Merge pull request #26 from sigven/dev

Dev update

DESCRIPTION

@@ -2,7 +2,7 @@ Package: oncoEnrichR
 Type: Package
 Title: Cancer-dedicated gene set interpretation
 Version: 1.3.0
-Date: 2022-09-12
+Date: 2022-09-23
 Authors@R: person(given = "Sigve", family = "Nakken", role = c("aut", "cre"),
              email = "[email protected]",
              comment = c(ORCID = "0000-0001-8468-2050"))

R/disease_drug.R

@@ -329,7 +329,11 @@ target_drug_associations <- function(qgenes,
                   .data$targeted_cancer_drugs_ep,
                   .data$approved_drugs) |>
     dplyr::filter(!is.na(.data$targeted_cancer_drugs_lp) |
-                    !is.na(.data$targeted_cancer_drugs_ep))
+                    !is.na(.data$targeted_cancer_drugs_ep)) |>
+    dplyr::rename(
+      drugs_late_phase = .data$targeted_cancer_drugs_lp,
+      drugs_early_phase = .data$targeted_cancer_drugs_ep
+    )
 
   lgr::lgr$info( paste0("Open Targets Platform: annotation of target tractabilities (druggability)"))
 

R/onco_enrichr.R

@@ -1610,25 +1610,36 @@ onco_enrich <- function(query = NULL,
           PROTEIN_DOMAIN = dplyr::if_else(
             !is.na(.data$PFAM_ID),
             paste0(
-            "<a href=\"http://pfam.xfam.org/family/", .data$PFAM_ID,
+            "<a href=\"http://pfam.xfam.org/family/",
+            .data$PFAM_ID,
             "\" target='_blank'>",
             .data$PFAM_DOMAIN_NAME,
             "</a>"),
             as.character(NA)
           )
         ) |>
-        dplyr::select(-c(.data$PFAM_DOMAIN_NAME, .data$PFAM_ID)) |>
-        dplyr::left_join(dplyr::select(oeDB[['genedb']][['all']],
-                                       .data$symbol, .data$ensembl_gene_id),
-                         by = c("SYMBOL" = "symbol")) |>
-        dplyr::rename(ENSEMBL_GENE_ID = .data$ensembl_gene_id) |>
-        dplyr::mutate(ENSEMBL_TRANSCRIPT_ID =
-                        paste0("<a href='https://www.ensembl.org/Homo_sapiens/Transcript/Summary?db=core;g=",
-                               .data$ENSEMBL_GENE_ID,
-                               ";t=",
-                               .data$ENSEMBL_TRANSCRIPT_ID,"' target='_blank'>",
-                               .data$ENSEMBL_TRANSCRIPT_ID,"</a>")) |>
+        dplyr::select(
+          -c(.data$PFAM_DOMAIN_NAME, .data$PFAM_ID)) |>
+        dplyr::left_join(
+          dplyr::select(oeDB[['genedb']][['all']],
+                        .data$symbol, .data$ensembl_gene_id),
+          by = c("SYMBOL" = "symbol")) |>
+        dplyr::mutate(
+          ENSEMBL_GENE_ID =
+            paste0(
+              "<a href='https://www.ensembl.org/Homo_sapiens/Gene/Summary?db=core;g=",
+              .data$ensembl_gene_id,"' target='_blank'>",
+              .data$ensembl_gene_id,"</a>")) |>
+        dplyr::mutate(
+          ENSEMBL_TRANSCRIPT_ID =
+            paste0(
+              "<a href='https://www.ensembl.org/Homo_sapiens/Transcript/Summary?db=core;g=",
+              .data$ensembl_gene_id,
+              ";t=",
+              .data$ENSEMBL_TRANSCRIPT_ID,"' target='_blank'>",
+              .data$ENSEMBL_TRANSCRIPT_ID,"</a>")) |>
         dplyr::select(-.data$VAR_ID) |>
+        dplyr::rename(CONSEQUENCE_ALTERNATE = .data$VEP_ALL_CSQ) |>
         dplyr::select(.data$SYMBOL,
                       .data$CONSEQUENCE,
                       .data$PROTEIN_CHANGE,
@@ -1637,7 +1648,11 @@ onco_enrich <- function(query = NULL,
                       .data$LOSS_OF_FUNCTION,
                       .data$ENSEMBL_GENE_ID,
                       .data$ENSEMBL_TRANSCRIPT_ID,
-                      dplyr::everything())
+                      .data$PRIMARY_SITE,
+                      .data$SITE_RECURRENCE,
+                      .data$TOTAL_RECURRENCE,
+                      .data$COSMIC_MUTATION_ID,
+                      .data$CONSEQUENCE_ALTERNATE)
     }
 
