update gnomAD tags for 110

sigven · Dec 15, 2023 · f2f8e12 · f2f8e12
1 parent f8c8920
commit f2f8e12
Show file tree

Hide file tree

Showing 3 changed files with 33 additions and 33 deletions.
diff --git a/pcgr/variant.py b/pcgr/variant.py
@@ -257,7 +257,7 @@ def clean_annotations(variant_set: pd.DataFrame, yaml_data: dict, germline: bool
         variant_set.loc[variant_set['CLINVAR_CONFLICTED'] != 1, "CLINVAR_CONFLICTED"] = False
 
     if not {'VCF_SAMPLE_ID'}.issubset(variant_set.columns):
-        variant_set['VCF_SAMPLE_ID'] = yaml_data['sample_id'].astype(str)
+        variant_set['VCF_SAMPLE_ID'] = str(yaml_data['sample_id'])
     variant_set['SAMPLE_ID'] = str(yaml_data['sample_id'])
     variant_set['GENOME_VERSION'] = yaml_data['genome_assembly']
     if {'CHROM','POS','REF','ALT',}.issubset(variant_set.columns):      

diff --git a/pcgrr/R/germline.R b/pcgrr/R/germline.R
@@ -12,15 +12,15 @@ max_af_gnomad <- function(sample_calls){
                                          "type data.frame"))
   )
   ## set maximum AF from gnomAD (all populations)
-  gnomad_cols <- c("gnomAD_AF",
-                   "gnomAD_NFE_AF",
-                   "gnomAD_AMR_AF",
-                   "gnomAD_AFR_AF",
-                   "gnomAD_SAS_AF",
-                   "gnomAD_EAS_AF",
-                   "gnomAD_ASJ_AF",
-                   "gnomAD_FIN_AF",
-                   "gnomAD_OTH_AF")
+  gnomad_cols <- c("gnomADe_AF",
+                   "gnomADe_NFE_AF",
+                   "gnomADe_AMR_AF",
+                   "gnomADe_AFR_AF",
+                   "gnomADe_SAS_AF",
+                   "gnomADe_EAS_AF",
+                   "gnomADe_ASJ_AF",
+                   "gnomADe_FIN_AF",
+                   "gnomADe_OTH_AF")
   sample_calls$MAX_AF_GNOMAD <- 0
   for (c in gnomad_cols) {
     if(c %in% colnames(sample_calls)){
@@ -358,7 +358,7 @@ assign_somatic_germline_evidence <- function(sample_calls, config) {
       pcgrr::assign_germline_popfreq_status(
         sample_calls,
         pop = pop,
-        dbquery = "gnomAD",
+        dbquery = "gnomADe",
         max_tolerated_af =
           config[["tumor_only"]][[paste0("maf_gnomad_", tolower(pop))]])
   }
@@ -382,23 +382,23 @@ assign_somatic_germline_evidence <- function(sample_calls, config) {
 #'
 #' @param sample_calls data frame with variants
 #' @param pop population code (1000 Genomes/gnomAD)
-#' @param dbquery 1KG or gnomAD
+#' @param dbquery gnomADe
 #' @param max_tolerated_af max tolerated germline allele frequency
 #'
 #' @return sample_calls
 #'
 #' @export
 assign_germline_popfreq_status <- function(sample_calls,
                                            pop = "EUR",
-                                           dbquery = "1KG",
+                                           dbquery = "gnomADe",
                                            max_tolerated_af = 0.01) {
 
 
-  if (dbquery == "gnomAD") {
+  if (dbquery == "gnomADe") {
     if (!("STATUS_POPFREQ_GNOMAD_ABOVE_TOLERATED" %in% colnames(sample_calls))) {
       sample_calls$STATUS_POPFREQ_GNOMAD_ABOVE_TOLERATED <- FALSE
     }
-    col <- paste0(pop, "_AF_GNOMAD")
+    col <- paste0(dbquery,"_",pop, "_AF")
     if (any(grepl(paste0("^", col, "$"), names(sample_calls)))) {
 
       sample_calls$max_tolerated_af <- max_tolerated_af

diff --git a/pcgrr/data-raw/data-raw.R b/pcgrr/data-raw/data-raw.R
@@ -187,15 +187,15 @@ data_coltype_defs[['snv_indel_somatic_raw']] <- readr::cols_only(
   SIMPLEREPEATS_HIT = readr::col_logical(),
   WINMASKER_HIT = readr::col_logical(),
   VEP_ALL_CSQ = readr::col_character(),
-  gnomAD_AF = readr::col_number(),
-  gnomAD_AMR_AF = readr::col_number(),
-  gnomAD_AFR_AF = readr::col_number(),
-  gnomAD_EAS_AF = readr::col_number(),
-  gnomAD_FIN_AF = readr::col_number(),
-  gnomAD_ASJ_AF = readr::col_number(),
-  gnomAD_OTH_AF = readr::col_number(),
-  gnomAD_NFE_AF = readr::col_number(),
-  gnomAD_SAS_AF = readr::col_number(),
+  gnomADe_AF = readr::col_number(),
+  gnomADe_AMR_AF = readr::col_number(),
+  gnomADe_AFR_AF = readr::col_number(),
+  gnomADe_EAS_AF = readr::col_number(),
+  gnomADe_FIN_AF = readr::col_number(),
+  gnomADe_ASJ_AF = readr::col_number(),
+  gnomADe_OTH_AF = readr::col_number(),
+  gnomADe_NFE_AF = readr::col_number(),
+  gnomADe_SAS_AF = readr::col_number(),
   EFFECT_PREDICTIONS = readr::col_character(),
   SAMPLE_ID = readr::col_character(),
   VCF_SAMPLE_ID = readr::col_character(),
@@ -299,15 +299,15 @@ data_coltype_defs[['snv_indel_germline_raw']] <- readr::cols_only(
   DBNSFP_BAYESDEL_ADDAF = readr::col_character(),
   DBNSFP_SPLICE_SITE_ADA = readr::col_character(),
   DBNSFP_SPLICE_SITE_RF = readr::col_character(),
-  gnomAD_AF = readr::col_number(),
-  gnomAD_AMR_AF = readr::col_number(),
-  gnomAD_AFR_AF = readr::col_number(),
-  gnomAD_EAS_AF = readr::col_number(),
-  gnomAD_FIN_AF = readr::col_number(),
-  gnomAD_ASJ_AF = readr::col_number(),
-  gnomAD_OTH_AF = readr::col_number(),
-  gnomAD_NFE_AF = readr::col_number(),
-  gnomAD_SAS_AF = readr::col_number(),
+  gnomADe_AF = readr::col_number(),
+  gnomADe_AMR_AF = readr::col_number(),
+  gnomADe_AFR_AF = readr::col_number(),
+  gnomADe_EAS_AF = readr::col_number(),
+  gnomADe_FIN_AF = readr::col_number(),
+  gnomADe_ASJ_AF = readr::col_number(),
+  gnomADe_OTH_AF = readr::col_number(),
+  gnomADe_NFE_AF = readr::col_number(),
+  gnomADe_SAS_AF = readr::col_number(),
   gnomADe_non_cancer_AC = readr::col_integer(),
   gnomADe_non_cancer_AN = readr::col_integer(),
   gnomADe_non_cancer_NHOMALT = readr::col_integer(),