server.R 23.2 KB
Newer Older
dmattek's avatar
dmattek committed
1

2

dmattek's avatar
dmattek committed
3

dmattek's avatar
dmattek committed
4 5 6 7 8 9 10 11 12 13
# This is the server logic for a Shiny web application.
# You can find out more about building applications with Shiny here:
#
# http://shiny.rstudio.com
#

library(shiny)
library(shinyjs) #http://deanattali.com/shinyjs/
library(data.table)
library(ggplot2)
dmattek's avatar
dmattek committed
14
library(gplots) # for heatmap.2
dmattek's avatar
dmattek committed
15
library(plotly)
dmattek's avatar
dmattek committed
16 17
library(d3heatmap) # for interactive heatmap
library(dendextend) # for color_branches
dmattek's avatar
Mod:  
dmattek committed
18
library(colorspace) # for palettes (ised to colour dendrogram)
dmattek's avatar
dmattek committed
19 20 21
library(RColorBrewer)
library(sparcl) # sparse hierarchical and k-means
library(scales) # for percentages on y scale
dmattek's avatar
dmattek committed
22 23
library(dtw) # for dynamic time warping
library(imputeTS) # for interpolating NAs
dmattek's avatar
dmattek committed
24

25
# increase file upload limit
dmattek's avatar
dmattek committed
26
options(shiny.maxRequestSize = 200 * 1024 ^ 2)
dmattek's avatar
dmattek committed
27

28
shinyServer(function(input, output, session) {
29
  useShinyjs()
dmattek's avatar
dmattek committed
30
  
31 32 33 34 35 36
  # This is only set at session start
  # we use this as a way to determine which input was
  # clicked in the dataInBoth reactive
  counter <- reactiveValues(
    # The value of inDataGen1,2 actionButton is the number of times they were pressed
    dataGen1     = isolate(input$inDataGen1),
dmattek's avatar
dmattek committed
37 38
    dataLoadNuc  = isolate(input$inButLoadNuc),
    dataLoadTrajRem = isolate(input$inButLoadTrajRem)
39
    #dataLoadStim = isolate(input$inButLoadStim)
dmattek's avatar
dmattek committed
40 41
  )
  
dmattek's avatar
dmattek committed
42 43 44
  ####
  ## UI for side panel
  
dmattek's avatar
dmattek committed
45
  # FILE LOAD
46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72
  # This button will reset the inFileLoad
  observeEvent(input$inButReset, {
    reset("inFileLoadNuc")  # reset is a shinyjs function
    #reset("inButLoadStim")  # reset is a shinyjs function
  })
  
  # generate random dataset 1
  dataGen1 <- eventReactive(input$inDataGen1, {
    cat("dataGen1\n")
    
    return(userDataGen())
  })
  
  # load main data file
  dataLoadNuc <- eventReactive(input$inButLoadNuc, {
    cat("dataLoadNuc\n")
    locFilePath = input$inFileLoadNuc$datapath
    
    counter$dataLoadNuc <- input$inButLoadNuc - 1
    
    if (is.null(locFilePath) || locFilePath == '')
      return(NULL)
    else {
      return(fread(locFilePath))
    }
  })
  
dmattek's avatar
dmattek committed
73 74 75 76 77 78 79
  # This button will reset the inFileLoad
  observeEvent(input$butReset, {
    reset("inFileLoadNuc")  # reset is a shinyjs function
    #    reset("inFileStimLoad")  # reset is a shinyjs function
    
  })
  
dmattek's avatar
dmattek committed
80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112
  # UI for loading csv with cell IDs for trajectory removal
  output$uiFileLoadTrajRem = renderUI({
    cat(file = stderr(), 'UI uiFileLoadTrajRem\n')
    
    if(input$chBtrajRem) 
      fileInput(
        'inFileLoadTrajRem',
        'Select data file (e.g. badTraj.csv) and press "Load Data"',
        accept = c('text/csv', 'text/comma-separated-values,text/plain')
      )
  })
  
  output$uiButLoadTrajRem = renderUI({
    cat(file = stderr(), 'UI uiButLoadTrajRem\n')
    
    if(input$chBtrajRem)
      actionButton("inButLoadTrajRem", "Load Data")
  })

