Prepare v0.1.3 for CRAN

* Actions taken regarding feedback from Prof. Brian Ripley: * Removed 'ncdFlow', 'flowWorkspaceData', and 'knitr' from Suggests * Created a random data set 'randCyto' and all documentation * Updated examples and testthat to use 'randCyto' data * Updated vignette with clearer language
lance-waller-lab · Nov 17, 2020 · 1056690 · 1056690
1 parent 12fe622
commit 1056690
Show file tree

Hide file tree

Showing 23 changed files with 298 additions and 479 deletions.
diff --git a/.Rbuildignore b/.Rbuildignore
@@ -5,3 +5,4 @@
 ^vignette\.Rmd$
 ^dev$
 ^CRAN-RELEASE$
+^data-raw$
diff --git a/DESCRIPTION b/DESCRIPTION
@@ -1,8 +1,8 @@
 Package: gateR
 Type: Package
 Title: Flow/Mass Cytometry Gating via Spatial Kernel Density Estimation
-Version: 0.1.3.9000
-Date: 2020-11-10
+Version: 0.1.3
+Date: 2020-11-16
 Authors@R: 
     c(person(given = "Ian D.",
              family = "Buller",
@@ -27,10 +27,10 @@ Authors@R:
       person(given = "NCI",
              role = "cph"))
 Maintainer: Ian D. Buller <[email protected]>
-Description: Estimates statistically significant fluorescent marker combination values within
+Description: Estimates statistically significant marker combination values within
         which one immunologically distinctive group (i.e., disease case) is more associated than
         another group (i.e., healthy control), successively, using various combinations (i.e.,
-        "gates") of fluorescent markers to examine features of cells that may be different between
+        "gates") of markers to examine features of cells that may be different between
         groups. For a two-group comparison, the 'gateR' package uses the spatial relative risk
         function that is estimated using the 'sparr' package. Details about the 'sparr' package
         methods can be found in the tutorial: Davies et al. (2018) <doi:10.1002/sim.7577>. Details
@@ -56,10 +56,7 @@ Imports:
     stats,
     tibble,
     utils
-Suggests: 
-    flowWorkspaceData,
-    knitr,
-    ncdfFlow,
+Suggests:
     R.rsp,
     spelling,
     testthat

diff --git a/NEWS.md b/NEWS.md
@@ -1,5 +1,7 @@
 # gateR (development version)
 
-# gateR v0.1.3.9000
-
-* 
+# gateR v0.1.3
+  * Removed 'ncdFlow', 'flowWorkspaceData', and 'knitr' from Suggests
+  * Created a random data set 'randCyto' and all documentation
+  * Updated examples and testthat to use 'randCyto' data
+  * Updated vignette with clearer language
diff --git a/R/gating.R b/R/gating.R
@@ -56,46 +56,13 @@
 #' 
 #' @examples
 #' if (interactive()) {
-#' # Use 'extdata' from the {flowWorkspaceData} package
-#'   flowDataPath <- system.file("extdata", package = "flowWorkspaceData")
-#'   fcsFiles <- list.files(pattern = "CytoTrol", flowDataPath, full = TRUE)
-#'   ncfs  <- ncdfFlow::read.ncdfFlowSet(fcsFiles)
-#'   fr1 <- ncfs[[1]]
-#'   fr2 <- ncfs[[2]]
-#' 
-#' # Comparison of two samples (single condition) "g1"
-#' ## Two gates (four markers) "CD4", "CD38", "CD8", and "CD3"
-#' ## Log10 Transformation for both markers
-#' ## Remove cells with NA and Inf values
-#' 
-#' # First sample
-#'   obs_dat1 <- data.frame("id" = seq(1, nrow(fr1@exprs), 1),
-#'                          "g1" = rep(1, nrow(fr1@exprs)),
-#'                          "log10_CD4" = log(fr1@exprs[ , 5], 10),
-#'                          "log10_CD38" = log(fr1@exprs[ , 6], 10),
-#'                          "log10_CD8" = log(fr1@exprs[ , 7], 10),
-#'                          "log10_CD3" = log(fr1@exprs[ , 8], 10))
-#' # Second sample
-#'   obs_dat2 <- data.frame("id" = seq(1, nrow(fr2@exprs), 1),
-#'                          "g1" = rep(2, nrow(fr2@exprs)),
-#'                          "log10_CD4" = log(fr2@exprs[ , 5], 10),
-#'                          "log10_CD38" = log(fr2@exprs[ , 6], 10),
-#'                          "log10_CD8" = log(fr2@exprs[ , 7], 10),
-#'                          "log10_CD3" = log(fr2@exprs[ , 8], 10))
-#' # Full set
-#'   obs_dat <- rbind(obs_dat1, obs_dat2)
-#'   obs_dat <- obs_dat[complete.cases(obs_dat), ] # remove NAs
-#'   obs_dat <- obs_dat[is.finite(rowSums(obs_dat)), ] # remove Infs
-#'   obs_dat$g1 <- as.factor(obs_dat$g1) # set "g1" as binary factor
-#' 
-#' # Run gating() function
 #' ## Single condition, no multiple testing correction
-#'   test_gate <- gateR::gating(dat = obs_dat,
-#'                              vars = c("log10_CD4", "log10_CD38",
-#'                                       "log10_CD8", "log10_CD3"),
+#'   test_gate <- gateR::gating(dat = randCyto,
+#'                              vars = c("arcsinh_CD4", "arcsinh_CD38",
+#'                                       "arcsinh_CD8", "arcsinh_CD3"),
 #'                              n_condition = 1,
 #'                              p_correct = "none")
-#' }                              
+#' }
 #' 
 gating <- function(dat,
                    vars,

