def get_feature_list(inputfile=None, outputfile=None, separator=""):
"""
Get the list of features enclosed in the GTF.
"""
gtf = GTF(inputfile, check_ensembl_format=False)
for i in gtf.get_feature_list(nr=True):
outputfile.write(str(i) + separator)
gc.disable()
close_properly(outputfile, inputfile)
def join_multi_file(inputfile=None,
outputfile=None,
target_feature=None,
key_to_join=None,
matrix_files=()):
"""
Join attributes from a set of tabulated files.
"""
# -----------------------------------------------------------
# load the GTF
# -----------------------------------------------------------
gtf = GTF(inputfile, check_ensembl_format=False)
# -----------------------------------------------------------
# Check target feature
# -----------------------------------------------------------
feat_list = gtf.get_feature_list(nr=True)
if target_feature is not None:
target_feature_list = target_feature.split(",")
for i in target_feature_list:
if i not in feat_list + ["*"]:
message("Feature " + i + " not found.", type="ERROR")
else:
target_feature = ",".join(feat_list)
# -----------------------------------------------------------
# Do it
# -----------------------------------------------------------
for join_file in matrix_files:
gtf = gtf.add_attr_from_matrix_file(feat=target_feature,
key=key_to_join,
inputfile=join_file.name)
gtf.write(outputfile, gc_off=True)
gc.disable()
close_properly(outputfile, inputfile)
def feature_size(inputfile=None,
outputfile=None,
ft_type="transcript",
names="transcript_id",
key_name='feature_size',
separator="|",
bed=False):
"""
Get the size and limits (start/end) of features enclosed in the GTF. If bed
format is requested returns the limits zero-based half open and the size as a score.
Otherwise output GTF file with 'feat_size' as a new key and size as value.
"""
message("Computing feature sizes.")
gtf = GTF(inputfile)
feat_list = gtf.get_feature_list(nr=True) + ['mature_rna']
if ft_type not in feat_list + ["*"]:
message("Unable to find requested feature.", type="ERROR")
names = names.split(",")
if ft_type != 'mature_rna':
if bed:
bed_obj = gtf.select_by_key("feature",
ft_type).to_bed(name=names,
sep=separator,
add_feature_type=True)
for i in bed_obj:
i.score = str(i.end - i.start)
write_properly(chomp(str(i)), outputfile)
else:
tmp_file = make_tmp_file(prefix="feature_size", suffix=".txt")
elmt = gtf.extract_data("feature,start,end",
as_list_of_list=True,
no_na=False,
hide_undef=False)
for i in elmt:
if i[0] != ft_type and ft_type != "*":
tmp_file.write("?\n")
else:
tmp_file.write(str(int(i[2]) - int(i[1]) + 1) + "\n")
tmp_file.close()
gtf.add_attr_column(tmp_file, key_name).write(outputfile,
gc_off=True)
else:
tx_size = gtf.get_transcript_size()
if bed:
bed_obj = gtf.select_by_key("feature", 'transcript').to_bed(
['transcript_id'] + names,
add_feature_type=False,
sep=separator,
more_name=['mature_rna'])
for i in bed_obj:
names = i.name.split(separator)
tx_id = names.pop(0)
i.score = tx_size[tx_id]
i.name = separator.join(names)
write_properly(chomp(str(i)), outputfile)
else:
if len(tx_size):
gtf = gtf.add_attr_from_dict(feat="transcript",
key="transcript_id",
a_dict=tx_size,
new_key=key_name)
gtf.write(outputfile, gc_off=True)
close_properly(outputfile, inputfile)
def join_attr(inputfile=None,
outputfile=None,
join_file=None,
has_header=False,
new_key=None,
target_feature=None,
key_to_join=None,
matrix=None):
"""
Join attributes from a tabulated file.
"""
# -----------------------------------------------------------
# Check argument consistency
# -----------------------------------------------------------
if matrix is True:
if new_key is not None:
message("--new-key and --matrix are mutually exclusive.",
type="ERROR")
else:
if new_key is None:
message("--new-key is required when --matrix is False.",
type="ERROR")
# -----------------------------------------------------------
# load the GTF
# -----------------------------------------------------------
gtf = GTF(inputfile, check_ensembl_format=False)
# -----------------------------------------------------------
# Check target feature
# -----------------------------------------------------------
feat_list = gtf.get_feature_list(nr=True)
if target_feature is not None:
target_feature_list = target_feature.split(",")
for i in target_feature_list:
if i not in feat_list + ["*"]:
message("Feature " + i + " not found.", type="ERROR")
else:
target_feature = ",".join(feat_list)
# -----------------------------------------------------------
# Do it
# -----------------------------------------------------------
if not matrix:
gtf = gtf.add_attr_from_file(feat=target_feature,
key=key_to_join,
new_key=new_key,
inputfile=join_file.name,
has_header=has_header)
gtf.write(outputfile, gc_off=True)
else:
gtf = gtf.add_attr_from_matrix_file(feat=target_feature,
key=key_to_join,
inputfile=join_file.name)
gtf.write(outputfile, gc_off=True)
gc.disable()
close_properly(outputfile, inputfile)