Update to MSigDB 7.2

igordot · Oct 2, 2020 · 8452596 · 8452596
1 parent c1d62bc
commit 8452596
Show file tree

Hide file tree

Showing 12 changed files with 197 additions and 40 deletions.
diff --git a/DESCRIPTION b/DESCRIPTION
@@ -1,7 +1,7 @@
 Package: msigdbr
 Type: Package
 Title: MSigDB Gene Sets for Multiple Organisms in a Tidy Data Format
-Version: 7.1.1.9001
+Version: 7.2.1
 Authors@R: person("Igor", "Dolgalev", email = "[email protected]", role = c("aut", "cre"))
 Description: Provides the 'Molecular Signatures Database' (MSigDB) gene sets
     typically used with the 'Gene Set Enrichment Analysis' (GSEA) software

diff --git a/NEWS.md b/NEWS.md
@@ -1,5 +1,6 @@
-# msigdbr (development version)
+# msigdbr 7.2.1
 
+* Based on MSigDB v7.2 release.
 * Added more annotation fields to the returned gene sets.
 * Added `msigdbr_species()` as an alternative to `msigdbr_show_species()`.
 * Added `msigdbr_collections()`.

diff --git a/R/functions.R b/R/functions.R
@@ -92,15 +92,25 @@ msigdbr <- function(species = "Homo sapiens", category = NULL, subcategory = NUL
     if (length(category) > 1) {
       stop("please specify only one category at a time")
     }
-    genesets_subset <- filter(genesets_subset, .data$gs_cat == category)
+    if (category %in% genesets_subset$gs_cat) {
+      genesets_subset <- filter(genesets_subset, .data$gs_cat == category)
+    } else {
+      stop("unknown category")
+    }
   }
 
-  # filter by sub-category
+  # filter by sub-category (with and without colon)
   if (is.character(subcategory)) {
     if (length(subcategory) > 1) {
       stop("please specify only one subcategory at a time")
     }
-    genesets_subset <- filter(genesets_subset, .data$gs_subcat == subcategory)
+    if (subcategory %in% genesets_subset$gs_subcat) {
+      genesets_subset <- filter(genesets_subset, .data$gs_subcat == subcategory)
+    } else if (subcategory %in% gsub(".*:", "", genesets_subset$gs_subcat)){
+      genesets_subset <- filter(genesets_subset, gsub(".*:", "", .data$gs_subcat) == subcategory)
+    } else {
+      stop("unknown subcategory")
+    }
   }
 
   # combine gene sets and genes

diff --git a/R/sysdata.rda b/R/sysdata.rda
diff --git a/cran-comments.md b/cran-comments.md
@@ -1,6 +1,6 @@
 ## Test environments
-* local R installation, R 4.0.0
-* ubuntu 16.04 (on travis-ci), R 4.0.0
+* local R installation, R 4.0.2
+* ubuntu 16.04 (on travis-ci), R 4.0.2
 * win-builder (devel)
 
 ## R CMD check results
@@ -9,13 +9,7 @@
 
 ## revdepcheck results
 
-We checked 5 reverse dependencies, comparing R CMD check results across CRAN and dev versions of this package.
+We checked 7 reverse dependencies (3 from CRAN + 4 from BioConductor), comparing R CMD check results across CRAN and dev versions of this package.
 
-* We saw 0 new problems
-* We failed to check 0 packages
-
-## Resubmission
-
-This is a resubmission. In this version I have:
-
-* Addressed the elapsed time notes.
+ * We saw 0 new problems
+ * We failed to check 0 packages
diff --git a/data-raw/msigdbr-prepare.R b/data-raw/msigdbr-prepare.R
@@ -11,7 +11,7 @@ library(usethis)
 # Import MSigDB gene sets -------------------------------------------------
 
