Merge pull request #33 from sigven/aug2023

Data update and citation fix
sigven · Aug 16, 2023 · f48003a · f48003a
2 parents 5fba21f + 8d75c1c
commit f48003a
Show file tree

Hide file tree

Showing 53 changed files with 1,164 additions and 1,687 deletions.
diff --git a/DESCRIPTION b/DESCRIPTION
@@ -2,7 +2,7 @@ Package: oncoEnrichR
 Type: Package
 Title: Cancer-dedicated gene set interpretation
 Version: 1.4.1
-Date: 2023-06-17
+Date: 2023-08-16
 Authors@R: person(given = "Sigve", family = "Nakken", role = c("aut", "cre"),
              email = "sigven@ifi.uio.no",
              comment = c(ORCID = "0000-0001-8468-2050"))
@@ -27,33 +27,27 @@ Description: oncoEnrichR performs annotation and prioritization of genesets
     report and an Excel workbook in which the user can interrogate the various 
     types of annotations and analyses performed with the query geneset. 
 Depends: 
-    R (>= 4.1), GSEABase (>= 1.54.0)
+    R (>= 4.1), GSEABase
 biocViews: 
 Imports: dplyr,
          assertthat,
-         jsonlite,
+         assertable,
+         clusterProfiler,
+         DT, 
+         gganatogram, 
+         ggpubr,
          openxlsx,
-         stringi,
          stringr,
-         tidyr,
-         glue,
          googledrive,
-         visNetwork (>= 2.0.9), 
-         SummarizedExperiment (>= 1.22.0),
-         DT (>= 0.18), 
+         visNetwork, 
+         SummarizedExperiment,
          plotly, 
          pals (>= 1.7), 
          org.Hs.eg.db, 
-         clusterProfiler, 
          igraph (>= 1.2.6), 
          lgr,
-         gganatogram, 
-         RCurl,
-         R.cache,
+         maftools, 
          rlang,
-         maftools (>= 2.8.0), 
-         ggpubr (>= 0.4.0), 
-         assertable, 
          TissueEnrich, 
          textclean (>= 0.9.3)
 Suggests: 

diff --git a/NAMESPACE b/NAMESPACE
@@ -7,6 +7,5 @@ importFrom(GSEABase,ENSEMBLIdentifier)
 importFrom(GSEABase,EntrezIdentifier)
 importFrom(GSEABase,GeneSet)
 importFrom(GSEABase,SymbolIdentifier)
-importFrom(RCurl,url.exists)
 importFrom(rlang,":=")
 importFrom(rlang,.data)
diff --git a/R/cell_tissue.R b/R/cell_tissue.R
@@ -26,14 +26,14 @@ gene_tissue_cell_spec_cat <-
       query_genes_df <-
         data.frame('entrezgene' = qgenes, stringsAsFactors = F) |>
         dplyr::inner_join(genedb, by = "entrezgene",
-                          multiple = "all") |>
+                          relationship = "many-to-many") |>
         dplyr::distinct()
 
     } else {
       stopifnot(is.character(qgenes))
       query_genes_df <- query_genes_df |>
         dplyr::inner_join(genedb, by = "symbol",
-                          multiple = "all") |>
+                          relationship = "many-to-many") |>
         dplyr::distinct()
     }
     etype <- "tissue"
@@ -77,7 +77,7 @@ gene_tissue_cell_spec_cat <-
                         c("symbol",
                         "ensembl_gene_id",
                         "name")),
-          by = "ensembl_gene_id", multiple = "all")
+          by = "ensembl_gene_id", relationship = "many-to-many")
     )
 
