Upkeep (#407)

* update email * unexport object_loc_lookup * T -> TRUE * add value info * add sessioninfo * fix more notes * run styler * test against devel container * forgot to save
rnabioco · Aug 23, 2024 · 8224ebc · 8224ebc
1 parent f621538
commit 8224ebc
Show file tree

Hide file tree

Showing 22 changed files with 984 additions and 844 deletions.
diff --git a/.github/workflows/check-bioc.yml b/.github/workflows/check-bioc.yml
@@ -53,8 +53,8 @@ jobs:
       fail-fast: false
       matrix:
         config:
-          - { os: ubuntu-latest, r: '4.3', bioc: '3.18', cont: "bioconductor/bioconductor_docker:RELEASE_3_18", rspm: "https://packagemanager.posit.co/cran/__linux__/jammy/latest" }
-          - { os: windows-latest, r: '4.3', bioc: '3.18'}
+          - { os: ubuntu-latest, r: '4.4', bioc: '3.20', cont: "bioconductor/bioconductor_docker:devel", rspm: "https://packagemanager.posit.co/cran/__linux__/jammy/latest" }
+          - { os: windows-latest, r: '4.4', bioc: '3.20'}
           ## Check https://github.com/r-lib/actions/tree/master/examples
           ## for examples using the http-user-agent
     env:
@@ -106,16 +106,16 @@ jobs:
         uses: actions/cache@v3
         with:
           path: ${{ env.R_LIBS_USER }}
-          key: ${{ env.cache-version }}-${{ runner.os }}-biocversion-RELEASE_3_18-r-4.3-${{ hashFiles('.github/depends.Rds') }}
-          restore-keys: ${{ env.cache-version }}-${{ runner.os }}-biocversion-RELEASE_3_18-r-4.3-
+          key: ${{ env.cache-version }}-${{ runner.os }}-biocversion-devel-r-4.4-${{ hashFiles('.github/depends.Rds') }}
+          restore-keys: ${{ env.cache-version }}-${{ runner.os }}-biocversion-devel-r-4.4-
 
       - name: Cache R packages on Linux
         if: "!contains(github.event.head_commit.message, '/nocache') && runner.os == 'Linux' "
         uses: actions/cache@v3
         with:
           path: /home/runner/work/_temp/Library
-          key: ${{ env.cache-version }}-${{ runner.os }}-biocversion-RELEASE_3_18-r-4.3-${{ hashFiles('.github/depends.Rds') }}
-          restore-keys: ${{ env.cache-version }}-${{ runner.os }}-biocversion-RELEASE_3_18-r-4.3-
+          key: ${{ env.cache-version }}-${{ runner.os }}-biocversion-devel-r-4.4-${{ hashFiles('.github/depends.Rds') }}
+          restore-keys: ${{ env.cache-version }}-${{ runner.os }}-biocversion-devel-r-4.4-
 
       - name: Install Linux system dependencies
         if: runner.os == 'Linux'
@@ -289,7 +289,7 @@ jobs:
         if: failure()
         uses: actions/upload-artifact@master
         with:
-          name: ${{ runner.os }}-biocversion-RELEASE_3_18-r-4.3-results
+          name: ${{ runner.os }}-biocversion-devel-r-4.4-results
           path: check
 
         ## Note that DOCKER_PASSWORD is really a token for your dockerhub

diff --git a/DESCRIPTION b/DESCRIPTION
@@ -13,7 +13,7 @@ Authors@R:
       person(given = "Kent",
              family = "Riemondy",
              role = c("cre", "aut"),
-             email = "kent.riemondy@cuanschutz.edu"),
+             email = "kent.riemondy@gmail.com"),
       person(given = "Austin",
              family = "Gillen",
              role = "ctb",
@@ -88,7 +88,7 @@ VignetteBuilder:
 ByteCompile: true
 Encoding: UTF-8
 Roxygen: list(markdown = TRUE)
-RoxygenNote: 7.3.1
+RoxygenNote: 7.3.2
 LazyData: true
 Config/Needs/website:
     pkgdown,

