def _load_seqfishplus(
save_path: str = "data/",
tissue_region: str = "subventricular cortex",
run_setup_anndata: bool = True,
) -> anndata.AnnData:
if tissue_region == "subventricular cortex":
file_prefix = "cortex_svz"
elif tissue_region == "olfactory bulb":
file_prefix = "ob"
else:
raise ValueError(
'`tissue_type` must be "subventricular cortex" or "olfactory bulb", but got {}'.format(
tissue_region
)
)
save_path = os.path.abspath(save_path)
url = "https://github.com/CaiGroup/seqFISH-PLUS/raw/master/sourcedata.zip"
save_fn = "seqfishplus.zip"
_download(url, save_path, save_fn)
adata = _load_seqfishplus_data(
os.path.join(save_path, save_fn), file_prefix, save_path, gene_by_cell=False
)
adata.obs["batch"] = np.zeros(adata.shape[0], dtype=np.int64)
adata.obs["labels"] = np.zeros(adata.shape[0], dtype=np.int64)
if run_setup_anndata:
_setup_anndata(adata, batch_key="batch", labels_key="labels")
return adata
def test_extra_covariates_transfer():
adata = synthetic_iid()
adata.obs["cont1"] = np.random.normal(size=(adata.shape[0], ))
adata.obs["cont2"] = np.random.normal(size=(adata.shape[0], ))
adata.obs["cat1"] = np.random.randint(0, 5, size=(adata.shape[0], ))
adata.obs["cat2"] = np.random.randint(0, 5, size=(adata.shape[0], ))
_setup_anndata(
adata,
batch_key="batch",
labels_key="labels",
protein_expression_obsm_key="protein_expression",
protein_names_uns_key="protein_names",
continuous_covariate_keys=["cont1", "cont2"],
categorical_covariate_keys=["cat1", "cat2"],
)
bdata = synthetic_iid()
bdata.obs["cont1"] = np.random.normal(size=(bdata.shape[0], ))
bdata.obs["cont2"] = np.random.normal(size=(bdata.shape[0], ))
bdata.obs["cat1"] = 0
bdata.obs["cat2"] = 1
transfer_anndata_setup(adata_source=adata, adata_target=bdata)
# give it a new category
del bdata.uns["_scvi"]
bdata.obs["cat1"] = 6
transfer_anndata_setup(adata_source=adata,
adata_target=bdata,
extend_categories=True)
assert bdata.uns["_scvi"]["extra_categoricals"]["mappings"]["cat1"][
-1] == 6
def _load_annotation_simulation(name: str,
save_path: str = "data/",
run_setup_anndata: bool = True) -> AnnData:
"""\
Simulated datasets for scANVI tutorials
name
One of "1", "2", or "3"
"""
save_path = os.path.abspath(save_path)
url = "https://github.com/YosefLab/scVI-data/raw/master/simulation/simulation_{}.loom".format(
name)
save_fn = "simulation_{}.loom".format(name)
_download(url, save_path, save_fn)
adata = _load_loom(os.path.join(save_path, save_fn))
adata.obs["labels"] = adata.obs.ClusterID.values
del adata.obs["ClusterID"]
adata.obs["batch"] = adata.obs.BatchID.values
del adata.obs["BatchID"]
if run_setup_anndata:
_setup_anndata(adata, batch_key="batch", labels_key="labels")
return adata
def test_brain_small(save_path):
sp = os.path.join(save_path, "10X")
dataset = dataset_10x(
dataset_name="neuron_9k",
save_path=sp,
remove_extracted_data=True,
)
_setup_anndata(dataset)
unsupervised_training_one_epoch(dataset)
def test_populate_and_train_one_v1(save_path):
sp = os.path.join(save_path, "10X")
dataset = dataset_10x(
dataset_name="cd4_t_helper",
remove_extracted_data=True,
save_path=sp,
)
_setup_anndata(dataset)
unsupervised_training_one_epoch(dataset)
def _load_cortex(save_path: str = "data/",
run_setup_anndata: bool = True) -> anndata.AnnData:
"""Loads cortex dataset."""