diff --git a/R/lotrrs.R b/R/lotrrs.R
@@ -44,42 +44,7 @@
 #' @export 
 #'
 #' @examples
-#' if (interactive()) {
-#' # Use 'extdata' from the {flowWorkspaceData} package
-#'   flowDataPath <- system.file("extdata", package = "flowWorkspaceData")
-#'   fcsFiles <- list.files(pattern = "CytoTrol", flowDataPath, full = TRUE)
-#'   ncfs  <- ncdfFlow::read.ncdfFlowSet(fcsFiles)
-#'   fr1 <- ncfs[[1]]
-#'   fr2 <- ncfs[[2]]
-#' 
-#' # Comparison of two samples at two time points (two conditions) "g1" and "g2"
-#' ## (Create a random binary variable for "g2")
-#' ## One gate (two markers) "CD4", "CD38"
-#' ## Log10 Transformation for both markers
-#' ## Remove cells with NA and Inf values
-#' 
-#' # First sample
-#'   obs_dat1 <- data.frame("id" = seq(1, nrow(fr1@exprs), 1),
-#'                          "g1" = rep(1, nrow(fr1@exprs)),
-#'                          "g2" = stats::rbinom(nrow(fr1@exprs), 1, 0.5),
-#'                          "log10_CD4" = log(fr1@exprs[ , 5], 10),
-#'                          "log10_CD38" = log(fr1@exprs[ , 6], 10))
-#' # Second sample
-#'   obs_dat2 <- data.frame("id" = seq(1, nrow(fr2@exprs), 1),
-#'                          "g1" = rep(2, nrow(fr2@exprs)),
-#'                          "g2" = stats::rbinom(nrow(fr2@exprs), 1, 0.5),
-#'                          "log10_CD4" = log(fr2@exprs[ , 5], 10),
-#'                          "log10_CD38" = log(fr2@exprs[ , 6], 10))
-#' # Full set
-#'   obs_dat <- rbind(obs_dat1, obs_dat2)
-#'   obs_dat <- obs_dat[complete.cases(obs_dat), ] # remove NAs
-#'   obs_dat <- obs_dat[is.finite(rowSums(obs_dat)), ] # remove Infs
-#'   obs_dat$g1 <- as.factor(obs_dat$g1) # set "g1" as binary factor
-#'   obs_dat$g2 <- as.factor(obs_dat$g2) # set "g2" as binary factor
-#' 
-#' # Run lotrrs() function
-#'   test_lotrrs <- lotrrs(dat = obs_dat, p_correct = "none")
-#' }   
+#' test_lotrrs <- lotrrs(dat = randCyto)
 #' 
 lotrrs <- function(dat, 
                    alpha = 0.05, 

