Skip to contents

Using scatterplot

Dawid Kałędkowski

2022-06-14

using-scatterplot.Rmd

Teal application to use scatter plot with various datasets types

This vignette will guide you through 4 parts to create a teal application using various types of datasets inside an scatter plot module:

  1. Load Libraries
  2. Create data sets
  3. Create an app variable
  4. Run the App

Loading libraries 

library(teal.modules.general) # used to create the app
library(scda) # used to create data sets
library(dplyr) # used to modify data sets

Create data sets

Inside this app 5 datasets will be used

  1. ADSL A wide data set with subject data
  2. ADSL2 A wide data set with subject data
  3. ADRS A long data set with response data for subjects at different time points of the study
  4. ADTTE A long data set with time to event data
  5. ADLB A long data set with lab measurements for each subject
ADSL <- synthetic_cdisc_data("latest")$adsl # nolint
ADSL2 <- synthetic_cdisc_data("latest")$adsl %>% # nolint
  mutate(TRTDUR = round(as.numeric(TRTEDTM - TRTSDTM), 1))
ADRS <- synthetic_cdisc_data("latest")$adrs # nolint
ADTTE <- synthetic_cdisc_data("latest")$adtte # nolint
ADLB <- synthetic_cdisc_data("latest")$adlb %>% # nolint
  mutate(CHGC = as.factor(case_when(
    CHG < 1 ~ "N",
    CHG > 1 ~ "P",
    TRUE ~ "-"
  )))

Create an app variable

This is the most important section. We will use the teal::init function to create an app. The data will be handed over using teal.data::cdisc_data. The app itself will be constructed by multiple calls of tm_g_scatterplot using different combinations of data sets.