save_path = os.path.abspath(save_path)
url = "https://storage.googleapis.com/linnarsson-lab-www-blobs/blobs/cortex/expression_mRNA_17-Aug-2014.txt"
save_fn = "expression.bin"
_download(url, save_path, save_fn)
adata = _load_cortex_txt(os.path.join(save_path, save_fn))
if run_setup_anndata:
_setup_anndata(adata, labels_key="labels")
return adata
def test_pbmc_cite(save_path):
file_path = os.path.join(
save_path, "10X/pbmc_10k_protein_v3/filtered_feature_bc_matrix.tar.gz")
sp = os.path.join(save_path, "10X/pbmc_10k_protein_v3/")
tar = tarfile.open(file_path, "r:gz")
tar.extractall(path=sp)
tar.close()
dataset = sc.read_10x_mtx(os.path.join(sp, "filtered_feature_bc_matrix"),
gex_only=False)
organize_cite_seq_10x(dataset)
_setup_anndata(dataset, protein_expression_obsm_key="protein_expression")
unsupervised_training_one_epoch(dataset)
def _load_seqfish(
save_path: str = "data/", run_setup_anndata: bool = True
) -> anndata.AnnData:
save_path = os.path.abspath(save_path)
url = "https://www.cell.com/cms/attachment/2080562255/2072099886/mmc6.xlsx"
save_fn = "SeqFISH.xlsx"
_download(url, save_path, save_fn)
adata = _load_seqfish_data(os.path.join(save_path, save_fn))
adata.obs["batch"] = np.zeros(adata.shape[0], dtype=np.int64)
adata.obs["labels"] = np.zeros(adata.shape[0], dtype=np.int64)
if run_setup_anndata:
_setup_anndata(adata, batch_key="batch", labels_key="labels")
return adata
def test_view_anndata_setup(save_path):
adata = synthetic_iid(run_setup_anndata=False)
adata.obs["cont1"] = np.random.uniform(5, adata.n_obs)
adata.obs["cont2"] = np.random.uniform(5, adata.n_obs)
adata.obs["cont1"][
0] = 939543895847598301.423432423523512351234123421341234
adata.obs["cont2"][1] = 0.12938471298374691827634
adata.obs["cat1"] = np.random.randint(0, 5, adata.n_obs).astype(str)
adata.obs["cat1"][8] = "asdf"
adata.obs["cat1"][9] = "f34"
adata.obs["cat2"] = np.random.randint(0, 7, adata.n_obs)
_setup_anndata(
adata,
protein_expression_obsm_key="protein_expression",
batch_key="batch",
labels_key="labels",
categorical_covariate_keys=["cat1", "cat2"],
continuous_covariate_keys=["cont1", "cont2"],
)
# test it works with adata
view_anndata_setup(adata)
# test it works with scvi setup dict
view_anndata_setup(adata.uns["_scvi"])
adata = scvi.data.synthetic_iid()
m = scvi.model.SCVI(adata)
folder_path = os.path.join(save_path, "tmp")
m.save(folder_path, save_anndata=True)
# test it works with a saved model folder
view_anndata_setup(folder_path)
adata_path = os.path.join(folder_path, "adata.h5ad")
# test it works with the path to an anndata
view_anndata_setup(adata_path)
m = scvi.model.SCVI(adata)
m.save(folder_path, overwrite=True)
# test it works without saving the anndata
view_anndata_setup(folder_path)
# test it throws error if adata was not setup
with pytest.raises(ValueError):
adata = synthetic_iid(run_setup_anndata=False)
view_anndata_setup(adata)
# test it throws error if we dont pass dict, anndata or str in
with pytest.raises(ValueError):
view_anndata_setup(0)
def _load_heart_cell_atlas_subsampled(
save_path: str = "data/",
run_setup_anndata: bool = True,
remove_nuisance_clusters: bool = True,
):
"""
Combined single cell and single nuclei RNA-Seq data of 485K cardiac cells with annotations.
Dataset was filtered down randomly to 20k cells using :func:`~scanpy.pp.subsample`. The original
data can be sourced from https://www.heartcellatlas.org/#DataSources.
Parameters
----------
save_path
Location to use when saving/loading the data.
run_setup_anndata
If true, runs setup_anndata() on dataset before returning
remove_nuisance_clusters
Remove doublets and unsassigned cells
Returns
-------
AnnData
Notes
-----
The data were filtered using the following sequence::
>>> adata = anndata.read_h5ad(path_to_anndata)
>>> bdata = sc.pp.subsample(adata, n_obs=20000, copy=True)
>>> sc.pp.filter_genes(bdata, min_counts=3)
>>> bdata.write_h5ad(path, compression="gzip")
"""
url = "https://github.com/YosefLab/scVI-data/blob/master/hca_subsampled_20k.h5ad?raw=true"
save_fn = "hca_subsampled_20k.h5ad"
_download(url, save_path, save_fn)
dataset = anndata.read_h5ad(os.path.join(save_path, save_fn))
if remove_nuisance_clusters:
remove = ["doublets", "NotAssigned"]
keep = [c not in remove for c in dataset.obs.cell_type.values]
dataset = dataset[keep, :].copy()
if run_setup_anndata:
_setup_anndata(
dataset,
)
return dataset
def _load_breast_cancer_dataset(save_path: str = "data/",
run_setup_anndata: bool = True):
save_path = os.path.abspath(save_path)
url = "http://www.spatialtranscriptomicsresearch.org/wp-content/uploads/2016/07/Layer2_BC_count_matrix-1.tsv"
save_fn = "Layer2_BC_count_matrix-1.tsv"
_download(url, save_path, save_fn)
adata = _load_csv(os.path.join(save_path, save_fn),
delimiter="\t",
gene_by_cell=False)
adata.obs["batch"] = np.zeros(adata.shape[0]).astype(int)
adata.obs["labels"] = np.zeros(adata.shape[0]).astype(int)
if run_setup_anndata:
_setup_anndata(adata, batch_key="batch", labels_key="labels")
return adata
def setup_anndata(
adata: AnnData,
batch_key: Optional[str] = None,
labels_key: Optional[str] = None,
layer: Optional[str] = None,
copy: bool = False,
) -> Optional[AnnData]:
"""
%(summary)s.
