def count(inputfile=None, outputfile=None, header=None, additional_text=None):
"""
Count the number of features in the gtf file.
"""
if header is not None:
header = header.split(",")
gtf = GTF(inputfile, check_ensembl_format=False)
feat_nb = OrderedDict()
for i in gtf.extract_data("feature"):
i = i[0]
if i in feat_nb:
feat_nb[i] += 1
else:
feat_nb[i] = 1
if header is not None:
outputfile.write("\t".join(header) + "\n")
for i in feat_nb:
if additional_text is None:
outputfile.write(i + "\t" + str(feat_nb[i]) + "\n")
else:
outputfile.write(i + "\t" + str(feat_nb[i]) + "\t" +
additional_text + "\n")
gc.disable()
close_properly(outputfile, inputfile)
def intronic(inputfile=None,
outputfile=None,
names='transcript_id',
separator="_",
intron_nb_in_name=False,
no_feature_name=False,
by_transcript=False):
"""
Extract intronic regions.
"""
message("Searching for intronic regions.")
# Need to load if the gtf comes from
# <stdin>
gtf = GTF(inputfile, check_ensembl_format=False)
if not by_transcript:
introns_bo = gtf.get_introns()
for i in introns_bo:
write_properly(chomp(str(i)), outputfile)
else:
introns_bo = gtf.get_introns(by_transcript=True,
name=names.split(","),
sep=separator,
intron_nb_in_name=intron_nb_in_name,
feat_name=not no_feature_name)
for i in introns_bo:
write_properly(chomp(str(i)), outputfile)
gc.disable()
close_properly(outputfile, inputfile)
def get_attr_value_list(inputfile=None,
outputfile=None,
key_name="gene_id",
print_key_name=False,
separator="\n",
count=False):
"""
Get the list of values observed for an attributes.
"""
gtf = GTF(inputfile, check_ensembl_format=False)
if not count:
for akey in key_name.split(","):
for i in gtf.get_attr_value_list(akey):
if print_key_name:
outputfile.write(akey + separator + i + "\n")
else:
outputfile.write(i + "\n")
gc.disable()
close_properly(outputfile, inputfile)
else:
if separator == "\n":
separator = "\t"
for akey in key_name.split(","):
for i in gtf.get_attr_value_list(akey, count=True):
if print_key_name:
outputfile.write(akey + separator + i[0] + separator +
i[1] + "\n")
else:
outputfile.write(i[0] + separator + i[1] + "\n")
gc.disable()
close_properly(outputfile, inputfile)
def convert(inputfile=None,
outputfile=None,
format="bed",
names="gene_id,transcript_id",
separator="|",
more_names=''):
"""
Convert a GTF to various format.
"""
if format == "bed3":
gtf = GTF(inputfile, check_ensembl_format=False)
for i in gtf.extract_data("seqid,start,end",
as_list_of_list=True,
hide_undef=False,
no_na=False):
i[1] = str(int(i[1]) - 1)
outputfile.write("\t".join(i) + "\n")
elif format in ["bed", "bed6"]:
gtf = GTF(inputfile,
check_ensembl_format=False).write_bed(outputfile=outputfile,
name=names,
sep=separator,
more_name=more_names)
gc.disable()
close_properly(outputfile, inputfile)
def midpoints(inputfile=None,
outputfile=None,
ft_type="transcript",
names="transcript_id",
separator="|"):
"""
Get the midpoint coordinates for the requested feature.
"""
message("Loading input file...")
if inputfile.name == '<stdin>':
is_gtf = True
else:
region_bo = BedTool(inputfile.name)
if len(region_bo) == 0:
message("Unable to find requested regions", type="ERROR")
if region_bo.file_type == 'gff':
is_gtf = True
else:
is_gtf = False
if is_gtf:
gtf = GTF(inputfile.name, check_ensembl_format=False)
bed_obj = gtf.select_by_key("feature", ft_type).get_midpoints(
name=names.split(","), sep=separator)
for line in bed_obj:
write_properly(chomp(str(line)), outputfile)
else:
for line in region_bo:
diff = line.end - line.start
if diff % 2 != 0:
# e.g 10-13 (zero based) -> 11-13 one based
# mipoint is 12 (one-based) -> 11-12 (zero based)
# e.g 949-1100 (zero based) -> 950-1100 one based
# mipoint is 1025 (one-based) -> 1024-1025 (zero based)
# floored division (python 2)...
line.end = line.start + int(diff // 2) + 1
line.start = line.end - 1
else:
