terra.harmonize_adata

terra.harmonize_adata#

terra.harmonize_adata(adata, gene_mapping_dict_file_path=None, gene_occurrence_count_file_path=None, gene_occurrence_count_filter_value=10, ensembl_release=111, species='human', min_genes_per_cell=10, min_cells_per_gene=10)#

Harmonize an AnnData object prior to tokenization.

Parameters:

  • adata (AnnData) – An unharmonized AnnData object.

  • gene_mapping_dict_file_path (Optional[str] (default: None)) – Path to a pickled gene-name-to-ensembl-ID mapping dictionary. If None, ensembl IDs are looked up from the specified Ensembl release instead.

  • gene_occurrence_count_file_path (Optional[str] (default: None)) – Path to a pickled dictionary of per-gene pretraining occurrence counts. If provided, genes with too few occurrences are filtered out; if None, this filtering step is skipped.

  • gene_occurrence_count_filter_value (int (default: 10)) – Minimum number of pretraining occurrences a gene must have to be kept.

  • ensembl_release (int (default: 111)) – Ensembl release used to retrieve ensembl IDs.

  • species (str (default: 'human')) – Species passed to the Ensembl release lookup.

  • min_genes_per_cell (int (default: 10)) – Minimum amount of genes per cell for a cell not to be filtered.

  • min_cells_per_gene (int (default: 10)) – Minimum number of cells a gene must be expressed in for the gene not to be filtered.

Returns:

  • adata (AnnData) – A harmonized AnnData object.

Contents