  # load main data file
  dataLoadTrajRem <- eventReactive(input$inButLoadTrajRem, {
    cat(file = stderr(), "dataLoadTrajRem\n")
    locFilePath = input$inFileLoadTrajRem$datapath
    
    counter$dataLoadTrajRem <- input$inButLoadTrajRem - 1
    
    if (is.null(locFilePath) || locFilePath == '')
      return(NULL)
    else {
      return(fread(locFilePath))
    }
  })
  
dmattek's avatar
dmattek committed
113 114
  
  # COLUMN SELECTION
dmattek's avatar
dmattek committed
115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150
  output$varSelTrackLabel = renderUI({
    cat(file = stderr(), 'UI varSelTrackLabel\n')
    locCols = getDataNucCols()
    locColSel = locCols[locCols %like% 'rack'][1] # index 1 at the end in case more matches; select 1st
    
    selectInput(
      'inSelTrackLabel',
      'Select Track Label (e.g. objNuc_Track_ObjectsLabel):',
      locCols,
      width = '100%',
      selected = locColSel
    )
  })
  
  output$varSelTime = renderUI({
    cat(file = stderr(), 'UI varSelTime\n')
    locCols = getDataNucCols()
    locColSel = locCols[locCols %like% 'RealTime'][1] # index 1 at the end in case more matches; select 1st
    
    cat(locColSel, '\n')
    selectInput(
      'inSelTime',
      'Select time column (e.g. RealTime):',
      locCols,
      width = '100%',
      selected = locColSel
    )
  })
  
  # This is main field to select plot facet grouping
  # It's typically a column with the entire experimental description,
  # e.g. in Yannick's case it's Stim_All_Ch or Stim_All_S.
  # In Coralie's case it's a combination of 3 columns called Stimulation_...
  output$varSelGroup = renderUI({
    cat(file = stderr(), 'UI varSelGroup\n')
    
dmattek's avatar
dmattek committed
151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170
    if (input$chBgroup) {
      
      locCols = getDataNucCols()
      
      if (!is.null(locCols)) {
        locColSel = locCols[locCols %like% 'ite']
        if (length(locColSel) == 0)
          locColSel = locCols[locCols %like% 'eries'][1] # index 1 at the end in case more matches; select 1st
        else if (length(locColSel) > 1) {
          locColSel = locColSel[1]
        }
        #    cat('UI varSelGroup::locColSel ', locColSel, '\n')
        selectInput(
          'inSelGroup',
          'Select one or more facet groupings (e.g. Site, Well, Channel):',
          locCols,
          width = '100%',
          selected = locColSel,
          multiple = TRUE
        )
dmattek's avatar
dmattek committed
171 172 173 174 175 176 177
      }
    }
  })
  
  output$varSelSite = renderUI({
    cat(file = stderr(), 'UI varSelSite\n')
    
dmattek's avatar
dmattek committed
178 179 180 181 182 183 184 185 186 187 188 189
    if (!input$chBtrackUni) {
      locCols = getDataNucCols()
      locColSel = locCols[locCols %like% 'ite'][1] # index 1 at the end in case more matches; select 1st
      
      selectInput(
        'inSelSite',
        'Select FOV (e.g. Metadata_Site or Metadata_Series):',
        locCols,
        width = '100%',
        selected = locColSel
      )
    }
dmattek's avatar
dmattek committed
190 191 192 193 194 195 196 197 198 199
  })
  
  
  
  
  output$varSelMeas1 = renderUI({
    cat(file = stderr(), 'UI varSelMeas1\n')
    locCols = getDataNucCols()
    
    if (!is.null(locCols)) {
dmattek's avatar
dmattek committed
200 201
      locColSel = locCols[locCols %like% 'objCyto_Intensity_MeanIntensity_imErkCor.*' |
                            locCols %like% 'Ratio'][1] # index 1 at the end in case more matches; select 1st
dmattek's avatar
dmattek committed
202

dmattek's avatar
dmattek committed
203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220
      selectInput(
        'inSelMeas1',
        'Select 1st measurement:',
        locCols,
        width = '100%',
        selected = locColSel
      )
    }
  })
  
  
  output$varSelMeas2 = renderUI({
    cat(file = stderr(), 'UI varSelMeas2\n')
    locCols = getDataNucCols()
    
