Add donor id metadata

DESCRIPTION

@@ -1,7 +1,7 @@
 Type: Package
 Package: cellNexus
 Title: Queries the Human Cell Atlas
-Version: 0.99.30
+Version: 0.99.31
 Authors@R: c(
     person(
         "Stefano",

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_v2.3.1.parquet",
+  cellnexus_output = "sample_hca2024_v2.3.2.parquet",
   census_version = "2024-07-01"
 ) {
   census_metadata <- get_census_metadata(census_version)

R/metadata.R

@@ -14,8 +14,8 @@ cache <- rlang::env(
 #' @keywords internal
 #' @noRd
 metadata_aliases <- c(
-  hca_2024 = "hca2024_v2.3.1.parquet",
-  hca_2025 = "hca2025_v0.1.0.parquet"
+  hca_2024 = "hca2024_v2.3.2.parquet",
+  hca_2025 = "hca2025_v0.1.1.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_v2.3.1.parquet"
+    "cellNexus-metadata/sample_hca2024_v2.3.2.parquet"
   )
 )
 
@@ -127,9 +127,8 @@ SAMPLE_DATABASE_URL <- c(
 #'
 #' Through harmonisation and curation we introduced custom columns not present
 #' in the original CELLxGENE metadata:
-#'
-#' `cell_count`: Number of cells in a dataset.
-#' `feature_count`: Number of genes in a dataset.
+#' 
+#' `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).
@@ -138,9 +137,15 @@ SAMPLE_DATABASE_URL <- c(
 #' `cell_type_unified_ensemble`: Consensus immune identity from Azimuth and SingleR (Blueprint, Monaco).
 #' `cell_annotation_azimuth_l2`: Azimuth cell annotation.
 #' `cell_annotation_blueprint_singler`: SingleR annotation (Blueprint).
-#' `cell_annotation_blueprint_monaco`: SingleR annotation (Monaco).
-#' `is_immune`: Whether a cell is an immune cell.
-#' `sample_heuristic`: Internal sample subdivision helper.
+#' `cell_annotation_monaco_singler`: SingleR annotation (Monaco).
+#' `subsets_Mito_percent`: Percent of each cell’s total counts coming from mitochondrial genes in a sample.
+#' `subsets_Ribo_percent`: Percent of each cell’s total counts coming from ribosomal genes in a sample.
+#' `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.
+#' `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.
 #' `file_id_cellNexus_pseudobulk`: Internal file id for pseudobulk layers.
 #' `sample_id`: Harmonised sample identifier.

index.md

@@ -69,8 +69,7 @@ Through harmonisation and curation, `cellNexus` adds columns that are not presen
 | `observation_joinid` | Cell ID join key linking metadata. |
 | `dataset_id` | Primary dataset identifier in the atlas. |
 | `sample_id` | Harmonised sample identifier. |
-| `sample_` | Internal sample subdivision helper. |
-| `sample_heuristic` | Internal sample subdivision helper. |
+| `donor_id` | Donor identifier. |
 | `age_days` | Donor age in days. |
 | `tissue_groups` | Coarse tissue grouping for analysis. |
 | `nFeature_expressed_in_sample` | Number of expressed features per cell. |
@@ -83,9 +82,6 @@ Through harmonisation and curation, `cellNexus` adds columns that are not presen
 | `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. |
 | `scDblFinder.class` | Quality-control flag for doublet classification from `scDblFinder`. |
-| `sample_chunk ` | Internal sample subdivision chunks. |
-| `cell_chunk ` | Internal cell subdivision chunks. |
-| `sample_pseudobulk_chunk ` | Internal pseudobulk subdivision chunks. |
 | `file_id_cellNexus_single_cell` | Internal file id for single-cell layers. |
 | `file_id_cellNexus_pseudobulk` | Internal file id for pseudobulk layers. |
 | `count_upper_bound` | Count capping threshold used in transformation. |

inst/NEWS.Rd

@@ -1,6 +1,17 @@
 \name{NEWS}
 \title{News for Package \pkg{cellNexus}}
 
+\section{News in version 0.99.31}{
+\itemize{
+    \item Added \code{donor_id} to harmonised metadata, enabling direct donor-level
+    queries across datasets.
+    \item Updated metadata parquet versions to \code{hca2024_v2.3.2}
+    \item Expanded and corrected documentation for metadata columns on website.
+    \item Removed internal columns (\code{sample_},
+    \code{sample_heuristic}, \code{sample_chunk}, \code{cell_chunk}, 
+    \code{sample_pseudobulk_chunk}) from documentation.
+}}
+
 \section{News in version 0.99.30}{
 \itemize{
     \item \code{get_seurat()} now correctly handles multiple assays and non-default