressed the problem of identifying potentially mediating taxaamong a large number of candidates. We here consider causal inference incompositional mediation when a priori knowledge is available about thehierarchy for a restricted number of taxa, building on a single hypothesisstructured in terms of contrasts between appropriate sub-compositions. Based onthe theory on multiple contemporaneous mediators and the assumed causal graph,we define non-parametric estimands for overall and coordinate-wise mediationeffects, and show how these indirect effects can be estimated from empiricaldata based on simple parametric linear models. The mediators havestraightforward and coherent interpretations, related to specific causalquestions about the interrelationships between the sub-compositions. We performa simulation study focusing on the impact of sparsity and overdispersion onestimation of mediation. While unbiased, the precision of the estimatorsdepends, for any given magnitude of indirect effect, on sparsity and therelative magnitudes of exposure-to-mediator and mediator-to-outcome effects ina complex manner. We demonstrate the approach on empirical data, finding aninverse association of fibre intake on insulin level, mainly attributable todirect rather than indirect effects.

Hypothesis-driven mediation analysis for compositional data: an application to gut microbiome