    if (!is.null(locCols) &&
        !(input$inSelMath %in% c('', '1 / '))) {
      locColSel = locCols[locCols %like% 'objNuc_Intensity_MeanIntensity_imErkCor.*'][1] # index 1 at the end in case more matches; select 1st
dmattek's avatar
dmattek committed
221

dmattek's avatar
dmattek committed
222 223 224 225 226 227 228 229 230 231
      selectInput(
        'inSelMeas2',
        'Select 2nd measurement',
        locCols,
        width = '100%',
        selected = locColSel
      )
    }
  })
  
dmattek's avatar
dmattek committed
232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255
  # UI for trimming x-axis (time)
  output$uiSlTimeTrim = renderUI({
    cat(file = stderr(), 'UI uiSlTimeTrim\n')
    
    if (input$chBtimeTrim) {
      locTpts  = getDataTpts()
      
      if(is.null(locTpts))
        return(NULL)
      
      locRTmin = min(locTpts)
      locRTmax = max(locTpts)
      
      sliderInput(
        'slTimeTrim',
        label = 'Time range to include',
        min = locRTmin,
        max = locRTmax,
        value = c(locRTmin, locRTmax),
        step = 1
      )
      
    }
  })
dmattek's avatar
dmattek committed
256
  
dmattek's avatar
dmattek committed
257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287
  # UI for normalization
  
  output$uiChBnorm = renderUI({
    cat(file = stderr(), 'UI uiChBnorm\n')
    
    if (input$chBnorm) {
      radioButtons(
        'rBnormMeth',
        label = 'Select method',
        choices = list('fold-change' = 'mean', 'z-score' = 'z.score')
      )
    }
  })
  
  output$uiSlNorm = renderUI({
    cat(file = stderr(), 'UI uiSlNorm\n')
    
    if (input$chBnorm) {
      locTpts  = getDataTpts()
      
      if(is.null(locTpts))
        return(NULL)
      
      locRTmin = min(locTpts)
      locRTmax = max(locTpts)
      
      sliderInput(
        'slNormRtMinMax',
        label = 'Time range for norm.',
        min = locRTmin,
        max = locRTmax,
dmattek's avatar
dmattek committed
288 289
        value = c(locRTmin, 0.1 * locRTmax), 
        step = 1
dmattek's avatar
dmattek committed
290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308
      )
    }
  })
  
  output$uiChBnormRobust = renderUI({
    cat(file = stderr(), 'UI uiChBnormRobust\n')
    
    if (input$chBnorm) {
      checkboxInput('chBnormRobust',
                    label = 'Robust stats',
                    FALSE)
    }
  })
  
  output$uiChBnormGroup = renderUI({
    cat(file = stderr(), 'UI uiChBnormGroup\n')
    
    if (input$chBnorm) {
      radioButtons('chBnormGroup',
dmattek's avatar
Mod:  
dmattek committed
309 310
                   label = 'Normalisation grouping',
                   choices = list('Entire dataset' = 'none', 'Per facet' = 'group', 'Per trajectory (Korean way)' = 'id'))
dmattek's avatar
dmattek committed
311 312 313 314
    }
  })
  
  
dmattek's avatar
dmattek committed
315 316 317 318 319
  # UI for removing outliers
  output$uiSlOutliers = renderUI({
    cat(file = stderr(), 'UI uiSlOutliers\n')
    
    if (input$chBoutliers) {
dmattek's avatar
Mod:  
dmattek committed
320
      
dmattek's avatar
dmattek committed
321 322 323 324 325
      sliderInput(
        'slOutliersPerc',
        label = 'Percentage of middle data',
        min = 90,
        max = 100,
dmattek's avatar
dmattek committed
326
        value = 99.5, 
dmattek's avatar
dmattek committed
327 328
        step = 0.1
      )
dmattek's avatar
dmattek committed
329
      
dmattek's avatar
Mod:  
dmattek committed
330
      
dmattek's avatar
dmattek committed
331 332 333
    }
  })
  
dmattek's avatar
dmattek committed
334 335 336 337 338 339 340 341 342
  output$uiTxtOutliers = renderUI({
    if (input$chBoutliers) {
      
      p("Total tracks")
      
    }
    
  })
  
dmattek's avatar
dmattek committed
343
  
dmattek's avatar
dmattek committed
344 345 346 347 348 349 350 351 352
  ####
  ## data processing
  