diff --git a/NAMESPACE b/NAMESPACE
@@ -49,7 +49,6 @@ export(make_comb_ref)
 export(marker_select)
 export(matrixize_markers)
 export(object_data)
-export(object_loc_lookup)
 export(object_ref)
 export(overcluster)
 export(overcluster_test)

diff --git a/R/cellbrowsers.R b/R/cellbrowsers.R
@@ -1,4 +1,3 @@
-
 #' Build reference atlases from external UCSC cellbrowsers
 #'
 #' @param cb_url URL of cellbrowser dataset (e.g. http://cells.ucsc.edu/?ds=cortex-dev).
@@ -11,72 +10,83 @@
 #' @return reference matrix
 #' @examples
 #' \dontrun{
-#' 
+#'
 #' # many datasets hosted by UCSC have UMI counts in the expression matrix
 #' # set if_log = FALSE if the expression matrix has not been natural log transformed
-#' 
-#' get_ucsc_reference(cb_url = "https://cells.ucsc.edu/?ds=evocell+mus-musculus+marrow",
-#'                    cluster_col = "Clusters", if_log = FALSE)
-#'                    
-#' get_ucsc_reference(cb_url = "http://cells.ucsc.edu/?ds=muscle-cell-atlas",
-#'                    cluster_col = "cell_annotation",
-#'                    if_log = FALSE)
+#'
+#' get_ucsc_reference(
+#'     cb_url = "https://cells.ucsc.edu/?ds=evocell+mus-musculus+marrow",
+#'     cluster_col = "Clusters", if_log = FALSE
+#' )
+#'
+#' get_ucsc_reference(
+#'     cb_url = "http://cells.ucsc.edu/?ds=muscle-cell-atlas",
+#'     cluster_col = "cell_annotation",
+#'     if_log = FALSE
+#' )
 #' }
 #' @export
 get_ucsc_reference <- function(cb_url,
                                cluster_col,
-                               ...){
-  if(!requireNamespace("R.utils", quietly = TRUE)) {
-    stop("This function requires the R.utils package, please install\n",
-         "install.packages('R.utils')")
-  }
-
-  if(!requireNamespace("data.table", quietly = TRUE)) {
-    stop("This function requires the data.table package, please install\n",
-         "install.packages('data.table')")
-  }
-
-  url <- httr::parse_url(cb_url)
-  base_url <- url
-  ds <- url$query$ds
-
-  # ds can include sub-datasets with syntax, "dataset+subdataset+and-so-on"
-  # files are hosted at urls: dataset/subdataset/andsoon/..."
-  ds_split <- strsplit(ds, "+", fixed = TRUE)[[1]]
-  ds <- paste0(ds_split, collapse = "/")
-  base_url$query <- ""
+                               ...) {
+    if (!requireNamespace("R.utils", quietly = TRUE)) {
+        stop(
+            "This function requires the R.utils package, please install\n",
+            "install.packages('R.utils')"
+        )
+    }
+
+    if (!requireNamespace("data.table", quietly = TRUE)) {
+        stop(
+            "This function requires the data.table package, please install\n",
+            "install.packages('data.table')"
+        )
+    }
+
+    url <- httr::parse_url(cb_url)
+    base_url <- url
+    ds <- url$query$ds
 
-  mdata_url <- httr::modify_url(base_url,
-                                path = file.path(ds, "meta.tsv"))
-  if(!httr::http_error(mdata_url)){
-    mdata <- data.table::fread(mdata_url, data.table = FALSE, sep = "\t")
-  } else {
-    stop("unable to find metadata at url: ", mdata_url)
-  }
-
-  mat_url <- httr::modify_url(base_url,
-                              path = file.path(ds, "exprMatrix.tsv.gz"))
-  if(!httr::http_error(mat_url)){
-    mat <- data.table::fread(mat_url, data.table = FALSE, sep = "\t")
-  } else {
-    stop("unable to find matrix at url: ", mat_url)
-  }
+    # ds can include sub-datasets with syntax, "dataset+subdataset+and-so-on"
+    # files are hosted at urls: dataset/subdataset/andsoon/..."
+    ds_split <- strsplit(ds, "+", fixed = TRUE)[[1]]
+    ds <- paste0(ds_split, collapse = "/")
+    base_url$query <- ""
 