diff --git a/R/package.R b/R/package.R
@@ -16,6 +16,10 @@
 #' 
 #' \code{\link{lotrrs}} Estimates a ratio of relative risk surfaces and computes the asymptotic p-value surface for a single gate with two conditions. Includes features for basic visualization. This function is used internally within the \code{\link{gating}} function to extract the points within the significant areas. This function can also be used as a standalone function.
 #' 
+#' \bold{Flow Cytometry Data}
+#' 
+#' \code{\link{randCyto}} A sample dataset containing information about flow cytometry data with two binary categorical variables. The data are a random subset of the 'extdata' data in the 'flowWorkspaceData' package found on Bioconductor \url{http://bioconductor.org/packages/release/data/experiment/html/flowWorkspaceData.html} and formated for gateR input.
+#' 
 #' @name gateR-package
 #' @aliases gateR-package gateR
 #' @docType package

diff --git a/R/randCyto.R b/R/randCyto.R
@@ -0,0 +1,19 @@
+#' Subset of the 'extdata' data in the 'flowWorkspaceData' package
+#'
+#' A sample dataset containing information about flow cytometry data with two binary conditions and four markers. The data are a random subset of the 'extdata' data in the 'flowWorkspaceData' package found on Bioconductor \url{http://bioconductor.org/packages/release/data/experiment/html/flowWorkspaceData.html} and formated for 'gateR' input. The selected markers are arcsinh transformed.
+#'
+#' @format A data frame with 11763 rows and 7 variables:
+#' \describe{
+#'   \item{id}{cell ID number}
+#'   \item{g1}{binary condition #1}
+#'   \item{g2}{binary condition #2}
+#'   \item{arcsinh_CD4}{arcsinh-transformed CD4}
+#'   \item{arcsinh_CD38}{arcsinh-transformed CD38}
+#'   \item{arcsinh_CD8}{arcsinh-transformed CD8}
+#'   \item{arcsinh_CD3}{arcsinh-transformed CD3}
+#' }
+#' @examples
+#' head(randCyto)
+#'
+#' @source \url{https://github.com/Waller-SUSAN/gateR/blob/master/README.md}
+"randCyto"
diff --git a/R/rrs.R b/R/rrs.R
@@ -37,44 +37,8 @@
 #' @importFrom sparr OS risk
 #' @export 
 #'
-#' @examples
-#' if (interactive()) {
-#' # Use 'extdata' from the {flowWorkspaceData} package
-#'   flowDataPath <- system.file("extdata", package = "flowWorkspaceData")
-#'   fcsFiles <- list.files(pattern = "CytoTrol", flowDataPath, full = TRUE)
-#'   ncfs  <- ncdfFlow::read.ncdfFlowSet(fcsFiles)
-#'   fr1 <- ncfs[[1]]
-#'   fr2 <- ncfs[[2]]
-#' 
-#' # Comparison of two samples (single condition) "g1"
-#' ## One gate (two markers) "CD4", "CD38"
-#' ## Log10 Transformation for both markers
-#' ## Remove cells with NA and Inf values
-#' 
-#' # First sample
-#'   obs_dat1 <- data.frame("id" = seq(1, nrow(fr1@exprs), 1),
-#'                          "g1" = rep(1, nrow(fr1@exprs)),
-#'                          "log10_CD4" = log(fr1@exprs[ , 5], 10),
-#'                          "log10_CD38" = log(fr1@exprs[ , 6], 10))
-#' # Second sample
-#'   obs_dat2 <- data.frame("id" = seq(1, nrow(fr2@exprs), 1),
-#'                          "g1" = rep(2, nrow(fr2@exprs)),
-#'                          "log10_CD4" = log(fr2@exprs[ , 5], 10),
-#'                          "log10_CD38" = log(fr2@exprs[ , 6], 10))
-#' # Full set
-#'   obs_dat <- rbind(obs_dat1, obs_dat2)
-#'   obs_dat <- obs_dat[complete.cases(obs_dat), ] # remove NAs
-#'   obs_dat <- obs_dat[is.finite(rowSums(obs_dat)), ] # remove Infs
-#'   obs_dat$g1 <- as.factor(obs_dat$g1) # set "g1" as binary factor
-#'   
-#' # Create a placeholder variable
-#'   g2 <- stats::rbinom(nrow(obs_dat), 1, 0.5)
-#'   obs_dat$g2 <- as.factor(g2)
-#'   obs_dat <- obs_dat[ , c(1:2,5,3:4)]
-#' 
-#' # Run rrs() function
-#'   test_rrs <- rrs(dat = obs_dat)
-#' }
+#' @examples 
+#' test_rrs <- rrs(dat = randCyto)
 #'   
 rrs <- function(dat, 
                 alpha = 0.05, 