# e.g 10-14 (zero based) -> 11-14 one based
# mipoint is 12-13 (one-based) -> 11-13 (zero based)
# e.g 9-5100 (zero based) -> 10-5100 one based
# mipoint is 2555-2555 (one-based) -> 2554-2555 (zero based)
# floored division (python 2)...
# No real center. Take both
line.start = line.start + int(diff // 2) - 1
line.end = line.start + 2
outputfile.write(str(line))
gc.disable()
close_properly(outputfile, inputfile)
def del_attr(inputfile=None,
outputfile=None,
key="transcript_id",
reg_exp=False,
invert_match=False):
"""
Delete extended attributes in the target gtf file. attr_list can be a
comma-separated list of attributes.
"""
# ----------------------------------------------------------------------
# Read the GTF and get the list of attributes
# ----------------------------------------------------------------------
gtf = GTF(inputfile, check_ensembl_format=False)
attr_list = gtf.attr_extended
# ----------------------------------------------------------------------
# If regExp, select the corresponding keys
# ----------------------------------------------------------------------
if reg_exp:
key_list = []
try:
rgxp = re.compile(key)
except:
message("Check the regular expression please.", type="ERROR")
for attr in attr_list:
if rgxp.search(attr):
key_list += [attr]
else:
key_list = key.split(",")
# ----------------------------------------------------------------------
# If invert-match select all but the selected
# ----------------------------------------------------------------------
key_to_del = []
if invert_match:
for attr in attr_list:
if attr not in key_list:
key_to_del += [attr]
else:
key_to_del = key_list
# ----------------------------------------------------------------------
# Delete the keys
# ----------------------------------------------------------------------
gtf = gtf.del_attr(feat="*", keys=",".join(key_list),
force=True).write(outputfile, gc_off=True)
close_properly(outputfile, inputfile)
def select_by_max_exon_nb(inputfile=None, outputfile=None):
"""
Select transcripts based on the number of exons.
"""
msg = "Selecting transcript with the highest number of exon for each gene."
message(msg)
gtf = GTF(inputfile, check_ensembl_format=False).select_by_max_exon_nb()
gtf.write(outputfile, gc_off=True)
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 add_prefix(inputfile=None,
outputfile=None,
key="transcript_id",
text=None,
target_feature="*",
suffix=False):
"""
Add a prefix to target values.
"""
gtf = GTF(inputfile, check_ensembl_format=False)
gtf.add_prefix(target_feature, key, text, suffix).write(outputfile,
gc_off=True)
close_properly(outputfile, inputfile)
def convert_ensembl(inputfile=None, outputfile=None, no_check_gene_chr=False):
"""
Convert the GTF file to ensembl format.
"""
GTF(inputfile, check_ensembl_format=False).convert_to_ensembl(
check_gene_chr=not no_check_gene_chr, ).write(outputfile, gc_off=True)
close_properly(outputfile, inputfile)
def select_by_nb_exon(inputfile=None,
outputfile=None,
min_exon_number=None,
max_exon_number=None):
"""
Select transcripts based on the number of exons.
"""
msg = "Selecting transcript by exon number (range: [{m},{M}])"
msg = msg.format(m=str(min_exon_number), M=str(max_exon_number))
message(msg)
gtf = GTF(inputfile, check_ensembl_format=False).select_by_number_of_exons(
min_exon_number, max_exon_number)
gtf.write(outputfile, gc_off=True)
close_properly(outputfile, inputfile)
def select_by_go(inputfile=None,
outputfile=None,
go_id=None,
https_proxy=None,
http_proxy=None,
list_datasets=None,
species=None,
invert_match=False):
""" Select lines from a GTF file based using a Gene Ontology ID (e.g GO:0050789).
