run_ancom {microbiomeMarker} | R Documentation |
Perform significant test by comparing the pairwise log ratios between all features.
run_ancom( ps, group, taxa_rank = "all", transform = c("identity", "log10", "log10p"), norm = "TSS", norm_para = list(), p_adjust = c("none", "fdr", "bonferroni", "holm", "hochberg", "hommel", "BH", "BY"), pvalue_cutoff = 0.05, W_cutoff = 0.75, test = c("aov", "wilcox.test", "kruskal.test"), ... )
ps |
a |
group |
character, the variable to set the group. |
taxa_rank |
character to specify taxonomic rank to perform
differential analysis on. Should be one of
|
transform |
character, the methods used to transform the microbial
abundance. See
|
norm |
the methods used to normalize the microbial abundance data. See
|
norm_para |
named |
p_adjust |
method for multiple test correction, default |
pvalue_cutoff |
significance level for each of the statistical tests, default 0.05. |
W_cutoff |
lower bound for the proportion for the W-statistic, default 0.7. |
test |
character, the test to dtermine the p value of log ratio, one of "aov", "wilcox.test", "kruskal.test". |
... |
additional arguments passed to the test function. |
In an experiment with only two treatments, this tests the following hypothesis for feature i:
H_{0i}: E(log(μ_i^1)) = E(log(μ_i^2))
where μ_i^1 and μ_i^2 are the mean abundances for feature i in the two groups.
The developers of this method recommend the following significance tests
if there are 2 groups, use non-parametric Wilcoxon rank sum test
stats::wilcox.test()
. If there are more than 2 groups, use nonparametric
stats::kruskal.test()
or one-way ANOVA stats::aov()
.
a microbiomeMarker object, in which the slot
of
marker_table
contains four variables:
feature
, significantly different features.
enrich_group
, the class of the differential features enriched.
effect_size
, differential means for two groups, or F statistic for more
than two groups.
W
, the W-statistic, number of features that a single feature is tested
to be significantly different against.
Huang Lin, Yang Cao
Mandal et al. "Analysis of composition of microbiomes: a novel method for studying microbial composition", Microbial Ecology in Health & Disease, (2015), 26.
data(enterotypes_arumugam) ps <- phyloseq::subset_samples( enterotypes_arumugam, Enterotype %in% c("Enterotype 3", "Enterotype 2") ) run_ancom(ps, group = "Enterotype")