Merge pull request #80 from stemangiola/change-cell-name-convention

change to cell_

Author: multimeric

DESCRIPTION

@@ -1,7 +1,7 @@
 Type: Package
 Package: CuratedAtlasQueryR
 Title: Queries the Human Cell Atlas
-Version: 0.4.0
+Version: 0.4.1
 Authors@R: c(
     person(
         "Stefano",

R/query.R

@@ -83,7 +83,7 @@ get_SingleCellExperiment <- function(
     cli_alert_info("Realising metadata.")
     raw_data <- collect(data)
     inherits(raw_data, "tbl") |> assert_that()
-    has_name(raw_data, c("_cell", "file_id_db")) |> assert_that()
+    has_name(raw_data, c("cell_", "file_id_db")) |> assert_that()
 
     versioned_cache_directory = file.path(cache_directory, COUNTS_VERSION)
     versioned_cache_directory |> dir.create(showWarnings = FALSE, recursive = TRUE)
@@ -177,14 +177,14 @@ group_to_sce <- function(i, df, dir_prefix, features) {
     sce <- loadHDF5SummarizedExperiment(sce_path)
     # The cells we select here are those that are both available in the SCE
     # object, and requested for this particular file
-    cells <- colnames(sce) |> intersect(df$`_cell`)
+    cells <- colnames(sce) |> intersect(df$cell_)
     # We need to make the cell names globally unique, which we can guarantee
     # by adding a suffix that is derived from file_id_db, which is the grouping
     # variable
     new_cellnames <- paste0(cells, "_", i)
     new_coldata <- df |>
-        mutate(original_cell_id = .data$`_cell`, `_cell` = new_cellnames) |>
-        column_to_rownames("_cell") |>
+        mutate(original_cell_id = .data$cell_, cell_ = new_cellnames) |>
+        column_to_rownames("cell_") |>
         as("DataFrame")
 
     features |>
@@ -406,10 +406,10 @@ get_seurat <- function(...) {
 #' - `.sample_name`: How samples were defined
 #' 
 get_metadata <- function(
-    remote_url = "https://object-store.rc.nectar.org.au/v1/AUTH_06d6e008e3e642da99d806ba3ea629c5/metadata/metadata.0.2.2.parquet",
+    remote_url = "https://object-store.rc.nectar.org.au/v1/AUTH_06d6e008e3e642da99d806ba3ea629c5/metadata/metadata.0.2.3.parquet",
     cache_directory = get_default_cache_dir()
 ) {
-    db_path <- file.path(cache_directory, "metadata.0.2.2.parquet")
+    db_path <- file.path(cache_directory, "metadata.0.2.3.parquet")
     sync_remote_file(
         remote_url,
         db_path,

README.Rmd

@@ -259,11 +259,11 @@ Dataset-specific columns (definitions available at cellxgene.cziscience.com)
 
 Sample-specific columns (definitions available at cellxgene.cziscience.com)
 
-`.sample`, `.sample_name`, `age_days`, `assay`, `assay_ontology_term_id`, `development_stage`, `development_stage_ontology_term_id`, `ethnicity`, `ethnicity_ontology_term_id`, `experiment___`, `organism`, `organism_ontology_term_id`, `sample_placeholder`, `sex`, `sex_ontology_term_id`, `tissue`, `tissue_harmonised`, `tissue_ontology_term_id`, `disease`, `disease_ontology_term_id`, `is_primary_data.x`
+`sample_`, `sample_name`, `age_days`, `assay`, `assay_ontology_term_id`, `development_stage`, `development_stage_ontology_term_id`, `ethnicity`, `ethnicity_ontology_term_id`, `experiment___`, `organism`, `organism_ontology_term_id`, `sample_placeholder`, `sex`, `sex_ontology_term_id`, `tissue`, `tissue_harmonised`, `tissue_ontology_term_id`, `disease`, `disease_ontology_term_id`, `is_primary_data.x`
 
 Cell-specific columns (definitions available at cellxgene.cziscience.com)
 
-`.cell`, `cell_type`, `cell_type_ontology_term_idm`, `cell_type_harmonised`, `confidence_class`, `cell_annotation_azimuth_l2`, `cell_annotation_blueprint_singler` 
+`cell_`, `cell_type`, `cell_type_ontology_term_idm`, `cell_type_harmonised`, `confidence_class`, `cell_annotation_azimuth_l2`, `cell_annotation_blueprint_singler` 
 
 Through harmonisation and curation we introduced custom column, not present in the original CELLxGENE metadata
 
@@ -276,8 +276,8 @@ Through harmonisation and curation we introduced custom column, not present in t
 - `cell_annotation_blueprint_monaco`: SingleR cell annotation using Monaco reference
 - `sample_id_db`: Sample subdivision for internal use
 - `file_id_db`: File subdivision for internal use
-- `.sample`: Sample ID
-- `.sample_name`: How samples were defined
+- `sample_`: Sample ID
+- `sample_name`: How samples were defined
 