"""
if not go_id.startswith("GO:"):
go_id = "GO:" + go_id
is_associated = OrderedDict()
bm = Biomart(http_proxy=http_proxy,
https_proxy=https_proxy)
bm.get_datasets('ENSEMBL_MART_ENSEMBL')
if list_datasets:
for i in sorted(bm.datasets):
write_properly(i.replace("_gene_ensembl", ""), outputfile)
sys.exit()
else:
if species + "_gene_ensembl" not in bm.datasets:
message("Unknow dataset/species.", type="ERROR")
bm.query({'query': XML.format(species=species, go=go_id)})
for i in bm.response.content.decode().split("\n"):
i = i.rstrip("\n")
if i != '':
is_associated[i] = 1
gtf = GTF(inputfile)
gtf_associated = gtf.select_by_key("gene_id",
",".join(list(is_associated.keys())),
invert_match)
gtf_associated.write(outputfile,
gc_off=True)
def seqid_list(inputfile=None, outputfile=None, separator=""):
"""
Select the seqid/chromosomes.
"""
for i in GTF(inputfile, check_ensembl_format=False).get_chroms(nr=True):
outputfile.write(str(i) + separator)
gc.disable()
close_properly(outputfile, inputfile)
def add_exon_nb(inputfile=None, outputfile=None, exon_numbering_key=None):
"""Add the exon number to each exon (based on 5' to 3' orientation)."""
message("Calling nb_exons.", type="DEBUG")
GTF(inputfile.name,
check_ensembl_format=False).add_exon_number(exon_numbering_key).write(
outputfile, gc_off=True)
close_properly(inputfile, outputfile)
def random_tx(inputfile=None,
outputfile=None,
max_transcript=None,
seed_value=None):
"""
Select randomly up to m transcript for each gene.
"""
message("loading the GTF.")
gtf = GTF(inputfile).select_by_key("feature", "gene", invert_match=True)
message("Getting gene_id and transcript_id")
gene2tx = gtf.extract_data("gene_id,transcript_id",
as_dict_of_merged_list=True,
no_na=True,
nr=True)
message("Selecting random transcript")
if seed_value is not None:
random.seed(seed_value, version=1)
tx_to_delete = []
for gn_id in gene2tx:
tx_list = gene2tx[gn_id]
nb_tx = len(tx_list)
max_cur = min(max_transcript, nb_tx)
pos_to_keep = random.sample(list(range(len(tx_list))), max_cur)
tx_list = [j for i, j in enumerate(tx_list) if i not in pos_to_keep]
tx_to_delete += tx_list
message("Printing results")
message("Selecting transcript.")
gtf.select_by_key("transcript_id",
",".join(tx_to_delete),
invert_match=True).write(outputfile, gc_off=True)
close_properly(outputfile, inputfile)
def intergenic(inputfile=None, outputfile=None, chrom_info=None):
"""
Extract intergenic regions.
"""
message("Searching for intergenic regions.")
gtf = GTF(inputfile)
intergenic_regions = gtf.get_intergenic(chrom_info)
nb_intergenic_region = 1
for i in intergenic_regions:
i.name = "region_" + str(nb_intergenic_region)
write_properly(chomp(str(i)), outputfile)
nb_intergenic_region += 1
gc.disable()
close_properly(outputfile, inputfile)
def get_attr_list(
inputfile=None,
outputfile=None,
separator="\n"):
"""
Get the list of attributes from a GTF file.
"""
gtf = GTF(inputfile, check_ensembl_format=False)
attr_list = gtf.get_attr_list()
n = 0
for i in attr_list:
if n != len(attr_list) - 1:
outputfile.write(i + separator)
else:
outputfile.write(i)
n += 1
gc.disable()
close_properly(outputfile, inputfile)
def select_by_numeric_value(inputfile=None,
outputfile=None,
test=None,
na_omit=None):
"""Select lines from a GTF file based on a boolean test on numeric values.
"""
GTF(inputfile, check_ensembl_format=False).eval_numeric(
test,
na_omit=na_omit,
).write(outputfile, gc_off=True)
close_properly(outputfile, inputfile)
def count_key_values(inputfile=None,
outputfile=None,
keys="gene_id,transcript_id",
uniq=True,
additional_text=None):
"""
Count the number values for a set of keys.
