def test_merger(self):
with tempfile.NamedTemporaryFile(suffix=".tmp", mode="wt", delete=False) as first, \
tempfile.NamedTemporaryFile(suffix=".tmp", mode="wt", delete=False) as second, \
tempfile.NamedTemporaryFile(suffix=".tmp", mode="wt", delete=False) as third,\
tempfile.NamedTemporaryFile(suffix=".out", mode="wt", delete=False) as out:
print("1/first case", file=first)
print("3/third case", file=first)
print("4/fourth case", file=first)
print("2/second case", file=second)
print("5/fifth case", file=third)
print("6/sixth case", file=second)
first.flush()
second.flush()
third.flush()
logger = create_default_logger("test_merger", level="DEBUG")
utilities.merge_partial([first.name, second.name, third.name], out, logger=logger)
with open(out.name) as _:
lines = [l for l in _]
self.assertEqual(len(lines), 6, (out.name, lines))
self.assertEqual(lines[0], "first case\n", lines)
self.assertEqual(lines[1], "second case\n")
self.assertEqual(lines[2], "third case\n")
self.assertEqual(lines[3], "fourth case\n")
self.assertEqual(lines[4], "fifth case\n")
self.assertEqual(lines[5], "sixth case\n")
# Verify the temporary files have been deleted correctly
existing = []
for handle in (first, second, third):
if os.path.exists(handle.name):
existing.append(handle.name)
self.assertEqual(len(existing), 0, [os.remove(name) for name in existing])
self.assertTrue(os.path.exists(out.name))
os.remove(out.name)
def main():
logger = create_default_logger("sanitizer")
parser = argparse.ArgumentParser(__doc__)
parser.add_argument("-o",
"--out",
default=sys.stdout,
type=argparse.FileType("wt"))
parser.add_argument("fasta", nargs="+", type=argparse.FileType("rt"))
args = parser.parse_args()
found_ids = Counter()
starter = 96
for fasta in args.fasta:
if len(args.fasta) > 1:
starter += 1
prefix = "{}_".format(chr(starter))
else:
prefix = ""
for record in Bio.SeqIO.parse(fasta, "fasta"):
if record.id in found_ids:
logger.warning(
"ID found other {} time{} in the input files!".format(
found_ids[record.id],
"s" if found_ids[record.id] > 1 else ""))
record.id = "{}{}".format(prefix, record.id)
record.description = ""
Bio.SeqIO.write(record, args.out, "fasta")
args.out.close()
def main():
logger = create_default_logger("sanitizer")
parser = argparse.ArgumentParser(__doc__)
parser.add_argument("-ml", "--min-length", default=0, type=pos)
parser.add_argument("-o", "--out", default=sys.stdout, type=argparse.FileType("wt"))
parser.add_argument("fasta", nargs="+", type=argparse.FileType("rt"))
args = parser.parse_args()
found_ids = Counter()
starter = 96
for fasta in args.fasta:
if fasta.name.endswith(".gz"):
fasta.close()
fasta = gzip.open(fasta.name, "rt")
if len(args.fasta) > 1:
starter += 1
prefix = "{}_".format(chr(starter))
else:
prefix = ""
for record in Bio.SeqIO.parse(fasta, "fasta"):
if record.id in found_ids:
logger.warning("ID found other {} time{} in the input files!".format(
found_ids[record.id], "s" if found_ids[record.id] > 1 else ""))
record.id = "{}{}".format(prefix, re.sub(r"\|", "_", record.id))
record.description = ""
if len(record) < args.min_length:
continue
Bio.SeqIO.write(record, args.out, "fasta")
args.out.close()
def main():
logger = create_default_logger("sanitizer")
parser = argparse.ArgumentParser(__doc__)
parser.add_argument("-o", "--out", default=sys.stdout, type=argparse.FileType("wt"))
parser.add_argument("fasta", nargs="+", type=argparse.FileType("rt"))
args = parser.parse_args()
found_ids = Counter()
starter = 96
for fasta in args.fasta:
if len(args.fasta) > 1:
starter += 1
prefix = "{}_".format(chr(starter))
else:
prefix = ""
for record in Bio.SeqIO.parse(fasta, "fasta"):
if record.id in found_ids:
logger.warning("ID found other {} time{} in the input files!".format(
found_ids[record.id], "s" if found_ids[record.id] > 1 else ""))
record.id = "{}{}".format(prefix, record.id)
record.description = ""
Bio.SeqIO.write(record, args.out, "fasta")
args.out.close()
def __init__(self, out_sq, queue, verbosity="INFO"):
super().__init__()
self.out_sq = out_sq
self.logging_queue = logging_queue
self.logger = create_default_logger("")
self.log_level = verbosity
create_queue_logger(self)