Parameters
----------
%(param_adata)s
%(param_batch_key)s
%(param_labels_key)s
%(param_layer)s
%(param_copy)s
Returns
-------
%(returns)s
"""
return _setup_anndata(
adata,
batch_key=batch_key,
labels_key=labels_key,
layer=layer,
copy=copy,
)
def _load_smfish(
save_path: str = "data/",
use_high_level_cluster: bool = True,
run_setup_anndata: bool = True,
) -> anndata.AnnData:
save_path = os.path.abspath(save_path)
url = "http://linnarssonlab.org/osmFISH/osmFISH_SScortex_mouse_all_cells.loom"
save_fn = "osmFISH_SScortex_mouse_all_cell.loom"
_download(url, save_path, save_fn)
adata = _load_smfish_data(
os.path.join(save_path, save_fn), use_high_level_cluster=use_high_level_cluster
)
adata.obs["batch"] = np.zeros(adata.shape[0], dtype=np.int64)
if run_setup_anndata:
_setup_anndata(adata, labels_key="labels", batch_key="batch")
return adata
def setup_anndata(
adata: AnnData,
batch_key: Optional[str] = None,
layer: Optional[str] = None,
categorical_covariate_keys: Optional[List[str]] = None,
continuous_covariate_keys: Optional[List[str]] = None,
copy: bool = False,
) -> Optional[AnnData]:
"""
%(summary)s.
Parameters
----------
%(param_adata)s
%(param_batch_key)s
%(param_layer)s
%(param_cat_cov_keys)s
%(param_cont_cov_keys)s
%(param_copy)s
Returns
-------
%(returns)s
"""
return _setup_anndata(
adata,
batch_key=batch_key,
layer=layer,
categorical_covariate_keys=categorical_covariate_keys,
continuous_covariate_keys=continuous_covariate_keys,
copy=copy,
)
def _load_retina(save_path: str = "data/",
run_setup_anndata: bool = True) -> AnnData:
"""\
Loads retina dataset
The dataset of bipolar cells contains after their original pipeline for filtering 27,499 cells and
13,166 genes coming from two batches. We use the cluster annotation from 15 cell-types from the author.
We also extract their normalized data with Combat and use it for benchmarking.
"""
save_path = os.path.abspath(save_path)
url = "https://github.com/YosefLab/scVI-data/raw/master/retina.loom"
save_fn = "retina.loom"
_download(url, save_path, save_fn)
adata = _load_loom(os.path.join(save_path, save_fn))
cell_types = [
"RBC",
"MG",
"BC5A",
"BC7",
"BC6",
"BC5C",
"BC1A",
"BC3B",
"BC1B",
"BC2",
"BC5D",
"BC3A",
"BC5B",
"BC4",
"BC8_9",
]
adata.obs["labels"] = [
cell_types[i]
for i in adata.obs["ClusterID"].values.astype(int).ravel()
]
del adata.obs["ClusterID"]
adata.obs["batch"] = pd.Categorical(adata.obs["BatchID"].values.copy())
del adata.obs["BatchID"]
if run_setup_anndata:
_setup_anndata(adata, batch_key="batch", labels_key="labels")
return adata
def _load_frontalcortex_dropseq(save_path: str = "data/",
run_setup_anndata: bool = True) -> AnnData:
save_path = os.path.abspath(save_path)
url = "https://github.com/YosefLab/scVI-data/raw/master/fc-dropseq.loom"
save_fn = "fc-dropseq.loom"
_download(url, save_path, save_fn)
adata = _load_loom(os.path.join(save_path, save_fn))
adata.obs["batch"] = adata.obs["Clusters"]
del adata.obs["Clusters"]
adata.obs["labels"] = np.zeros(adata.shape[0], dtype=np.int64)
# reorder labels such that layers of the cortex are in order
# order_labels = [5, 6, 3, 2, 4, 0, 1, 8, 7, 9, 10, 11, 12, 13]
# self.reorder_cell_types(self.cell_types[order_labels])
if run_setup_anndata:
_setup_anndata(adata, batch_key="batch", labels_key="labels")
return adata
def _generate_synthetic(
batch_size: int = 128,
n_genes: int = 100,
n_proteins: int = 100,
n_batches: int = 2,
n_labels: int = 3,
run_setup_anndata: bool = True,
) -> AnnData:
data = np.random.negative_binomial(5,
0.3,
size=(batch_size * n_batches, n_genes))
mask = np.random.binomial(n=1,
p=0.7,
size=(batch_size * n_batches, n_genes))
data = data * mask # We put the batch index first
labels = np.random.randint(0, n_labels, size=(batch_size * n_batches, ))
labels = np.array(["label_%d" % i for i in labels])
batch = []
for i in range(n_batches):
batch += ["batch_{}".format(i)] * batch_size
adata = AnnData(data)
adata.obs["batch"] = pd.Categorical(batch)
adata.obs["labels"] = pd.Categorical(labels)
# Protein measurements
p_data = np.random.negative_binomial(5,
0.3,
size=(adata.shape[0], n_proteins))
adata.obsm["protein_expression"] = p_data
adata.uns["protein_names"] = np.arange(n_proteins).astype(str)
if run_setup_anndata:
_setup_anndata(
adata,
batch_key="batch",
labels_key="labels",
protein_expression_obsm_key="protein_expression",
protein_names_uns_key="protein_names",
)
return adata
def test_saving(save_path):
save_path = os.path.join(save_path, "tmp_adata.h5ad")
adata = synthetic_iid(run_setup_anndata=False)
adata.obs["cont1"] = np.random.uniform(5, adata.n_obs)
adata.obs["cont2"] = np.random.uniform(5, adata.n_obs)
adata.obs["cat1"] = np.random.randint(0, 3, adata.n_obs).astype(str)
adata.obs["cat1"][1] = "asdf"
adata.obs["cat1"][2] = "f34"
adata.obs["cat2"] = np.random.randint(0, 7, adata.n_obs)
_setup_anndata(
adata,
protein_expression_obsm_key="protein_expression",
batch_key="batch",
labels_key="labels",
categorical_covariate_keys=["cat1", "cat2"],
continuous_covariate_keys=["cont1", "cont2"],
)
adata.write(save_path)
anndata.read(save_path)
def test_data_format():
# if data was dense np array, check after setup_anndata, data is C_CONTIGUOUS
adata = synthetic_iid(run_setup_anndata=False)
old_x = adata.X
old_pro = adata.obsm["protein_expression"]
old_obs = adata.obs
adata.X = np.asfortranarray(old_x)
adata.obsm["protein_expression"] = np.asfortranarray(old_pro)
assert adata.X.flags["C_CONTIGUOUS"] is False
assert adata.obsm["protein_expression"].flags["C_CONTIGUOUS"] is False
_setup_anndata(adata, protein_expression_obsm_key="protein_expression")
assert adata.X.flags["C_CONTIGUOUS"] is True
assert adata.obsm["protein_expression"].flags["C_CONTIGUOUS"] is True
assert np.array_equal(old_x, adata.X)
assert np.array_equal(old_pro, adata.obsm["protein_expression"])
assert np.array_equal(old_obs, adata.obs)
assert np.array_equal(adata.X, get_from_registry(adata, _CONSTANTS.X_KEY))
assert np.array_equal(
adata.obsm["protein_expression"],
get_from_registry(adata, _CONSTANTS.PROTEIN_EXP_KEY),
)
# if obsm is dataframe, make it C_CONTIGUOUS if it isnt
adata = synthetic_iid()
pe = np.asfortranarray(adata.obsm["protein_expression"])
adata.obsm["protein_expression"] = pd.DataFrame(pe, index=adata.obs_names)
assert adata.obsm["protein_expression"].to_numpy(
).flags["C_CONTIGUOUS"] is False
_setup_anndata(adata, protein_expression_obsm_key="protein_expression")
new_pe = get_from_registry(adata, "protein_expression")
assert new_pe.to_numpy().flags["C_CONTIGUOUS"] is True
assert np.array_equal(pe, new_pe)
assert np.array_equal(adata.X, get_from_registry(adata, _CONSTANTS.X_KEY))
assert np.array_equal(
adata.obsm["protein_expression"],
get_from_registry(adata, _CONSTANTS.PROTEIN_EXP_KEY),
)
def _load_prefrontalcortex_starmap(save_path: str = "data/",
run_setup_anndata: bool = True) -> AnnData:
"""\
Loads a starMAP dataset of 3,704 cells and 166 genes from the mouse pre-frontal cortex (Wang et al., 2018)
"""
save_path = os.path.abspath(save_path)
url = "https://github.com/YosefLab/scVI-data/raw/master/mpfc-starmap.loom"
save_fn = "mpfc-starmap.loom"
_download(url, save_path, save_fn)
adata = _load_loom(os.path.join(save_path, save_fn))
adata.obs["labels"] = adata.obs.Clusters.values
del adata.obs["Clusters"]
adata.obs["batch"] = adata.obs.BatchID.values
del adata.obs["BatchID"]
adata.obs["x_coord"] = adata.obsm["Spatial_coordinates"][:, 0]
adata.obs["y_coord"] = adata.obsm["Spatial_coordinates"][:, 1]
if run_setup_anndata:
_setup_anndata(adata, batch_key="batch", labels_key="labels")
return adata
def test_backed_anndata(save_path):
adata = scvi.data.synthetic_iid()
path = os.path.join(save_path, "test_data.h5ad")
adata.write_h5ad(path)
adata = anndata.read_h5ad(path, backed="r+")
_setup_anndata(adata, batch_key="batch")
# test get item
bd = AnnTorchDataset(adata)
bd[np.arange(adata.n_obs)]
# sparse
adata = scvi.data.synthetic_iid()
adata.X = csr_matrix(adata.X)
path = os.path.join(save_path, "test_data2.h5ad")
adata.write_h5ad(path)
adata = anndata.read_h5ad(path, backed="r+")
_setup_anndata(adata, batch_key="batch")
# test get item
bd = AnnTorchDataset(adata)
bd[np.arange(adata.n_obs)]
def _load_brainlarge_dataset(
save_path: str = "data/",
run_setup_anndata: bool = True,
sample_size_gene_var: int = 10000,
max_cells_to_keep: int = None,
n_genes_to_keep: int = 720,
loading_batch_size: int = 100000,
) -> anndata.AnnData:
"""Loads brain-large dataset."""
