def t_parent_child(self):
"""Summarize parent-child relationships in a GFF file.
"""
gff_examiner = GFFExaminer()
pc_map = gff_examiner.parent_child_map(self._test_gff_file)
print
pprint.pprint(pc_map)
def explore_gff(self, gff_path):
from BCBio.GFF import GFFExaminer
examiner = GFFExaminer()
with open(gff_path) as h:
parentchild = examiner.parent_child_map(h)
pprint.pprint(parentchild)
with open(gff_path) as h:
pprint.pprint(examiner.available_limits(h))
def t_examiner_with_fasta(self):
"""Perform high level examination of files with FASTA directives.
"""
examiner = GFFExaminer()
pc_map = examiner.parent_child_map(self._gff_file)
assert pc_map[('UCSC', 'mRNA')] == [('UCSC', 'CDS')]
limits = examiner.available_limits(self._gff_file)
assert limits['gff_id'].keys()[0][0] == 'chr17'
assert sorted(limits['gff_source_type'].keys()) == \
[('UCSC', 'CDS'), ('UCSC', 'mRNA')]
def t_parent_child_file_modes(self):
"""Summarize parent-child relationships in a GFF file.
"""
gff_examiner = GFFExaminer()
# Use the loaded-from-filename as reference
pc_map = gff_examiner.parent_child_map(self._test_gff_file)
with open(self._test_gff_file, "rt") as handle:
assert pc_map == gff_examiner.parent_child_map(handle)
with open(self._test_gff_file, "rb") as handle:
if six.PY2:
assert pc_map == gff_examiner.parent_child_map(handle)
else:
try:
gff_examiner.parent_child_map(handle)
except TypeError as e:
assert str(
e) == "input handle must be opened in text mode", e
else:
assert False, "expected TypeError to be raised"
dest="prefix",
help="Prefix of output files",
default="prefix")
parser.add_argument("-l",
"--length_distribution_file_prefix",
action="store",
dest="len_distr_file",
help="Output file with lengths distibutions",
default="length_distribution")
args = parser.parse_args()
examiner = GFFExaminer()
with open(args.gff, "r") as in_fd:
pprint.pprint(examiner.parent_child_map(in_fd))
with open(args.gff, "r") as in_fd:
record_dict = dict([(record.id, record) for record in GFF.parse(in_fd)])
gene_dict = OrderedDict({})
for record_id in record_dict:
for feature in record_dict[record_id].features:
if feature.type == "gene":
gene_dict[feature.qualifiers["Name"][0]] = OrderedDict({})
for sub_feature in feature.sub_features:
gene_dict[feature.qualifiers["Name"][0]][
sub_feature.type] = len(sub_feature)
if feature.type in ("snoRNA", "ncRNA", "snRNA"):
gene_dict[feature.qualifiers["Name"][0]] = OrderedDict(
{"ncRNA": len(feature)})
# -*- coding: utf-8 -*-
"""
Getting gene sequences from our PG files
Author: Daniel Martinez-Martinez
"""
import os
import pprint
from BCBio import GFF
from BCBio.GFF import GFFExaminer
ann_folder = '.\\annotations'
file = "NT12004_22.gff"
in_file = os.path.join(ann_folder, file)
# to explore gff files
examiner = GFFExaminer()
in_handle = open(in_file)
pprint.pprint(examiner.parent_child_map(in_handle))
# in_handle.close()
# to parse the document
in_handle = open(file)
for rec in GFF.parse(in_handle):
print(rec)
in_handle.close()
import pprint
from BCBio.GFF import GFFExaminer
in_file = "Nagalakshmi_2008_UTRs.gff3"
examiner = GFFExaminer()
in_handle = open(in_file)
pprint.pprint(examiner.parent_child_map(in_handle))
in_handle.close()
from BCBio import GFF
in_file = "Nagalakshmi_2008_UTRs.gff3"
in_handle = open(in_file)
for rec in GFF.parse(in_handle):
print rec
in_handle.close()
