Added getVariantPopData & convertVariantIds

daynefiler · Dec 3, 2021 · f5f8e34 · f5f8e34
1 parent a71fdc7
commit f5f8e34
Show file tree

Hide file tree

Showing 11 changed files with 179 additions and 3 deletions.
diff --git a/NAMESPACE b/NAMESPACE
@@ -4,8 +4,11 @@ export(DatasetIds)
 export(ReferenceGenomeIds)
 export(apiUrl)
 export(compatibleGenomeDataset)
+export(convertVariantIds)
 export(getDatasets)
 export(getGenomes)
+export(getLiftoverIdName)
+export(getVariantPopData)
 export(getVariantsFromRegion)
 export(validDatasets)
 export(validGenomes)

diff --git a/R/convertVariantIds.R b/R/convertVariantIds.R
@@ -0,0 +1,46 @@
+#' @title Get variant IDs for alternate reference genome
+#' @inheritParams pkgParams
+#' @param genomes The genome associated with the given variant_id
+#' @description
+#' Returns the variant_id(s) for the alternate reference genome
+#'
+#' @return variant_id(s)
+#'
+#' @examples
+#' \dontrun{
+#' convertVariantIds(varids = '1-89388944-A-C', genomes = "GRCh37")
+#' }
+#'
+#' @import ghql
+#' @importFrom glue glue glue_collapse
+#' @importFrom jsonlite fromJSON
+#' @export
+
+convertVariantIds <- function(varids, genomes) {
+  stopifnot(validGenomes(genomes))
+  gmCon <- GraphqlClient$new(url = apiUrl())
+  datasets <- getDatasets(genomes)
+  idnames <- getLiftoverIdName(genomes)
+  tmp <-
+  '
+    {genomes}_{gsub("-", "_", varids)}:
+    liftover({idnames}: "{varids}", reference_genome: {genomes}) {{
+      source {{
+        variant_id
+        reference_genome
+      }}
+      liftover {{
+        variant_id
+        reference_genome
+      }}
+    }}
+  '
+  qryBody <- glue_collapse(glue(tmp), sep = "\n")
+  qry <- Query$new()$query('convertIds',
+                           glue('query convertIds {{ {qryBody} }}'))
+  tryres <- try(jsn <- gmCon$exec(qry$convertIds), silent = TRUE)
+  if (is(tryres, 'try-error')) stop(qfailmessage)
+  res <- fromJSON(jsn, flatten = TRUE)$data
+  res
+}
+
diff --git a/R/getVariantPopData.R b/R/getVariantPopData.R
@@ -0,0 +1,56 @@
+#' @title Get variant population data
+#' @inheritParams pkgParams
+#' @param genomes The genome(s) associated with the given variant_id
+#' @description
+#' Returns the variant_id(s) for the alternate reference genome
+#'
+#' @return List of population data for the given variant_id(s)
+#'
+#' @examples
+#' \dontrun{
+#' getVariantPopData(varids = '1-88923261-A-C', genomes = "GRCh38")
+#' }
+#'
+#' @import ghql
+#' @importFrom glue glue glue_collapse
+#' @importFrom jsonlite fromJSON
+#' @export
+
+getVariantPopData <- function(varids, genomes) {
+  stopifnot(validGenomes(genomes))
+  gmCon <- GraphqlClient$new(url = apiUrl())
+  datasets <- getDatasets(genomes)
+  tmp <-
+    '
+    {genomes}_{gsub("-", "_", varids)}:
+    variant(variantId: "{varids}", dataset: {datasets}) {{
+      variantId
+      chrom
+      pos
+      genome {{
+        populations {{
+          id
+          ac
+          an
+          homozygote_count
+          hemizygote_count
+        }}
+      }}
+    }}
+  '
+  qryBody <- glue_collapse(glue(tmp), sep = "\n")
+  qry <- Query$new()$query('convertIds',
+                           glue('query convertIds {{ {qryBody} }}'))
+  tryres <- try(jsn <- gmCon$exec(qry$convertIds), silent = TRUE)
+  if (is(tryres, 'try-error')) stop(qfailmessage)
+  resLst <- fromJSON(jsn, flatten = TRUE)$data
+  procPopData <- function(x) {
+    cbind(varid = x$variantId,
+          chrom = x$chrom,
+          pos = x$pos,
+          x$genome$populations)
+  }
+  res <- lapply(resLst, procPopData)
+  res
+}
+
diff --git a/R/getVariantsFromRegion.R b/R/getVariantsFromRegion.R
@@ -24,7 +24,8 @@ getVariantsFromRegion <- function(genomes, chroms, starts, stops = starts) {
   datasets <- getDatasets(genomes)
   tmp <-
   '
-  {genomes}_{chroms}_{starts}_{stops}: region(chrom: "{chroms}",
+    {genomes}_{chroms}_{starts}_{stops}:
+    region(chrom: "{chroms}",
            start: {starts},
            stop: {stops},
            reference_genome: {genomes}) {{

diff --git a/R/gnomadR-package.R b/R/gnomadR-package.R
@@ -26,5 +26,7 @@ NULL
 #' @param starts Integer, starting position(s)
 #' @param start Integer scalar, starting position
 #' @param stop Integer scalar, ending position
+#' @param varid Charactter scalar, gnomAD variant_id
+#' @param varids Character, gnomAD variant_id(s)
 #'
 NULL
diff --git a/R/utils.R b/R/utils.R
@@ -32,6 +32,8 @@ ReferenceGenomeIds <- c("GRCh38", "GRCh37")
 attr(ReferenceGenomeIds, "defDatasetOpt") <-
   glue("gnomadr.{ReferenceGenomeIds}.dataset")
 attr(ReferenceGenomeIds, "defDataset") <- c("gnomad_r3", "gnomad_r2_1")
+attr(ReferenceGenomeIds, "liftoverIdName") <-
+  c("liftover_variant_id", "source_variant_id")
 
 #' @rdname gnomad-ids
 #' @export
@@ -94,3 +96,12 @@ getDatasets <- function(genomes) {
   stopifnot(compatibleGenomeDataset(datasets = ds, genomes = genomes))
   ds
 }
+
+#' @rdname gnomad-ids
+#' @inheritParams pkgParams
+#' @export
+
+getLiftoverIdName <- function(genomes) {
+  stopifnot(validGenomes(genomes))
+  attr(ReferenceGenomeIds, "liftoverIdName")[match(genomes, ReferenceGenomeIds)]
+}
diff --git a/man/convertVariantIds.Rd b/man/convertVariantIds.Rd
diff --git a/man/getVariantPopData.Rd b/man/getVariantPopData.Rd
diff --git a/man/getVariantsFromRegion.Rd b/man/getVariantsFromRegion.Rd
diff --git a/man/gnomad-ids.Rd b/man/gnomad-ids.Rd
diff --git a/man/pkgParams.Rd b/man/pkgParams.Rd