Duplicated file id

[stemangiola]

obs_enriched <- get_metadata() |>
  keep_quality_cells() |>

  # Pre-join filters (metadata columns only; keeps the census join small)
  filter(
    age_days >= 1 * 365,
    dataset_id == "01ad3cd7-3929-4654-84c0-6db05bd5fd59") |>

  join_census_table() |>

  # Post-join filters (census columns)
  filter(
    tissue == "blood",
    feature_count >= 3000)

obs_enriched |> get_pseudobulk(as_SummarizedExperiment = TRUE) |> colnames() |> table() |> sort()

there are duplicated colnames

this is due to file id

se = obs_enriched |> get_pseudobulk(as_SummarizedExperiment = TRUE)

> colData(se[,colnames(se)=="fbdb2809a4eafeb6a027316dc63384ee___t cd4"])$file_id_cellNexus_pseudobulk
[1] "0df584f4d948aeae6c0334f2a4009407___1.h5ad"
[2] "0df584f4d948aeae6c0334f2a4009407___2.h5ad"