url = "http://cf.10xgenomics.com/samples/cell-exp/1.3.0/1M_neurons/1M_neurons_filtered_gene_bc_matrices_h5.h5"
save_fn = "brain_large.h5"
_download(url, save_path, save_fn)
adata = _load_brainlarge_file(
os.path.join(save_path, save_fn),
sample_size_gene_var=sample_size_gene_var,
max_cells_to_keep=max_cells_to_keep,
n_genes_to_keep=n_genes_to_keep,
loading_batch_size=loading_batch_size,
)
if run_setup_anndata:
_setup_anndata(adata, batch_key="batch", labels_key="labels")
return adata
def _load_purified_pbmc_dataset(
save_path: str = "data/",
subset_datasets: List[str] = None,
run_setup_anndata: bool = True,
) -> anndata.AnnData:
url = "https://github.com/YosefLab/scVI-data/raw/master/PurifiedPBMCDataset.h5ad"
save_fn = "PurifiedPBMCDataset.h5ad"
_download(url, save_path, save_fn)
path_to_file = os.path.join(save_path, save_fn)
adata = anndata.read(path_to_file)
dataset_names = [
"cd4_t_helper",
"regulatory_t",
"naive_t",
"memory_t",
"cytotoxic_t",
"naive_cytotoxic",
"b_cells",
"cd4_t_helper",
"cd34",
"cd56_nk",
"cd14_monocytes",
]
if subset_datasets is not None:
row_indices = []
for dataset in subset_datasets:
assert dataset in dataset_names
idx = np.where(adata.obs["cell_types"] == dataset)[0]
row_indices.append(idx)
row_indices = np.concatenate(row_indices)
adata = adata[row_indices].copy()
if run_setup_anndata:
_setup_anndata(adata, batch_key="batch", labels_key="labels")
return adata
def setup_anndata(
adata: AnnData,
size_factor_key: str,
batch_key: Optional[str] = None,
layer: Optional[str] = None,
categorical_covariate_keys: Optional[List[str]] = None,
continuous_covariate_keys: Optional[List[str]] = None,
copy: bool = False,
) -> Optional[AnnData]:
"""
%(summary)s.
Parameters
----------
%(param_adata)s
size_factor_key
key in `adata.obs` with continuous valued size factors.
%(param_batch_key)s
%(param_layer)s
%(param_cat_cov_keys)s
%(param_cat_cov_keys)s
%(param_copy)s
Returns
-------
%(returns)s
"""
setup_data = _setup_anndata(
adata,
batch_key=batch_key,
layer=layer,
categorical_covariate_keys=categorical_covariate_keys,
continuous_covariate_keys=continuous_covariate_keys,
copy=copy,
)
register_tensor_from_anndata(
adata if setup_data is None else setup_data,
"_size_factor",
"obs",
size_factor_key,
)
return setup_data
def setup_anndata(
adata: AnnData,
protein_expression_obsm_key: str,
protein_names_uns_key: Optional[str] = None,
batch_key: Optional[str] = None,
layer: Optional[str] = None,
categorical_covariate_keys: Optional[List[str]] = None,
continuous_covariate_keys: Optional[List[str]] = None,
copy: bool = False,
) -> Optional[AnnData]:
"""
%(summary)s.
Parameters
----------
%(param_adata)s
protein_expression_obsm_key
key in `adata.obsm` for protein expression data.
protein_names_uns_key
key in `adata.uns` for protein names. If None, will use the column names of `adata.obsm[protein_expression_obsm_key]`
if it is a DataFrame, else will assign sequential names to proteins.
%(param_batch_key)s
%(param_layer)s
%(param_cat_cov_keys)s
%(param_cont_cov_keys)s
%(param_copy)s
Returns
-------
%(returns)s
"""
return _setup_anndata(
adata,
batch_key=batch_key,
layer=layer,
protein_expression_obsm_key=protein_expression_obsm_key,
protein_names_uns_key=protein_names_uns_key,
categorical_covariate_keys=categorical_covariate_keys,
continuous_covariate_keys=continuous_covariate_keys,
copy=copy,
)
def test_setup_anndata():
# test regular setup
adata = synthetic_iid(run_setup_anndata=False)
_setup_anndata(
adata,
batch_key="batch",
labels_key="labels",
protein_expression_obsm_key="protein_expression",
protein_names_uns_key="protein_names",
)
np.testing.assert_array_equal(
get_from_registry(adata, "batch_indices"),
np.array(adata.obs["_scvi_batch"]).reshape((-1, 1)),
)
np.testing.assert_array_equal(
get_from_registry(adata, "labels"),
np.array(adata.obs["labels"].cat.codes).reshape((-1, 1)),
)
np.testing.assert_array_equal(get_from_registry(adata, "X"), adata.X)
np.testing.assert_array_equal(
get_from_registry(adata, "protein_expression"),
adata.obsm["protein_expression"],
)
np.testing.assert_array_equal(adata.uns["_scvi"]["protein_names"],
adata.uns["protein_names"])
# test that error is thrown if its a view:
adata = synthetic_iid()
with pytest.raises(ValueError):
_setup_anndata(adata[1])
