BrainLargeDataset¶
-
class
scvi.dataset.
BrainLargeDataset
(filename=None, save_path='data/', sample_size_gene_var=10000, max_cells_to_keep=None, nb_genes_to_keep=720, loading_batch_size=100000, delayed_populating=False)[source]¶ Bases:
scvi.dataset.dataset.DownloadableDataset
Loads brain-large dataset.
This dataset contains 1.3 million brain cells from 10x Genomics. We randomly shuffle the data to get a 1M subset of cells and order genes by variance to retain first 10,000 and then 720 sampled variable genes. This dataset is then sampled multiple times in cells for the runtime and goodness-of-fit analysis. We report imputation scores on the 10k cells and 720 genes samples only.
- Parameters
filename (
str
,None
Optional
[str
]) – File name to use when saving/loading the data.save_path (
str
str
) – Location to use when saving/loading the data.sample_size_gene_var (
int
int
) – Number of cells to use to estimate gene variances.max_cells_to_keep (
int
,None
Optional
[int
]) – Maximum number of cells to keep.nb_genes_to_keep (
int
int
) – Number of genes to keep, ordered by decreasing variance.loading_batch_size (
int
int
) – Number of cells to use for each chunk loaded.delayed_populating (
bool
bool
) – Switch for delayed populating mechanism.
Examples
>>> gene_dataset = BrainLargeDataset()
Methods Summary
populate
()Populates a
DonwloadableDataset
object’s data attributes.Methods Documentation