def load_velocity(self, velocity_file=None, loader_type=None):
velocity_file = self._velocity_file_name if velocity_file is None else velocity_file
loader_type = self._velocity_file_type if loader_type is None else loader_type
transpose = not self.expression_matrix_columns_are_genes
loader = InferelatorDataLoader(
input_dir=self.input_dir,
file_format_settings=self._file_format_settings)
Debug.vprint("Loading velocity data from {f}".format(f=velocity_file),
level=1)
if loader_type == _TSV or loader_type is None:
self._velocity_data = loader.load_data_tsv(
velocity_file, transpose_expression_data=transpose)
elif loader_type == _H5AD:
self._velocity_data = loader.load_data_h5ad(
velocity_file, use_layer=self._velocity_h5_layer)
elif loader_type == _HDF5:
self._velocity_data = loader.load_data_hdf5(
velocity_file,
transpose_expression_data=transpose,
use_layer=self._velocity_h5_layer)
else:
raise ValueError(
"Invalid velocity_file_type: {a}".format(a=loader_type))
self._velocity_data.name = "Velocity"
def read_priors(self, priors_file=None, gold_standard_file=None):
"""
Read in the priors and gold standard files
"""
priors_file = priors_file if priors_file is not None else self.priors_file
gold_standard_file = gold_standard_file if gold_standard_file is not None else self.gold_standard_file
loader = InferelatorDataLoader(input_dir=self.input_dir, file_format_settings=self._file_format_settings)
if priors_file is not None:
Debug.vprint("Loading prior data from file {file}".format(file=priors_file), level=1)
self.priors_data = loader.input_dataframe(priors_file)
# Print debug info & check prior for duplicate indices (which will raise errors later)
self.loaded_file_info("Priors data", self.priors_data)
self._check_network_labels_unique("Priors_data", priors_file, self.priors_data)
if gold_standard_file is not None:
Debug.vprint("Loading gold_standard data from file {file}".format(file=gold_standard_file), level=1)
self.gold_standard = loader.input_dataframe(gold_standard_file)
# Print debug info & check gold standard for duplicate indices (which will raise errors later)
self.loaded_file_info("Gold standard", self.gold_standard)
self._check_network_labels_unique("Gold standard", gold_standard_file, self.gold_standard)
def load_activity(self, file=None, file_type=None):
file = self._tfa_input_file if file is None else file
file_type = self._tfa_input_file_type if file_type is None else file_type
loader = InferelatorDataLoader(
input_dir=self.input_dir,
file_format_settings=self._file_format_settings)
if file_type.lower() == "h5ad":
self.design = loader.load_data_h5ad(file)
elif self._expression_loader.lower() == "tsv":
self.design = loader.load_data_tsv(file)
Debug.vprint("Loaded {f} as design matrix {d}".format(
d=self.design.shape, f=file),
level=1)
self.design.trim_genes(
remove_constant_genes=False,
trim_gene_list=self.design.gene_names.intersection(self.tf_names))
Debug.vprint("Trimmed to {d} for TF activity".format(
d=self.design.shape, f=file),
level=1)
assert check.indexes_align(
[self.design.sample_names, self.response.sample_names])
def create_output_dir(self):
"""
Set a default output_dir if nothing is set. Create the path if it doesn't exist.
