update to the latest data hubs

ropensci · Oct 29, 2024 · 2f1742d · 2f1742d
1 parent 8462937
commit 2f1742d
Show file tree

Hide file tree

Showing 11 changed files with 72 additions and 62 deletions.
diff --git a/DESCRIPTION b/DESCRIPTION
@@ -54,4 +54,4 @@ VignetteBuilder:
 Encoding: UTF-8
 LazyData: true
 Roxygen: list(markdown = TRUE)
-RoxygenNote: 7.2.3
+RoxygenNote: 7.3.2
diff --git a/NEWS.md b/NEWS.md
@@ -1,7 +1,8 @@
 # UCSCXenaTools 1.6.0
 
+- Totally 2486 datasets are included in the current list.
 - Single cell hub was found disabled.
-- GDC hub was completely updated.
+- GDC hub was completely updated. The old GDC hub has been renamed to gdcHubV18.
 
 # UCSCXenaTools 1.5.0
 

diff --git a/R/XenaFilter.R b/R/XenaFilter.R
@@ -26,57 +26,57 @@ XenaFilter <- function(x,
                        filterCohorts = NULL,
                        filterDatasets = NULL,
                        ignore.case = TRUE, ...) {
-  if (is.null(filterCohorts) & is.null(filterDatasets)) {
-    warning("No operation for input, do nothing...")
-    return(x)
-  }
+    if (is.null(filterCohorts) & is.null(filterDatasets)) {
+        warning("No operation for input, do nothing...")
+        return(x)
+    }
 
-  cohorts_select <- character()
-  datasets_select <- character()
+    cohorts_select <- character()
+    datasets_select <- character()
 
-  # suppress binding notes
-  XenaHosts <- XenaCohorts <- XenaDatasets <- NULL
+    # suppress binding notes
+    XenaHosts <- XenaCohorts <- XenaDatasets <- NULL
 
-  if (!is.null(filterCohorts)) {
-    cohorts_select <- grep(
-      pattern = filterCohorts,
-      x@cohorts,
-      ignore.case = ignore.case,
-      value = TRUE,
-      ...
-    )
-  }
+    if (!is.null(filterCohorts)) {
+        cohorts_select <- grep(
+            pattern = filterCohorts,
+            x@cohorts,
+            ignore.case = ignore.case,
+            value = TRUE,
+            ...
+        )
+    }
 
-  if (!is.null(filterDatasets)) {
-    datasets_select <- grep(
-      pattern = filterDatasets,
-      x@datasets,
-      ignore.case = ignore.case,
-      value = TRUE,
-      ...
-    )
-  }
+    if (!is.null(filterDatasets)) {
+        datasets_select <- grep(
+            pattern = filterDatasets,
+            x@datasets,
+            ignore.case = ignore.case,
+            value = TRUE,
+            ...
+        )
+    }
 
-  if (identical(cohorts_select, character()) &
-    identical(datasets_select, character())) {
-    warning("No valid cohorts or datasets find! Please check your input.")
-  } else {
     if (identical(cohorts_select, character()) &
-      !identical(datasets_select, character())) {
-      UCSCXenaTools::XenaGenerate(subset = XenaHosts %in% x@hosts &
-        XenaDatasets %in% datasets_select)
-    } else { # nocov start
-      if (!identical(cohorts_select, character()) &
         identical(datasets_select, character())) {
-        UCSCXenaTools::XenaGenerate(subset = XenaHosts %in% x@hosts &
-          XenaCohorts %in% cohorts_select)
-      } else {
-        UCSCXenaTools::XenaGenerate(
-          subset = XenaHosts %in% x@hosts &
-            XenaCohorts %in% cohorts_select &
-            XenaDatasets %in% datasets_select
-        )
-      }
-    } # nocov end
-  }
+        warning("No valid cohorts or datasets find! Please check your input.")
+    } else {
+        if (identical(cohorts_select, character()) &
+            !identical(datasets_select, character())) {
+            UCSCXenaTools::XenaGenerate(
+                subset = XenaHosts %in% x@hosts &
+                    XenaDatasets %in% datasets_select)
+        } else if (!identical(cohorts_select, character()) &
+                   identical(datasets_select, character())) {
+            UCSCXenaTools::XenaGenerate(
+                subset = XenaHosts %in% x@hosts &
+                    XenaCohorts %in% cohorts_select)
+        } else {
+            UCSCXenaTools::XenaGenerate(
+                subset = XenaHosts %in% x@hosts &
+                    XenaCohorts %in% cohorts_select &
+                    XenaDatasets %in% datasets_select
+            )
+        }
+    }
 }
diff --git a/R/XenaHub-class.R b/R/XenaHub-class.R
@@ -54,31 +54,33 @@ xena_default_hosts <- function() {
     "https://ucscpublic.xenahubs.net",
     "https://tcga.xenahubs.net",
     "https://gdc.xenahubs.net",
+    "https://gdcV18.xenahubs.net",
     "https://icgc.xenahubs.net",
     "https://toil.xenahubs.net",
     "https://pancanatlas.xenahubs.net",
     "https://xena.treehouse.gi.ucsc.edu:443",
     "https://pcawg.xenahubs.net",
     "https://atacseq.xenahubs.net",
     "https://singlecellnew.xenahubs.net",
-    "https://kidsfirst.xenahubs.net"
-    #"https://tdi.xenahubs.net"
+    "https://kidsfirst.xenahubs.net",
+    "https://tdi.xenahubs.net"
   )
 }
 