diff --git a/README.md b/README.md
@@ -76,6 +76,30 @@ Available functions
 </tbody>
 <table>
 
+<h2 id="available-data">
+
+Available sample data sets
+
+</h2>
+
+<table>
+<colgroup>
+<col width="30%" />
+<col width="70%" />
+</colgroup>
+<thead>
+<tr class="header">
+<th>Function</th>
+<th>Description</th>
+</tr>
+</thead>
+<tbody>
+<td><code>randCyto</code></td>
+<td>A sample dataset containing information about flow cytometry data with two binary conditions and four markers. The data are a random subset of the 'extdata' data in the {flowWorkspaceData} package found on [Bioconductor](http://bioconductor.org/packages/release/data/experiment/html/flowWorkspaceData.html) and formated for {gateR} input.</td>
+</tr>
+</tbody>
+<table>
+
 <h2 id="authors">
 
 Authors
@@ -99,6 +123,7 @@ set.seed(1234) # for reproducibility
 # ------------------ #
 
 library(gateR)
+library(dplyr)
 library(flowWorkspaceData)
 library(ncdfFlow)
 library(stats)
@@ -146,6 +171,9 @@ g2 <- stats::rbinom(nrow(obs_dat), 1, 0.5)
 obs_dat$g2 <- as.factor(g2)
 obs_dat <- obs_dat[ , c(1:2,7,3:6)]
 
+# Export 'randCyto' data for CRAN examples
+randCyto <- dplyr::sample_frac(obs_dat, size = 0.1) # random subsample
+
 # ---------------------------- #
 # Run gateR with one condition #
 # ---------------------------- #

diff --git a/cran-comments.md b/cran-comments.md
@@ -1,8 +1,10 @@
-## This is the second resubmission
+## This is the third resubmission
 
-* Actions taken regarding feedback from Gregor Seyer:
-  * Reduced the length of the title to less than 65 characters
-  * Replaced cat() with message() in gating(), lotrrs(), and rrs() functions to allow for suppressable information messages
+* Actions taken regarding feedback from Prof. Brian Ripley:
+  * Removed 'ncdFlow', 'flowWorkspaceData', and 'knitr' from Suggests
+  * Created a random data set 'randCyto' and all documentation
+  * Updated examples and testthat to use 'randCyto' data
+  * Updated vignette with clearer language
 
 ## Test environments
 * local OS X install, R 3.6.3
@@ -12,23 +14,14 @@
   * Ubuntu Linux 16.04 LTS, R-release, GCC
   * Windows Server 2008 R2 SP1, R-devel, 32⁄64 bit
   * Debian Linux, R-devel, GCC
-
-There was 1 NOTE:
-
-* Possibly mis-spelled words in DESCRIPTION:
-  * Bithell (38:63, 40:24)
-  * Cytometry (3:57)
-  * al (37:57)
-  * et (37:54)
-  * immunologically (32:19)
 