-  rownames(mat) <- mat[, 1]
-  mat[, 1] <- NULL
-  mat <- as.matrix(mat)
-
-  mm <- max(mat)
-
-  if(mm > 50) {
-    dots <- list(...)
-    if(!"if_log" %in% names(dots) || dots$if_log) {
-      warning("the data matrix has a maximum value of ",   mm, "\n",
-              "the data are likely not log transformed,\n",
-              "please set the if_log argument for average clusters accordingly")
+    mdata_url <- httr::modify_url(base_url,
+        path = file.path(ds, "meta.tsv")
+    )
+    if (!httr::http_error(mdata_url)) {
+        mdata <- data.table::fread(mdata_url, data.table = FALSE, sep = "\t")
+    } else {
+        stop("unable to find metadata at url: ", mdata_url)
     }
-  }
-
-  average_clusters(mat, mdata, cluster_col = cluster_col, ...)
-}
 
+    mat_url <- httr::modify_url(base_url,
+        path = file.path(ds, "exprMatrix.tsv.gz")
+    )
+    if (!httr::http_error(mat_url)) {
+        mat <- data.table::fread(mat_url, data.table = FALSE, sep = "\t")
+    } else {
+        stop("unable to find matrix at url: ", mat_url)
+    }
+
+    rownames(mat) <- mat[, 1]
+    mat[, 1] <- NULL
+    mat <- as.matrix(mat)
+
+    mm <- max(mat)
+
+    if (mm > 50) {
+        dots <- list(...)
+        if (!"if_log" %in% names(dots) || dots$if_log) {
+            warning(
+                "the data matrix has a maximum value of ", mm, "\n",
+                "the data are likely not log transformed,\n",
+                "please set the if_log argument for average clusters accordingly"
+            )
+        }
+    }
+
+    average_clusters(mat, mdata, cluster_col = cluster_col, ...)
+}
diff --git a/R/common_dplyr.R b/R/common_dplyr.R
@@ -19,7 +19,8 @@
 #'
 #' cor_to_call(res)
 #' @export
-cor_to_call <- function(cor_mat,
+cor_to_call <- function(
+    cor_mat,
     metadata = NULL,
     cluster_col = "cluster",
     collapse_to_cluster = FALSE,
@@ -131,17 +132,18 @@ cor_to_call <- function(cor_mat,
 #'     cluster_col = "classified",
 #'     ref_mat = cbmc_ref
 #' )
-#' 
+#'
 #' res2 <- cor_to_call(res, cluster_col = "classified")
-#' 
+#'
 #' call_to_metadata(
 #'     res = res2,
 #'     metadata = pbmc_meta,
 #'     cluster_col = "classified",
 #'     rename_prefix = "assigned"
 #' )
 #' @export
-call_to_metadata <- function(res,
+call_to_metadata <- function(
+    res,
     metadata,
     cluster_col,
     per_cell = FALSE,
@@ -255,7 +257,8 @@ call_to_metadata <- function(res,
 #'     threshold = 0
 #' )
 #' @export
-collapse_to_cluster <- function(res,
+collapse_to_cluster <- function(
+    res,
     metadata,
     cluster_col,
     threshold = 0) {
@@ -331,7 +334,8 @@ collapse_to_cluster <- function(res,
 #'
 #' cor_to_call_rank(res, threshold = "auto")
 #' @export
-cor_to_call_rank <- function(cor_mat,
+cor_to_call_rank <- function(
+    cor_mat,
     metadata = NULL,
     cluster_col = "cluster",
     collapse_to_cluster = FALSE,