     for(psite in names(onc_rep[["data"]][["tcga"]][["aberration"]][["table"]][["snv_indel"]])){
@@ -2106,6 +2121,7 @@ write <- function(report,
                   "subcellcomp",
                   "cell_tissue",
                   "aberration",
+                  "recurrent_variants",
                   "coexpression",
                   "prognostic_association_I",
                   "prognostic_association_II"
@@ -2115,6 +2131,10 @@ write <- function(report,
       if(elem == "cancer_association"){
         show_elem <- "disease"
       }
+
+      if(elem == "recurrent_variants"){
+        show_elem <- "aberration"
+      }
       if(elem == "prognostic_association_I"){
         show_elem <- "cancer_prognosis"
       }

R/utils.R

@@ -1077,23 +1077,23 @@ add_excel_sheet <- function(
               )
           ) |>
           dplyr::mutate(
-            targeted_cancer_drugs_lp =
+            drugs_late_phase =
               stringr::str_replace_all(
                 stringr::str_squish(
                   stringr::str_trim(
-                    textclean::replace_html(.data$targeted_cancer_drugs_lp)
+                    textclean::replace_html(.data$drugs_late_phase)
                   )
                 ),
                 " , ",
                 ", "
               )
           ) |>
           dplyr::mutate(
-            targeted_cancer_drugs_ep =
+            drugs_early_phase =
               stringr::str_replace_all(
                 stringr::str_squish(
                   stringr::str_trim(
-                    textclean::replace_html(.data$targeted_cancer_drugs_ep)
+                    textclean::replace_html(.data$drugs_early_phase)
                   )
                 ),
                 " , ",
@@ -1420,6 +1420,78 @@ add_excel_sheet <- function(
 
   }
 
+  if(analysis_output == "recurrent_variants"){
+
+    if(is.data.frame(report$data$tcga$recurrent_variants)){
+      if(NROW(report$data$tcga$recurrent_variants) > 0){
+        df <-
+          report$data$tcga$recurrent_variants
+
+        colnames(df) <- tolower(colnames(df))
+        df <- as.data.frame(
+          df |>
+            dplyr::mutate(
+              site_recurrence = as.numeric(.data$site_recurrence)
+            ) |>
+            dplyr::arrange(
+              dplyr::desc(.data$total_recurrence),
+              dplyr::desc(.data$site_recurrence)) |>
+            dplyr::mutate(
+              annotation_source = report$config$resources$tcga$name,
+              version = report$config$resources$tcga$version) |>
+            dplyr::mutate(
+              ensembl_gene_id =
+                stringr::str_trim(
+                  textclean::replace_html(.data$ensembl_gene_id)
+                )
+            ) |>
+            dplyr::mutate(
+              ensembl_transcript_id =
+                stringr::str_trim(
+                  textclean::replace_html(.data$ensembl_transcript_id)
+                )
+            ) |>
+            dplyr::mutate(
+              protein_domain =
+                stringr::str_trim(
+                  textclean::replace_html(.data$protein_domain)
+                )
+            ) |>
+            dplyr::mutate(
+              cosmic_mutation_id =
+                stringr::str_trim(
+                  textclean::replace_html(.data$cosmic_mutation_id)
+                )
+            ) |>
+            dplyr::mutate(
+              site_recurrence = paste(.data$primary_site,
+                                      .data$site_recurrence, sep=":")
+            ) |>
+            dplyr::group_by(
+              .data$symbol, .data$consequence,
+              .data$protein_change, .data$protein_domain,
+              .data$mutation_hotspot,
+              .data$loss_of_function,
+              .data$ensembl_gene_id,
+              .data$ensembl_transcript_id,
+              .data$total_recurrence,
+              .data$cosmic_mutation_id
+            ) |>
+            dplyr::summarise(site_recurrence = paste(
+              .data$site_recurrence, collapse=", "
+            ), .groups = "drop") |>
+            dplyr::arrange(
+              dplyr::desc(.data$total_recurrence)
+            )
+
+        )
+
+        target_df <- target_df |>
+          dplyr::bind_rows(df)
+      }
+    }
+  }
+
   if(analysis_output == "aberration"){
 
     ## cna aberrations

README.md

@@ -20,21 +20,22 @@ Web-based access to **oncoEnrichR** is available at [**https://oncotools.elixir.
 