 ## R CMD check results
 0 errors | 0 warnings | 0 notes
 
 * Duration
-  * local OS X install, R 3.6.3: 99 seconds
-  * win-builder, devel: 341 seconds
-  * win-builder, oldrelease: 282 seconds
-  * win-builder, release: 330 seconds
+  * local OS X install, R 3.6.3: 98 seconds
+  * win-builder, devel: 337 seconds
+  * win-builder, oldrelease: 302 seconds
+  * win-builder, release: 345 seconds
 
 ## Submitted by Maintainer
diff --git a/data-raw/get_randCyto.R b/data-raw/get_randCyto.R
@@ -0,0 +1,62 @@
+# code to prepare `randCyto` dataset
+
+set.seed(1234)
+
+# ------------------ #
+# Necessary packages #
+# ------------------ #
+
+library(dplyr)
+library(flowWorkspaceData)
+library(ncdfFlow)
+library(stats)
+library(usethis)
+
+# ---------------- #
+# Data preparation #
+# ---------------- #
+
+# Use 'extdata' from the {flowWorkspaceData} package
+flowDataPath <- system.file("extdata", package = "flowWorkspaceData")
+fcsFiles <- list.files(pattern = "CytoTrol", flowDataPath, full = TRUE)
+ncfs  <- ncdfFlow::read.ncdfFlowSet(fcsFiles)
+fr1 <- ncfs[[1]]
+fr2 <- ncfs[[2]]
+
+## Comparison of two samples (single condition) "g1"
+## Two gates (four markers) "CD4", "CD38", "CD8", and "CD3"
+## Arcsinh Transformation for all markers
+## Remove cells with NA and Inf values
+
+# First sample
+obs_dat1 <- data.frame("id" = seq(1, nrow(fr1@exprs), 1),
+                       "g1" = rep(1, nrow(fr1@exprs)),
+                       "arcsinh_CD4" = asinh(fr1@exprs[ , 5]),
+                       "arcsinh_CD38" = asinh(fr1@exprs[ , 6]),
+                       "arcsinh_CD8" = asinh(fr1@exprs[ , 7]),
+                       "arcsinh_CD3" = asinh(fr1@exprs[ , 8]))
+# Second sample
+obs_dat2 <- data.frame("id" = seq(1, nrow(fr2@exprs), 1),
+                       "g1" = rep(2, nrow(fr2@exprs)),
+                       "arcsinh_CD4" = asinh(fr2@exprs[ , 5]),
+                       "arcsinh_CD38" = asinh(fr2@exprs[ , 6]),
+                       "arcsinh_CD8" = asinh(fr2@exprs[ , 7]),
+                       "arcsinh_CD3" = asinh(fr2@exprs[ , 8]))
+
+# Full set
+obs_dat <- rbind(obs_dat1, obs_dat2)
+obs_dat <- obs_dat[complete.cases(obs_dat), ] # remove NAs
+obs_dat <- obs_dat[is.finite(rowSums(obs_dat)), ] # remove Infs
+obs_dat$g1 <- as.factor(obs_dat$g1) # set "g1" as binary factor
+
+## Create a second condition (randomly split the data)
+## In practice, use data with a measured second condition
+g2 <- stats::rbinom(nrow(obs_dat), 1, 0.5)
+obs_dat$g2 <- as.factor(g2)
+obs_dat <- obs_dat[ , c(1:2,7,3:6)]
+
+# Reduce size for CRAN exportation
+randCyto <- dplyr::sample_frac(obs_dat, size = 0.1) # saved as `randCyto` data
+
+# Export
+usethis::use_data(randCyto, overwrite = TRUE)
diff --git a/data/randCyto.rda b/data/randCyto.rda
diff --git a/dev/build.R b/dev/build.R
@@ -4,6 +4,7 @@ install.packages(c("devtools", "roxygen2", "testthat", "knitr"))
 library(devtools)
 devtools::has_devel()
 library(roxygen2)
+library(rhub)
 library(testthat)
 
 devtools::load_all()
@@ -35,7 +36,7 @@ usethis::use_build_ignore(c("build"))
 usethis::use_build_ignore(c("figures"))
 
 # rhub
-devtools::check_rhub()
+#devtools::check_rhub()
 rhub::check_for_cran()
 
 # Check on windows