
T-test for cell group comparisons
scores.ttest.RdPerforms a two-sample t-test (Welch's, unequal variances) comparing cell group scores between two groups
of a binary trait.
Significant features are plotted as boxplots and saved as PDF files in the "Results/" directory
(Results/Ttest_<trait>_<feature>.pdf).
Arguments
- scores
A samples x features score matrix, a list whose first element is that matrix (e.g. the output of
construct_cell_groups()), or the output ofcompute.latent_factors()(its factor scoresZare tested).- coldata
A data frame (or tibble) containing sample-level annotations including the trait to test. Its rows are matched to the samples of the scores by row name; without sample names, they must be in the order of the scores. Samples with a missing trait are left out (with a message).
- trait
Character. Name of the column in
coldataused as the grouping variable (categorical, two groups).- pval
Numeric. Threshold for significance: a feature is significant if its (adjusted) p-value is
<= pval(default = 0.05).- padj
Logical; if TRUE, the p-values are corrected for multiple testing across the features with the Benjamini-Hochberg method, and the adjusted p-values are compared with the threshold. Default FALSE.
Value
A list with the significant features: its first element is the score matrix restricted to them (no
column if none is significant), followed by the matching parts of the other elements of scores (e.g.
Composition and Weights of construct_cell_groups()), with their names.
The last element, Statistics, is a data frame with the test of every feature (feature, test,
statistic_name, statistic, p_value, p_adjusted, significant).
Examples
data("network.tuto")
data("deconv_subgroups.tuto")
data("traitdata.tuto")
cell_groups <- construct_cell_groups(network.tuto, deconv_subgroups.tuto)
#> Warning: Length of color vector was shorter than the number of clusters - color vector was recycled
#> Warning: Length of color vector was shorter than the number of clusters - color vector was recycled
#> Warning: Length of color vector was shorter than the number of clusters - color vector was recycled
#> Warning: Length of color vector was shorter than the number of clusters - color vector was recycled
#> Warning: Length of color vector was shorter than the number of clusters - color vector was recycled
#> Warning: Length of color vector was shorter than the number of clusters - color vector was recycled
#> Warning: Length of color vector was shorter than the number of clusters - color vector was recycled
#> Warning: Length of color vector was shorter than the number of clusters - color vector was recycled
#> Dendrogram plots saved to: Results/Dendrogram_color_clusters.pdf
#> 44 of 897 features were not assigned to any cluster by the tree cut and are not part of any cell group (pink: 2, yellow: 8, red: 2, blue: 6, brown: 4, turquoise: 12, black: 4, green: 6)
res <- scores.ttest(cell_groups$Cell_groups[, 1:5], traitdata.tuto, "binaryResponse")
#> 3 significant feature(s) after Welch's t-test (p-value <= 0.05): Dendrogram_pink_group_1, Dendrogram_pink_group_2, Dendrogram_pink_group_3
res$Statistics
#> feature test statistic_name statistic p_value
#> 1 Dendrogram_pink_group_1 Welch's t-test t 2.78212854 0.008297032
#> 2 Dendrogram_pink_group_2 Welch's t-test t 2.17742792 0.036433660
#> 3 Dendrogram_pink_group_3 Welch's t-test t 2.72545759 0.010177443
#> 4 Dendrogram_pink_group_4 Welch's t-test t 1.53700466 0.134682645
#> 5 Dendrogram_pink_group_5 Welch's t-test t -0.06210619 0.950920316
#> p_adjusted significant
#> 1 0.008297032 TRUE
#> 2 0.036433660 TRUE
#> 3 0.010177443 TRUE
#> 4 0.134682645 FALSE
#> 5 0.950920316 FALSE