# If obsm is a df and protein_names_uns_key is None, protein names should be grabbed from column of df
adata = synthetic_iid()
new_protein_names = np.array(random.sample(range(100), 100)).astype("str")
df = pd.DataFrame(
adata.obsm["protein_expression"],
index=adata.obs_names,
columns=new_protein_names,
)
adata.obsm["protein_expression"] = df
_setup_anndata(adata, protein_expression_obsm_key="protein_expression")
np.testing.assert_array_equal(adata.uns["_scvi"]["protein_names"],
new_protein_names)
# test that layer is working properly
adata = synthetic_iid()
true_x = adata.X
adata.layers["X"] = true_x
adata.X = np.ones_like(adata.X)
_setup_anndata(adata, layer="X")
np.testing.assert_array_equal(get_from_registry(adata, "X"), true_x)
# test that it creates layers and batch if no layers_key is passed
adata = synthetic_iid()
_setup_anndata(
adata,
protein_expression_obsm_key="protein_expression",
protein_names_uns_key="protein_names",
)
np.testing.assert_array_equal(get_from_registry(adata, "batch_indices"),
np.zeros((adata.shape[0], 1)))
np.testing.assert_array_equal(get_from_registry(adata, "labels"),
np.zeros((adata.shape[0], 1)))
def test_transfer_anndata_setup():
# test transfer_anndata function
adata1 = synthetic_iid(run_setup_anndata=False)
adata2 = synthetic_iid(run_setup_anndata=False)
adata2.X = adata1.X
_setup_anndata(adata1)
transfer_anndata_setup(adata1, adata2)
np.testing.assert_array_equal(adata1.obs["_scvi_labels"],
adata2.obs["_scvi_labels"])
# test if layer was used initially, again used in transfer setup
adata1 = synthetic_iid(run_setup_anndata=False)
adata2 = synthetic_iid(run_setup_anndata=False)
raw_counts = adata1.X.copy()
adata1.layers["raw"] = raw_counts
adata2.layers["raw"] = raw_counts
zeros = np.zeros_like(adata1.X)
ones = np.ones_like(adata1.X)
adata1.X = zeros
adata2.X = ones
_setup_anndata(adata1, layer="raw")
transfer_anndata_setup(adata1, adata2)
np.testing.assert_array_equal(adata1.obs["_scvi_labels"],
adata2.obs["_scvi_labels"])
# test that an unknown batch throws an error
adata1 = synthetic_iid()
adata2 = synthetic_iid(run_setup_anndata=False)
adata2.obs["batch"] = [2] * adata2.n_obs
with pytest.raises(ValueError):
transfer_anndata_setup(adata1, adata2)
# TODO: test that a batch with wrong dtype throws an error
# adata1 = synthetic_iid()
# adata2 = synthetic_iid(run_setup_anndata=False)
# adata2.obs["batch"] = ["0"] * adata2.n_obs
# with pytest.raises(ValueError):
# transfer_anndata_setup(adata1, adata2)
# test that an unknown label throws an error
adata1 = synthetic_iid()
adata2 = synthetic_iid(run_setup_anndata=False)
adata2.obs["labels"] = ["label_123"] * adata2.n_obs
with pytest.raises(ValueError):
transfer_anndata_setup(adata1, adata2)
# test that correct mapping was applied
adata1 = synthetic_iid()
adata2 = synthetic_iid(run_setup_anndata=False)
adata2.obs["labels"] = ["label_1"] * adata2.n_obs
transfer_anndata_setup(adata1, adata2)
labels_mapping = adata1.uns["_scvi"]["categorical_mappings"][
"_scvi_labels"]["mapping"]
correct_label = np.where(labels_mapping == "label_1")[0][0]
adata2.obs["_scvi_labels"][0] == correct_label
# test that transfer_anndata_setup correctly looks for adata.obs['batch']
adata1 = synthetic_iid()
adata2 = synthetic_iid(run_setup_anndata=False)
del adata2.obs["batch"]
with pytest.raises(KeyError):
transfer_anndata_setup(adata1, adata2)
# test that transfer_anndata_setup assigns same batch and label to cells
# if the original anndata was also same batch and label
adata1 = synthetic_iid(run_setup_anndata=False)
_setup_anndata(adata1)
adata2 = synthetic_iid(run_setup_anndata=False)
del adata2.obs["batch"]
transfer_anndata_setup(adata1, adata2)
assert adata2.obs["_scvi_batch"][0] == 0
assert adata2.obs["_scvi_labels"][0] == 0
# test that if a category mapping is a subset, transfer anndata is called
a1 = scvi.data.synthetic_iid()
a2 = scvi.data.synthetic_iid(run_setup_anndata=False)
a2.obs["batch"] = "batch_1"
scvi.model.SCVI.setup_anndata(a2, batch_key="batch")
m = scvi.model.SCVI(a1)
m.train(1)
m.get_latent_representation(a2)
assert a2.obs["_scvi_batch"].all() == 1
def test_scvi(save_path):
n_latent = 5
adata = synthetic_iid(run_setup_anndata=False)
SCVI.setup_anndata(
adata,
batch_key="batch",
labels_key="labels",
)