 
@@ -127,7 +127,7 @@ gene_tissue_cell_spec_cat <-
       if (nrow(dplyr::inner_join(
         df,
         specificity_groups_target,
-        by = "category", multiple = "all")) == 0) {
+        by = "category", relationship = "many-to-many")) == 0) {
         specificity_groups_target <-
           specificity_groups_target |>
           dplyr::bind_rows(df)
@@ -171,7 +171,7 @@ gene_tissue_cell_spec_cat <-
               query_genes_df,
               c("symbol",
                 "ensembl_gene_id")),
-            by = "ensembl_gene_id", multiple = "all") |>
+            by = "ensembl_gene_id", relationship = "many-to-many") |>
           dplyr::mutate(exp = round(log2(.data$nTPM + 1), digits = 3)) |>
           dplyr::mutate(exp_measure = "log2(nTPM + 1)")
       )
@@ -186,7 +186,7 @@ gene_tissue_cell_spec_cat <-
               query_genes_df,
               c("symbol",
                 "ensembl_gene_id")),
-            by = "ensembl_gene_id", multiple = "all") |>
+            by = "ensembl_gene_id", relationship = "many-to-many") |>
           dplyr::mutate(exp = round(log2(.data$nTPM + 1), digits = 3)) |>
           dplyr::mutate(exp_measure = "log2(nTPM  + 1)")
       )
@@ -246,7 +246,7 @@ gene_tissue_cell_enrichment <-
                       "symbol",
                       "name",
                       "cancer_max_rank")),
-        by = "entrezgene", multiple = "all")
+        by = "entrezgene", relationship = "many-to-many")
 
     if (resolution == "tissue") {
       df <- df |>
@@ -271,14 +271,14 @@ gene_tissue_cell_enrichment <-
     q <- bg |>
       dplyr::select("ensembl_gene_id") |>
       dplyr::inner_join(
-        df, by = "ensembl_gene_id", multiple = "all") |>
+        df, by = "ensembl_gene_id", relationship = "many-to-many") |>
       dplyr::distinct()
     query_ensembl <- q$ensembl_gene_id
 
     specificities_per_gene <- bg |>
       dplyr::filter(!is.na(.data$ensembl_gene_id)) |>
       dplyr::inner_join(
-        df, by = "ensembl_gene_id", multiple = "all")
+        df, by = "ensembl_gene_id", relationship = "many-to-many")
 
     if (nrow(specificities_per_gene) > 0) {
 
@@ -312,11 +312,11 @@ gene_tissue_cell_enrichment <-
         dplyr::inner_join(
           dplyr::select(
             genedb, c("ensembl_gene_id", "entrezgene")),
-          by = "entrezgene", multiple = "all"
+          by = "entrezgene", relationship = "many-to-many"
         )
       bg <- bg |>
         dplyr::inner_join(
-          df, by = "ensembl_gene_id", multiple = "all") |>
+          df, by = "ensembl_gene_id", relationship = "many-to-many") |>
         dplyr::distinct()
       background_ensembl <- bg$ensembl_gene_id
 

diff --git a/R/disease_drug.R b/R/disease_drug.R
@@ -22,7 +22,7 @@ target_disease_associations <-
     validate_db_df(otdb_gene_rank, dbtype = "opentarget_disease_site_rank")
 
     target_genes <- data.frame('symbol' = qgenes, stringsAsFactors = F) |>
-      dplyr::inner_join(genedb, by = "symbol", multiple = "all") |>
+      dplyr::inner_join(genedb, by = "symbol", relationship = "many-to-many") |>
       dplyr::distinct()
 
 
@@ -32,7 +32,7 @@ target_disease_associations <-
 
     target_assocs <- target_genes |>
       dplyr::inner_join(otdb_all, by=c("ensembl_gene_id"),
-                       multiple = "all")
+                       relationship = "many-to-many")
 
     result <- list()
     result[['target']] <- target_genes
@@ -93,7 +93,7 @@ target_disease_associations <-
           tmp[['cancer_assocs']] |>
             dplyr::left_join(
               otdb_global_cancer_rank, by = "ensembl_gene_id",
-              multiple = "all") |>
+              relationship = "many-to-many") |>
             dplyr::select(c("symbol", "global_assoc_rank")) |>
             dplyr::distinct() |>
             dplyr::arrange(dplyr::desc(.data$global_assoc_rank)) |>
@@ -109,7 +109,7 @@ target_disease_associations <-
         result[['assoc_pr_gene']][['cancer']] <- as.data.frame(
           tmp[['cancer_assocs']] |>
             dplyr::left_join(gene_targetset_cancer_rank,
-                             by = "symbol", multiple = "all") |>
+                             by = "symbol", relationship = "many-to-many") |>
             dplyr::arrange(dplyr::desc(.data$targetset_cancer_rank),
                            dplyr::desc(.data$ot_association_score)) |>
             dplyr::select(-c("primary_site")) |>
@@ -173,7 +173,7 @@ target_disease_associations <-
         result[['assoc_pr_gene']][['other']] <- as.data.frame(
           tmp[['disease_assocs']] |>
             dplyr::left_join(gene_targetset_disease_rank,
-                             by = "symbol", multiple = "all") |>
+                             by = "symbol", relationship = "many-to-many") |>
             dplyr::arrange(dplyr::desc(.data$targetset_disease_rank),
                            dplyr::desc(.data$ot_association_score)) |>
 
