def save_enriched_motifs(df, fname: str) -> None:
"""
Save enriched motifs.
Supported file formats are CSV, TSV, GMT, DAT (pickle), JSON or YAML.
:param df:
:param fname:
:return:
"""
extension = PurePath(fname).suffixes
if is_valid_suffix(extension, 'ctx'):
df.to_csv(fname, sep=suffixes_to_separator(extension))
else:
regulons = df2regulons(df)
if '.json' in extension:
name2targets = {
r.name: list(r.gene2weight.keys())
for r in regulons
}
with openfile(fname, 'w') as f:
f.write(json.dumps(name2targets))
elif '.dat' in extension:
with openfile(fname, 'wb') as f:
pickle.dump(regulons, f)
elif '.gmt' in extension:
GeneSignature.to_gmt(fname, regulons)
elif is_valid_suffix(extension, 'ctx_yaml'):
save_to_yaml(regulons, fname)
else:
raise ValueError("Unknown file format \"{}\".".format(fname))
def load_signatures(fname: str) -> Sequence[Type[GeneSignature]]:
"""
Load genes signatures from disk.
Supported file formats are GMT, DAT (pickled), YAML or CSV (enriched motifs).
:param fname: The name of the file that contains the signatures.
:return: A list of gene signatures.
"""
extension = PurePath(fname).suffixes
if is_valid_suffix(extension, 'ctx'):
# csv/tsv
return df2regulons(
load_motifs(fname, sep=suffixes_to_separator(extension)))
elif is_valid_suffix(extension, 'ctx_yaml'):
return load_from_yaml(fname)
elif '.gmt' in extension:
sep = guess_separator(fname)
return GeneSignature.from_gmt(fname,
field_separator=sep,
gene_separator=sep)
elif extension == '.dat':
with openfile(fname, 'rb') as f:
return pickle.load(f)
else:
raise ValueError("Unknown file format \"{}\".".format(fname))
def load_modules(fname: str) -> Sequence[Type[GeneSignature]]:
# Loading from YAML is extremely slow. Therefore this is a potential performance improvement.
# Potential improvements are switching to JSON or to use a CLoader:
# https://stackoverflow.com/questions/27743711/can-i-speedup-yaml
# The alternative for which was opted in the end is binary pickling.
extension = PurePath(fname).suffixes
if is_valid_suffix(extension, 'ctx_yaml'):
return load_from_yaml(fname)
elif '.dat' in extension:
with openfile(fname, 'rb') as f:
return pickle.load(f)
elif '.gmt' in extension:
return GeneSignature.from_gmt(fname)
else:
raise ValueError("Unknown file format for \"{}\".".format(fname))
def guess_separator(fname: str) -> str:
with openfile(fname, 'r') as f:
lines = f.readlines()
# decode if gzipped file:
for i,x in enumerate(lines):
if isinstance(x, (bytes, bytearray)):
lines[i] = x.decode()
def count_columns(sep):
return [len(line.split(sep)) for line in lines if not line.strip().startswith('#') and line.strip()]
# Check if '\t' is used:
for sep in ('\t', ';', ','):
if min(count_columns(sep)) >= 3:
return sep
raise ValueError("Unknown file format \"{}\".".format(fname))