def read_multimodal_data(self, attach_zarrobj = False) -> MultimodalData:
""" Read MultimodalData
"""
data = MultimodalData()
for key, group in self.root.groups():
unidata = self.read_unimodal_data(group)
data.add_data(unidata)
if self.root.attrs.get('_selected', None) is not None:
data.select_data(self.root.attrs['_selected'])
if attach_zarrobj:
data._zarrobj = self
return data
def write_loom_file(data: MultimodalData, output_file: str) -> None:
""" Write a MultimodalData to loom file. Will assert data only contain one type of experiment.
"""
keys = data.list_data()
if len(keys) > 1:
raise ValueError(
f"Data contain multiple modalities: {','.join(keys)}!")
data.select_data(keys[0])
matrices = data.list_keys()
assert "X" in matrices
if len(matrices) == 0:
raise ValueError("Could not write empty matrix to a loom file!")
def _process_attrs(key_name: str, attrs: pd.DataFrame,
attrs_multi: dict) -> Dict[str, object]:
res_dict = {key_name: attrs.index.values}
for key in attrs.columns:
res_dict[key] = np.array(attrs[key].values)
for key, value in attrs_multi.items():
if value.ndim > 1: # value.ndim == 1 refers to np.recarray, which will not be written to a loom file.
res_dict[key] = value if value.shape[1] > 1 else value[:, 0]
return res_dict
row_attrs = _process_attrs("Gene", data.var, data.varm)
col_attrs = _process_attrs("CellID", data.obs, data.obsm)
accession_key = "featureid" if "featureid" in row_attrs else (
"gene_ids" if "gene_ids" in row_attrs else None)
if accession_key is not None:
row_attrs["Accession"] = row_attrs.pop(accession_key)
layers = {}
for matkey in matrices:
layers["" if matkey == "X" else matkey] = data.get_matrix(matkey).T
file_attrs = {}
for key, value in data.uns.items():
if isinstance(value, str):
file_attrs[key] = value
import loompy
loompy.create(output_file,
layers,
row_attrs,
col_attrs,
file_attrs=file_attrs)
logger.info(f"{output_file} is written.")