self.engine = sqlalchemy.create_engine("sqlite:///{}".format(out_sq))
transfer_base.metadata.create_all(self.engine)
self.Session = sessionmaker(bind=self.engine)
self.session = self.Session()
self.queue = queue
def test_with_no_gff_utr(self):
"""
Test the creation of the transcript without the UTR lines, verify that everything is still alright
:return:
"""
tr_gff = """Chr2 TAIR10 mRNA 626642 629176 . + . ID=AT2G02380.1;Parent=AT2G02380
Chr2 TAIR10 exon 626642 626780 . + . Parent=AT2G02380.1
Chr2 TAIR10 exon 626842 626880 . + . Parent=AT2G02380.1
Chr2 TAIR10 CDS 626878 626880 . + 0 Parent=AT2G02380.1
Chr2 TAIR10 exon 626963 627059 . + . Parent=AT2G02380.1
Chr2 TAIR10 CDS 626963 627059 . + 0 Parent=AT2G02380.1
Chr2 TAIR10 exon 627137 627193 . + . Parent=AT2G02380.1
Chr2 TAIR10 CDS 627137 627193 . + 2 Parent=AT2G02380.1
Chr2 TAIR10 exon 627312 627397 . + . Parent=AT2G02380.1
Chr2 TAIR10 CDS 627312 627397 . + 2 Parent=AT2G02380.1
Chr2 TAIR10 exon 627488 627559 . + . Parent=AT2G02380.1
Chr2 TAIR10 CDS 627488 627559 . + 0 Parent=AT2G02380.1
Chr2 TAIR10 exon 627696 627749 . + . Parent=AT2G02380.1
Chr2 TAIR10 CDS 627696 627749 . + 0 Parent=AT2G02380.1
Chr2 TAIR10 exon 627840 627915 . + . Parent=AT2G02380.1
Chr2 TAIR10 CDS 627840 627915 . + 0 Parent=AT2G02380.1
Chr2 TAIR10 exon 628044 628105 . + . Parent=AT2G02380.1
Chr2 TAIR10 CDS 628044 628105 . + 2 Parent=AT2G02380.1
Chr2 TAIR10 exon 628182 628241 . + . Parent=AT2G02380.1
Chr2 TAIR10 CDS 628182 628241 . + 0 Parent=AT2G02380.1
Chr2 TAIR10 exon 628465 628676 . + . Parent=AT2G02380.1
Chr2 TAIR10 CDS 628465 628569 . + 0 Parent=AT2G02380.1
Chr2 TAIR10 exon 629070 629176 . + . Parent=AT2G02380.1"""
tr_lines = tr_gff.split("\n")
logger = create_default_logger("test")
logger.setLevel("INFO")
for pos, line in enumerate(tr_lines):
tr_lines[pos] = re.sub(r"\s+", "\t", line)
assert len(tr_lines[pos].split("\t")) == 9, line.split("\t")
tr_gff_lines = [parsers.GFF.GffLine(line) for line in tr_lines]
transcript = loci.Transcript(tr_gff_lines[0], logger=logger)
for line in tr_gff_lines[1:]:
transcript.add_exon(line)
self.assertEqual(transcript.exons, self.tr.exons)
self.assertNotEqual([], transcript.combined_cds)
transcript.finalize()
self.assertTrue(transcript.is_coding)
self.assertEqual(transcript.five_utr, self.tr.five_utr)
self.assertEqual(transcript.three_utr, self.tr.three_utr)
def test_split(self):
self.tr.load_orfs([self.bed1, self.bed2])
self.assertEqual(self.tr.selected_cds_start, 15494127)
self.assertEqual(self.tr.selected_cds_end, 15495994)
self.assertEqual(self.tr.combined_cds_start, 15490903)
# The other CDS starts at 15494127
logger = create_default_logger(self.tr.id)
logger.setLevel("WARN")
self.tr.logger = logger
new_transcripts = [_ for _ in self.tr.split_by_cds()]
self.assertEqual(len(new_transcripts), 2)
def test_split(self):
# Chr3 Cufflinks mRNA 2949168 2952410 1000 - . ID=cufflinks_cufflinks_star_at.10687.1.orf1;
# Chr3 Cufflinks three_prime_UTR 2949168 2950204 . - . Parent=cufflinks_cufflinks_star_at.10687.1.orf1
# Chr3 Cufflinks exon 2949168 2952410 . - . Parent=cufflinks_cufflinks_star_at.10687.1.orf1
# Chr3 Cufflinks CDS 2,950,205 2,952,208 . - 0 Parent=cufflinks_cufflinks_star_at.10687.1.orf1
# Chr3 Cufflinks five_prime_UTR 2952209 2952410 . - . Parent=cufflinks_cufflinks_star_at.10687.1.orf1
#
# Chr3 Cufflinks mRNA 2949168 2952410 1000 - . ID=cufflinks_cufflinks_star_at.10687.1.orf2;
# Chr3 Cufflinks three_prime_UTR 2949168 2949169 . - . Parent=cufflinks_cufflinks_star_at.10687.1.orf2
# Chr3 Cufflinks exon 2949168 2952410 . - . Parent=cufflinks_cufflinks_star_at.10687.1.orf2
# Chr3 Cufflinks CDS 2,949,170 2,949,868 . - 0 Parent=cufflinks_cufflinks_star_at.10687.1.orf2
# Chr3 Cufflinks five_prime_UTR 2949869 2952410 . - . Parent=cufflinks_cufflinks_star_at.10687.1.orf2
# =============>
# Chr3 Cufflinks mRNA 2950205 2952410 1000 - . ID=cufflinks_cufflinks_star_at.10687.1.split1;
# Chr3 Cufflinks exon 2950205 2952410 . - . Parent=cufflinks_cufflinks_star_at.10687.1.split1
# Chr3 Cufflinks CDS 2950205 2952208 . - 0 Parent=cufflinks_cufflinks_star_at.10687.1.split1
# Chr3 Cufflinks five_prime_UTR 2952209 2952410 . - . Parent=cufflinks_cufflinks_star_at.10687.1.split1
#
# Chr3 Cufflinks mRNA 2949168 2949868 1000 - . ID=cufflinks_cufflinks_star_at.10687.1.split2;
# Chr3 Cufflinks three_prime_UTR 2949168 2949169 . - . Parent=cufflinks_cufflinks_star_at.10687.1.split2
# Chr3 Cufflinks exon 2949168 2949868 . - . Parent=cufflinks_cufflinks_star_at.10687.1.split2
# Chr3 Cufflinks CDS 2949170 2949868 . - 0 Parent=cufflinks_cufflinks_star_at.10687.1.split2
self.tr.load_orfs([self.bed1, self.bed2])
