Garfield.preprocessing.preprocessing_rna

Garfield.preprocessing.preprocessing_rna(adata: AnnData, min_features: int = 600, min_cells: int = 3, target_sum: int = 10000, used_hvgs: bool = True, used_pca_graph: bool = True, rna_n_top_features=2000, n_components: int = 50, n: int = 15, batch_key: str = 'batch', metric: str = 'euclidean', svd_solver: str = 'arpack', keep_mt: bool = False, backed: bool = False)[source]

Preprocessing single-cell RNA-seq data

Parameters:

  • adata – An AnnData matrice of shape n_obs x n_vars. Rows correspond to cells and columns to genes.

  • min_features – Filtered out cells that are detected in less than n genes. Default: 600.

  • min_cells – Filtered out genes that are detected in less than n cells. Default: 3.

  • target_sum – After normalization, each cell has a total count equal to target_sum. If None, total count of each cell equal to the median of total counts for cells before normalization.

  • rna_n_top_features – Number of highly-variable genes to keep. Default: 2000.

Return type:

The AnnData object after preprocessing.