Update metadata

DESCRIPTION

@@ -1,7 +1,7 @@
 Type: Package
 Package: cellNexus
 Title: Queries the Human Cell Atlas
-Version: 0.99.34
+Version: 0.99.35
 Authors@R: c(
     person(
         "Stefano",

R/data.R

@@ -60,7 +60,6 @@
 #'   \item{self_reported_ethnicity}{Character vector of ethnicity labels}
 #'   \item{sex}{Character vector of sex labels}
 #'   \item{tissue}{Character vector of tissue types}
-#'   \item{tissue_groups}{Character vector of tissue group labels}
 #' }
 #'
 #' @source Generated from cellNexus metadata

R/dev.R

@@ -240,7 +240,7 @@ hdf5_to_anndata <- function(input_directory, output_directory) {
 #' @param census_version Character scalar. Census LTS release in date format.
 #' @return NULL
 downsample_metadata <- function(
-  cellnexus_output = "sample_hca2024_v2.3.2.parquet",
+  cellnexus_output = "sample_hca2024_v2.4.0.parquet",
   census_version = "2024-07-01"
 ) {
   census_metadata <- get_census_metadata(census_version)

R/interface_app.R

@@ -185,8 +185,7 @@ create_interface_app <- function(ui_choices, return_as_list = FALSE) {
     "self_reported_ethnicity",
     "sex",
     # "age_days",
-    "tissue",
-    "tissue_groups"
+    "tissue"
   )
 
   # Extract sample choices from pre-computed choices

R/metadata.R

@@ -14,8 +14,8 @@ cache <- rlang::env(
 #' @keywords internal
 #' @noRd
 metadata_aliases <- c(
-  hca_2024 = "hca2024_v2.3.2.parquet",
-  hca_2025 = "hca2025_v0.1.1.parquet"
+  hca_2024 = "hca2024_v2.4.0.parquet",
+  hca_2025 = "hca2025_v0.2.0.parquet"
 )
 
 #' Returns the URLs for all metadata files
@@ -62,7 +62,7 @@ get_metadata_url <- function(databases = c("hca_2024")) {
 SAMPLE_DATABASE_URL <- c(
   paste0(
     "https://object-store.rc.nectar.org.au/v1/AUTH_06d6e008e3e642da99d806ba3ea629c5/",
-    "cellNexus-metadata/sample_hca2024_v2.3.2.parquet"
+    "cellNexus-metadata/sample_hca2024_v2.4.0.parquet"
   )
 )
 
@@ -96,7 +96,6 @@ SAMPLE_DATABASE_URL <- c(
 #' filtered_metadata <- get_metadata(cloud_metadata = SAMPLE_DATABASE_URL) |>
 #'   filter(
 #'     imputed_ethnicity == "African" &
-#'       tissue_groups == "breast" &
 #'       cell_type_unified_ensemble %LIKE% "%cd14%"
 #'   )
 #'
@@ -130,7 +129,6 @@ SAMPLE_DATABASE_URL <- c(
 #'
 #' `sample_id`: Sample identifier.
 #' `age_days`: Donor age in days.
-#' `tissue_groups`: Coarse tissue grouping for analysis.
 #' `empty_droplet`: Whether a cell is called an empty droplet from expressed-gene count per sample (default threshold 200; targeted panels may differ).
 #' `alive`: Whether a cell passes viability / mitochondrial QC.
 #' `scDblFinder.class`: Doublet, singlet, or unknown (`scDblFinder` default parameters).
@@ -143,7 +141,7 @@ SAMPLE_DATABASE_URL <- c(
 #' `high_mitochondrion`: TRUE if the cell’s mitochondrial percent exceeds the QC cutoff.
 #' `high_ribosome`: TRUE if the cell’s ribosomal percent exceeds the QC cutoff.
 #' `count_upper_bound`: Count capping threshold used in counts transformation.
-#' `inverse_transform`: Transformation method used in pre-processing pipeline.
+#' `inversed_inferred_distribution`: Transformation method used in pre-processing pipeline.
 #' `nfeature_expressed_thresh`: Threshold of the number of expressed features per cell.
 #' `is_immune`: Curated logical flag for immune-cell context.
 #' `file_id_cellNexus_single_cell`: Internal file id for single-cell layers.

R/utils.R

@@ -476,7 +476,9 @@ duplicate_single_column_assay <- function(sce) {
 #' @param doublet_col A string specifying the column name
 #'   that indicates doublets (default: `"scDblFinder.class"`).
 #'   Expected character vector: `"doublet"` and/or `"singlet"` and/or `"unknown"`.
-#'
+#' @param nfeature_col Column containing the number of detected features per dataset
+#' @param min_features Minimum number of detected features required.
+#' 
 #' @return A filtered data frame containing only cells that pass all QC checks.
 #' @examples
 #' get_metadata(cloud_metadata = SAMPLE_DATABASE_URL, cache_directory = tempdir()) |>
@@ -489,12 +491,15 @@ duplicate_single_column_assay <- function(sce) {
 keep_quality_cells <- function(data,
                                empty_droplet_col = "empty_droplet",
                                alive_col = "alive",
-                               doublet_col = "scDblFinder.class") {
+                               doublet_col = "scDblFinder.class",
+                               nfeature_col = "feature_count",
+                               min_features = 5000L) {
   data |>
     filter(
       !.data[[empty_droplet_col]],
       .data[[alive_col]],
-      .data[[doublet_col]] != "doublet"
+      .data[[doublet_col]] != "doublet",
+      .data[[nfeature_col]] >= min_features
     )
 }
 

R/zzz.R

@@ -20,7 +20,7 @@
 #' \preformatted{
 #' filtered_metadata <- metadata |>
 #'     dplyr::filter(
-#'         tissue_groups == "blood" &
+#'         imputed_ethnicity == "African" &
 #'         cell_type_unified_ensemble \%LIKE\% "\%cd4\%"
 #'     )
 #'