Merge pull request #7 from sigven/dev

1.0.8 release
sigven · Feb 20, 2022 · 14ee626 · 14ee626
2 parents c8043fb + dafff08
commit 14ee626
Show file tree

Hide file tree

Showing 182 changed files with 8,442 additions and 19,787 deletions.
diff --git a/.Rbuildignore b/.Rbuildignore
@@ -9,3 +9,7 @@
 ^_pkgdown.yml$
 ^omnipathr-log$
 ^db$
+^_pkgdown\.yml$
+^pkgdown$
+.bumpversion.cfg
+rlogging.log
diff --git a/.Rinstignore b/.Rinstignore
@@ -1 +1 @@
-internal_db/oeDB.rda
+#internal_db/oeDB.rda
diff --git a/.bumpversion.cfg b/.bumpversion.cfg
@@ -0,0 +1,16 @@
+[bumpversion]
+current_version = 1.0.8
+commit = True
+tag = False
+
+[bumpversion:file:DESCRIPTION]
+search = Version: {current_version}
+replace = Version: {new_version}
+
+[bumpversion:file:vignettes/installation.Rmd]
+search = {current_version}
+replace = {new_version}
+
+[bumpversion:file:.github/workflows/pkgdown.yaml]
+search = VERSION: '{current_version}'
+replace = VERSION: '{new_version}'
diff --git a/.github/workflows/pkgdown.yaml b/.github/workflows/pkgdown.yaml
@@ -0,0 +1,39 @@
+# Workflow derived from https://github.com/r-lib/actions/tree/master/examples
+# Need help debugging build failures? Start at https://github.com/r-lib/actions#where-to-find-help
+on:
+  push:
+    branches: [main, master, dev]
+  release:
+    types: [published]
+  workflow_dispatch:
+
+env:
+  VERSION: '1.0.8' #versioned by bump2version
+
+name: pkgdown
+
+jobs:
+  pkgdown:
+    runs-on: ubuntu-latest
+    if: "startsWith(github.event.head_commit.message, 'Bump version:')"
+    env:
+      GITHUB_PAT: ${{ secrets.GITHUB_TOKEN }}
+    steps:
+      - uses: actions/checkout@v2
+
+      - uses: r-lib/actions/setup-pandoc@v1
+
+      - uses: r-lib/actions/setup-r@v1
+        with:
+          use-public-rspm: true
+
+      - uses: r-lib/actions/setup-r-dependencies@v1
+        with:
+          extra-packages: pkgdown
+          needs: website
+
+      - name: Deploy package
+        run: |
+          git config --local user.name "$GITHUB_ACTOR"
+          git config --local user.email "[email protected]"
+          Rscript -e 'pkgdown::deploy_to_branch(new_process = FALSE)'
diff --git a/CODE_OF_CONDUCT.md b/CODE_OF_CONDUCT.md
diff --git a/DESCRIPTION b/DESCRIPTION
@@ -1,8 +1,8 @@
 Package: oncoEnrichR
 Type: Package
 Title: Cancer-dedicated gene set interpretation
-Version: 1.0.7
-Date: 2021-11-25
+Version: 1.0.8
+Date: 2022-02-20
 Authors@R: 
     c(person(given = "Sigve",
              family = "Nakken",

diff --git a/R/annotate.R b/R/annotate.R
@@ -18,10 +18,12 @@ target_disease_associations <-
     dplyr::inner_join(genedb, by = "symbol") %>%
       dplyr::distinct()
 
-  log4r_info(logger, paste0("Open Targets Platform: annotation of protein targets to disease phenotypes (minimum association score =  ",min_association_score,")"))
+  log4r_info(logger, paste0(
+    "Open Targets Platform: annotation of protein targets to disease phenotypes (minimum association score =  ",
+    min_association_score,")"))
 
   target_assocs <- target_genes %>%
-    dplyr::left_join(oeDB$otdb$all, by=c("ensembl_gene_id","symbol"))
+    dplyr::left_join(oeDB$otdb$all, by=c("ensembl_gene_id"))
 
   result <- list()
   result[['target']] <- target_genes
@@ -250,14 +252,17 @@ target_disease_associations <-
     dplyr::distinct()
 