"""
gtf = GTF(inputfile, check_ensembl_format=False)
if uniq:
val_list = defaultdict(set)
else:
val_list = defaultdict(list)
if keys == "*":
key_list = gtf.get_attr_list()
keys = ",".join(key_list)
else:
key_list = keys.split(",")
for i in gtf.extract_data(keys, as_list_of_list=True):
for k, v in zip(key_list, i):
if v in ['.', '?']:
continue
if uniq:
val_list[k].add(v)
else:
val_list[k] += [v]
for i in key_list:
if additional_text is None:
outputfile.write(i + "\t" + str(len(val_list[i])) + "\n")
else:
outputfile.write(i + "\t" + str(len(val_list[i])) + "\t" +
additional_text + "\n")
gc.disable()
close_properly(outputfile, inputfile)
def exon_sizes(inputfile=None, outputfile=None, key_name=None):
"""
Add a new key to transcript features containing a comma-separated list of exon-size.
"""
gtf = GTF(inputfile)
all_tx_ids = gtf.get_tx_ids(nr=True)
tx_to_size_list = dict()
exons_starts = gtf.select_by_key("feature", "exon").extract_data(
"transcript_id,start",
as_dict_of_merged_list=True,
no_na=True,
nr=False)
if not len(exons_starts):
message("No exon found.", type="ERROR")
exons_ends = gtf.select_by_key("feature", "exon").extract_data(
"transcript_id,end", as_dict_of_merged_list=True, no_na=True, nr=False)
strands = gtf.select_by_key("feature", "transcript").extract_data(
"transcript_id,strand",
as_dict_of_values=True,
no_na=True,
nr=True,
hide_undef=True)
for tx_id in all_tx_ids:
size_list = []
for s, e in zip(exons_starts[tx_id], exons_ends[tx_id]):
size = str(int(e) - int(s) + 1)
size_list += [size]
if strands[tx_id] == "-":
size_list = reversed(size_list)
tx_to_size_list[tx_id] = ",".join(size_list)
if len(tx_to_size_list):
gtf = gtf.add_attr_from_dict(feat="transcript",
key="transcript_id",
a_dict=tx_to_size_list,
new_key=key_name)
gtf.write(outputfile, gc_off=True)
close_properly(outputfile, inputfile)
def select_by_regexp(inputfile=None,
outputfile=None,
key=None,
regexp=None,
invert_match=False):
"""Select lines from a GTF file based on attributes and
associated values.
"""
GTF(inputfile, check_ensembl_format=False).select_by_regexp(
key, regexp, invert_match).write(outputfile, gc_off=True)
close_properly(outputfile, inputfile)
def nb_transcripts(inputfile=None,
outputfile=None,
text_format=False,
key_name=""):
"""
Compute the number of transcript per gene.
"""
gtf = GTF(inputfile)
message("Computing the number of transcript per gene in input GTF file.")
# Computation of transcript number is performed on exon lines
# Just in case some transcript lines would be lacking (but they should
# not...)
n_tx = gtf.get_gn_to_tx()
if not text_format:
tmp_file = make_tmp_file(prefix="nb_tx", suffix=".txt")
for i in n_tx:
if not text_format:
tmp_file.write(i + "\t" + str(len(n_tx[i])) + "\n")
else:
outputfile.write(i + "\t" + str(len(n_tx[i])) + "\n")
if not text_format:
tmp_file.close()
gtf.add_attr_from_file(feat="gene",
key="gene_id",
new_key=key_name,
inputfile=tmp_file.name).write(outputfile,
gc_off=True)
close_properly(outputfile, inputfile)
def intron_sizes(
inputfile=None,
outputfile=None,
key_name=None):
"""
Add a new key to transcript features containing a comma-separated list of intron sizes.