@@ -198,7 +198,7 @@ target_disease_associations <-
         result[['target']] <- result[['target']] |>
           dplyr::left_join(
             result[['assoc_pr_gene']][['cancer']],
-            by = "symbol", multiple = "all")
+            by = "symbol", relationship = "many-to-many")
       } else {
         result[['target']]$targetset_cancer_rank <- NA
         result[['target']]$global_cancer_rank <- NA
@@ -210,7 +210,7 @@ target_disease_associations <-
         result[['target']] <- result[['target']] |>
           dplyr::left_join(
             result[['assoc_pr_gene']][['other']],
-            by = "symbol", multiple = "all")
+            by = "symbol", relationship = "many-to-many")
       } else {
         result[['target']]$targetset_disease_rank <- NA
         result[['target']]$ot_links <- NA
@@ -276,7 +276,7 @@ target_disease_associations <-
                         c("primary_site",
                         "ensembl_gene_id",
                         "tissue_assoc_rank")),
-          by = "ensembl_gene_id", multiple = "all"
+          by = "ensembl_gene_id", relationship = "many-to-many"
         ) |>
         dplyr::select(-c("ensembl_gene_id")) |>
         dplyr::distinct()

diff --git a/R/enrich.R b/R/enrich.R
@@ -128,7 +128,7 @@ get_go_enrichment <- function(query_entrez,
                           c("entrezgene",
                           "symbol")),
             by=c("gene_id" = "entrezgene"),
-            multiple = "all") |>
+            relationship = "many-to-many") |>
           dplyr::mutate(
             entrez_url =
               paste0("<a href='https://www.ncbi.nlm.nih.gov/gene/",
@@ -148,7 +148,7 @@ get_go_enrichment <- function(query_entrez,
                         c("go_id",
                         "gene_symbol_link",
                         "gene_symbol")),
-          by="go_id", multiple = "all") |>
+          by="go_id", relationship = "many-to-many") |>
         dplyr::rename(exact_source = "go_id",
                       description = "go_description",
                       description_link = "go_description_link") |>
@@ -215,7 +215,7 @@ get_universal_enrichment <- function(query_entrez,
   stopifnot(is.character(TERM2GENE$entrez_gene))
 
   stopifnot(NROW(
-    dplyr::inner_join(TERM2NAME, TERM2GENE, by = "standard_name", multiple = "all")
+    dplyr::inner_join(TERM2NAME, TERM2GENE, by = "standard_name", relationship = "many-to-many")
   ) > 0)
 
   enr <-
@@ -290,7 +290,7 @@ get_universal_enrichment <- function(query_entrez,
       stopifnot(!is.null(TERM2SOURCE) | !is.data.frame(TERM2SOURCE))
       stopifnot("standard_name" %in% colnames(TERM2SOURCE))
       df <- df |>
-        dplyr::left_join(TERM2SOURCE, by="standard_name", multiple = "all") |>
+        dplyr::left_join(TERM2SOURCE, by="standard_name", relationship = "many-to-many") |>
         dplyr::mutate(
           description_link =
             dplyr::if_else(
@@ -354,7 +354,7 @@ get_universal_enrichment <- function(query_entrez,
           dplyr::mutate(gene_id = as.integer(.data$gene_id)) |>
           dplyr::left_join(
             dplyr::select(genedb, c("entrezgene", "symbol")),
-            by = c("gene_id" = "entrezgene"), multiple = "all") |>
+            by = c("gene_id" = "entrezgene"), relationship = "many-to-many") |>
           dplyr::mutate(
             entrez_url =
               paste0("<a href='https://www.ncbi.nlm.nih.gov/gene/",
@@ -373,7 +373,7 @@ get_universal_enrichment <- function(query_entrez,
                         c("standard_name",
                         "gene_symbol_link",
                         "gene_symbol")),
-          by = "standard_name", multiple = "all")
+          by = "standard_name", relationship = "many-to-many")
     }
     if (!is.null(df)) {
       df$setting_p_value_cutoff <- p_value_cutoff