 
-  ttype_rank_df <- dplyr::select(target_genes, .data$symbol) %>%
+  ttype_rank_df <- dplyr::select(target_genes,
+                                 .data$symbol,
+                                 .data$ensembl_gene_id) %>%
     dplyr::left_join(
       dplyr::select(oeDB$otdb$site_rank,
                     .data$primary_site,
-                    .data$symbol,
+                    .data$ensembl_gene_id,
                     .data$tissue_assoc_rank),
-      by = "symbol"
-    )
+      by = "ensembl_gene_id"
+    ) %>%
+    dplyr::select(-.data$ensembl_gene_id)
 
   if(nrow(ttype_rank_df) > 0){
 
@@ -309,9 +314,7 @@ target_drug_associations <- function(qgenes,
   stopifnot(!is.null(genedb))
   stopifnot(!is.null(logger))
   stopifnot(!is.null(cancerdrugdb))
-  stopifnot(!is.null(cancerdrugdb[['tractability']]))
   validate_db_df(genedb, dbtype = "genedb")
-  #validate_db_df(genedb, dbtype = "drug_tractability")
 
   target_genes <- data.frame('symbol' = qgenes,
                              stringsAsFactors = F) %>%
@@ -335,17 +338,27 @@ target_drug_associations <- function(qgenes,
   log4r_info(logger, paste0("Open Targets Platform: annotation of target tractabilities (druggability)"))
 
   result[['tractability_ab']] <- target_genes %>%
-    dplyr::select(.data$ensembl_gene_id) %>%
-    dplyr::inner_join(cancerdrugdb[['tractability']][['ab']],
-                      by = "ensembl_gene_id") %>%
+    dplyr::select(.data$ensembl_gene_id,
+                  .data$symbol,
+                  .data$AB_tractability_category,
+                  .data$AB_tractability_support) %>%
+    dplyr::mutate(symbol = paste0(
+      "<a href='https://platform.opentargets.org/target/",
+      .data$ensembl_gene_id,"' target='_blank'>", .data$symbol, "</a>"
+    )) %>%
     dplyr::select(-.data$ensembl_gene_id) %>%
     dplyr::arrange(.data$AB_tractability_category,
                    dplyr::desc(nchar(.data$AB_tractability_support)))
 
   result[['tractability_sm']] <- target_genes %>%
-    dplyr::select(.data$ensembl_gene_id) %>%
-    dplyr::inner_join(cancerdrugdb[['tractability']][['sm']],
-                      by = "ensembl_gene_id") %>%
+    dplyr::select(.data$ensembl_gene_id,
+                  .data$symbol,
+                  .data$SM_tractability_category,
+                  .data$SM_tractability_support) %>%
+    dplyr::mutate(symbol = paste0(
+      "<a href='https://platform.opentargets.org/target/",
+      .data$ensembl_gene_id,"' target='_blank'>", .data$symbol, "</a>"
+    )) %>%
     dplyr::select(-.data$ensembl_gene_id) %>%
     dplyr::arrange(.data$SM_tractability_category,
                    dplyr::desc(nchar(.data$SM_tractability_support)))

diff --git a/R/cell_tissue.R b/R/cell_tissue.R
@@ -24,15 +24,16 @@ gene_tissue_cell_spec_cat <-
     validate_db_df(genedb, dbtype = "genedb")
     stopifnot(resolution == "tissue" | resolution == "single_cell")
     stopifnot(q_id_type == "symbol" | q_id_type == "entrezgene")
-    stopifnot(is.character(qgenes))
     query_genes_df <- data.frame('symbol' = qgenes, stringsAsFactors = F)
     if(q_id_type == 'entrezgene'){
+      stopifnot(is.integer(qgenes))
       query_genes_df <-
         data.frame('entrezgene' = qgenes, stringsAsFactors = F) %>%
         dplyr::inner_join(genedb, by = "entrezgene") %>%
         dplyr::distinct()
 