self.assertEqual(self.tr.strand, "-")
self.assertEqual(self.tr.number_internal_orfs, 2)
self.assertEqual(self.tr.combined_cds_end, 2949170)
self.assertEqual(self.tr.combined_cds_start, 2952208)
self.assertEqual(self.tr.selected_cds_start, 2952208)
self.assertEqual(self.tr.selected_cds_end, 2950205)
logger = create_default_logger("splitter")
logger.setLevel("ERROR")
self.tr.logger = logger
new_transcripts = sorted([_ for _ in self.tr.split_by_cds()])
self.assertEqual(new_transcripts[0].start, self.tr.start)
self.assertEqual(new_transcripts[0].end, 2949868,
"\n\n".join([str(_) for _ in new_transcripts]))
def test_split(self):
# Chr3 Cufflinks mRNA 2949168 2952410 1000 - . ID=cufflinks_cufflinks_star_at.10687.1.orf1;
# Chr3 Cufflinks three_prime_UTR 2949168 2950204 . - . Parent=cufflinks_cufflinks_star_at.10687.1.orf1
# Chr3 Cufflinks exon 2949168 2952410 . - . Parent=cufflinks_cufflinks_star_at.10687.1.orf1
# Chr3 Cufflinks CDS 2,950,205 2,952,208 . - 0 Parent=cufflinks_cufflinks_star_at.10687.1.orf1
# Chr3 Cufflinks five_prime_UTR 2952209 2952410 . - . Parent=cufflinks_cufflinks_star_at.10687.1.orf1
#
# Chr3 Cufflinks mRNA 2949168 2952410 1000 - . ID=cufflinks_cufflinks_star_at.10687.1.orf2;
# Chr3 Cufflinks three_prime_UTR 2949168 2949169 . - . Parent=cufflinks_cufflinks_star_at.10687.1.orf2
# Chr3 Cufflinks exon 2949168 2952410 . - . Parent=cufflinks_cufflinks_star_at.10687.1.orf2
# Chr3 Cufflinks CDS 2,949,170 2,949,868 . - 0 Parent=cufflinks_cufflinks_star_at.10687.1.orf2
# Chr3 Cufflinks five_prime_UTR 2949869 2952410 . - . Parent=cufflinks_cufflinks_star_at.10687.1.orf2
# =============>
# Chr3 Cufflinks mRNA 2950205 2952410 1000 - . ID=cufflinks_cufflinks_star_at.10687.1.split1;
# Chr3 Cufflinks exon 2950205 2952410 . - . Parent=cufflinks_cufflinks_star_at.10687.1.split1
# Chr3 Cufflinks CDS 2950205 2952208 . - 0 Parent=cufflinks_cufflinks_star_at.10687.1.split1
# Chr3 Cufflinks five_prime_UTR 2952209 2952410 . - . Parent=cufflinks_cufflinks_star_at.10687.1.split1
#
# Chr3 Cufflinks mRNA 2949168 2949868 1000 - . ID=cufflinks_cufflinks_star_at.10687.1.split2;
# Chr3 Cufflinks three_prime_UTR 2949168 2949169 . - . Parent=cufflinks_cufflinks_star_at.10687.1.split2
# Chr3 Cufflinks exon 2949168 2949868 . - . Parent=cufflinks_cufflinks_star_at.10687.1.split2
# Chr3 Cufflinks CDS 2949170 2949868 . - 0 Parent=cufflinks_cufflinks_star_at.10687.1.split2
self.tr.load_orfs([self.bed1, self.bed2])
self.assertEqual(self.tr.strand, "-")
self.assertEqual(self.tr.number_internal_orfs, 2)
self.assertEqual(self.tr.combined_cds_end, 2949170)
self.assertEqual(self.tr.combined_cds_start, 2952208)
self.assertEqual(self.tr.selected_cds_start, 2952208)
self.assertEqual(self.tr.selected_cds_end, 2950205)
logger = create_default_logger("splitter")
logger.setLevel("ERROR")
self.tr.logger = logger
new_transcripts = sorted([_ for _ in self.tr.split_by_cds()])
self.assertEqual(new_transcripts[0].start, self.tr.start)
self.assertEqual(new_transcripts[0].end, 2949868, "\n\n".join([str(_) for _ in new_transcripts]))
def test_split(self):
self.tr.load_orfs([self.bed1, self.bed2])
self.assertEqual(self.tr.number_internal_orfs, 2)
logger = create_default_logger("splitter")
logger.setLevel("ERROR")
self.tr.logger = logger
new_transcripts = [_ for _ in self.tr.split_by_cds()]
new_transcripts = sorted(new_transcripts,
key=operator.attrgetter("start", "end"))
self.assertEqual(len(new_transcripts), 2)
self.assertEqual(new_transcripts[0].start, 72914)
self.assertEqual(new_transcripts[0].end, 74914)
self.assertEqual(new_transcripts[1].end, 76276, self.tr.internal_orfs)
self.assertEqual(new_transcripts[1].start, 75394)
self.assertEqual(new_transcripts[0].selected_cds_start, 74914)