 .xena_hosts <- c(
   "publicHub",
   "tcgaHub",
   "gdcHub",
+  "gdcHubV18",
   "icgcHub",
   "toilHub",
   "pancanAtlasHub",
   "treehouseHub",
   "pcawgHub",
   "atacseqHub",
   "singlecellHub",
-  "kidsfirstHub"
-  #"tdiHub"
+  "kidsfirstHub",
+  "tdiHub"
 )
 
 names(.xena_hosts) <- xena_default_hosts()
@@ -148,15 +150,16 @@ XenaHub <- function(hosts = xena_default_hosts(),
                       "publicHub",
                       "tcgaHub",
                       "gdcHub",
+                      "gdcHubV18",
                       "icgcHub",
                       "toilHub",
                       "pancanAtlasHub",
                       "treehouseHub",
                       "pcawgHub",
                       "atacseqHub",
                       "singlecellHub",
-                      "kidsfirstHub"
-                      #"tdiHub"
+                      "kidsfirstHub",
+                      "tdiHub"
                     )) {
   stopifnot(
     is.character(hosts),

diff --git a/R/XenaQuery.R b/R/XenaQuery.R
@@ -39,7 +39,7 @@ XenaQuery <- function(x) {
   query <- data_list %>%
     dplyr::filter(XenaDatasets %in% datasetsName) %>%
     dplyr::rename(hosts = XenaHosts, datasets = XenaDatasets) %>%
-    dplyr::mutate(url = ifelse(.data$XenaHostNames == "gdcHub",
+    dplyr::mutate(url = ifelse(.data$XenaHostNames %in% c("gdcHub", "gdcHubV18"),
       file.path(hosts, "download", url_encode(basename(datasets))),
       file.path(hosts, "download", url_encode(datasets))
     )) %>%

diff --git a/R/XenaQueryProbeMap.R b/R/XenaQueryProbeMap.R
@@ -24,7 +24,7 @@ XenaQueryProbeMap <- function(x) {
   } else {
     query <- query %>%
       dplyr::rename(hosts = XenaHosts, datasets = ProbeMap) %>%
-      dplyr::mutate(url = ifelse(.data$XenaHostNames == "gdcHub",
+      dplyr::mutate(url = ifelse(.data$XenaHostNames %in% c("gdcHub", "gdcHubV18"),
         file.path(hosts, "download", url_encode(basename(datasets))),
         file.path(hosts, "download", url_encode(datasets))
       )) %>%

diff --git a/R/api_inner.R b/R/api_inner.R
@@ -3,6 +3,9 @@
 # post --------------------------------------------------------------------
 
 .xena_post <- function(host, query, ...) {
+  # allow insecure options like curl -k
+  # https://stackoverflow.com/questions/65531599/how-to-pass-the-k-or-insecure-argument-to-curl-in-the-r-package-httr
+  httr::set_config(httr::config(ssl_verifypeer = 0L, ssl_verifyhost = 0L))
   host <- paste0(host, "/data/")
   res <- POST(host, body = query)
   stop_for_status(res)

diff --git a/README.Rmd b/README.Rmd
@@ -71,7 +71,8 @@ Currently, **UCSCXenaTools** supports the following data hubs of UCSC Xena.
 
 * UCSC Public Hub: <https://ucscpublic.xenahubs.net/>
 * TCGA Hub: <https://tcga.xenahubs.net/>
-* GDC Xena Hub: <https://gdc.xenahubs.net/>
+* GDC Xena Hub (new): <https://gdc.xenahubs.net/>
+* GDC v18.0 Xena Hub (old): <https://gdcV18.xenahubs.net/>
 * ICGC Xena Hub: <https://icgc.xenahubs.net/>
 * Pan-Cancer Atlas Hub: <https://pancanatlas.xenahubs.net/>
 * UCSC Toil RNAseq Recompute Compendium Hub: <https://toil.xenahubs.net/>

diff --git a/README.md b/README.md
@@ -69,7 +69,8 @@ Xena.
 
 - UCSC Public Hub: <https://ucscpublic.xenahubs.net/>
 - TCGA Hub: <https://tcga.xenahubs.net/>
-- GDC Xena Hub: <https://gdc.xenahubs.net/>
+- GDC Xena Hub (new): <https://gdc.xenahubs.net/>
+- GDC v18.0 Xena Hub (old): <https://gdcV18.xenahubs.net/>
 - ICGC Xena Hub: <https://icgc.xenahubs.net/>
 - Pan-Cancer Atlas Hub: <https://pancanatlas.xenahubs.net/>
 - UCSC Toil RNAseq Recompute Compendium Hub:
@@ -114,7 +115,7 @@ You can load `XenaData` after loading `UCSCXenaTools` into R.
 ``` r
 library(UCSCXenaTools)
 #> =========================================================================================
-#> UCSCXenaTools version 1.5.0
+#> UCSCXenaTools version 1.4.8
 #> Project URL: https://github.com/ropensci/UCSCXenaTools
 #> Usages: https://cran.r-project.org/web/packages/UCSCXenaTools/vignettes/USCSXenaTools.html
 #> 
@@ -171,7 +172,7 @@ Query and download.
 XenaQuery(df_todo) %>%
   XenaDownload() -> xe_download
 #> This will check url status, please be patient.
-#> All downloaded files will under directory /var/folders/37/gt0rbmqn61b513tbr8pyz_y40000gn/T//RtmpbXwIKj.
+#> All downloaded files will under directory /tmp/RtmpB0pxLW.
 #> The 'trans_slash' option is FALSE, keep same directory structure as Xena.
 #> Creating directories for datasets...
 #> Downloading TCGA.LUNG.sampleMap/LUNG_clinicalMatrix

diff --git a/data/XenaData.rda b/data/XenaData.rda
diff --git a/man/XenaHub.Rd b/man/XenaHub.Rd