 # Define MSigDB download variables
-msigdb_version = "7.1"
+msigdb_version = "7.2"
 msigdb_url_base = "https://data.broadinstitute.org/gsea-msigdb/msigdb/release"
 msigdb_zip_url = glue("{msigdb_url_base}/{msigdb_version}/msigdb_v{msigdb_version}_files_to_download_locally.zip")
 msigdb_dir = glue("msigdb_v{msigdb_version}_files_to_download_locally")
@@ -96,6 +96,7 @@ human_tbl =
   distinct() %>%
   mutate(
     species_name = "Homo sapiens",
+    species_common_name = "human",
     entrez_gene = human_entrez_gene,
     gene_symbol = human_gene_symbol
   )
@@ -130,7 +131,7 @@ msigdbr_orthologs =
     species_id = ortholog_species,
     entrez_gene = ortholog_species_entrez_gene,
     gene_symbol = ortholog_species_symbol,
-    sources = support
+    ortholog_sources = support
   ) %>%
   filter(
     human_entrez_gene != "-",
@@ -140,15 +141,15 @@ msigdbr_orthologs =
   mutate(
     human_entrez_gene = as.integer(human_entrez_gene),
     entrez_gene = as.integer(entrez_gene),
-    num_sources = str_count(sources, ",") + 1
+    num_ortholog_sources = str_count(ortholog_sources, ",") + 1
   ) %>%
   filter(
     human_entrez_gene %in% msigdb_entrez_genes,
-    num_sources > 2
+    num_ortholog_sources > 2
   )
 
 # List the number of supporting sources
-table(msigdbr_orthologs$num_sources, useNA = "ifany")
+table(msigdbr_orthologs$num_ortholog_sources, useNA = "ifany")
 
 # Names and IDs of common species
 species_tbl =
@@ -173,9 +174,8 @@ msigdbr_orthologs = inner_join(species_tbl, msigdbr_orthologs, by = "species_id"
 # For each human gene, only keep the best ortholog (found in the most databases)
 msigdbr_orthologs =
   msigdbr_orthologs %>%
-  select(-species_id) %>%
   group_by(human_entrez_gene, species_name) %>%
-  top_n(1, num_sources) %>%
+  top_n(1, num_ortholog_sources) %>%
   ungroup()
 
 # For each human gene, ignore ortholog pairs with many orthologs
@@ -191,7 +191,8 @@ msigdbr_orthologs =
   bind_rows(human_tbl) %>%
   select(
     human_entrez_gene, human_gene_symbol,
-    species_name, species_common_name, entrez_gene, gene_symbol, sources, num_sources
+    species_name, species_common_name, entrez_gene, gene_symbol,
+    ortholog_sources, num_ortholog_sources
   ) %>%
   arrange(human_gene_symbol, human_entrez_gene, species_name) %>%
   distinct()
@@ -203,7 +204,7 @@ hcop %>%
   summarize(n_distinct(ortholog_species_symbol))
 msigdbr_orthologs %>%
   group_by(species_name) %>%
-  summarize(n_distinct(human_gene_symbol), n_distinct(gene_symbol), max(num_sources))
+  summarize(n_distinct(human_gene_symbol), n_distinct(gene_symbol), max(num_ortholog_sources))
 
 # Prepare package ---------------------------------------------------------
 

diff --git a/revdep/README.md b/revdep/README.md
@@ -2,23 +2,33 @@
 
 |field    |value                        |
 |:--------|:----------------------------|
-|version  |R version 4.0.0 (2020-04-24) |
+|version  |R version 4.0.2 (2020-06-22) |
 |os       |macOS Mojave 10.14.6         |
 |system   |x86_64, darwin17.0           |
 |ui       |RStudio                      |
 |language |(EN)                         |
 |collate  |en_US.UTF-8                  |
 |ctype    |en_US.UTF-8                  |
 |tz       |America/New_York             |
-|date     |2020-05-12                   |
+|date     |2020-10-02                   |
 
 # Dependencies
 
-|package    |old   |new   |Δ  |
-|:----------|:-----|:-----|:--|
-|msigdbr    |7.0.1 |7.1.1 |*  |
-|tidyselect |NA    |1.0.0 |*  |
-|vctrs      |NA    |0.2.4 |*  |
+|package |old   |new   |Δ  |
+|:-------|:-----|:-----|:--|
+|msigdbr |7.1.1 |7.2.1 |*  |
 
