scvi.dataset Package


AnnDatasetFromAnnData(ad[, batch_label, …])

Forms a GeneExpressionDataset from a anndata.AnnData object.

DownloadableAnnDataset([filename, …])

Forms a DownloadableDataset from a .h5ad file using the anndata package.

BrainLargeDataset([filename, save_path, …])

Loads brain-large dataset.

CiteSeqDataset([name, save_path, …])

Allows to form 3 different CiteSeq datasets.

CbmcDataset([save_path, delayed_populating])

Loads cbmc dataset.

CellMeasurement(name, data, …)

CortexDataset([save_path, genes_to_keep, …])

Loads cortex dataset.

CsvDataset(filename[, save_path, url, …])

Loads a .csv file.

BreastCancerDataset([save_path, …])

MouseOBDataset([save_path, delayed_populating])


Generic class representing RNA counts and annotation information.

DownloadableDataset([urls, filenames, …])

Sub-class of GeneExpressionDataset which downloads its data to disk and then populates its attributes with it.

Dataset10X([dataset_name, filename, …])

Loads a file from 10x website.

BrainSmallDataset([save_path, …])

This dataset consists in 9,128 mouse brain cells profiled using 10x Genomics.

HematoDataset([save_path, delayed_populating])

Loads the hemato dataset.

LoomDataset(filename[, save_path, url, …])

Loads a potentially remote .loom file.

RetinaDataset([save_path, delayed_populating])

Loads retina dataset.

FrontalCortexDropseqDataset([save_path, …])

“Load the cells from the mouse frontal cortex sequenced by the Dropseq technology (Saunders et al., 2018)

PreFrontalCortexStarmapDataset([save_path, …])

Loads a starMAP dataset of 3,704 cells and 166 genes from the mouse pre-frontal cortex (Wang et al., 2018)

PbmcDataset([save_path, save_path_10X, …])

Loads pbmc dataset.

PurifiedPBMCDataset([save_path, …])

Purified PBMC dataset from: “Massively parallel digital transcriptional profiling of single cells”.

SeqfishDataset([save_path, delayed_populating])

SeqFishPlusDataset([tissue_region, …])

seqFISH+ can image mRNAs for 10,000 genes in single cells—with high accuracy and sub-diffraction-limit resolution—in the cortex, subventricular zone and olfactory bulb of mouse brain

SmfishDataset([save_path, …])

Loads osmFISH data of mouse cortex cells from the Linarsson lab.

SyntheticDataset([batch_size, nb_genes, …])

SyntheticRandomDataset([mu, theta, dropout, …])

SyntheticDatasetCorr([n_cells_cluster, …])

ZISyntheticDatasetCorr([dropout_coef_high, …])