def load_objects(self, is_bedgraph, verbose=False, test=False):
"""Load files and initialize object.
*Keyword arguments:*
- is_bedgraph -- Whether regions are in bedgraph format (default = False).
- verbose -- Verbose output (default = False).
- test -- Fetch only 10 regions form each BED files for test.
"""
for i, t in enumerate(self.types):
if verbose:
print("Loading file ",
self.files[self.names[i]],
file=sys.stderr)
if t not in ["regions", "genes"] and verbose:
print("Cannot load objects", file=sys.stderr)
if t == "regions":
regions = GenomicRegionSet(self.names[i])
if is_bedgraph:
regions.read_bedgraph(
os.path.abspath(self.files[self.names[i]]))
else:
regions.read_bed(os.path.abspath(
self.files[self.names[i]]))
if test: regions.sequences = regions.sequences[0:11]
self.objectsDict[self.names[i]] = regions
elif t == "genes":
genes = GeneSet(self.names[i])
genes.read(
os.path.abspath(self.files[self.names[i]])
) # Here change the relative path into absolute path
self.objectsDict[self.names[i]] = genes
def load_objects(self, is_bedgraph, verbose=False, test=False):
"""Load files and initialize object.
*Keyword arguments:*
- is_bedgraph -- Whether regions are in bedgraph format (default = False).
- verbose -- Verbose output (default = False).
- test -- Fetch only 10 regions form each BED files for test.
"""
for i, t in enumerate(self.types):
if verbose: print("Loading file ", self.files[self.names[i]], file = sys.stderr)
if t not in ["regions", "genes"] and verbose:
print("Cannot load objects", file=sys.stderr)
if t == "regions":
regions = GenomicRegionSet(self.names[i])
if is_bedgraph:
regions.read_bedgraph(os.path.abspath(self.files[self.names[i]]))
else:
if test:
g = GenomicRegionSet(self.names[i])
g.read_bed(os.path.abspath(self.files[self.names[i]]))
regions.sequences = g.sequences[0:11]
else:
regions.read_bed(os.path.abspath(self.files[self.names[i]])) # Here change the relative path into absolute path
self.objectsDict[self.names[i]] = regions
elif t == "genes":
genes = GeneSet(self.names[i])
genes.read(os.path.abspath(self.files[self.names[i]])) # Here change the relative path into absolute path
self.objectsDict[self.names[i]] = genes
def match_ms_tags(self, field, test=False):
"""Add more entries to match the missing tags of the given field. For example, there are tags for cell like 'cell_A' and 'cell_B' for reads, but no these tag for regions. Then the regions are repeated for each tags from reads to match all reads.
*Keyword arguments:*
- field -- Field to add extra entries.
"""
# check regions or reads have empty tag
altypes = self.fieldsDict[field].keys()
if "ALL" in altypes:
altypes.remove("ALL")
for name in self.fieldsDict[field]["ALL"]:
i = self.names.index(name)
for t in altypes:
# print("\t"+t)
n = name + "_" + t
# print("\t\t"+n)
self.names.append(n)
self.types.append(self.types[i])
self.files[n] = self.files[name]
# types = self.get_types(name,skip_all=True)
# print("************")
# print(types)
for f in self.fields[3:]:
if f == field:
try:
self.fieldsDict[f][t].append(n)
except:
self.fieldsDict[f][t] = [n]
else:
try:
self.fieldsDict[f][self.get_type(
name=name, field=f)].append(n)
except:
self.fieldsDict[f][self.get_type(
name=name, field=f)] = [n]
# for f in self.fieldsDict.keys():
# for ty in types:
# try: self.fieldsDict[f][ty].append(n)
# except: pass
if self.types[i] == "regions":
g = GenomicRegionSet(n)
g.read_bed(self.files[name])
if test: g.sequences = g.sequences[0:11]
self.objectsDict[n] = g
self.trash.append(name)