 ## News
 
+-   September 23rd 2022: [**1.3.1 release**](https://sigven.github.io/oncoEnrichR/articles/CHANGELOG.html#version-1-3-1)
 -   September 12th 2022: [**1.3.0 release**](https://sigven.github.io/oncoEnrichR/articles/CHANGELOG.html#version-1-3-0)
 -   September 2nd 2022: [**1.2.2 release**](https://sigven.github.io/oncoEnrichR/articles/CHANGELOG.html#version-1-2-2)
 -   July 13th 2022: [**1.2.1 release**](https://sigven.github.io/oncoEnrichR/articles/CHANGELOG.html#version-1-2-1)
 
 ## Example report
 
-<a href="https://doi.org/10.5281/zenodo.7070557"><img src="https://zenodo.org/badge/DOI/10.5281/zenodo.7070557.svg" alt="DOI"/></a>
+<a href="https://doi.org/10.5281/zenodo.7104355"><img src="https://zenodo.org/badge/DOI/10.5281/zenodo.7104355.svg" alt="DOI"/></a>
 
 ### Contact
 
 sigven AT ifi.uio.no
 
 ### Funding and Collaboration
 
-OncoEnrichR is supported by the [Centre for Cancer Cell Reprogramming](https://www.med.uio.no/cancell/english/) at the [University of Oslo](https://www.uio.no)/[Oslo University Hospital](https://radium.no), and [Elixir Norway (Oslo node)](https://elixir.no/organization/organisation/elixir-uio).
+oncoEnrichR is supported by the [Centre for Cancer Cell Reprogramming](https://www.med.uio.no/cancell/english/) at the [University of Oslo](https://www.uio.no)/[Oslo University Hospital](https://radium.no), and [Elixir Norway (Oslo node)](https://elixir.no/organization/organisation/elixir-uio).
 