  # generate random dataset 1
  dataGen1 <- eventReactive(input$inDataGen1, {
    cat("dataGen1\n")
    
    return(userDataGen())
  })
353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401
  
  dataInBoth <- reactive({
    # Without direct references to inDataGen1,2 and inFileLoad, inDataGen2
    #    does not trigger running this reactive once inDataGen1 is used.
    # This is one of the more nuanced areas of reactive programming in shiny
    #    due to the if else logic, it isn't fetched once inDataGen1 is available
    # The morale is use direct retrieval of inputs to guarantee they are available
    #    for if else logic checks!
    
    locInGen1 = input$inDataGen1
    locInLoadNuc = input$inButLoadNuc
    #locInLoadStim = input$inButLoadStim
    
    cat(
      "dataInBoth\ninGen1: ",
      locInGen1,
      "   prev=",
      isolate(counter$dataGen1),
      "\ninDataNuc: ",
      locInLoadNuc,
      "   prev=",
      isolate(counter$dataLoadNuc),
      # "\ninDataStim: ",
      # locInLoadStim,
      # "   prev=",
      # isolate(counter$dataLoadStim),
      "\n"
    )
    
    # isolate the checks of counter reactiveValues
    # as we set the values in this same reactive
    if (locInGen1 != isolate(counter$dataGen1)) {
      cat("dataInBoth if inDataGen1\n")
      dm = dataGen1()
      # no need to isolate updating the counter reactive values!
      counter$dataGen1 <- locInGen1
    } else if (locInLoadNuc != isolate(counter$dataLoadNuc)) {
      cat("dataInBoth if inDataLoadNuc\n")
      dm = dataLoadNuc()
      # no need to isolate updating the counter reactive values!
      counter$dataLoadNuc <- locInLoadNuc
    } else {
      cat("dataInBoth else\n")
      dm = NULL
    }
    return(dm)
  })
  
  # return column names of the main dt
dmattek's avatar
dmattek committed
402
  getDataNucCols <- reactive({
403 404 405 406 407 408 409 410 411 412 413
    cat(file = stderr(), 'getDataNucCols: in\n')
    loc.dt = dataInBoth()
    
    if (is.null(loc.dt))
      return(NULL)
    else
      return(colnames(loc.dt))
  })
  
  # return dt with an added column with unique track object label
  dataMod <- reactive({
dmattek's avatar
dmattek committed
414
    cat(file = stderr(), 'dataMod\n')
415 416
    loc.dt = dataInBoth()
    
dmattek's avatar
dmattek committed
417
    if (is.null(loc.dt))
418 419
      return(NULL)
    
dmattek's avatar
dmattek committed
420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439
    if (!input$chBtrackUni) {
      loc.types = lapply(loc.dt, class)
      if(loc.types[[input$inSelTrackLabel]] %in% c('numeric', 'integer') & loc.types[[input$inSelSite]] %in% c('numeric', 'integer'))
      {
        loc.dt[, trackObjectsLabelUni := paste(sprintf("%03d", get(input$inSelSite)),
                                               sprintf("%04d", get(input$inSelTrackLabel)),
                                               sep = "_")]
      } else if(loc.types[[input$inSelTrackLabel]] %in% c('numeric', 'integer')) {
        loc.dt[, trackObjectsLabelUni := paste(sprintf("%s", get(input$inSelSite)),
                                               sprintf("%04d", get(input$inSelTrackLabel)),
                                               sep = "_")]
      } else if(loc.types[[input$inSelSite]] %in% c('numeric', 'integer')) {
        loc.dt[, trackObjectsLabelUni := paste(sprintf("%03d", get(input$inSelSite)),
                                               sprintf("%s", get(input$inSelTrackLabel)),
                                               sep = "_")]
      } else {
        loc.dt[, trackObjectsLabelUni := paste(sprintf("%s", get(input$inSelSite)),
                                               sprintf("%s", get(input$inSelTrackLabel)),
                                               sep = "_")]
      }
dmattek's avatar
dmattek committed
440
    } else {
dmattek's avatar
dmattek committed
441
      loc.dt[, trackObjectsLabelUni := get(input$inSelTrackLabel)]
dmattek's avatar
dmattek committed
442 443
    }
    
dmattek's avatar
dmattek committed
444
    
dmattek's avatar
dmattek committed
445 446 447 448 449 450
    # remove trajectories based on uploaded csv

    if (input$chBtrajRem) {
      cat(file = stderr(), 'dataMod: trajRem not NULL\n')
      
      loc.dt.rem = dataLoadTrajRem()
dmattek's avatar
dmattek committed
451 452 453
      
      
      loc.dt = loc.dt[!(trackObjectsLabelUni %in% loc.dt.rem[[1]])]
dmattek's avatar
dmattek committed
454 455
    }
    