app <- init(
  data = cdisc_data(
    cdisc_dataset("ADSL", ADSL, code = "ADSL <- synthetic_cdisc_data(\"latest\")$adsl"),
    cdisc_dataset(
      "ADSL2",
      ADSL2,
      keys = get_cdisc_keys("ADSL"),
      code = "ADSL2 <- synthetic_cdisc_data(\"latest\")$adsl %>%
              mutate(TRTDUR = round(as.numeric(TRTEDTM - TRTSDTM), 1))"
    ),
    cdisc_dataset("ADRS", ADRS, code = "ADRS <- synthetic_cdisc_data(\"latest\")$adrs"),
    cdisc_dataset("ADTTE", ADTTE, code = "ADTTE <- synthetic_cdisc_data(\"latest\")$adtte"),
    cdisc_dataset("ADLB", ADLB,
      code = "ADLB <- synthetic_cdisc_data(\"latest\")$adlb %>%
            mutate(CHGC = as.factor(case_when(
            CHG < 1 ~ 'N',
            CHG > 1 ~ 'P',
            TRUE ~ '-'
            )))"
    ),
    check = TRUE
  ),
  modules = modules(
    modules(
      label = "Scatterplot",
      tm_g_scatterplot(
        label = "Single wide dataset",
        x = data_extract_spec(
          dataname = "ADSL",
          select = select_spec(
            label = "Select variable:",
            choices = variable_choices(ADSL, c("AGE", "BMRKR1", "BMRKR2")),
            selected = "AGE",
            multiple = FALSE,
            fixed = FALSE
          )
        ),
        y = data_extract_spec(
          dataname = "ADSL",
          select = select_spec(
            label = "Select variable:",
            choices = variable_choices(ADSL, c("AGE", "BMRKR1", "BMRKR2")),
            selected = "BMRKR1",
            multiple = FALSE,
            fixed = FALSE
          )
        ),
        color_by = data_extract_spec(
          dataname = "ADSL",
          select = select_spec(
            label = "Select variables:",
            choices = variable_choices(ADSL, c("RACE", "SEX")),
            selected = NULL,
            multiple = TRUE,
            fixed = FALSE
          )
        )
      ),
      # .. Two wide -----
      tm_g_scatterplot(
        label = "Two wide datasets",
        x = data_extract_spec(
          dataname = "ADSL",
          select = select_spec(
            label = "Select variable:",
            choices = variable_choices(ADSL, c("BMRKR1", "BMRKR2")),
            selected = "BMRKR1",
            multiple = FALSE,
            fixed = FALSE
          )
        ),
        y = data_extract_spec(
          dataname = "ADSL2",
          select = select_spec(
            label = "Select variable:",
            choices = variable_choices(ADSL2, c("AGE", "SEX")),
            selected = "AGE",
            multiple = FALSE,
            fixed = FALSE
          )
        ),
        color_by = data_extract_spec(
          dataname = "ADSL2",
          select = select_spec(
            label = "Select variable:",
            choices = variable_choices(ADSL2, c("COUNTRY", "AGE", "RACE")),
            selected = "COUNTRY",
            multiple = FALSE,
            fixed = FALSE
          )
        )
      ),
      tm_g_scatterplot(
        label = "Different long datasets",
        x = data_extract_spec(
          dataname = "ADRS",
          select = select_spec(
            label = "Select variable:",
            choices = variable_choices(ADRS),
            selected = "AVAL",
            multiple = FALSE,
            fixed = FALSE
          ),
          filter = filter_spec(
            label = "Select endpoint:",
            vars = c("PARAMCD", "AVISIT"),
            choices = value_choices(ADRS, c("PARAMCD", "AVISIT"), c("PARAM", "AVISIT")),
            selected = "OVRINV - SCREENING",
            multiple = FALSE
          )
        ),
        y = data_extract_spec(
          dataname = "ADTTE",
          select = select_spec(
            label = "Select variable:",
            choices = variable_choices(ADTTE),
            selected = "AVAL",
            multiple = FALSE,
            fixed = FALSE
          ),
          filter = filter_spec(
            label = "Select parameters:",
            vars = c("PARAMCD"),
            choices = value_choices(ADTTE, "PARAMCD", "PARAM"),
            selected = "OS",
            multiple = TRUE
          )
        ),
        color_by = data_extract_spec(
          dataname = "ADSL",
          select = select_spec(
            label = "Select variable:",
            choices = variable_choices(ADSL, c("AGE", "SEX")),
            selected = "AGE",
            multiple = FALSE,
            fixed = FALSE
          )
        )
      ),
      tm_g_scatterplot(
        label = "Wide and long datasets",
        x = data_extract_spec(
          dataname = "ADSL",
          select = select_spec(
            label = "Select variable:",
            choices = variable_choices(ADSL, c("SEX", "AGE", "BMRKR1", "COUNTRY")),
            selected = "AGE",
            multiple = FALSE,
            fixed = FALSE
          )
        ),
        y = data_extract_spec(
          dataname = "ADLB",
          filter = list(
            filter_spec(
              vars = "PARAMCD",
              choices = value_choices(ADLB, "PARAMCD", "PARAM"),
              selected = levels(ADLB$PARAMCD)[1],
              multiple = FALSE,
              label = "Select measurement:"
            ),
            filter_spec(
              vars = "AVISIT",
              choices = levels(ADLB$AVISIT),
              selected = levels(ADLB$AVISIT)[1],
              multiple = FALSE,
              label = "Select visit:"
            )
          ),
          select = select_spec(
            label = "Selected variable:",
            choices = "AVAL",
            selected = "AVAL",
            multiple = FALSE,
            fixed = TRUE
          )
        ),
        color_by = data_extract_spec(
          dataname = "ADSL",
          select = select_spec(
            label = "Select variable:",
            choices = variable_choices(ADSL, c("SEX", "AGE", "RACE", "COUNTRY")),
            selected = NULL,
            multiple = FALSE,
            fixed = FALSE
          )
        )
      ),
      tm_g_scatterplot(
        label = "Same long datasets (same subsets)",
        x = data_extract_spec(
          dataname = "ADRS",
          select = select_spec(
            choices = variable_choices(ADRS, c("AVAL", "BMRKR1", "BMRKR2")),
            selected = "AVAL",
            multiple = FALSE,
            fixed = FALSE,
            label = "Select variable:"
          )
        ),
        y = data_extract_spec(
          dataname = "ADRS",
          select = select_spec(
            choices = variable_choices(ADRS, c("AVAL", "BMRKR1", "BMRKR2")),
            selected = "BMRKR1",
            multiple = FALSE,
            fixed = FALSE,
            label = "Select variable:"
          )
        ),
        color_by = data_extract_spec(
          dataname = "ADRS",
          select = select_spec(
            choices = variable_choices(ADRS, c("AGE", "SEX", "RACE")),
            selected = NULL,
            multiple = FALSE,
            fixed = FALSE,
            label = "Select variable:"
          )
        )
      ),
      tm_g_scatterplot(
        label = "Same long datasets (different subsets)",
        x = data_extract_spec(
          dataname = "ADLB",
          filter = list(
            filter_spec(
              vars = "PARAMCD",
              choices = value_choices(ADLB, "PARAMCD", "PARAM"),
              selected = levels(ADLB$PARAMCD)[1],
              multiple = FALSE,
              label = "Select lab:"
            ),
            filter_spec(
              vars = "AVISIT",
              choices = levels(ADLB$AVISIT),
              selected = levels(ADLB$AVISIT)[1],
              multiple = FALSE,
              label = "Select visit:"
            )
          ),
          select = select_spec(
            choices = "AVAL",
            selected = "AVAL",
            multiple = FALSE,
            fixed = TRUE
          )
        ),
        y = data_extract_spec(
          dataname = "ADLB",
          filter = list(
            filter_spec(
              vars = "PARAMCD",
              choices = value_choices(ADLB, "PARAMCD", "PARAM"),
              selected = levels(ADLB$PARAMCD)[1],
              multiple = FALSE,
              label = "Select lab:"
            ),
            filter_spec(
              vars = "AVISIT",
              choices = levels(ADLB$AVISIT),
              selected = levels(ADLB$AVISIT)[1],
              multiple = FALSE,
              label = "Select visit:"
            )
          ),
          select = select_spec(
            choices = "AVAL",
            selected = "AVAL",
            multiple = FALSE,
            fixed = TRUE
          )
        ),
        color_by = data_extract_spec(
          dataname = "ADLB",
          filter = list(
            filter_spec(
              vars = "PARAMCD",
              choices = value_choices(ADLB, "PARAMCD", "PARAM"),
              selected = levels(ADLB$PARAMCD)[1],
              multiple = FALSE,
              label = "Select lab:"
            ),
            filter_spec(
              vars = "AVISIT",
              choices = levels(ADLB$AVISIT),
              selected = levels(ADLB$AVISIT)[1],
              multiple = FALSE,
              label = "Select visit:"
            )
          ),
          select = select_spec(
            choices = variable_choices(ADLB, c("RACE", "SEX")),
            selected = "SEX",
            multiple = FALSE,
            fixed = FALSE,
            label = "Select variable:"
          )
        )
      )
    )
  )
)

Run the app

A simple shiny::shinyApp call will let you run the app. Note that app is only displayed when running this code inside an R session.

shinyApp(app$ui, app$server, options = list(height = 1024, width = 1024))