johrpan/geposan
1
0
Fork 0
mirror of https://github.com/johrpan/geposan.git synced 2025-10-26 10:47:25 +01:00
Code Issues Projects Releases Packages Wiki Activity Actions

compare: Include confidence intervals

Browse source
This commit is contained in:
Elias Projahn 2022-06-03 17:41:45 +02:00
parent 3217c9bd29
commit 3df4ec5d89
3 changed files with 27 additions and 21 deletions
Download patch file Download diff file Expand all files Collapse all files

33
R/comparison.R
View file

@ -11,9 +11,7 @@
#' \item{`mean_score`}{The mean score of the genes.} #' \item{`mean_score`}{The mean score of the genes.}
#' \item{`mean_rank`}{The mean rank of the genes.} #' \item{`mean_rank`}{The mean rank of the genes.}
#' \item{`mean_percentile`}{The mean percentile of the genes.} #' \item{`mean_percentile`}{The mean percentile of the genes.}
#' \item{`p_value`}{p-value for the null hypothesis that the comparison #' \item{`test_result`}{Results of applying a Wilcoxon rank sum test.}
#' genes do _not_ rank better than other genes. In other words: A low
#' p-value means that the comparison genes rank particularly high.}
#' } #' }
#' #'
#' @export #' @export
@ -34,11 +32,11 @@ compare <- function(ranking, comparison_gene_ids) {
percentile = stats::quantile(comparison_ranking[, percentile]) percentile = stats::quantile(comparison_ranking[, percentile])
) )
p_value <- stats::wilcox.test( test <- stats::wilcox.test(
x = comparison_ranking[, score], x = comparison_ranking[, score],
y = ranking[!gene %chin% comparison_gene_ids, score], y = ranking[!gene %chin% comparison_gene_ids, score],
alternative = "greater" conf.int = TRUE
)$p.value )
structure( structure(
list( list(
@ -46,7 +44,7 @@ compare <- function(ranking, comparison_gene_ids) {
mean_score = comparison_ranking[, mean(score)], mean_score = comparison_ranking[, mean(score)],
mean_rank = comparison_ranking[, mean(rank)], mean_rank = comparison_ranking[, mean(rank)],
mean_percentile = comparison_ranking[, mean(percentile)], mean_percentile = comparison_ranking[, mean(percentile)],
p_value = p_value test_result = test
), ),
class = "geposan_comparison" class = "geposan_comparison"
) )
@ -75,17 +73,16 @@ print.geposan_comparison <- function(x, ...) {
print(quantiles_formatted, row.names = FALSE) print(quantiles_formatted, row.names = FALSE)
cat(sprintf( cat(glue::glue(
paste0( "\n",
"\n Mean score: %.3f", "\n Mean score: {num(x$mean_score, 3)}",
"\n Mean rank: %.1f", "\n Mean rank: {num(x$mean_rank, 1)}",
"\n Mean percentile: %.1f%%", "\n Mean percentile: {num(x$mean_percentile * 100, 2)}",
"\n p-value for better scores: %.4f\n" "\n",
), "\n Estimated difference in medians: ",
x$mean_score, "{num(x$test$conf.int[1], 2)} to {num(x$test$conf.int[2], 2)}",
x$mean_rank, "\n Confidence level: 95%",
x$mean_percentile * 100, "\n p-value: {num(x$test$p.value, 4)}"
x$p_value
)) ))
invisible(x) invisible(x)

11
R/utils.R
View file

@ -29,6 +29,17 @@ cached <- function(name, objects, expr) {
data data
} }
#' Format and round a numeric value.
#'
#' @param number The number to use.
#' @param digits Number of decimal places.
#'
#' @return A character value.
#' @noRd
num <- function(number, digits) {
format(round(number, digits = digits), nsmall = digits)
}
# This is needed to make data.table's symbols available within the package. # This is needed to make data.table's symbols available within the package.
#' @import data.table #' @import data.table
NULL NULL

4
man/compare.Rd
View file

@ -20,9 +20,7 @@ score, rank and percentile of the comparison genes.
\item{\code{mean_score}}{The mean score of the genes.} \item{\code{mean_score}}{The mean score of the genes.}
\item{\code{mean_rank}}{The mean rank of the genes.} \item{\code{mean_rank}}{The mean rank of the genes.}
\item{\code{mean_percentile}}{The mean percentile of the genes.} \item{\code{mean_percentile}}{The mean percentile of the genes.}
\item{\code{p_value}}{p-value for the null hypothesis that the comparison \item{\code{test_result}}{Results of applying a Wilcoxon rank sum test.}
genes do \emph{not} rank better than other genes. In other words: A low
p-value means that the comparison genes rank particularly high.}
} }
} }
\description{ \description{