def test_pbmc():
pbmc_dataset = PbmcDataset(save_path='tests/data/')
purified_pbmc_dataset = PurifiedPBMCDataset(save_path='tests/data/') # all cells
purified_t_cells = PurifiedPBMCDataset(save_path='tests/data/', filter_cell_types=range(6)) # only t-cells
base_benchmark(pbmc_dataset)
assert len(purified_t_cells.cell_types) == 6
assert len(purified_pbmc_dataset.cell_types) == 10
def test_populate(self):
dataset = PbmcDataset(
save_path="tests/data/",
save_path_10X="tests/data/10X",
remove_extracted_data=True,
)
unsupervised_training_one_epoch(dataset)
def load_datasets(dataset_name, save_path='data/', url=None):
if dataset_name == 'synthetic':
gene_dataset = SyntheticDataset()
elif dataset_name == 'cortex':
gene_dataset = CortexDataset()
elif dataset_name == 'brain_large':
gene_dataset = BrainLargeDataset(save_path=save_path)
elif dataset_name == 'retina':
gene_dataset = RetinaDataset(save_path=save_path)
elif dataset_name == 'cbmc':
gene_dataset = CbmcDataset(save_path=save_path)
elif dataset_name == 'brain_small':
gene_dataset = BrainSmallDataset(save_path=save_path)
elif dataset_name == 'hemato':
gene_dataset = HematoDataset(save_path='data/HEMATO/')
elif dataset_name == 'pbmc':
gene_dataset = PbmcDataset(save_path=save_path)
elif dataset_name[-5:] == ".loom":
gene_dataset = LoomDataset(filename=dataset_name,
save_path=save_path,
url=url)
elif dataset_name[-5:] == ".h5ad":
gene_dataset = AnnDataset(dataset_name, save_path=save_path, url=url)
elif ".csv" in dataset_name:
gene_dataset = CsvDataset(dataset_name, save_path=save_path)
else:
raise "No such dataset available"
return gene_dataset
def load_datasets(dataset_name, save_path="data/", url=None):
if dataset_name == "synthetic":
gene_dataset = SyntheticDataset()
elif dataset_name == "cortex":
gene_dataset = CortexDataset()
elif dataset_name == "brain_large":
gene_dataset = BrainLargeDataset(save_path=save_path)
elif dataset_name == "retina":
gene_dataset = RetinaDataset(save_path=save_path)
elif dataset_name == "cbmc":
gene_dataset = CbmcDataset(save_path=save_path)
elif dataset_name == "brain_small":
gene_dataset = BrainSmallDataset(save_path=save_path)
elif dataset_name == "hemato":
gene_dataset = HematoDataset(save_path="data/HEMATO/")
elif dataset_name == "pbmc":
gene_dataset = PbmcDataset(save_path=save_path)
elif dataset_name[-5:] == ".loom":
gene_dataset = LoomDataset(filename=dataset_name, save_path=save_path, url=url)
elif dataset_name[-5:] == ".h5ad":
gene_dataset = AnnDataset(dataset_name, save_path=save_path, url=url)
elif ".csv" in dataset_name:
gene_dataset = CsvDataset(dataset_name, save_path=save_path)
else:
raise Exception("No such dataset available")
return gene_dataset
benchmark_stvae,
benchmark_scvi,
benchmark_scgen,
benchmark_trvae
)
FRAMEWORKS = (
'stvae',
'scvi',
'scgen',
'trvae'
)
#EPOCHS = (600, 100, 100, 300)
EPOCHS = (1, 1, 1, 1)
datasets = {
'scvi_pbmc': PbmcDataset(),
'bermuda_pbmc': CsvDataset(
str(DIRPATH / './pbmc/expression.csv'),
labels_file = str(DIRPATH / './pbmc/labels.csv'),
batch_ids_file = str(DIRPATH / './pbmc/batches.csv'),
gene_by_cell = False
),
'mouse': CsvDataset(
str(DIRPATH / './mouse_genes/ST1 - original_expression.csv'),
labels_file = str(DIRPATH / './mouse_genes/labels.csv'),
batch_ids_file = str(DIRPATH / './mouse_genes/batches.csv'),
gene_by_cell = False
),
#'pancreas': BermudaDataset('./pancreas/muraro_seurat.csv'),
'retina': RetinaDataset(),
'starmap': PreFrontalCortexStarmapDataset(),
def test_pbmc():
pbmc_dataset = PbmcDataset(save_path='tests/data/')
base_benchmark(pbmc_dataset)