     }else{
+      stopifnot(is.character(qgenes))
       query_genes_df <- query_genes_df %>%
         dplyr::inner_join(genedb, by = "symbol") %>%
         dplyr::distinct()
@@ -205,27 +206,26 @@ gene_tissue_cell_enrichment <-
              ") in target set with TissueEnrich"))
 
     stopifnot(!is.null(qgenes_entrez) &
-                is.character(qgenes_entrez))
+                is.integer(qgenes_entrez))
     stopifnot(!is.null(genedb) |
                 !is.data.frame(genedb))
     stopifnot(!is.null(oeDB$tissuecelldb))
     stopifnot(resolution == "tissue" | resolution == "single_cell")
     assertable::assert_colnames(
       genedb, c("ensembl_gene_id",
                 "entrezgene",
-                "gencode_gene_biotype",
+                "gene_biotype",
                 "cancer_max_rank"),
       only_colnames = F, quiet = T)
 
-    df <- data.frame('entrezgene' = as.character(qgenes_entrez),
+    df <- data.frame('entrezgene' = as.integer(qgenes_entrez),
                      stringsAsFactors = F) %>%
       dplyr::left_join(
         dplyr::select(genedb,
                       .data$entrezgene,
                       .data$ensembl_gene_id,
                       .data$symbol,
                       .data$name,
-                      #.data$genename,
                       .data$cancer_max_rank),
         by = "entrezgene")
 
@@ -256,7 +256,6 @@ gene_tissue_cell_enrichment <-
 
     q <- bg %>%
       dplyr::select(.data$ensembl_gene_id) %>%
-      #dplyr::filter(!is.na(.data$entrezgene)) %>%
       dplyr::inner_join(df, by = "ensembl_gene_id") %>%
       dplyr::distinct()
     query_ensembl <- q$ensembl_gene_id
@@ -291,7 +290,7 @@ gene_tissue_cell_enrichment <-
     background_ensembl <- bg$ensembl_gene_id
     if(!is.null(background_entrez)){
       df <-
-        data.frame('entrezgene' = as.character(background_entrez),
+        data.frame('entrezgene' = as.integer(background_entrez),
                    stringsAsFactors = F)
       bg <- bg %>%
         dplyr::inner_join(df, by = "entrezgene") %>%

diff --git a/R/enrich.R b/R/enrich.R
@@ -30,7 +30,7 @@ get_go_enrichment <- function(query_entrez,
     bg <- dplyr::select(genedb, .data$entrezgene) %>%
       dplyr::filter(!is.na(.data$entrezgene)) %>%
       dplyr::distinct()
-    background_entrez <- bg$entrezgene
+    background_entrez <- as.character(bg$entrezgene)
   }else{
     stopifnot(is.character(background_entrez))
   }
@@ -110,7 +110,7 @@ get_go_enrichment <- function(query_entrez,
           dplyr::select(.data$go_id, .data$gene_id) %>%
           tidyr::separate_rows(.data$gene_id, sep="/") %>%
           dplyr::mutate(
-            gene_id = as.character(.data$gene_id)) %>%
+            gene_id = as.integer(.data$gene_id)) %>%
           dplyr::left_join(
             dplyr::select(genedb,
                           .data$entrezgene,
@@ -186,7 +186,7 @@ get_universal_enrichment <- function(query_entrez,
     bg <- dplyr::select(genedb, .data$entrezgene) %>%
       dplyr::filter(!is.na(.data$entrezgene)) %>%
       dplyr::distinct()
-    background_entrez <- bg$entrezgene
+    background_entrez <- as.character(bg$entrezgene)
   }else{
     stopifnot(is.character(background_entrez))
 
@@ -303,7 +303,7 @@ get_universal_enrichment <- function(query_entrez,
         df %>%
           dplyr::select(.data$standard_name, .data$gene_id) %>%
           tidyr::separate_rows(.data$gene_id, sep="/") %>%
-          dplyr::mutate(gene_id = as.character(.data$gene_id)) %>%
+          dplyr::mutate(gene_id = as.integer(.data$gene_id)) %>%
           dplyr::left_join(
             dplyr::select(genedb, .data$entrezgene, .data$symbol),
             by=c("gene_id" = "entrezgene")) %>%