# Test with observed lib size.
adata = synthetic_iid(run_setup_anndata=False)
SCVI.setup_anndata(
adata,
batch_key="batch",
labels_key="labels",
)
model = SCVI(adata, n_latent=n_latent)
model.train(1, check_val_every_n_epoch=1, train_size=0.5)
model = SCVI(adata,
n_latent=n_latent,
var_activation=Softplus(),
use_observed_lib_size=False)
model.train(1, check_val_every_n_epoch=1, train_size=0.5)
model.train(1, check_val_every_n_epoch=1, train_size=0.5)
# tests __repr__
print(model)
assert model.is_trained is True
z = model.get_latent_representation()
assert z.shape == (adata.shape[0], n_latent)
assert len(model.history["elbo_train"]) == 2
model.get_elbo()
model.get_marginal_ll(n_mc_samples=3)
model.get_reconstruction_error()
model.get_normalized_expression(transform_batch="batch_1")
adata2 = synthetic_iid()
model.get_elbo(adata2)
model.get_marginal_ll(adata2, n_mc_samples=3)
model.get_reconstruction_error(adata2)
latent = model.get_latent_representation(adata2, indices=[1, 2, 3])
assert latent.shape == (3, n_latent)
denoised = model.get_normalized_expression(adata2)
assert denoised.shape == adata.shape
denoised = model.get_normalized_expression(adata2,
indices=[1, 2, 3],
transform_batch="batch_1")
denoised = model.get_normalized_expression(
adata2, indices=[1, 2, 3], transform_batch=["batch_0", "batch_1"])
assert denoised.shape == (3, adata2.n_vars)
sample = model.posterior_predictive_sample(adata2)
assert sample.shape == adata2.shape
sample = model.posterior_predictive_sample(adata2,
indices=[1, 2, 3],
gene_list=["1", "2"])
assert sample.shape == (3, 2)
sample = model.posterior_predictive_sample(adata2,
indices=[1, 2, 3],
gene_list=["1", "2"],
n_samples=3)
assert sample.shape == (3, 2, 3)
model.get_feature_correlation_matrix(correlation_type="pearson")
model.get_feature_correlation_matrix(
adata2,
indices=[1, 2, 3],
correlation_type="spearman",
rna_size_factor=500,
n_samples=5,
)
model.get_feature_correlation_matrix(
adata2,
indices=[1, 2, 3],
correlation_type="spearman",
rna_size_factor=500,
n_samples=5,
transform_batch=["batch_0", "batch_1"],
)
params = model.get_likelihood_parameters()
assert params["mean"].shape == adata.shape
assert (params["mean"].shape == params["dispersions"].shape ==
params["dropout"].shape)
params = model.get_likelihood_parameters(adata2, indices=[1, 2, 3])
assert params["mean"].shape == (3, adata.n_vars)
params = model.get_likelihood_parameters(adata2,
indices=[1, 2, 3],
n_samples=3,
give_mean=True)
assert params["mean"].shape == (3, adata.n_vars)
model.get_latent_library_size()
model.get_latent_library_size(adata2, indices=[1, 2, 3])
# test transfer_anndata_setup
adata2 = synthetic_iid(run_setup_anndata=False)
transfer_anndata_setup(adata, adata2)
model.get_elbo(adata2)
# test automatic transfer_anndata_setup + on a view
adata = synthetic_iid()
model = SCVI(adata)
adata2 = synthetic_iid(run_setup_anndata=False)
model.get_elbo(adata2[:10])
# test that we catch incorrect mappings
adata = synthetic_iid()
adata2 = synthetic_iid(run_setup_anndata=False)
transfer_anndata_setup(adata, adata2)
adata2.uns["_scvi"]["categorical_mappings"]["_scvi_labels"][
"mapping"] = np.array(["label_4", "label_0", "label_2"])
with pytest.raises(ValueError):
model.get_elbo(adata2)
# test that same mapping different order doesn't raise error
adata = synthetic_iid()
adata2 = synthetic_iid(run_setup_anndata=False)
transfer_anndata_setup(adata, adata2)
adata2.uns["_scvi"]["categorical_mappings"]["_scvi_labels"][
"mapping"] = np.array(["label_1", "label_0", "label_2"])
model.get_elbo(adata2) # should automatically transfer setup
# test mismatched categories raises ValueError
adata2 = synthetic_iid(run_setup_anndata=False)
adata2.obs.labels.cat.rename_categories(["a", "b", "c"], inplace=True)
with pytest.raises(ValueError):
model.get_elbo(adata2)
# test differential expression
model.differential_expression(groupby="labels", group1="label_1")
model.differential_expression(groupby="labels",
group1="label_1",
group2="label_2",
mode="change")
model.differential_expression(groupby="labels")
model.differential_expression(idx1=[0, 1, 2], idx2=[3, 4, 5])
model.differential_expression(idx1=[0, 1, 2])
# transform batch works with all different types
a = synthetic_iid(run_setup_anndata=False)
batch = np.zeros(a.n_obs)
batch[:64] += 1
a.obs["batch"] = batch
_setup_anndata(a, batch_key="batch")
m = SCVI(a)
m.train(1, train_size=0.5)
m.get_normalized_expression(transform_batch=1)
m.get_normalized_expression(transform_batch=[0, 1])
# test get_likelihood_parameters() when dispersion=='gene-cell'
model = SCVI(adata, dispersion="gene-cell")
model.get_likelihood_parameters()
# test train callbacks work
a = synthetic_iid()
m = scvi.model.SCVI(a)
lr_monitor = LearningRateMonitor()
m.train(
callbacks=[lr_monitor],
max_epochs=10,
check_val_every_n_epoch=1,
log_every_n_steps=1,
plan_kwargs={"reduce_lr_on_plateau": True},
