def test_sparse_no_batch_correction(self):
for flavor in ["seurat", "cell_ranger"]:
dataset = BrainLargeDataset(
save_path="tests/data",
sample_size_gene_var=10,
nb_genes_to_keep=128,
max_cells_to_keep=256,
)
n_genes = dataset.nb_genes
n_top = n_genes // 2
dataset.subsample_genes(mode=flavor, new_n_genes=n_top, n_bins=3)
assert dataset.nb_genes < n_genes
# For some reason the new number of genes can be slightly different than n_top
dataset.highly_variable_genes(flavor=flavor, n_bins=3)
dataset = BrainLargeDataset(
save_path="tests/data",
sample_size_gene_var=10,
nb_genes_to_keep=128,
max_cells_to_keep=256,
)
n_genes = dataset.nb_genes
dataset.subsample_genes()
assert dataset.nb_genes < n_genes, "subsample_genes did not filter out genes"
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
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 test_populate(self):
dataset = BrainLargeDataset(
save_path="tests/data",
sample_size_gene_var=10,
nb_genes_to_keep=10,
max_cells_to_keep=128,
)
unsupervised_training_one_epoch(dataset)
def test_brain_large():
brain_large_dataset = BrainLargeDataset(subsample_size=128, save_path='tests/data/')
base_benchmark(brain_large_dataset)