"""
gtf = GTF(inputfile, check_ensembl_format=False)
all_tx_ids = gtf.get_tx_ids(nr=True)
intron_bo = gtf.get_introns(by_transcript=True,
name=["transcript_id"],
intron_nb_in_name=False,
feat_name=False)
strands = gtf.select_by_key("feature",
"transcript").extract_data("transcript_id,strand",
as_dict_of_values=True,
no_na=True,
nr=True,
hide_undef=True)
intron_size = {tx: [] for tx in all_tx_ids}
for bed_line in intron_bo:
intron_size[bed_line.name] += [str(bed_line.end - bed_line.start)]
for tx_id in intron_size:
if len(intron_size[tx_id]):
if strands[tx_id] == "-":
intron_size[tx_id] = ",".join(reversed(intron_size[tx_id]))
else:
intron_size[tx_id] = ",".join(intron_size[tx_id])
else:
intron_size[tx_id] = "0"
if len(intron_size):
gtf = gtf.add_attr_from_dict(feat="transcript",
key="transcript_id",
a_dict=intron_size,
new_key=key_name)
gtf.write(outputfile,
gc_off=True)
close_properly(outputfile, inputfile)
def merge_attr(inputfile=None,
outputfile=None,
src_key="gene_id,transcript_id",
separator="|",
target_feature="*",
dest_key="gene_tx_ids"):
"""
Merge a set of attributes into a destination attribute.
"""
GTF(inputfile,
check_ensembl_format=False).merge_attr(target_feature, src_key,
dest_key,
separator).write(outputfile,
gc_off=True)
close_properly(outputfile, inputfile)
def select_by_tx_size(inputfile=None,
outputfile=None,
min_size=None,
max_size=None):
"""
Select features by size.
"""
msg = "Selecting 'mature/spliced transcript by size (range: [{m},{M}])."
msg = msg.format(m=str(min_size),
M=str(max_size))
message(msg)
GTF(inputfile
).select_by_transcript_size(min_size,
max_size
).write(outputfile,
gc_off=True)
def select_most_5p_tx(inputfile=None, outputfile=None, keep_gene_lines=False):
"""
Select the most 5' transcript of each gene.
"""
message("Selecting the most 5' transcript of each gene.")
gtf = GTF(inputfile)
if keep_gene_lines:
gtf = gtf.select_5p_transcript()
else:
gtf = gtf.select_5p_transcript().select_by_key("feature", "gene", 1)
gtf.write(outputfile, gc_off=True)
def short_long(inputfile=None,
outputfile=None,
longs=None,
keep_gene_lines=False):
""" Select the shortest transcript for each gene, Or the longuest if the \
-l arguments is used. """
gtf = GTF(inputfile, check_ensembl_format=False)
if longs:
gtf = gtf.select_longuest_transcripts()
else:
gtf = gtf.select_shortest_transcripts()
if not keep_gene_lines:
gtf = gtf.select_by_key("feature", "gene", 1)
gtf.write(outputfile,
gc_off=True)
def random_list(inputfile=None,
outputfile=None,
number=None,
ft_type=None,
seed_value=None):
"""
Select a random list of genes or transcripts.
"""
message("loading the GTF.")
gtf = GTF(inputfile)
message("Getting ID list.")
if ft_type == 'gene':
id_list = gtf.extract_data("gene_id",
as_list=True,
nr=True,
hide_undef=True,
no_na=True)
else:
id_list = gtf.extract_data("transcript_id",
as_list=True,
nr=True,
hide_undef=True,
no_na=True)
if number > len(id_list):
message("To much feature. Using : " + str(len(id_list)),
type="WARNING")
number = len(id_list)
if seed_value is not None:
random.seed(seed_value, version=1)
id_list = random.sample(id_list, number)
message("Printing.")
my_id = ft_type + "_id"
gtf.select_by_key(my_id, ",".join(id_list)).write(outputfile, gc_off=True)
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 nb_exons(inputfile=None,
outputfile=None,
key_name=None,
text_format=False):
"""
Count the number of exons in the gtf file.
"""
gtf = GTF(inputfile)
n_exons = defaultdict(int)
# -------------------------------------------------------------------------
# Computing number of exon for each transcript in input GTF file
#
# -------------------------------------------------------------------------
message("Computing number of exons for each transcript in input GTF file.")
exon = gtf.select_by_key("feature", "exon")
fields = exon.extract_data("transcript_id")
for i in fields:
tx_id = i[0]
n_exons[tx_id] += 1
if text_format:
for tx_id in n_exons:
outputfile.write(tx_id + "\t" + str(n_exons[tx_id]) +
"\ttranscript\n")
else:
if len(n_exons):
gtf = gtf.add_attr_from_dict(feat="transcript",
key="transcript_id",
a_dict=n_exons,
new_key=key_name)
gtf.write(outputfile, gc_off=True)
close_properly(outputfile, inputfile)