456 457 458
    return(loc.dt)
  })
  
dmattek's avatar
dmattek committed
459 460 461 462 463
  # return all unique track object labels (created in dataMod)
  # This will be used to display in UI for trajectory highlighting
  getDataTrackObjLabUni <- reactive({
    cat(file = stderr(), 'getDataTrackObjLabUni\n')
    loc.dt = dataMod()
464
    
dmattek's avatar
dmattek committed
465 466 467 468
    if (is.null(loc.dt))
      return(NULL)
    else
      return(unique(loc.dt$trackObjectsLabelUni))
469 470
  })
  
dmattek's avatar
Mod:  
dmattek committed
471
  
dmattek's avatar
dmattek committed
472 473 474
  # return all unique time points (real time)
  # This will be used to display in UI for box-plot
  # These timepoints are from the original dt and aren't affected by trimming of x-axis
dmattek's avatar
dmattek committed
475 476 477
  getDataTpts <- reactive({
    cat(file = stderr(), 'getDataTpts\n')
    loc.dt = dataMod()
478
    
dmattek's avatar
dmattek committed
479 480 481 482
    if (is.null(loc.dt))
      return(NULL)
    else
      return(unique(loc.dt[[input$inSelTime]]))
483 484
  })
  
dmattek's avatar
dmattek committed
485
  
486 487 488
  
  # prepare data for plotting time courses
  # returns dt with these columns:
dmattek's avatar
dmattek committed
489
  #    realtime - selected from input
dmattek's avatar
dmattek committed
490
  #    y        - measurement selected from input
dmattek's avatar
dmattek committed
491 492 493 494 495
  #               (can be a single column or result of an operation on two cols)
  #    id       - trackObjectsLabelUni (created in dataMod)
  #    group    - grouping variable for facetting from input
  #    mid.in   - column with trajectory selection status from the input file or
  #               highlight status from UI
496
  data4trajPlot <- reactive({
dmattek's avatar
dmattek committed
497
    cat(file = stderr(), 'data4trajPlot\n')
498 499
    
    loc.dt = dataMod()
dmattek's avatar
dmattek committed
500
    if (is.null(loc.dt))
501 502 503
      return(NULL)
    
    
dmattek's avatar
dmattek committed
504
    if (input$inSelMath == '')
505 506 507 508 509 510 511 512 513
      loc.s.y = input$inSelMeas1
    else if (input$inSelMath == '1 / ')
      loc.s.y = paste0(input$inSelMath, input$inSelMeas1)
    else
      loc.s.y = paste0(input$inSelMeas1, input$inSelMath, input$inSelMeas2)
    
    # create expression for parsing
    # creates a merged column based on other columns from input
    # used for grouping of plot facets
dmattek's avatar
dmattek committed
514 515 516 517 518 519 520 521 522 523 524
    if (input$chBgroup) {
      if(length(input$inSelGroup) == 0)
        return(NULL)
      
      loc.s.gr = sprintf("paste(%s, sep=';')",
                         paste(input$inSelGroup, sep = '', collapse = ','))
    } else {
      # if no grouping required, fill 'group' column with 0
      # because all the plotting relies on the presence of the group column
      loc.s.gr = "paste('0')"
    }
525
    
dmattek's avatar
dmattek committed
526 527

    # column name with time
528 529
    loc.s.rt = input$inSelTime
    
dmattek's avatar
dmattek committed
530 531 532 533
    # Assign tracks selected for highlighting in UI
    loc.tracks.highlight = input$inSelHighlight
    locBut = input$chBhighlightTraj
    
dmattek's avatar
dmattek committed
534 535
    
    # Find column names with position
dmattek's avatar
Mod:  
dmattek committed
536 537
    loc.s.pos.x = names(loc.dt)[names(loc.dt) %like% c('.*ocation.*X') | names(loc.dt) %like% c('.*os.x')]
    loc.s.pos.y = names(loc.dt)[names(loc.dt) %like% c('.*ocation.*Y') | names(loc.dt) %like% c('.*os.y')]
dmattek's avatar
dmattek committed
538 539 540 541 542 543
    
    if (length(loc.s.pos.x) == 1 & length(loc.s.pos.y) == 1)
      locPos = TRUE
    else
      locPos = FALSE
    
