Enhanced error handling and debugging in plotting the frequency of peptide identifications across a chromatographic gradient.

modules/max_quant/010_Chromatography/chrom_01_IDfreq_by_RT.R

@@ -7,11 +7,18 @@ init <- function() {
 
   .validate <- function(data, input) {
     validate(need(data()[['evidence']], paste0('Upload evidence.txt')))
+
+    validate(need(
+      all(c('Retention.time', 'PEP', 'Type') %in% colnames(data()[['evidence']])),
+      'Columns "Retention.time", "PEP", or "Type" not found in evidence.txt.'
+    ))
   }
 
   .plotdata <- function(data, input) {
     plotdata <- data()[['evidence']][,c('Raw.file', 'Retention.time', 'PEP','Type')]
+    print(colnames(data()[['evidence']]))
     plotdata <- plotdata %>% dplyr::filter(Type != "MULTI-MATCH")
+    validate(need((nrow(plotdata) > 0), "No valid data after filtering Type"))
     plotdata <- plotdata %>% dplyr::select('Raw.file', 'Retention.time', 'PEP')
     return(plotdata)
   }
@@ -23,7 +30,7 @@ init <- function() {
 
     maxRT <- max(plotdata$Retention.time)
     ggplot(plotdata, aes(Retention.time)) + 
-      facet_wrap(~Raw.file, nrow = 1, scales = "free_x") + 
+      facet_wrap(~Raw.file, nrow = 1, scales = "free_x") +
       geom_histogram(bins=100) + 
       coord_flip() + 
       xlim(10, maxRT) +

modules/max_quant/020_Ion_Sampling/instrument_03_MS1_int_z_all.R

@@ -1,40 +1,62 @@
-init <- function() {
+init <- function() { 
 
   type <- 'plot'
   box_title <- 'MS1 Intensity for all ions'
   help_text <- 'Plotting the MS1 intensity for all ions observed (not necessarily sent to MS2).'
   source_file <- 'allPeptides'
 
+  # validate if the correct file is being uploaded
   .validate <- function(data, input) {
     validate(need(data()[['allPeptides']], paste0('Upload allPeptides.txt')))
   }
 
+  # Plot data preparation function with an indicator message
   .plotdata <- function(data, input) {
-    plotdata <- data()[['allPeptides']][,c('Raw.file', 'Charge', 'Intensity', 'MS.MS.Count')]
-    plotdata$Intensity <- log10(plotdata$Intensity)
-    #plotdata <- plotdata[plotdata$MS.MS.Count >= 1,]
+    # Basic columns needed for plotting
+    plotdata <- data()[['allPeptides']][, c('Raw.file', 'Charge', 'Intensity')]
+
+    # Check if MS.MS.Count or Number.of.pasef.MS.MS columns are present
+    msms_count_present <- "MS.MS.count" %in% colnames(data()[['allPeptides']])
+    pasef_msms_present <- "Number.of.pasef.MS.MS" %in% colnames(data()[['allPeptides']])
 
-    # Thresholding data at 1 and 99th percentiles
-    ceiling <- quantile(plotdata$Intensity, probs=.99, na.rm = TRUE)
-    floor <- quantile(plotdata$Intensity, probs=.01, na.rm = TRUE)
+    if (msms_count_present) {
+      plotdata <- data()[['allPeptides']][, c('Raw.file', 'Charge', 'Intensity', 'MS.MS.count')]
+      plot_type_message <- "Plot generated using MS.MS.count data."
+    } else if (pasef_msms_present) {
+      plotdata <- data()[['allPeptides']][, c('Raw.file', 'Charge', 'Intensity', 'Number.of.pasef.MS.MS')]
+      plot_type_message <- "Plot generated using Number.of.pasef.MS.MS data."
+    } else {
+      # if neither column is present, show validation message and stop
+      validate(need(FALSE, "Neither MS.MS.count nor Number.of.pasef.MS.MS is available. Cannot generate plot."))
+    }
+
+    # Log-transform Intensity column for better scaling
+    plotdata$Intensity <- log10(plotdata$Intensity)
 
-    plotdata <- dplyr::filter(plotdata, is.finite(Intensity))
+    # Thresholding data at the 1st and 99th percentiles
+    ceiling <- quantile(plotdata$Intensity, probs = .99, na.rm = TRUE)
+    floor <- quantile(plotdata$Intensity, probs = .01, na.rm = TRUE)
 
-    plotdata[plotdata$Intensity >= ceiling, 3] <- ceiling
+    plotdata <- dplyr::filter(plotdata, is.finite(Intensity)) # Checks whether the Intensity values are finite (i.e., not Inf, -Inf, or NA).
+    # the colnames: Raw.file, Charge, Intensity, Number.of.pasef.MS.MS. the 3rd column is 'intensity'
+    # Any Intensity value greater than or equal to the ceiling/floor is replaced with the ceiling/floor value. This caps the upper/lower outliers.
+    plotdata[plotdata$Intensity >= ceiling, 3] <- ceiling 
     plotdata[plotdata$Intensity <= floor, 3] <- floor
 
     return(plotdata)
   }
 
   .plot <- function(data, input) {
-    .validate(data, input)
-    plotdata <- .plotdata(data, input)
+    .validate(data, input)  # Check if required file is uploaded
+    plotdata <- .plotdata(data, input)  # Prepare the data for plotting
 
+    # is there data to plot?
     validate(need((nrow(plotdata) > 1), paste0('No Rows selected')))
 
+    # generate the plot
     ggplot(plotdata, aes(Intensity)) + 
       facet_wrap(~Raw.file, nrow = 1, scales = "free_x") + 
-      geom_histogram(bins=30) + 
+      geom_histogram(bins = 30) + 
       coord_flip() + 
       labs(x=expression(bold('Log'[10]*' Precursor Intensity')), y='Number of Ions') +
       theme_base(input=input)