)
assert "lr-Adam" in m.history.keys()
def _load_pbmc_dataset(
save_path: str = "data/",
run_setup_anndata: bool = True,
remove_extracted_data: bool = True,
) -> anndata.AnnData:
urls = [
"https://github.com/YosefLab/scVI-data/raw/master/gene_info.csv",
"https://github.com/YosefLab/scVI-data/raw/master/pbmc_metadata.pickle",
]
save_fns = ["gene_info_pbmc.csv", "pbmc_metadata.pickle"]
for i in range(len(urls)):
_download(urls[i], save_path, save_fns[i])
de_metadata = pd.read_csv(os.path.join(save_path, "gene_info_pbmc.csv"),
sep=",")
pbmc_metadata = pd.read_pickle(
os.path.join(save_path, "pbmc_metadata.pickle"))
pbmc8k = _load_dataset_10x(
"pbmc8k",
save_path=save_path,
var_names="gene_ids",
remove_extracted_data=remove_extracted_data,
)
pbmc4k = _load_dataset_10x(
"pbmc4k",
save_path=save_path,
var_names="gene_ids",
remove_extracted_data=remove_extracted_data,
)
barcodes = np.concatenate((pbmc8k.obs_names, pbmc4k.obs_names))
adata = pbmc8k.concatenate(pbmc4k)
adata.obs_names = barcodes
dict_barcodes = dict(zip(barcodes, np.arange(len(barcodes))))
subset_cells = []
barcodes_metadata = pbmc_metadata["barcodes"].index.values.ravel().astype(
np.str)
for barcode in barcodes_metadata:
if (barcode in dict_barcodes
): # barcodes with end -11 filtered on 10X website (49 cells)
subset_cells += [dict_barcodes[barcode]]
adata = adata[np.asarray(subset_cells), :].copy()
idx_metadata = np.asarray(
[not barcode.endswith("11") for barcode in barcodes_metadata],
dtype=np.bool)
genes_to_keep = list(de_metadata["ENSG"].values
) # only keep the genes for which we have de data
difference = list(set(genes_to_keep).difference(set(
adata.var_names))) # Non empty only for unit tests
for gene in difference:
genes_to_keep.remove(gene)
adata = adata[:, genes_to_keep].copy()
design = pbmc_metadata["design"][idx_metadata]
raw_qc = pbmc_metadata["raw_qc"][idx_metadata]
normalized_qc = pbmc_metadata["normalized_qc"][idx_metadata]
design.index = adata.obs_names
raw_qc.index = adata.obs_names
normalized_qc.index = adata.obs_names
adata.obs["batch"] = adata.obs["batch"].astype(np.int64)
adata.obsm["design"] = design
adata.obsm["raw_qc"] = raw_qc
adata.obsm["normalized_qc"] = normalized_qc
adata.obsm["qc_pc"] = pbmc_metadata["qc_pc"][idx_metadata]
labels = pbmc_metadata["clusters"][idx_metadata]
cell_types = pbmc_metadata["list_clusters"]
adata.obs["labels"] = labels
adata.uns["cell_types"] = cell_types
adata.obs["str_labels"] = [cell_types[i] for i in labels]
adata.var["n_counts"] = np.squeeze(np.asarray(np.sum(adata.X, axis=0)))
if run_setup_anndata:
_setup_anndata(adata, batch_key="batch", labels_key="labels")
return adata
def test_anntorchdataset_getitem():
adata = synthetic_iid()
_setup_anndata(
adata,
batch_key="batch",
labels_key="labels",
protein_expression_obsm_key="protein_expression",
protein_names_uns_key="protein_names",
)
# check that we can successfully pass in a list of tensors to get
tensors_to_get = ["batch_indices", "labels"]
bd = AnnTorchDataset(adata, getitem_tensors=tensors_to_get)
np.testing.assert_array_equal(tensors_to_get, list(bd[1].keys()))
# check that we can successfully pass in a dict of tensors and their associated types
bd = AnnTorchDataset(adata,
getitem_tensors={
"X": np.int,
"labels": np.int64
})
assert bd[1]["X"].dtype == np.int64
assert bd[1]["labels"].dtype == np.int64
# check that by default we get all the registered tensors
bd = AnnTorchDataset(adata)
all_registered_tensors = list(adata.uns["_scvi"]["data_registry"].keys())
np.testing.assert_array_equal(all_registered_tensors, list(bd[1].keys()))
assert bd[1]["X"].shape[0] == bd.adata.uns["_scvi"]["summary_stats"][
"n_vars"]
# check that AnnTorchDataset returns numpy array
adata1 = synthetic_iid()
bd = AnnTorchDataset(adata1)
for key, value in bd[1].items():
assert type(value) == np.ndarray
# check AnnTorchDataset returns numpy array counts were sparse
adata = synthetic_iid(run_setup_anndata=False)
adata.X = sparse.csr_matrix(adata.X)
_setup_anndata(adata)
bd = AnnTorchDataset(adata)
for key, value in bd[1].items():
assert type(value) == np.ndarray
# check AnnTorchDataset returns numpy array if pro exp was sparse
adata = synthetic_iid(run_setup_anndata=False)
adata.obsm["protein_expression"] = sparse.csr_matrix(
adata.obsm["protein_expression"])
_setup_anndata(adata,
batch_key="batch",
protein_expression_obsm_key="protein_expression")
bd = AnnTorchDataset(adata)
for key, value in bd[1].items():
assert type(value) == np.ndarray
# check pro exp is being returned as numpy array even if its DF
adata = synthetic_iid(run_setup_anndata=False)
adata.obsm["protein_expression"] = pd.DataFrame(
adata.obsm["protein_expression"], index=adata.obs_names)
_setup_anndata(adata,
batch_key="batch",
protein_expression_obsm_key="protein_expression")
bd = AnnTorchDataset(adata)
for key, value in bd[1].items():
assert type(value) == np.ndarray
