ClinVar update

DESCRIPTION

@@ -35,6 +35,8 @@ Imports:
     ggplot2,
     pcgrr,
     rlang,
+    quarto,
+    openxlsx2,
     stringr,
     tidyr
 Depends:

R/classification.R

@@ -185,7 +185,7 @@ assign_classification <- function(var_calls) {
 
 #' Function that assigns variant pathogenicity evidence based on ACMG guidelines
 #'
-#' @param calls sample calls with dbnsfp annotations
+#' @param var_calls sample calls with dbnsfp annotations
 #' @param settings cpsr settings object
 #' @param ref_data pcgr data object
 #'
@@ -1176,7 +1176,7 @@ exclude_vars_noncoding <- function(
     var_calls = NULL,
     conf = NULL){
 
-  if(config[['other']][['show_noncoding']] == T){
+  if(conf[['other']][['show_noncoding']] == T){
     return(var_calls)
   }
   if("CODING_STATUS" %in% colnames(var_calls) &
@@ -1194,7 +1194,7 @@ exclude_vars_noncoding <- function(
       )
     )
     var_calls <-
-      var_cals |>
+      var_calls |>
       dplyr::filter(
         .data$CODING_STATUS == "coding")
 

R/input_data.R

@@ -36,13 +36,14 @@ load_germline_snv_indel <- function(
     dplyr::mutate(
       ENTREZGENE = as.character(.data$ENTREZGENE)) |>
     dplyr::select(
-      ENTREZGENE, PRIMARY_TARGET
+      c("ENTREZGENE", "PRIMARY_TARGET")
     )
 
   if(NROW(callset[['variant']]) > 0){
     callset[['variant']] <- callset[['variant']] |>
       cpsr::append_cpg_properties(ref_data = ref_data) |>
       cpsr::get_insilico_prediction_statistics() |>
+      pcgrr::append_tfbs_annotation() |>
       pcgrr::append_gwas_citation_phenotype(
        ref_data = ref_data) |>
       cpsr::assign_pathogenicity_evidence(
@@ -130,9 +131,9 @@ load_germline_snv_indel <- function(
   cpsr_callset[['variant']][['all']] <- callset$variant |>
     dplyr::left_join(primary_targets, by = "ENTREZGENE") |>
     dplyr::mutate(PRIMARY_TARGET = dplyr::if_else(
-      is.na(PRIMARY_TARGET),
+      is.na(.data$PRIMARY_TARGET),
       FALSE,
-      as.logical(PRIMARY_TARGET)
+      as.logical(.data$PRIMARY_TARGET)
     ))
   ## Make variant set for tier reporting (virtual panel genes only)
   cpsr_callset[['variant']][['cpg_non_sf']] <- callset$variant |>

R/main.R

@@ -207,7 +207,6 @@ generate_cpsr_report <- function(yaml_fname = NULL) {
           ref_data = ref_data) |>
         pcgrr::append_dbnsfp_var_link() |>
         pcgrr::append_annotation_links() |>
-        pcgrr::append_tfbs_annotation() |>
         pcgrr::append_dbmts_var_link()
 
       if(c != "all"){
@@ -323,7 +322,7 @@ write_cpsr_output <- function(report,
       quarto::quarto_render(
         input = quarto_main_template_sample,
         execute_dir = tmp_quarto_dir,
-        quiet = !cps_report$settings$conf$debug)
+        quiet = !report$settings$conf$debug)
 