self.assertEqual(new_transcripts[0].selected_cds_end, 74336)
self.assertEqual(new_transcripts[1].selected_cds_start, 75804)
self.assertEqual(new_transcripts[1].selected_cds_end, 75394)
def test_split(self):
self.tr.load_orfs([self.bed1, self.bed2])
self.assertEqual(self.tr.number_internal_orfs, 2)
logger = create_default_logger("splitter")
logger.setLevel("ERROR")
self.tr.logger = logger
new_transcripts = [_ for _ in self.tr.split_by_cds()]
new_transcripts = sorted(new_transcripts,
key=operator.attrgetter("start", "end"))
self.assertEqual(len(new_transcripts), 2)
self.assertEqual(new_transcripts[0].start, 72914)
self.assertEqual(new_transcripts[0].end, 74914)
self.assertEqual(new_transcripts[1].end, 76276, self.tr.internal_orfs)
self.assertEqual(new_transcripts[1].start, 75394)
self.assertEqual(new_transcripts[0].selected_cds_start, 74914)
self.assertEqual(new_transcripts[0].selected_cds_end, 74336)
self.assertEqual(new_transcripts[1].selected_cds_start, 75804)
self.assertEqual(new_transcripts[1].selected_cds_end, 75394)
class MonoHolderTester(unittest.TestCase):
logger = create_default_logger("MonoHolderTester")
def setUp(self):
self.conf = dict()
self.t1 = Transcript()
self.t1.chrom = "Chr1"
self.t1.strand = "+"
self.t1.score = 20
self.t1.id = "G1.1"
self.t1.parent = "G1"
self.t1.start = 101
self.t1.end = 1500
self.t1.add_exons([(101, 500), (601, 700), (1001, 1300), (1401, 1500)],
"exon")
self.t1.add_exons([(401, 500), (601, 700), (1001, 1300), (1401, 1440)],
"CDS")
self.t1.finalize()
def testCdsOverlap(self):
t2 = Transcript()
t2.chrom = "Chr1"
t2.strand = "+"
t2.score = 1
t2.id = "G2.1"
t2.parent = "G2"
t2.start = 101
t2.end = 1600
t2.add_exons([(101, 500), (601, 700), (1001, 1300), (1401, 1460),
(1501, 1600)], "exon")
t2.add_exons([(401, 500), (601, 700), (1001, 1300), (1401, 1440)],
"CDS")
t2.finalize()
self.assertTrue(MonosublocusHolder.is_intersecting(self.t1, t2))
def test_intronMatch(self):
t2 = Transcript()
t2.chrom = "Chr1"
t2.strand = "+"
t2.score = 1
t2.id = "G2.1"
t2.parent = "G2"
t2.start = 101
t2.end = 1600
t2.add_exons([(101, 500), (601, 700), (1001, 1320), (1451, 1460),
(1501, 1600)], "exon")
t2.add_exons([(401, 500), (601, 700), (1001, 1320), (1451, 1460),
(1501, 1510)], "CDS")
t2.finalize()
self.assertTrue(self.t1.is_coding)
self.assertTrue(t2.is_coding)
self.assertTrue(
MonosublocusHolder.is_intersecting(self.t1, t2,
logger=self.logger))
self.assertTrue(
MonosublocusHolder.is_intersecting(self.t1,
t2,
cds_only=True,
logger=self.logger))
def test_intronOverlap(self):
self.t1.strip_cds()
t2 = Transcript()
t2.chrom = "Chr1"
t2.strand = "+"
t2.score = 1
t2.id = "G2.1"
t2.parent = "G2"
t2.start = 101
t2.end = 1470
t2.add_exons([(101, 510), (601, 700), (960, 1350), (1420, 1470)])
t2.finalize()
self.assertTrue(MonosublocusHolder.is_intersecting(self.t1, t2))
def test_noIntronOverlap(self):
self.t1.strip_cds()
t2 = Transcript()
t2.chrom = "Chr1"
t2.strand = "+"
t2.score = 1
t2.id = "G2.1"
t2.parent = "G2"
t2.start = 1250
t2.end = 2000
t2.add_exons([(1250, 1560), (1800, 2000)])
t2.finalize()
self.assertFalse(MonosublocusHolder.is_intersecting(self.t1, t2))
def test_noCDSOverlap(self):
self.t1.strip_cds()
self.assertEqual(self.t1.combined_cds_introns, set())
self.t1.finalized = False
self.t1.add_exons([(401, 500), (601, 700), (1001, 1100)], "CDS")
self.t1.finalize()
t2 = Transcript()
t2.logger = self.logger
t2.chrom = "Chr1"
t2.strand = "+"
t2.score = 1
t2.id = "G2.1"
t2.parent = "G2"
t2.start = 101
t2.end = 1470
t2.add_exons([(101, 510), (601, 700), (960, 1350), (1421, 1470)])
t2.add_exons([(1201, 1350), (1421, 1450)], "CDS")
t2.finalize()
self.assertTrue(self.t1.is_coding)
self.assertTrue(t2.is_coding)
self.assertGreaterEqual(
0,
overlap((self.t1.combined_cds_start, self.t1.combined_cds_end),
(t2.combined_cds_start, t2.combined_cds_end)),
[(self.t1.combined_cds_start, self.t1.combined_cds_end),
(t2.combined_cds_start, t2.combined_cds_end)])
self.assertTrue(
MonosublocusHolder.is_intersecting(self.t1, t2,
logger=self.logger))
self.assertFalse(
MonosublocusHolder.is_intersecting(self.t1,
t2,
cds_only=True,
logger=self.logger))