diff --git a/R/gene_fitness.R b/R/gene_fitness.R
@@ -25,7 +25,7 @@ get_fitness_lof_scores <- function(qgenes,
     target_genes |>
     dplyr::inner_join(
       depmapdb[['fitness_scores']],
-      by = c("symbol"), multiple = "all") |>
+      by = c("symbol"), relationship = "many-to-many") |>
     dplyr::arrange(.data$scaled_BF)
   )
   if (nrow(fitness_lof_hits) > 0) {
@@ -71,8 +71,8 @@ get_fitness_lof_scores <- function(qgenes,
 
     fitness_lof_results[['targets']] <- fitness_lof_results[['targets']] |>
       dplyr::left_join(gene_pr_tissue_stats,
-                       by = c("symbol","tissue"), multiple = "all") |>
-      dplyr::left_join(gene_stats, by = "symbol", multiple = "all") |>
+                       by = c("symbol","tissue"), relationship = "many-to-many") |>
+      dplyr::left_join(gene_stats, by = "symbol", relationship = "many-to-many") |>
       dplyr::select(c("symbol",
                     "symbol_link_ps",
                     "model_name",
@@ -117,7 +117,7 @@ get_target_priority_scores <-
 
     targets_crispr_priority <- as.data.frame(
       depmapdb[['target_priority_scores']] |>
-        dplyr::inner_join(target_genes, by = c("symbol"), multiple = "all")
+        dplyr::inner_join(target_genes, by = c("symbol"), relationship = "many-to-many")
       )
 
     prioritized_targets[["n_pri_targets"]] <-

diff --git a/R/ligand_receptor.R b/R/ligand_receptor.R
@@ -27,9 +27,9 @@ annotate_ligand_receptor_interactions <- function(qgenes,
                         c("entrezgene",
                           "symbol")),
           !is.na(.data$symbol)),
-        by = c("symbol"), multiple = "all") |>
+        by = c("symbol"), relationship = "many-to-many") |>
       dplyr::filter(!is.na(.data$entrezgene)) |>
-      dplyr::inner_join(query_df, by = "symbol", multiple = "all")
+      dplyr::inner_join(query_df, by = "symbol", relationship = "many-to-many")
   )
 
   query_hits <- list()
@@ -43,7 +43,7 @@ annotate_ligand_receptor_interactions <- function(qgenes,
   valid_query_hits <-
     query_hits[['ligand']] |>
     dplyr::inner_join(query_hits[['receptor']],
-                      by = "interaction_id", multiple = "all")
+                      by = "interaction_id", relationship = "many-to-many")
 
   ligand_receptor_results <- list()
   ligand_receptor_results[['cell_cell_contact']] <-
@@ -59,7 +59,7 @@ annotate_ligand_receptor_interactions <- function(qgenes,
         ligand_receptor_db |>
           dplyr::filter(.data$annotation == "Cell-Cell Contact") |>
           dplyr::inner_join(valid_query_hits,
-                            by = "interaction_id", multiple = "all")
+                            by = "interaction_id", relationship = "many-to-many")
       ) |>
       dplyr::select(-c("interaction_id",
                        "annotation",
@@ -71,7 +71,7 @@ annotate_ligand_receptor_interactions <- function(qgenes,
         ligand_receptor_db |>
           dplyr::filter(.data$annotation == "Secreted Signaling") |>
           dplyr::inner_join(valid_query_hits,
-                            by = "interaction_id", multiple = "all")
+                            by = "interaction_id", relationship = "many-to-many")
       ) |>
       dplyr::select(-c("interaction_id",
                        "annotation",
@@ -84,7 +84,7 @@ annotate_ligand_receptor_interactions <- function(qgenes,
         ligand_receptor_db |>
           dplyr::filter(.data$annotation == "ECM-Receptor") |>
           dplyr::inner_join(valid_query_hits,
-                            by = "interaction_id", multiple = "all")
+                            by = "interaction_id", relationship = "many-to-many")
       ) |>
       dplyr::select(-c("interaction_id",
                        "annotation",