add filter options from FragPipe-Analyst

DESCRIPTION

@@ -55,5 +55,5 @@ Suggests:
     testthat (>= 3.0.0)
 biocViews: Software
 Config/testthat/edition: 3
-RoxygenNote: 7.3.2
+RoxygenNote: 7.3.3
 VignetteBuilder: knitr

NAMESPACE

@@ -18,8 +18,10 @@ export(average_samples)
 export(bar_number)
 export(colData)
 export(consensus_clustering_analysis)
+export(filter_by_condition)
 export(get_cluster_heatmap)
 export(get_density)
+export(global_filter)
 export(glycoPSM_barplot)
 export(impute)
 export(make_se_customized)
@@ -68,12 +70,22 @@ importFrom(SNFtool,spectralClustering)
 importFrom(SNFtool,standardNormalization)
 importFrom(SummarizedExperiment,"assay<-")
 importFrom(SummarizedExperiment,"colData<-")
+importFrom(SummarizedExperiment,"metadata<-")
 importFrom(SummarizedExperiment,"rowData<-")
 importFrom(SummarizedExperiment,SummarizedExperiment)
 importFrom(SummarizedExperiment,assay)
 importFrom(SummarizedExperiment,colData)
+importFrom(SummarizedExperiment,metadata)
 importFrom(SummarizedExperiment,rowData)
+importFrom(assertthat,assert_that)
+importFrom(circlize,colorRamp2)
+importFrom(cluster,daisy)
 importFrom(clusterProfiler,GSEA)
+importFrom(clusterProfiler,bitr)
+importFrom(clusterProfiler,gseGO)
+importFrom(clusterProfiler,gseKEGG)
+importFrom(clusterProfiler,read.gmt)
+importFrom(clusterProfiler,setReadable)
 importFrom(cmapR,GCT)
 importFrom(cmapR,ids)
 importFrom(cmapR,mat)
@@ -85,11 +97,14 @@ importFrom(data.table,melt.data.table)
 importFrom(data.table,setDT)
 importFrom(dplyr,all_of)
 importFrom(dplyr,arrange)
+importFrom(dplyr,ends_with)
 importFrom(dplyr,filter)
 importFrom(dplyr,group_by)
+importFrom(dplyr,if_all)
 importFrom(dplyr,left_join)
 importFrom(dplyr,mutate)
 importFrom(dplyr,n)
+importFrom(dplyr,pull)
 importFrom(dplyr,recode)
 importFrom(dplyr,rename)
 importFrom(dplyr,select)
@@ -100,6 +115,7 @@ importFrom(dplyr,summarize)
 importFrom(fdrtool,fdrtool)
 importFrom(ggplot2,aes)
 importFrom(ggplot2,aes_string)
+importFrom(ggplot2,annotate)
 importFrom(ggplot2,coord_fixed)
 importFrom(ggplot2,element_blank)
 importFrom(ggplot2,element_line)
@@ -110,8 +126,11 @@ importFrom(ggplot2,geom_boxplot)
 importFrom(ggplot2,geom_col)
 importFrom(ggplot2,geom_histogram)
 importFrom(ggplot2,geom_jitter)
+importFrom(ggplot2,geom_line)
 importFrom(ggplot2,geom_point)
 importFrom(ggplot2,geom_text)
+importFrom(ggplot2,geom_text_repel)
+importFrom(ggplot2,geom_violin)
 importFrom(ggplot2,geom_vline)
 importFrom(ggplot2,ggplot)
 importFrom(ggplot2,ggplot_build)
@@ -128,9 +147,18 @@ importFrom(ggplot2,scale_x_continuous)
 importFrom(ggplot2,scale_y_continuous)
 importFrom(ggplot2,theme)
 importFrom(ggplot2,theme_bw)
+importFrom(ggplot2,theme_classic)
+importFrom(ggplot2,theme_void)
+importFrom(ggplot2,xlab)
+importFrom(ggplot2,ylab)
+importFrom(ggplotify,as.ggplot)
 importFrom(ggrepel,geom_text_repel)
 importFrom(grDevices,colorRampPalette)
+importFrom(grDevices,dev.off)
+importFrom(grDevices,png)
 importFrom(grid,gpar)
+importFrom(grid,grid.rect)
+importFrom(grid,grid.text)
 importFrom(grid,unit)
 importFrom(httr,GET)
 importFrom(limma,contrasts.fit)
@@ -145,10 +173,20 @@ importFrom(plotly,layout)
 importFrom(plotly,plot_ly)
 importFrom(purrr,map_df)
 importFrom(readr,parse_factor)
+importFrom(scales,percent)
+importFrom(stats,complete.cases)
+importFrom(stats,cor)
+importFrom(stats,kmeans)
+importFrom(stats,lm)
+importFrom(stats,mad)
+importFrom(stats,median)
+importFrom(stats,prcomp)
 importFrom(stringr,str_count)
 importFrom(tibble,column_to_rownames)
+importFrom(tibble,is_tibble)
 importFrom(tibble,rownames_to_column)
 importFrom(tidyr,gather)
+importFrom(tidyr,replace_na)
 importFrom(tidyr,spread)
 importFrom(tidyr,unite)
 importFrom(vsn,predict)

R/filter.R

@@ -0,0 +1,48 @@
+#' Filter proteins by missing values globally
+#'
+#' \code{global_filter} removes proteins that have missing values in more than
+#' a given percentage of all samples.
+#'
+#' @param se SummarizedExperiment, proteomics data.
+#' @param percentage Numeric, maximum percentage of missing values allowed
+#'   across all samples (0-100). Default is 50.
+#' @return A filtered SummarizedExperiment object.
+#' @examples
+#' data("ccrcc", package = "FragPipeAnalystR")
+#' filtered <- global_filter(ccrcc, percentage = 50)
+#'
+#' @export
+global_filter <- function(se, percentage=50){
+  percentage <- percentage / 100
+  ridx <- rowSums(is.na(assay(se))) / ncol(assay(se)) <= percentage
+  se <- se[ridx,]
+  return(se)
+}
+
+#' Filter proteins by missing values per condition
+#'
+#' \code{filter_by_condition} retains proteins that are observed in at least
+#' \code{min_percentage} of samples in at least one condition.
+#'
+#' @param se SummarizedExperiment, proteomics data. Must have a \code{condition}
+#'   column in \code{colData}.
+#' @param min_percentage Numeric, minimum percentage of non-missing values
+#'   required within at least one condition (0-100). Default is 50.
+#' @return A filtered SummarizedExperiment object.
+#' @examples
+#' data("ccrcc", package = "FragPipeAnalystR")
+#' filtered <- filter_by_condition(ccrcc, min_percentage = 50)
+#'
+#' @export
+filter_by_condition <- function(se, min_percentage=50) {
+  min_percentage <- min_percentage / 100
+  conditions <- unique(colData(se)$condition)
+  row_ids <- rep(0, nrow(assay(se)))
+  for (c in conditions){
+    se_c <- se[,colData(se)$condition == c]
+    ridx <- rowSums(!is.na(assay(se_c))) / ncol(assay(se_c)) >= min_percentage
+    row_ids <- row_ids + ridx
+  }
+  se <- se[row_ids > 0,]
+  return(se)
+}