def test_only_CDS_overlap(self):
t2 = Transcript()
t2.chrom = "Chr1"
t2.strand = "+"
t2.score = 1
t2.id = "G2.1"
t2.parent = "G2"
t2.start = 1250
t2.end = 2000
t2.add_exons([(1250, 1560), (1801, 2000)])
t2.add_exons([(1401, 1560), (1801, 1850)], "CDS")
t2.finalize()
self.assertFalse(MonosublocusHolder.is_intersecting(self.t1, t2))
t2.strip_cds()
t2.finalized = False
t2.add_exons([(1461, 1560), (1801, 1850)], "CDS")
# No CDS overlap this time
self.assertFalse(MonosublocusHolder.is_intersecting(self.t1, t2))
def test_no_overlap(self):
t2 = Transcript()
t2.chrom = "Chr1"
t2.strand = "+"
t2.score = 1
t2.id = "G2.1"
t2.parent = "G2"
t2.start = 1600
t2.end = 2000
t2.add_exons([(1600, 1700), (1801, 2000)])
t2.add_exons([(1661, 1700), (1801, 1850)], "CDS")
t2.finalize()
self.assertFalse(MonosublocusHolder.is_intersecting(self.t1, t2))
def test_same_id(self):
t2 = Transcript()
t2.chrom = "Chr1"
t2.strand = "+"
t2.score = 1
t2.id = "G1.1"
t2.parent = "G1"
t2.start = 1250
t2.end = 2000
t2.add_exons([(1250, 1560), (1801, 2000)])
t2.add_exons([(1401, 1560), (1801, 1850)], "CDS")
t2.finalize()
# This fails because they have the same ID
self.assertFalse(MonosublocusHolder.is_intersecting(self.t1, t2))
def main():
parser = argparse.ArgumentParser(__doc__)
parser.add_argument("--bed12",
nargs=2,
required=True,
help="Transcriptomic cDNAs BED12s")
parser.add_argument("--cdnas", nargs=2, required=True)
parser.add_argument("-gf",
help="GFF3/BED12 of the transferred annotation.",
required=True)
parser.add_argument("--out",
default=sys.stdout,
type=argparse.FileType("wt"))
parser.add_argument("-ob",
"--out-bed",
dest="out_bed",
required=False,
default=None,
type=argparse.FileType("wt"))
log = parser.add_mutually_exclusive_group()
log.add_argument("-q", "--quiet", default=False, action="store_true")
log.add_argument("-v", "--verbose", default=False, action="store_true")
parser.add_argument("-p", "--processes", type=int, default=mp.cpu_count())
args = parser.parse_args()
logger = create_default_logger("master")
verbosity = "INFO"
if args.verbose is True:
verbosity = "DEBUG"
elif args.quiet is True:
verbosity = "WARNING"
listener = logging.handlers.QueueListener(logging_queue, logger)
listener.propagate = False
listener.start()
logger.setLevel(verbosity)
cdnas = dict()
beds = dict()
beds["ref"] = dict()
beds["target"] = dict()
gmap_pat = re.compile("\.mrna[0-9]*$")
logger.info("Loading reference cDNAS")
cdnas["ref"] = pyfaidx.Fasta(args.cdnas[0])
logger.info("Loading target cDNAS")
cdnas["target"] = pyfaidx.Fasta(args.cdnas[1])
logger.info("Loaded cDNAs")
logger.info("Loading reference BED12")
for entry in Bed12Parser(args.bed12[0], transcriptomic=True):
if entry.header:
continue
name = entry.chrom
if name in beds["ref"]:
raise KeyError("Duplicated ID for the reference: {}".format(name))
if name not in cdnas["ref"]:
raise KeyError("Reference {} not found in the cDNAs!".format(name))
beds["ref"][name] = entry
logger.info("Loading target BED12")
beds["target"] = defaultdict(dict)
for entry in Bed12Parser(args.bed12[1], transcriptomic=True):
# Now, here we have to account for the fact that there *might* be multiple alignments
name = re.sub(gmap_pat, "", entry.chrom)
if entry.chrom not in cdnas["target"]:
raise KeyError("Target {} not found in the cDNAs!".format(
entry.chrom))
beds["target"][name][entry.chrom] = entry
logger.info("Loaded BED12s")
# Now let us start parsing the GFF3, which we presume being a GMAP GFF3
transcript = None
logger.info("Launching sub-processes")
procs = []
queue = mp.Queue(-1)
for proc in range(args.processes):
sq = tempfile.NamedTemporaryFile(mode="wb")
sq.close()
sq = sq.name
_proc = Transferer(sq, queue, verbosity=verbosity)
_proc.start()
procs.append(_proc)
logger.info("Launched sub-processes, starting parsing annotation")
# pool = mp.Pool(processes=args.processes)
tnum = -1
if args.gf.endswith(("bed12", "bed")):
parser = Bed12Parser(args.gf, transcriptomic=False)
for line in parser:
if line.header:
continue
else:
transcript = Transcript(line)
tid = re.sub(gmap_pat, "", transcript.id)
logger.debug("Found %s", tid)
ref_cdna = str(cdnas["ref"][tid])
ref_bed = beds["ref"][tid]
