Skip to content

PCA: export loadings and corresponding protein names #54

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
KarinSchork merged 1 commit into from
Dec 8, 2025
Merged

PCA: export loadings and corresponding protein names #54

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
16 changes: 13 additions & 3 deletions R/PCA_Plot.R
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2,6 +2,8 @@
#'
#' @param D \strong{data.frame} \cr
#' The data set containing intensities of the sample.
#' @param id \strong{data.frame} \cr
#' The corresponding ID columns for the parameter D e.g. containing further columns like protein or gene names
#' @param groupvar1 \strong{character vector} \cr
#' The variable used for colors.
#' @param groupvar2 \strong{character vector} \cr
Expand Down Expand Up @@ -49,6 +51,7 @@
#'

PCA_Plot <- function(D,
id = NULL,
groupvar1 = NULL, groupvar2 = NULL,

impute = FALSE, impute_method = "mean", propNA = 0,
Expand All @@ -67,7 +70,9 @@ PCA_Plot <- function(D,

mess = ""

filtered_D <- filter_PCA_data(D = D, impute = impute, impute_method = impute_method, propNA = propNA)
filtered_data <- filter_PCA_data(D = D, id = id, impute = impute, impute_method = impute_method, propNA = propNA)
filtered_D <- filtered_data$D
filtered_id <- filtered_data$id

if(is.null(filtered_D)){
mess <- paste0(mess, "All rows were filtered out. \n")
Expand Down Expand Up @@ -142,7 +147,12 @@ PCA_Plot <- function(D,

message(mess)

return(list("plot" = pl, "D_PCA_plot" = cbind(D_PCA, "Sample" = colnames(D)),
"pca" = pca, "message" = mess, "filtered_D" = filtered_D, "loadings" = pca$rotation))
Loadings <- as.data.frame(pca$rotation)
if (!is.null(filtered_id)) {
Loadings <- cbind(filtered_id, Loadings)
}

return(list("D_PCA_plot" = cbind(D_PCA, "Sample" = colnames(D)),
"pca" = pca, "message" = mess, "filtered_D" = filtered_D, "loadings" = Loadings, "plot" = pl))
}

12 changes: 9 additions & 3 deletions R/PCA_helper.R
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -3,6 +3,8 @@
#'
#' @param D \strong{data.frame} \cr
#' The data set containing intensities of the sample.
#' @param id \strong{data.frame} \cr
#' The corresponding ID columns for the parameter D e.g. containing further columns like protein or gene names
#' @param impute \strong{logical} \cr
#' If \code{TRUE}, missing values will be imputed.
#' @param impute_method \strong{character} \cr
Expand All @@ -17,13 +19,17 @@
#'
#'

filter_PCA_data <- function(D, impute = FALSE, impute_method = "mean", propNA = 0){
filter_PCA_data <- function(D, id = NULL, impute = FALSE, impute_method = "mean", propNA = 0){

# proportion if missing values per protein
mean_NA <- apply(D, 1, function(x) mean(is.na(x)))

### remove rows with too many missing values
D <- D[mean_NA <= propNA, ]
index_to_keep <- mean_NA <= propNA
D <- D[index_to_keep, ]
if (!is.null(id)) {
id <- id[index_to_keep, ]
}

if (nrow(D) == 0){
return(NULL)
Expand Down Expand Up @@ -52,7 +58,7 @@ filter_PCA_data <- function(D, impute = FALSE, impute_method = "mean", propNA =
ind_zeroVar <- which(v < 1e-25)
if (length(ind_zeroVar) > 0) D <- D[-ind_zeroVar,]

return(D)
return(list(D = D, id = id))
}


Expand Down