Fixed: NA treatment. Now NA's are allowed in clustering. NA removal and...

Fixed: NA treatment. Now NA's are allowed in clustering. NA removal and interpolaton happen when the checkbox is checked in UI.

modules/auxfunc.R

@@ -95,7 +95,9 @@ help.text = c(
   Say, the main data file contains columns Metadata_Site and TrackLabel. 
   These two columns should be then selected in UI to form a unique cell ID, e.g. 001_0001 where former part corresponds to Metadata_Site and the latter to TrackLabel.',
   'Plotting and data processing requires a unique cell ID across entire dataset. A typical dataset from CellProfiler assigns unique cell ID (TrackLabel) within each field of view (Metadata_Site).
-                   Therefore, a unique ID is created by concatenating these two columns. If the dataset already contains a unique ID, UNcheck this box and select a single column only.'
+                   Therefore, a unique ID is created by concatenating these two columns. If the dataset already contains a unique ID, UNcheck this box and select a single column only.',
+  'This option allows to interpolate NAs or missing data. Some rows in the input file might be missing because a particular time point might not had been acquired. 
+  This option, interpolates such missing points as well as points with NAs in the measurement column. When this option is checked, the interval of time column must be provided!'
 )
 
 

modules/trajPlot.R

@@ -88,7 +88,7 @@ modTrajPlot = function(input, output, session,
     
       locYmin = signif(min(loc.dt$y, na.rm = T), 4)
       locYmax = signif(max(loc.dt$y, na.rm = T), 4)
-      
+
       sliderInput(
         ns('slYTrim'),
         label = 'Trim y-axis',

server.R

@@ -451,7 +451,6 @@ shinyServer(function(input, output, session) {
       cat(file = stderr(), 'dataMod: trajRem not NULL\n')
       
       loc.dt.rem = dataLoadTrajRem()
-      print(loc.dt.rem)
       loc.dt = loc.dt[!(trackObjectsLabelUni %in% loc.dt.rem[[1]])]
     }
     
@@ -613,18 +612,18 @@ shinyServer(function(input, output, session) {
     }
       
 
-    ## Interpolate NA's and data points that are missing
+    ## Interpolate missing data and NA data points
     # From: https://stackoverflow.com/questions/28073752/r-how-to-add-rows-for-missing-values-for-unique-group-sequences
     # Tracks are interpolated only within first and last time points of every cell id
     # Datasets can have different realtime frequency (e.g. every 1', 2', etc),
     # or the frame number metadata can be missing, as is the case for tCourseSelected files that already have realtime column.
-    # Therefore, we cnanot rely on that info to get time frequency; user provides this number!
+    # Therefore, we cannot rely on that info to get time frequency; user provides this number!
     
     setkey(loc.out, group, id, realtime)
 
     if (input$chBtrajInter) {
       # here we fill missing data with NA's
-      loc.out = loc.out[setkey(loc.out[, .(seq(min(realtime), max(realtime), input$inSelTimeFreq)), by = .(group, id)], group, id, V1)]
+      loc.out = loc.out[setkey(loc.out[, .(seq(min(realtime, na.rm = T), max(realtime, na.rm = T), input$inSelTimeFreq)), by = .(group, id)], group, id, V1)]
       
       # x-check: print all rows with NA's
       print('Rows with NAs:')
@@ -727,11 +726,13 @@ shinyServer(function(input, output, session) {
     loc.out = as.matrix(loc.out[, -1])
     rownames(loc.out) = loc.rownames
     
+    # This might be removed entirely because all NA treatment happens in data4trajPlot
+    # Clustering should work with NAs present. These might result from data itself or from missing time point rows that were turned into NAs when dcast-ing from long format.
     # Remove NA's
     # na.interpolation from package imputeTS works with multidimensional data
     # but imputation is performed for each column independently
     # The matrix for clustering contains time series in rows, hence transposing it twice
-    loc.out = t(na.interpolation(t(loc.out)))
+    # loc.out = t(na.interpolation(t(loc.out)))
     
     return(loc.out)
   }) 

ui.R

@@ -42,7 +42,15 @@ shinyUI(fluidPage(
       uiOutput('uiButLoadTrajRem'),
       
       tags$hr(),
-      checkboxInput('chBtrajInter', 'Interpolate NAs?', value = T),
+      checkboxInput('chBtrajInter', 'Interpolate NAs and missing data?', value = T),
+      helpPopup(
+        title = 'Interpolation of NAs and missing data',
+        content = help.text[3],
+        placement = 'right',
+        trigger = 'hover'
+      ),
+      
+      uiOutput('varSelTimeFreq'),
       checkboxInput('chBtrackUni', 'Create unique TrackLabel', T),
       helpPopup(
         title = 'Create unique cell ID',
@@ -57,7 +65,6 @@ shinyUI(fluidPage(
       checkboxInput('chBgroup', 'Dataset contains grouping column (e.g. treatment, condition)', TRUE),                
       uiOutput('varSelGroup'),
       uiOutput('varSelTime'),
-      uiOutput('varSelTimeFreq'),
       uiOutput('varSelMeas1'),
       radioButtons(
         'inSelMath',