target_cdna = str(cdnas["target"][transcript.id])
target_bed = beds["target"][tid][transcript.id]
tnum += 1
logger.debug("Submitting %s", tid)
queue.put((tnum, (transcript, ref_cdna, ref_bed, target_cdna,
target_bed)))
if tnum >= 10**4 and tnum % 10**4 == 0:
logger.info("Parsed {} transcripts", tnum)
logger.info("Finished parsing input genomic BED file")
else:
parser = to_gff(args.gf)
for pos, line in enumerate(parser):
if line.header is True: # or (not isinstance(line, BED12) and line.is_gene is True):
if str(line) == "###":
continue
try:
print(line, file=args.out)
except IndexError:
raise IndexError(line._line)
continue
elif not isinstance(line, BED12) and line.is_gene is True:
continue
elif line.is_transcript is True:
if transcript:
if transcript.alias is None:
tid = re.sub(gmap_pat, "", transcript.id)
else:
tid = re.sub(gmap_pat, "", transcript.alias)
ref_cdna = str(cdnas["ref"][tid])
ref_bed = beds["ref"][tid]
target_cdna = str(cdnas["target"][transcript.id])
store = beds["target"].get(tid, None)
if store is None:
raise KeyError((tid, beds["target"].keys()))
target_bed = store.get(transcript.id, None)
if target_bed is None:
raise KeyError((tid, store.keys()))
tnum += 1
queue.put((tnum, (transcript, ref_cdna, ref_bed,
target_cdna, target_bed)))
try:
transcript = Transcript(line)
except (ValueError, TypeError):
raise ValueError((pos, line))
elif line.is_exon is True:
transcript.add_exon(line)
if tnum >= 10**4 and tnum % 10**4 == 0:
logger.info("Parsed {} transcripts", tnum)
if transcript:
tnum += 1
tid = re.sub(gmap_pat, "", transcript.id)
ref_cdna = str(cdnas["ref"][tid])
ref_bed = beds["ref"][tid]
target_cdna = str(cdnas["target"][transcript.id])
target_bed = beds["target"][tid][transcript.id]
queue.put((tnum, (transcript, ref_cdna, ref_bed, target_cdna,
target_bed)))
logger.info("Finished parsing input genomic GF file")
queue.put("EXIT")
logger.info("Waiting for subprocesses to finish")
[_proc.join() for _proc in procs]
# Now the printing ...
# results = dict()
logger.info("Subprocesses finished, printing")
for proc in procs:
sq = sqlalchemy.create_engine("sqlite:///{}".format(proc.out_sq))
for res in sq.execute("select * from storer"):
num, bed12, gff3 = res
if args.out_bed is not None:
print(bed12.decode(), file=args.out_bed)
print(*gff3.decode().split("\n"), file=args.out, sep="\n")
os.remove(proc.out_sq)
logger.info("Finished!")
return
def main():
logger = create_default_logger("stat_serializer")
parser = argparse.ArgumentParser(__doc__)
parser.add_argument("--db",
required=True,
help="SQLite database to connect to.")
parser.add_argument("--force", action="store_true", default=False)
parser.add_argument(
"input_files",
help=
"""TXT tab-delimited file, specifying the input files in the following way:
- species
- aligner
- assembler
- basename for the comparisons against the complete reference
- basename for the comparisons against the filtered reference
""")
args = parser.parse_args()
# Create the database
connector = functools.partial(sqlite3.connect,
database=args.db,
check_same_thread=False)
engine = create_engine("sqlite://", creator=connector)
if args.force is True:
logger.warn("Removing old data because force option in place")
meta = sqlalchemy.MetaData(bind=engine)
meta.reflect(engine)
for tab in reversed(meta.sorted_tables):
logger.warn("Dropping %s", tab)
tab.drop()
inspector = Inspector.from_engine(engine)
Session = sessionmaker(bind=engine)
# session = Session(bind=engine, autocommit=True, autoflush=True)
session = Session()
if Indexer.__tablename__ not in inspector.get_table_names():
DBBASE.metadata.create_all(engine) # @UndefinedVariable
with open(args.input_files) as input_files:
for row in input_files:
species, aligner, assembler, complete, filtered = row.rstrip(
).split()
if not os.path.exists("{}.stats".format(complete)):
raise ValueError(
"Original file not found; line:\n{}".format(row))
if not os.path.exists("{}.stats".format(filtered)):
raise ValueError(
"Filtered file {} not found; line:\n{}".format(
"{}.stats".format(filtered), row))
current_species = Indexer(species, aligner, assembler)
session.add(current_species)
session.commit()
print(current_species.m_index)