 # RNA abundance
 

README.md

@@ -82,6 +82,7 @@ get_metadata() |>
 #>  8 heart right ventricle          16
 #>  9 left cardiac atrium             7
 #> 10 interventricular septum        16
+
 #> # … with more rows
 ```
 
@@ -273,9 +274,8 @@ cellxgene.cziscience.com)
 Sample-specific columns (definitions available at
 cellxgene.cziscience.com)
 
-`.sample`, `.sample_name`, `age_days`, `assay`,
-`assay_ontology_term_id`, `development_stage`,
-`development_stage_ontology_term_id`, `ethnicity`,
+`sample_`, `sample_name`, `age_days`, `assay`, `assay_ontology_term_id`,
+`development_stage`, `development_stage_ontology_term_id`, `ethnicity`,
 `ethnicity_ontology_term_id`, `experiment___`, `organism`,
 `organism_ontology_term_id`, `sample_placeholder`, `sex`,
 `sex_ontology_term_id`, `tissue`, `tissue_harmonised`,
@@ -285,7 +285,7 @@ cellxgene.cziscience.com)
 Cell-specific columns (definitions available at
 cellxgene.cziscience.com)
 
-`.cell`, `cell_type`, `cell_type_ontology_term_idm`,
+`cell_`, `cell_type`, `cell_type_ontology_term_idm`,
 `cell_type_harmonised`, `confidence_class`,
 `cell_annotation_azimuth_l2`, `cell_annotation_blueprint_singler`
 
@@ -307,8 +307,8 @@ present in the original CELLxGENE metadata
   Monaco reference
 - `sample_id_db`: Sample subdivision for internal use
 - `file_id_db`: File subdivision for internal use
-- `.sample`: Sample ID
-- `.sample_name`: How samples were defined
+- `sample_`: Sample ID
+- `sample_name`: How samples were defined
 
 # RNA abundance
 

man/get_metadata.Rd

@@ -2,7 +2,7 @@ library(CuratedAtlasQueryR)
 
 test_that("get_SingleCellExperiment() correctly handles duplicate cell IDs", {
     meta <- get_metadata() |>
-        dplyr::filter(`_cell` == "868417_1") |>
+        dplyr::filter(cell_ == "868417_1") |>
         dplyr::collect()
     sce <- get_SingleCellExperiment(meta)
     # This query should return multiple cells, despite querying only 1 cell ID

tests/testthat/test-query.R

@@ -279,11 +279,11 @@ Dataset-specific columns (definitions available at cellxgene.cziscience.com)
 
 Sample-specific columns (definitions available at cellxgene.cziscience.com)
 
-`.sample`, `.sample_name`, `age_days`, `assay`, `assay_ontology_term_id`, `development_stage`, `development_stage_ontology_term_id`, `ethnicity`, `ethnicity_ontology_term_id`, `experiment___`, `organism`, `organism_ontology_term_id`, `sample_placeholder`, `sex`, `sex_ontology_term_id`, `tissue`, `tissue_harmonised`, `tissue_ontology_term_id`, `disease`, `disease_ontology_term_id`, `is_primary_data.x`
+`sample_`, `sample_name`, `age_days`, `assay`, `assay_ontology_term_id`, `development_stage`, `development_stage_ontology_term_id`, `ethnicity`, `ethnicity_ontology_term_id`, `experiment___`, `organism`, `organism_ontology_term_id`, `sample_placeholder`, `sex`, `sex_ontology_term_id`, `tissue`, `tissue_harmonised`, `tissue_ontology_term_id`, `disease`, `disease_ontology_term_id`, `is_primary_data.x`
 
 Cell-specific columns (definitions available at cellxgene.cziscience.com)
 
-`.cell`, `cell_type`, `cell_type_ontology_term_idm`, `cell_type_harmonised`, `confidence_class`, `cell_annotation_azimuth_l2`, `cell_annotation_blueprint_singler` 
+`cell_`, `cell_type`, `cell_type_ontology_term_idm`, `cell_type_harmonised`, `confidence_class`, `cell_annotation_azimuth_l2`, `cell_annotation_blueprint_singler` 
 
 Through harmonisation and curation we introduced custom column, not present in the original CELLxGENE metadata
 
@@ -296,7 +296,7 @@ Through harmonisation and curation we introduced custom column, not present in t
 - `cell_annotation_blueprint_monaco`: SingleR cell annotation using Monaco reference
 - `sample_id_db`: Sample subdivision for internal use
 - `file_id_db`: File subdivision for internal use
-- `.sample`: Sample ID
+- `sample_`: Sample ID
 - `.sample_name`: How samples were defined
 
 # RNA abundance