544 545 546
    # if dataset contains column mid.in with trajectory filtering status,
    # then, include it in plotting
    if (sum(names(loc.dt) %in% 'mid.in') > 0) {
dmattek's avatar
dmattek committed
547 548 549 550 551 552
      if (locPos) # position columns present
        loc.out = loc.dt[, .(
          y = eval(parse(text = loc.s.y)),
          id = trackObjectsLabelUni,
          group = eval(parse(text = loc.s.gr)),
          realtime = eval(parse(text = loc.s.rt)),
dmattek's avatar
Mod:  
dmattek committed
553 554
          pos.x = get(loc.s.pos.x),
          pos.y = get(loc.s.pos.y),
dmattek's avatar
dmattek committed
555
          mid.in = mid.in
dmattek's avatar
Mod:  
dmattek committed
556 557 558 559 560 561 562 563 564 565 566 567 568 569 570
        )] else
          loc.out = loc.dt[, .(
            y = eval(parse(text = loc.s.y)),
            id = trackObjectsLabelUni,
            group = eval(parse(text = loc.s.gr)),
            realtime = eval(parse(text = loc.s.rt)),
            mid.in = mid.in
          )]
        
        # add 3rd level with status of track selection
        # to a column with trajectory filtering status
        if (locBut) {
          loc.out[, mid.in := ifelse(id %in% loc.tracks.highlight, 'SELECTED', mid.in)]
        }
        
571
    } else {
dmattek's avatar
dmattek committed
572 573 574 575 576
      if (locPos) # position columns present
        loc.out = loc.dt[, .(
          y = eval(parse(text = loc.s.y)),
          id = trackObjectsLabelUni,
          group = eval(parse(text = loc.s.gr)),
dmattek's avatar
Mod:  
dmattek committed
577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592
          realtime = eval(parse(text = loc.s.rt)),
          pos.x = get(loc.s.pos.x),
          pos.y = get(loc.s.pos.y)
        )] else
          loc.out = loc.dt[, .(
            y = eval(parse(text = loc.s.y)),
            id = trackObjectsLabelUni,
            group = eval(parse(text = loc.s.gr)),
            realtime = eval(parse(text = loc.s.rt))
          )]
        
        
        # add a column with status of track selection
        if (locBut) {
          loc.out[, mid.in := ifelse(id %in% loc.tracks.highlight, 'SELECTED', 'NOT SEL')]
        }
593
    }
dmattek's avatar
dmattek committed
594

595 596 597 598 599 600
    ## Interpolate NA's and data points not include
    # From: https://stackoverflow.com/questions/28073752/r-how-to-add-rows-for-missing-values-for-unique-group-sequences
    # Tracks are interpolated only within min and max realtime of every cell id
    setkey(loc.out, group, id, realtime)
    loc.out = loc.out[setkey(loc.out[, .(min(realtime):max(realtime)), by = .(group, id)], group, id, V1)]

dmattek's avatar
dmattek committed
601
    
602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628
    # # dt with a full span of realtime for every group and cell id 
    # # (here id is already unique across entire dataset) combination
    # loc.dt.IdRt =  CJ(id = loc.out[['id']], 
    #                   realtime = loc.out[['realtime']], 
    #                   unique = TRUE, sorted = TRUE )
    # 
    # print('loc.dt.IdRt:')
    # print(loc.dt.IdRt)
    # 
    # # dt with all cell id's and their associated group names
    # loc.dt.GrId = loc.out[, .(group = first(group)), by = id]
    # 
    # print('loc.dt.GrId:')
    # print(loc.dt.GrId)
    # 
    # # merge the 2 above to have all id~rt combinations with associated group names
    # loc.dt.GrIdRt = merge(loc.dt.IdRt, loc.dt.GrId, by = 'id')
    # 
    # print('loc.dt.GrIdRt:')
    # print(loc.dt.GrIdRt)
    # 
    # # join with the original to expand it and create NA's for non-existing group-id-rt combinations
    # loc.out = merge(loc.dt.GrIdRt, loc.out, all.x = TRUE, by = c('group', 'id', 'realtime'))
    # 
    # print('loc.out:')
    # print(loc.out)
    # 
dmattek's avatar
dmattek committed
629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656
    