complete_load = CompareFiles(current_species.m_index,
complete,
filtered=False)
session.add(complete_load)
# session.commit()
# filtered_load = CompareFiles(current_species.index, filtered, filtered=True)
# session.add(filtered_load)
# session.commit()
#
# orig_lines = [line.rstrip() for line in open(orig)]
# filtered_lines = [line.rstrip() for line in open(filtered)]
# # In the stats we have precision as second and sensitivity as first,
# # we have to invert
# for index, line_index in enumerate([5, 7, 8, 9, 12, 15]):
# precision = float(orig_lines[line_index].split(":")[1].split()[1])
# recall = float(filtered_lines[line_index].split(":")[1].split()[0])
# stats[
# # Name of the statistic:Base, Exon, etc
# list(stats.keys())[index]][
# b"TopHat"].append((precision, recall))
session.commit()
class TestMetricsEndDistances(unittest.TestCase):
logger = create_default_logger("End")
logger.setLevel("ERROR")
def setUp(self):
self.tr = Transcript()
self.tr.logger = self.logger
self.tr.start = 101
self.tr.end = 10000
self.tr.add_exons([(101, 300),
(501, 800),
(1001, 1200),
(1301, 2000),
(3501, 5000),
(5501, 6000),
(6201, 7000),
(7301, 7700),
(8201, 9000),
(9101, 9300),
(9501, 9700),
(9801, 10000)])
self.tr.id = "test1"
self.tr.parent = "test1.gene"
def test_end_positive(self):
self.tr.strand = "+"
cds = [(1161, 1200), # 40 % 3 == 1
(1301, 2000), # 700 % 3 == 1
(3501, 5000), # 1500 % 3 == 0
(5501, 6000), # 500 % 3 == 2
(6201, 7000), # 800 % 3 == 2
(7301, 7700), # 400 % 3 == 1
(8201, 9000), # 800 % 3 == 2
(9101, 9130)]
self.tr.add_exons(cds, features="CDS")
self.tr.finalize()
self.assertEqual(self.tr.selected_cds_end,
self.tr.combined_cds_end)
self.assertEqual(self.tr.selected_cds_end,
9130)
self.assertEqual(self.tr.end_distance_from_junction,
(9300 - 9131 + 1) + (9700 - 9501 + 1)
)
self.assertEqual(self.tr.end_distance_from_tes,
(9300 - 9131 + 1) + (9700 - 9501 + 1) + (10000 - 9801 + 1)
)
self.tr.strip_cds()
self.assertEqual(len(self.tr.internal_orfs), 0, self.tr.internal_orfs)
self.tr.finalized = False
cds = [(1161, 1200), # 40 % 3 == 1
(1301, 2000), # 700 % 3 == 1
(3501, 5000), # 1500 % 3 == 0
(5501, 6000), # 500 % 3 == 2
(6201, 7000), # 800 % 3 == 2
(7301, 7700), # 400 % 3 == 1
(8201, 9000), # 800 % 3 == 2
(9101, 9300), # 200 % 3 == 2
(9501, 9690) # 190 % 3 == 1
]
self.tr.add_exons(cds, features="CDS")
self.tr.finalize()
self.assertEqual(self.tr.combined_cds_end,
9690)
self.assertEqual(self.tr.selected_cds_end,
self.tr.combined_cds_end)
self.assertEqual(self.tr.end_distance_from_junction,
(9700 - 9691 + 1)
)
self.assertEqual(self.tr.end_distance_from_tes,
(9700 - 9691 + 1) + (10000 - 9801 + 1)
)
self.tr.strip_cds()
self.assertEqual(self.tr.combined_cds_end,
self.tr.selected_cds_end,
self.tr.combined_cds)
self.assertEqual(self.tr.combined_cds_end,
None,
self.tr.combined_cds_end)
self.tr.finalized = False
cds = [(1161, 1200), # 40 % 3 == 1
(1301, 2000), # 700 % 3 == 1
(3501, 5000), # 1500 % 3 == 0
(5501, 6000), # 500 % 3 == 2
(6201, 7000), # 800 % 3 == 2
(7301, 7700), # 400 % 3 == 1
(8201, 9000), # 800 % 3 == 2
(9101, 9300), # 200 % 3 == 2
(9501, 9700), # 200 % 3 == 2
(9801, 9820), # 20 % 2 == 2
]
self.tr.add_exons(cds, features="CDS")
self.tr.finalize()
self.assertEqual(self.tr.combined_cds_end,
9820)
self.assertEqual(self.tr.selected_cds_end,
self.tr.combined_cds_end)
self.assertEqual(self.tr.end_distance_from_tes,
180)
self.assertEqual(self.tr.end_distance_from_junction,
0)
def test_end_negative(self):
self.tr.strand = "-"
# self.tr.add_exons([(101, 300),
# (501, 800),
# (1001, 1200),
# (1301, 2000),
# (3501, 5000),
# (5501, 6000),
# (6201, 7000),
# (7301, 7700),
# (8201, 9000),
# (9101, 9300),
# (9501, 9700),
# (9801, 10000)])
cds = [(1161, 1200), # 40 % 3 == 1
(1301, 2000), # 700 % 3 == 1
(3501, 5000), # 1500 % 3 == 0
(5501, 6000), # 500 % 3 == 2
(6201, 7000), # 800 % 3 == 2
(7301, 7700), # 400 % 3 == 1
(8201, 9000), # 800 % 3 == 2
(9101, 9130)]
self.assertEqual(sum(x[1] - x[0] + 1 for x in cds) % 3, 0)
self.tr.add_exons(cds, features="CDS")
self.tr.finalize()
self.assertTrue(self.tr.is_coding)
self.assertEqual(self.tr.selected_cds_end,
self.tr.combined_cds_end)