       ## Copy output HTML report from temporary rendering directory
       ## to designated HTML file in output directory

data-raw/data-raw.R

@@ -12,9 +12,9 @@ col_format_output[['html_tier']] <-
     "PROTEIN_DOMAIN",
     "HGVSp",
     "HGVSc",
+    "ENSEMBL_GENE_ID",
     "REFSEQ_TRANSCRIPT_ID",
     "ENSEMBL_TRANSCRIPT_ID",
-    "ENSEMBL_GENE_ID",
     "CDS_CHANGE",
     "MUTATION_HOTSPOT",
     "RMSK_HIT",
@@ -57,9 +57,9 @@ col_format_output[['html_sf']] <-
     "PROTEIN_DOMAIN",
     "HGVSp",
     "HGVSc",
+    "ENSEMBL_GENE_ID",
     "REFSEQ_TRANSCRIPT_ID",
     "ENSEMBL_TRANSCRIPT_ID",
-    "ENSEMBL_GENE_ID",
     "CDS_CHANGE",
     "PREDICTED_EFFECT",
     "LOSS_OF_FUNCTION",
@@ -90,9 +90,9 @@ col_format_output[['html_gwas']] <-
     "GWAS_CITATION",
     "HGVSp",
     "HGVSc",
+    "ENSEMBL_GENE_ID",
     "REFSEQ_TRANSCRIPT_ID",
     "ENSEMBL_TRANSCRIPT_ID",
-    "ENSEMBL_GENE_ID",
     "CDS_CHANGE",
     "CODING_STATUS",
     "miRNA_TARGET_HIT",
@@ -112,9 +112,11 @@ col_format_output[['tsv']] <-
   c("SAMPLE_ID",
     "GENOMIC_CHANGE",
     "VAR_ID",
-    "GENOTYPE",
     "GENOME_VERSION",
+    "GENOTYPE",
+    "CPSR_CLASSIFICATION_SOURCE",
     "VARIANT_CLASS",
+    "CODING_STATUS",
     "SYMBOL",
     "GENENAME",
     "CCDS",
@@ -134,7 +136,6 @@ col_format_output[['tsv']] <-
     "LAST_EXON",
     "EXON",
     "EXON_AFFECTED",
-    "CODING_STATUS",
     "EXON_POSITION",
     "INTRON_POSITION",
     "VEP_ALL_CSQ",
@@ -145,8 +146,6 @@ col_format_output[['tsv']] <-
     "LOSS_OF_FUNCTION",
     "NULL_VARIANT",
     "DBMTS",
-    "miRNA_TARGET_HIT",
-    "miRNA_TARGET_HIT_PREDICTION",
     "REGULATORY_ANNOTATION",
     "TF_BINDING_SITE_VARIANT",
     "TF_BINDING_SITE_VARIANT_INFO",
@@ -183,16 +182,17 @@ col_format_output[['html_bm']] <-
     'BM_DISEASE_ONTOLOGY_ID',
     'BM_PRIMARY_SITE',
     'BM_CLINICAL_SIGNIFICANCE',
-    'BM_EVIDENCE_TYPE',
     'BM_THERAPEUTIC_CONTEXT',
     'BM_REFERENCE',
     'BM_MOLECULAR_PROFILE_NAME',
     'BM_RATING',
+    'BM_EVIDENCE_TYPE',
     'BM_EVIDENCE_DIRECTION',
     'BM_EVIDENCE_DESCRIPTION',
     'BM_SOURCE_DB',
     'BM_EVIDENCE_ID',
     'BM_VARIANT_ORIGIN',
+    'BM_MATCH',
     'BM_RESOLUTION',
     'PROTEIN_DOMAIN',
     'CDS_CHANGE',
@@ -201,9 +201,9 @@ col_format_output[['html_bm']] <-
     'FINAL_CLASSIFICATION',
     'PREDICTED_EFFECT',
     'DBSNP_RSID',
+    'ENSEMBL_GENE_ID',
     'ENSEMBL_TRANSCRIPT_ID',
     'REFSEQ_TRANSCRIPT_ID',
-    'ENSEMBL_GENE_ID',
     'GENOMIC_CHANGE',
     'GENOME_VERSION')
 
@@ -304,19 +304,23 @@ col_format_output[['xlsx_biomarker']] <-
     "CPSR_PATHOGENICITY_SCORE",
     "CPSR_CLASSIFICATION_CODE",
     "CLINVAR_CLASSIFICATION",
+    "BM_CANCER_TYPE",
+    "BM_DISEASE_ONTOLOGY_ID",
+    "BM_PRIMARY_SITE",
     "BM_CLINICAL_SIGNIFICANCE",
-    "BM_SOURCE_DB",
-    "BM_RESOLUTION",
+    "BM_THERAPEUTIC_CONTEXT",
     "BM_CITATION",
-    "BM_MATCH",
+    "BM_RATING",
+    "BM_MOLECULAR_PROFILE_NAME",
     "BM_EVIDENCE_TYPE",
     "BM_EVIDENCE_LEVEL",
     "BM_EVIDENCE_DIRECTION",
-    "BM_EVIDENCE_ID",
     "BM_EVIDENCE_DESCRIPTION",
-    "BM_THERAPEUTIC_CONTEXT",
-    "BM_DISEASE_ONTOLOGY_ID",
-    "BM_PRIMARY_SITE"
+    "BM_SOURCE_DB",
+    "BM_EVIDENCE_ID",
+    "BM_VARIANT_ORIGIN",
+    "BM_MATCH",
+    "BM_RESOLUTION"
   )
 
 

pkgdown/index.md

@@ -62,12 +62,6 @@ The variant sets can be interactively explored and filtered further through diff
    4) The list of [virtual gene panels](articles/virtual_panels.html) available in CPSR
 
 
-### Related work
-
-* [CharGer - Characterization of Germline variants](https://github.com/ding-lab/CharGer)
-* [PathoMan - Pathogenicity of Mutation Analyzer (Beta)](https://pathoman.mskcc.org/)
-* [SherLoc - Variant classification](https://www.invitae.com/en/variant-classification/)
-
 ### Contact
 
 sigven@ifi.uio.no

vignettes/annotation_resources.Rmd

@@ -15,7 +15,7 @@ output: rmarkdown::html_document
   * [Cancer Hotspots](http://cancerhotspots.org) - a resource for statistically significant mutations in cancer (v2, 2017)
 
 ### Variant databases of clinical utility
-  * [ClinVar](http://www.ncbi.nlm.nih.gov/clinvar/) - database of clinically related variants (February 2024)
+  * [ClinVar](http://www.ncbi.nlm.nih.gov/clinvar/) - database of clinically related variants (March 2024)
   * [CIViC](https://civicdb.org) - clinical interpretations of variants in cancer (February 29th 2024)
 
 ### Protein domains/functional features
@@ -25,7 +25,7 @@ output: rmarkdown::html_document
 ### Cancer gene knowledge bases
   * [CancerMine](http://bionlp.bcgsc.ca/cancermine/) - Literature-mined database of tumor suppressor genes/proto-oncogenes (v50, March 2023)
   * [Genomics England PanelApp](https://panelapp.genomicsengland.co.uk) - cancer phenotype panels as of February 2nd 2024
-
+  * [Cancer Gene Census](https://www.sanger.ac.uk/data/cancer-gene-census/) - genes implicated with cancer susceptibility (v99)
 
 ### Phenotype ontologies
   * [UMLS/MedGen](https://www.ncbi.nlm.nih.gov/medgen/) - February 2024