 # Revdeps
 
+## Failed to check (1)
+
+|package  |version |error |warning |note |
+|:--------|:-------|:-----|:-------|:----|
+|tidybulk |?       |      |        |     |
+
+## New problems (1)
+
+|package                    |version |error |warning |note |
+|:--------------------------|:-------|:-----|:-------|:----|
+|[hypeR](problems.md#hyper) |1.4.0   |      |__+1__  |2    |
+
diff --git a/revdep/cran.md b/revdep/cran.md
@@ -0,0 +1,7 @@
+## revdepcheck results
+
+We checked 7 reverse dependencies (3 from CRAN + 4 from BioConductor), comparing R CMD check results across CRAN and dev versions of this package.
+
+ * We saw 0 new problems
+ * We failed to check 0 packages
+
diff --git a/revdep/failures.md b/revdep/failures.md
@@ -1 +1,45 @@
-*Wow, no problems at all. :)*
+# tidybulk
+
+<details>
+
+* Version: 
+* GitHub: https://github.com/igordot/msigdbr
+* Source code: NA
+* Number of recursive dependencies: 0
+
+</details>
+
+## Error before installation
+
+### Devel
+
+```
+
+  There is a binary version available but the source version is later:
+        binary source needs_compilation
+RSQLite  2.2.0  2.2.1              TRUE
+
+  Binaries will be installed
+
+
+installing the source packages ‘EGSEAdata’, ‘hgu133a.db’, ‘hgu133plus2.db’, ‘KEGGdzPathwaysGEO’, ‘org.Mm.eg.db’, ‘org.Rn.eg.db’
+
+
+
+```
+### CRAN
+
+```
+
+  There is a binary version available but the source version is later:
+        binary source needs_compilation
+RSQLite  2.2.0  2.2.1              TRUE
+
+  Binaries will be installed
+
+
+installing the source packages ‘EGSEAdata’, ‘hgu133a.db’, ‘hgu133plus2.db’, ‘KEGGdzPathwaysGEO’, ‘org.Mm.eg.db’, ‘org.Rn.eg.db’
+
+
+
+```
diff --git a/revdep/problems.md b/revdep/problems.md
@@ -1 +1,68 @@
-*Wow, no problems at all. :)*
+# hypeR
+
+<details>
+
+* Version: 1.4.0
+* GitHub: https://github.com/montilab/hypeR
+* Source code: https://github.com/cran/hypeR
+* Date/Publication: 2020-04-27
+* Number of recursive dependencies: 111
+
+Run `revdep_details(, "hypeR")` for more info
+
+</details>
+
+## Newly broken
+
+*   checking examples ... WARNING
+    ```
+    Found the following significant warnings:
+    
+      Warning: 'msigdbr::msigdbr_show_species' is deprecated.
+      Warning: 'msigdbr::msigdbr_show_species' is deprecated.
+      Warning: 'msigdbr::msigdbr_show_species' is deprecated.
+      Warning: 'msigdbr::msigdbr_show_species' is deprecated.
+      Warning: 'msigdbr::msigdbr_show_species' is deprecated.
+      Warning: 'msigdbr::msigdbr_show_species' is deprecated.
+      Warning: 'msigdbr::msigdbr_show_species' is deprecated.
+      Warning: 'msigdbr::msigdbr_show_species' is deprecated.
+      Warning: 'msigdbr::msigdbr_show_species' is deprecated.
+      Warning: 'msigdbr::msigdbr_show_species' is deprecated.
+    Deprecated functions may be defunct as soon as of the next release of
+    R.
+    See ?Deprecated.
+    ```
+
+## In both
+
+*   checking R code for possible problems ... NOTE
+    ```
+    ...
+      ‘is’
+    hyp_to_table: no visible global function definition for ‘is’
+    hyp_to_table: no visible global function definition for
+      ‘packageVersion’
+    hyp_to_table: no visible global function definition for ‘write.table’
+    hypeR: no visible global function definition for ‘is’
+    msigdb_available: no visible binding for global variable ‘gs_cat’
+    msigdb_available: no visible binding for global variable ‘gs_subcat’
+    msigdb_download: no visible binding for global variable ‘gs_name’
+    msigdb_download: no visible binding for global variable ‘gene_symbol’
+    msigdb_download: no visible binding for global variable ‘.’
+    msigdb_version: no visible global function definition for
+      ‘packageVersion’
+    Undefined global functions or variables:
+      . fdr from gene_symbol gs_cat gs_name gs_subcat is label
+      packageVersion pval significance size to write.table x y
+    Consider adding
+      importFrom("methods", "is")
+      importFrom("utils", "packageVersion", "write.table")
+    to your NAMESPACE file (and ensure that your DESCRIPTION Imports field
+    contains 'methods').
+    ```
+
+*   checking for unstated dependencies in vignettes ... NOTE
+    ```
+    'library' or 'require' call not declared from: ‘tidyverse’
+    ```
+