    # x-check: print all rows with NA's
    print('Rows with NAs:')
    print(loc.out[rowSums(is.na(loc.out)) > 0, ])
    
    # Merge will create NA's where a realtime is missing.
    # Also, NA's may be already present in the dataset'.
    # Interpolate (linear) them with na.interpolate
    if(locPos) {
      s.cols = c('y', 'pos.x', 'pos.y')
      loc.out[, (s.cols) := lapply(.SD, na.interpolation), by = id, .SDcols = s.cols]
    }
    else {
      s.cols = c('y')
      loc.out[, (s.cols) := lapply(.SD, na.interpolation), by = id, .SDcols = s.cols]
    }
    

    # !!! Current issue with interpolation:
    # The column mid.in is not taken into account.
    # If a trajectory is selected in the UI,
    # the mid.in column is added (if it doesn't already exist in the dataset),
    # and for the interpolated point, it will still be NA. Not really an issue.
    #
    # Also, think about the current option of having mid.in column in the uploaded dataset.
    # Keep it? Expand it?
    # Create a UI filed for selecting the column with mid.in data.
    # What to do with that column during interpolation (see above)
dmattek's avatar
Mod:  
dmattek committed
657
    
658
    ## Trim x-axis (time)
dmattek's avatar
dmattek committed
659 660 661
    if(input$chBtimeTrim) {
      loc.out = loc.out[realtime >= input$slTimeTrim[[1]] & realtime <= input$slTimeTrim[[2]] ]
    }
dmattek's avatar
dmattek committed
662
    
663
    ## Normalization
dmattek's avatar
dmattek committed
664
    # F-n myNorm adds additional column with .norm suffix
dmattek's avatar
dmattek committed
665 666 667 668 669 670 671 672 673 674 675 676
    if (input$chBnorm) {
      loc.out = myNorm(
        in.dt = loc.out,
        in.meas.col = 'y',
        in.rt.col = 'realtime',
        in.rt.min = input$slNormRtMinMax[1],
        in.rt.max = input$slNormRtMinMax[2],
        in.type = input$rBnormMeth,
        in.robust = input$chBnormRobust,
        in.by.cols = if(input$chBnormGroup %in% 'none') NULL else input$chBnormGroup
      )
      
dmattek's avatar
dmattek committed
677 678
      # Column with normalized data is renamed to the original name
      # Further code assumes column name y produced by data4trajPlot
dmattek's avatar
dmattek committed
679 680 681 682
      loc.out[, y := NULL]
      setnames(loc.out, 'y.norm', 'y')
    }
    
dmattek's avatar
dmattek committed
683 684 685 686 687 688
    ##### MOD HERE
    ## display number of filtered tracks in textUI: uiTxtOutliers
    ## How? 
    ## 1. through reactive values?
    ## 2. through additional comumn to tag outliers?
    
dmattek's avatar
dmattek committed
689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705
    # Remove outliers
    # 1. Scale all points (independently per track)
    # 2. Pick time points that exceed the bounds
    # 3. Identify IDs of outliers
    # 4. Select cells that don't have these IDs
    
    cat('Ncells orig = ', length(unique(loc.out$id)), '\n')
    
    if (input$chBoutliers) {
      loc.out[, y.sc := scale(y)]  
      loc.tmp = loc.out[ y.sc < quantile(y.sc, (1 - input$slOutliersPerc * 0.01)*0.5) | 
                           y.sc > quantile(y.sc, 1 - (1 - input$slOutliersPerc * 0.01)*0.5)]
      loc.out = loc.out[!(id %in% unique(loc.tmp$id))]
      loc.out[, y.sc := NULL]
    }
    
    cat('Ncells trim = ', length(unique(loc.out$id)), '\n')
dmattek's avatar
Mod:  
dmattek committed
706
    
dmattek's avatar
dmattek committed
707
    return(loc.out)
dmattek's avatar
dmattek committed
708 709
  })
  
dmattek's avatar
dmattek committed
710 711 712 713 714 715 716 717 718 719 720 721 722
  
