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 '.dat' in extension:
with openfile(fname, 'rb') as f:
return pickle.load(f)
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 = os.path.splitext(fname)[1].lower()
if extension in FILE_EXTENSION2SEPARATOR.keys():
return df2regulons(
load_motifs(fname, sep=FILE_EXTENSION2SEPARATOR[extension]))
elif extension in {'.yaml', '.yml'}:
return load_from_yaml(fname)
elif extension.endswith('.gmt'):
sep = guess_separator(fname)
return GeneSignature.from_gmt(fname,
field_separator=sep,
gene_separator=sep)
elif extension == '.dat':
with open(fname, 'rb') as f:
return pickle.load(f)
else:
raise ValueError("Unknown file format \"{}\".".format(fname))
adjacencies, ex_matrix)) # identifies modules from GENIE3
# save GRNBoost2 product so we don't have to repeat again
adjacencies.to_csv("grnboost_output.csv")
# load product in case something goes wrong
adjacencies = pd.read_csv("grnboost_output.csv", index_col=0)
# cisTarget process: IDs cis-regulatory footprints from motifs around the TSS
with ProgressBar(
): # calculate a list of enriched motifs and the corresponding target genes for all modules
df = prune2df(dbs, modules, "motifs-v9-nr-mgi.txt")
regulons = df2regulons(
df) # create regulons from this table of enriched motifs
# save the discovered motifs and regulons
df.to_csv(motifs_filename)
with open(regulons_filename, "wb") as f:
pickle.dump(regulons, f)
# load the discovered motifs and regulons if saved previously
df = load_motifs(motifs_filename)
with open(regulons_filename, "rb") as f:
regulons = pickle.load(f)
# AUCell process: finds enrichment of each discovered regulon
auc_matrix = aucell(ex_matrix, regulons, num_workers=4)
# export the product back to R for analysis
auc_matrix.to_csv("SCENIC_export.csv")
import os
sc.settings.set_figure_params(frameon=True, color_map='Spectral_r')
sc.settings.verbosity = 3
plt.rcParams["axes.grid"] = False
# Run time for demo data: several minutes.
DATA_FOLDER = './Data/'
exp_matrix = pd.read_csv(os.path.join(DATA_FOLDER, 'DC_exp.csv'), index_col=0)
exp_meta = pd.read_csv(os.path.join(DATA_FOLDER, 'DC_meta.txt'),
sep='\t',
index_col=0)
## Generate the regulons
Motifs_NAME = 'exp_matrix'
motifs = load_motifs(
os.path.join(DATA_FOLDER, '{}.motifs.csv'.format(Motifs_NAME)))
regulons = df2regulons(motifs)
## Make a meta matrix for the regulon
reg_num = []
reg_target = []
reg_tf = []
for i in regulons:
reg_tf.append(i.transcription_factor)
reg_target.append(list(i.gene2weight.keys()))
reg_num.append(len(list(i.gene2weight.keys())))
reg_meta = pd.DataFrame([reg_num, reg_target]).T
reg_meta.index = reg_tf
reg_meta.columns = ['n_targets', 'targets']