"""
if self.output_dir is None:
new_path = datetime.datetime.now().strftime('%Y-%m-%d_%H-%M-%S')
self.output_dir = InferelatorDataLoader.make_path_safe(os.path.join(self.input_dir, new_path))
else:
self.output_dir = InferelatorDataLoader.make_path_safe(self.output_dir)
try:
os.makedirs(os.path.expanduser(self.output_dir))
except FileExistsError:
pass
def read_tfs(self, file=None):
"""
Read tf names file into tf_names
"""
# Load the class variable if no file is passed
file = self.tf_names_file if file is None else file
if file is not None:
Debug.vprint("Loading TF feature names from file {file}".format(file=file), level=1)
# Read in a dataframe with no header or index
loader = InferelatorDataLoader(input_dir=self.input_dir, file_format_settings=self._file_format_settings)
tfs = loader.input_dataframe(file, header=None, index_col=None)
# Cast the dataframe into a list
assert tfs.shape[1] == 1
self.tf_names = tfs.values.flatten().tolist()
def output_path(self, filename):
"""
Join filename to output_dir
:param filename: Path to some file that needs to be attached to the output path
:type filename: str
:return: File joined to output_dir instance variable
:rtype: str
"""
return InferelatorDataLoader.filename_path_join(self.output_dir, filename)
def read_genes(self, file=None):
"""
Read gene names file into gene_names
"""
# Load the class variable if no file is passed
file = self.gene_names_file if file is None else file
if file is not None:
Debug.vprint("Loading Gene feature names from file {file}".format(file=file), level=1)
# Read in a dataframe with no header or index
loader = InferelatorDataLoader(input_dir=self.input_dir, file_format_settings=self._file_format_settings)
genes = loader.input_dataframe(file, header=None, index_col=None)
# Cast the dataframe into a list
assert genes.shape[1] == 1
self.gene_names = genes.values.flatten().tolist()
# Use the gene names in the data file if no restrictive list is provided
if self.gene_names is None and self.data is not None:
self.gene_names = self.data.gene_names.copy()
def read_expression(self, expression_matrix_file=None, meta_data_file=None, gene_data_file=None):
"""
Read expression matrix file into an InferelatorData object
"""
expression_file = expression_matrix_file if expression_matrix_file is not None else self.expression_matrix_file
meta_data_file = meta_data_file if meta_data_file is not None else self.meta_data_file
gene_data_file = gene_data_file if gene_data_file is not None else self.gene_metadata_file
loader = InferelatorDataLoader(input_dir=self.input_dir, file_format_settings=self._file_format_settings)
if self._expression_loader == _H5AD:
self.data = loader.load_data_h5ad(expression_file,
use_layer=self._h5_layer,
meta_data_file=meta_data_file,
meta_data_handler=self.metadata_handler,
gene_data_file=gene_data_file,
gene_name_column=self.gene_list_index)
elif self._expression_loader == _TSV:
self.data = loader.load_data_tsv(expression_file,
transpose_expression_data=not self.expression_matrix_columns_are_genes,
expression_matrix_metadata=self.expression_matrix_metadata,
meta_data_file=meta_data_file,
meta_data_handler=self.metadata_handler,
gene_data_file=gene_data_file,
gene_name_column=self.gene_list_index)
elif self._expression_loader == _MTX:
self.data = loader.load_data_mtx(expression_file[0],
mtx_feature=expression_file[2],
mtx_obs=expression_file[1],
meta_data_file=meta_data_file,
meta_data_handler=self.metadata_handler,
gene_data_file=gene_data_file,
gene_name_column=self.gene_list_index)
elif self._expression_loader == _TENX:
self.data = loader.load_data_tenx(expression_file,
meta_data_file=meta_data_file,
meta_data_handler=self.metadata_handler,
gene_data_file=gene_data_file,
gene_name_column=self.gene_list_index)
elif self._expression_loader == _HDF5:
self.data = loader.load_data_hdf5(expression_file,
transpose_expression_data=not self.expression_matrix_columns_are_genes,
use_layer=self._h5_layer,
meta_data_file=meta_data_file,
meta_data_handler=self.metadata_handler,
gene_data_file=gene_data_file,
gene_name_column=self.gene_list_index)
self.data.name = "Expression"
def read_priors(self, priors_file=None, gold_standard_file=None):
"""
Read in the priors and gold standard files
"""
priors_file = priors_file if priors_file is not None else self.priors_file
gold_standard_file = gold_standard_file if gold_standard_file is not None else self.gold_standard_file
loader = InferelatorDataLoader(
input_dir=self.input_dir,
file_format_settings=self._file_format_settings)
if priors_file is not None:
Debug.vprint(
"Loading prior data from file {file}".format(file=priors_file),
level=1)
self.priors_data = loader.input_dataframe(priors_file)
self.loaded_file_info("Priors data", self.priors_data)
if gold_standard_file is not None:
Debug.vprint("Loading gold_standard data from file {file}".format(
file=gold_standard_file),
level=1)
self.gold_standard = loader.input_dataframe(gold_standard_file)
self.loaded_file_info("Gold standard", self.gold_standard)