Add CMap dataset

DESCRIPTION

@@ -15,7 +15,7 @@ Description: This package contains precomputed data including comparisons in
 License: AGPL (>= 3)
 Encoding: UTF-8
 Roxygen: list(markdown = TRUE)
-RoxygenNote: 7.2.1
+RoxygenNote: 7.3.1
 Depends:
     R (>= 2.10)
 LazyData: true

R/data.R

@@ -10,3 +10,6 @@
 #' The results from the analysis across Human Protein Atlas' tissue aggregated
 #' data.
 "hpa_tissues"
+
+#' The results from the analysis on CMap data.
+"cmap"

R/server.R

@@ -9,6 +9,8 @@ server <- function(custom_dataset = NULL) {
         ubigen::hpa_tissues
       } else if (input$dataset == "gtex_all") {
         ubigen::gtex_all
+      } else if (input$dataset == "cmap") {
+        ubigen::cmap
       } else {
         custom_dataset
       }

R/ui.R

@@ -26,7 +26,8 @@ ui <- function(custom_dataset = NULL) {
                 choices <- list(
                   "GTEx (across tissues and conditions)" = "gtex_all",
                   "GTEx (across tissues)" = "gtex_tissues",
-                  "Human Protein Atlas (across tissues)" = "hpa_tissues"
+                  "Human Protein Atlas (across tissues)" = "hpa_tissues",
+                  "CMap" = "cmap"
                 )
 
                 if (!is.null(custom_dataset)) {

man/cmap.Rd

@@ -0,0 +1,16 @@
+% Generated by roxygen2: do not edit by hand
+% Please edit documentation in R/data.R
+\docType{data}
+\name{cmap}
+\alias{cmap}
+\title{The results from the analysis on CMap data.}
+\format{
+An object of class \code{data.table} (inherits from \code{data.frame}) with 12382 rows and 17 columns.
+}
+\usage{
+cmap
+}
+\description{
+The results from the analysis on CMap data.
+}
+\keyword{datasets}

scripts/cmap.R

@@ -0,0 +1,33 @@
+library(data.table)
+library(gprofiler2)
+library(here)
+
+i_am("scripts/cmap.R")
+
+# Source: custom
+load(here("scripts", "input", "CMap_20180808.RData"))
+
+data <- CMap$"HT_HG-U133A"
+rm(CMap)
+
+transcripts <- dimnames(data)$transcripts
+genes <- gconvert(
+  transcripts,
+  numeric_ns = "ENTREZGENE_ACC",
+  mthreshold = 1,
+  filter_na = FALSE
+)$target
+dimnames(data)[[1]] <- genes
+
+d <- as.data.table(data)
+d <- na.omit(d)
+d <- d[data == "logMean", .(transcripts, drugs, value)]
+
+setnames(
+  d,
+  c("transcripts", "drugs", "value"),
+  c("gene", "sample", "expression")
+)
+
+cmap <- ubigen::analyze(d)
+usethis::use_data(cmap, overwrite = TRUE)