  
  # prepare data for clustering
  # return a matrix with:
  # cells as columns
  # time points as rows
  data4clust <- reactive({
    cat(file = stderr(), 'data4clust\n')
    
    loc.dt = data4trajPlot()
    if (is.null(loc.dt))
      return(NULL)
    
dmattek's avatar
dmattek committed
723
    #print(loc.dt)
dmattek's avatar
dmattek committed
724
    loc.out = dcast(loc.dt, id ~ realtime, value.var = 'y')
dmattek's avatar
dmattek committed
725
    #print(loc.out)
dmattek's avatar
dmattek committed
726 727
    loc.rownames = loc.out$id
    
dmattek's avatar
Mod:  
dmattek committed
728
    
dmattek's avatar
dmattek committed
729 730
    loc.out = as.matrix(loc.out[, -1])
    rownames(loc.out) = loc.rownames
dmattek's avatar
dmattek committed
731 732 733 734 735 736 737
    
    # 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)))
    
dmattek's avatar
dmattek committed
738
    return(loc.out)
dmattek's avatar
Mod:  
dmattek committed
739
  }) 
740
  
dmattek's avatar
dmattek committed
741
  
dmattek's avatar
dmattek committed
742 743 744 745 746 747 748 749 750
  # download data as prepared for plotting
  # after all modification
  output$downloadDataClean <- downloadHandler(
    filename = 'tCoursesSelected_clean.csv',
    content = function(file) {
      write.csv(data4trajPlot(), file, row.names = FALSE)
    }
  )
  
dmattek's avatar
dmattek committed
751
  
dmattek's avatar
dmattek committed
752 753 754 755
  ####
  ## UI for trajectory plot
  output$varSelHighlight = renderUI({
    cat(file = stderr(), 'UI varSelHighlight\n')
dmattek's avatar
dmattek committed
756
    
dmattek's avatar
dmattek committed
757 758 759
    locBut = input$chBhighlightTraj
    if (!locBut)
      return(NULL)
dmattek's avatar
dmattek committed
760
    
dmattek's avatar
dmattek committed
761
    loc.v = getDataTrackObjLabUni()
dmattek's avatar
dmattek committed
762
    if (!is.null(loc.v)) {
763
      selectInput(
dmattek's avatar
dmattek committed
764 765 766
        'inSelHighlight',
        'Select one or more rajectories:',
        loc.v,
767
        width = '100%',
dmattek's avatar
dmattek committed
768
        multiple = TRUE
769
      )
dmattek's avatar
dmattek committed
770 771 772
    }
  })
  
dmattek's avatar
dmattek committed
773
  ###### Trajectory plotting
dmattek's avatar
Mod:  
dmattek committed
774
  callModule(modTrajPlot, 'modTrajPlot', data4trajPlot)
dmattek's avatar
dmattek committed
775
  
dmattek's avatar
dmattek committed
776 777 778
  ###### AUC caluclation and plotting
  callModule(modAUCplot, 'tabAUC', data4trajPlot)
  
dmattek's avatar
dmattek committed
779 780
  ###### Box-plot
  callModule(tabBoxPlot, 'tabBoxPlot', data4trajPlot)
dmattek's avatar
dmattek committed
781
  
dmattek's avatar
dmattek committed
782 783
  
  
dmattek's avatar
dmattek committed
784 785 786
  ###### Scatter plot
  callModule(tabScatterPlot, 'tabScatter', data4trajPlot)
  
dmattek's avatar
dmattek committed
787
  ##### Hierarchical clustering
dmattek's avatar
dmattek committed
788
  callModule(clustHier, 'tabClHier', data4clust, data4trajPlot)
dmattek's avatar
dmattek committed
789 790
  
  ##### Sparse hierarchical clustering using sparcl
dmattek's avatar
dmattek committed
791
  callModule(clustHierSpar, 'tabClHierSpar', data4clust, data4trajPlot)
dmattek's avatar
dmattek committed
792

dmattek's avatar
Mod:  
dmattek committed
793
  
dmattek's avatar
dmattek committed
794
})