 <br> <br>
 

data_processing_code/RELEASE_NOTES.txt

@@ -1,26 +1,26 @@
-##ONCOENRICHR_DB_VERSION = 20220910
-oncoEnrichR	https://gihtub.com/sigven/oncoEnrichR	R package for functional interrogation of genesets in the context of cancer	v1.3.0	oncoEnrichR	software
+##ONCOENRICHR_DB_VERSION = 20220921
+oncoEnrichR	https://gihtub.com/sigven/oncoEnrichR	R package for functional interrogation of genesets in the context of cancer	v1.3.1	oncoEnrichR	software
 Omnipath	https://omnipathdb.org/	Database of molecular biology prior knowledge: gene regulatory interactions, enzyme-PTM relationships, protein complexes, protein annotations etc.	v3.4.0/OmnipathR	omnipath	db
 hu.MAP	http://humap2.proteincomplexes.org/	Human Protein Complex Map	v2.0	humap2	db
 dorothea	https://saezlab.github.io/dorothea/	Gene set resource containing signed transcription factor (TF) - target interactions	v1.8.0	dorothea	db
 tissueEnrich	https://www.bioconductor.org/packages/release/bioc/vignettes/TissueEnrich/inst/doc/TissueEnrich.html	 R package used to calculate enrichment of tissue-specific genes in a set of input genes	v1.16.0	tissueenrich	software
-oncoPhenoMap	https://github.com/sigven/oncoPhenoMap	Crossmapped phenotype ontologies for the oncology domain	v0.3.8	oncophenomap	software
+oncoPhenoMap	https://github.com/sigven/oncoPhenoMap	Crossmapped phenotype ontologies for the oncology domain	v0.4.0	oncophenomap	software
 STRING	https://string-db.org	Protein-protein interaction database	v11.5	string	db
 GENCODE	https://www.gencodegenes.org/	High quality reference gene annotation and experimental validation	v41	gencode	db
-TCGA	https://cancergenome.nih.gov	The Cancer Genome Atlas - Tumor gene expression and somatic DNA aberrations	v32.0 (March 29th 2022)	tcga	db
+TCGA	https://cancergenome.nih.gov	The Cancer Genome Atlas - Tumor gene expression and somatic DNA aberrations	v34.0 (July 27th 2022)	tcga	db
 UniProtKB	http://www.uniprot.org	Comprehensive resource of protein sequence and functional information	v2022_03	uniprot	db
 NetPath	http://www.netpath.org	Manually curated resource of signal transduction pathways in humans	v1 (2010)	netpath	db
-EFO	https://github.com/EBISPOT/efo	Experimental Factor Ontology	v3.43.0	efo	db
-DiseaseOntology	https://github.com/DiseaseOntology	Human Disease Ontology	2022-06-07	do	db
+EFO	https://github.com/EBISPOT/efo	Experimental Factor Ontology	v3.46.0	efo	db
+DiseaseOntology	https://github.com/DiseaseOntology	Human Disease Ontology	2022-08-29	do	db
 COMPPI	https://comppi.linkgroup.hu/	Compartmentalized protein-protein interaction database	v2.1.1 (October 2018)	comppi	db
-WikiPathways	https://www.wikipathways.org	A database of biological pathways maintained by and for the scientific community	20220810	wikipathway	db
+WikiPathways	https://www.wikipathways.org	A database of biological pathways maintained by and for the scientific community	20220910	wikipathway	db
 MSigDB	http://software.broadinstitute.org/gsea/msigdb/index.jsp	Molecular Signatures Database - collection of annotated gene sets	August 2022 (MSigDB v2022.1)	msigdb	db
 REACTOME	https://reactome.org	Manually curated and peer-reviewed pathway database	v81 (MSigDB v2022.1)	reactome	db
 CellChatDB	http://www.cellchat.org/cellchatdb/	Multimeric ligand-receptor complexes	v1 (2021)	cellchatdb	db
 CellTalkDB	http://tcm.zju.edu.cn/celltalkdb/	A manually curated database of literature-supported ligand-receptor interactions in human and mouse	Nov 2020	celltalkdb	db
 GeneOntology	https://geneontology.org	Knowledgebase that contains the largest structural source of information on the functions of genes	August 2022 (MSigDB v2022.1)	go	db
 KEGG	https://www.genome.jp/kegg/pathway.html	Collection of manually drawn pathway maps representing our knowledge on the molecular interaction, reaction and relation networks	20220809	kegg	db
-CancerMine	http://bionlp.bcgsc.ca/cancermine/	Literature-mined database of tumor suppressor genes/proto-oncogenes	v47 - 20220708	cancermine	db
+CancerMine	http://bionlp.bcgsc.ca/cancermine/	Literature-mined database of tumor suppressor genes/proto-oncogenes	v48 - 20220920	cancermine	db
 NCG	http://ncg.kcl.ac.uk/index.php	Network of cancer genes - a web resource to analyze duplicability, orthology and network properties of cancer genes	v7.0	ncg	db
 CGC	https://cancer.sanger.ac.uk/census	Cancer Gene Census	v96	cgc	db
 Pfam	http://pfam.xfam.org	Collection of protein families/domains	2021_11 (v35.0)	pfam	db

data_processing_code/data_raw.R

@@ -4,7 +4,7 @@ library(gganatogram)
 source('data_processing_code/data_utility_functions.R')
 
 msigdb_version <- '2022.1'
-wikipathways_version <- "20220810"
+wikipathways_version <- "20220910"
 netpath_version <- "2010"
 opentargets_version <- "2022.06"
 kegg_version <- "20220809"
@@ -14,17 +14,17 @@ uniprot_release <- "2022_03"
 ## Which databases to update or retrieve from last updated state
 update_omnipathdb <- F
 update_hpa <- F
-update_ncbi_gene_summary <- T
+update_ncbi_gene_summary <- F
 update_project_score <- F
 update_project_survival <- F
-update_tcga <- F
+update_tcga <- T
 update_cancer_hallmarks <- F
 update_omnipath_regulatory <- F
 update_omnipath_complexdb <- F
 update_gencode <- F
 update_ligand_receptor_db <- T
 
-oe_version <- "1.3.0"
+oe_version <- "1.3.1"
 
 data_raw_dir <- "/Users/sigven/project_data/package__oncoEnrichR/db/raw"
 data_output_dir <- "/Users/sigven/project_data/package__oncoEnrichR/db/output"
@@ -99,7 +99,7 @@ ts_oncogene_annotations <-
   get_ts_oncogene_annotations(
     raw_db_dir = data_raw_dir,
     gene_info = gene_info,
-    version = "47") |>
+    version = "48") |>
   dplyr::select(
     entrezgene, tumor_suppressor,
     oncogene, citation_links_oncogene,