self.assertEqual(self.tr.selected_cds_end,
1161)
self.assertEqual(self.tr.end_distance_from_junction,
(1161-1001) + (800-501+1),
(self.tr.end_distance_from_junction,
(1161-1001) + (800-501+1))
)
self.assertEqual(self.tr.end_distance_from_tes,
self.tr.end_distance_from_junction + (300 - 101 + 1),
(self.tr.end_distance_from_tes,
self.tr.end_distance_from_junction + (300 - 101 + 1))
)
self.tr.strip_cds()
self.assertEqual(len(self.tr.internal_orfs), 0, self.tr.internal_orfs)
self.tr.finalized = False
cds = [(721, 800),
(1001, 1200), # 200 % 3 == 2
(1301, 2000), # 700 % 3 == 1
(3501, 5000), # 1500 % 3 == 0
(5501, 6000), # 500 % 3 == 2
(6201, 7000), # 800 % 3 == 2
(7301, 7700), # 400 % 3 == 1
(8201, 9000), # 800 % 3 == 2
(9101, 9130), # 200 % 3 == 2
]
self.tr.add_exons(cds, features="CDS")
self.tr.finalize()
self.assertEqual(self.tr.combined_cds_end,
721)
self.assertEqual(self.tr.selected_cds_end,
self.tr.combined_cds_end)
self.assertEqual(self.tr.end_distance_from_junction,
(721-501),
(self.tr.end_distance_from_junction, (721-501))
)
self.assertEqual(self.tr.end_distance_from_tes,
self.tr.end_distance_from_junction + (300 - 101 + 1),
(self.tr.end_distance_from_tes,
self.tr.end_distance_from_junction + (300 - 101 + 1))
)
self.tr.strip_cds()
self.assertEqual(self.tr.combined_cds_end,
self.tr.selected_cds_end,
self.tr.combined_cds)
self.assertEqual(self.tr.combined_cds_end,
None,
self.tr.combined_cds_end)
self.tr.finalized = False
cds = [(161, 300), # 140 % 3 == 2
(501, 800), # 300 % 3 == 0
(1001, 1200), # 200 % 3 == 2
(1301, 2000), # 700 % 3 == 1
(3501, 5000), # 1500 % 3 == 0
(5501, 6000), # 500 % 3 == 2
(6201, 7000), # 800 % 3 == 2
(7301, 7700), # 400 % 3 == 1
(8201, 9000), # 800 % 3 == 2
(9101, 9130), # 30 % 3 == 0
]
self.assertEqual(sum((_[1] - _[0] +1) % 3 for _ in cds ) % 3, 0)
self.tr.logger = self.logger
self.tr.add_exons(cds, features="CDS")
self.tr.finalize()
self.assertEqual(self.tr.combined_cds_end,
161)
self.assertEqual(self.tr.selected_cds_end,
self.tr.combined_cds_end)
self.assertEqual(self.tr.end_distance_from_tes,
60)
self.assertEqual(self.tr.end_distance_from_junction,
0)
class AugustusTester(unittest.TestCase):
logger = create_default_logger("augustus")
logger.setLevel("DEBUG")
def test_truncated(self):
lines = """Triticum_aestivum_CS42_TGACv1_scaffold_000043_1AL Triticum_aestivum_CS42_TGACv1_TRIAE4565_Augustus mRNA 1 2785 . + . ID=TRIAE4565_1AL_Aug_0021880.1;Parent=TRIAE4565_1AL_Aug_0021880;Name=TRIAE4565_1AL_Aug_0021880.1
Triticum_aestivum_CS42_TGACv1_scaffold_000043_1AL Triticum_aestivum_CS42_TGACv1_TRIAE4565_Augustus CDS 1601 2446 . + 1 ID=TRIAE4565_1AL_Aug_0021880.1.CDS1;Parent=TRIAE4565_1AL_Aug_0021880.1
Triticum_aestivum_CS42_TGACv1_scaffold_000043_1AL Triticum_aestivum_CS42_TGACv1_TRIAE4565_Augustus exon 1601 2446 . + . ID=TRIAE4565_1AL_Aug_0021880.1.exon1;Parent=TRIAE4565_1AL_Aug_0021880.1
Triticum_aestivum_CS42_TGACv1_scaffold_000043_1AL Triticum_aestivum_CS42_TGACv1_TRIAE4565_Augustus CDS 2540 2654 . + 1 ID=TRIAE4565_1AL_Aug_0021880.1.CDS2;Parent=TRIAE4565_1AL_Aug_0021880.1
Triticum_aestivum_CS42_TGACv1_scaffold_000043_1AL Triticum_aestivum_CS42_TGACv1_TRIAE4565_Augustus exon 2540 2785 . + . ID=TRIAE4565_1AL_Aug_0021880.1.exon2;Parent=TRIAE4565_1AL_Aug_0021880.1
Triticum_aestivum_CS42_TGACv1_scaffold_000043_1AL Triticum_aestivum_CS42_TGACv1_TRIAE4565_Augustus three_prime_UTR 2655 2785 . + . ID=TRIAE4565_1AL_Aug_0021880.1.three_prime_UTR1;Parent=TRIAE4565_1AL_Aug_0021880.1"""
lines = [
parsers.GFF.GffLine("\t".join(_.split()))
for _ in lines.split("\n")
]
transcript = loci.Transcript(lines[0], logger=self.logger)
transcript.add_exons(lines[1:])
with self.assertLogs("augustus", level="WARNING") as cm_out:
transcript.finalize()
self.assertTrue(
any("The transcript TRIAE4565_1AL_Aug_0021880.1 has coordinates 1:2785"
in _ for _ in cm_out.output))
self.assertTrue(transcript.is_coding)
def test_three_truncated(self):
lines = """Triticum_aestivum_CS42_TGACv1_scaffold_000112_1AL Triticum_aestivum_CS42_TGACv1_TRIAE4565_Augustus mRNA 204336 224434 . + . ID=TRIAE4565_1AL_Aug_0024630.1;Parent=TRIAE4565_1AL_Aug_0024630;Name=TRIAE4565_1AL_Aug_0024630.1
Triticum_aestivum_CS42_TGACv1_scaffold_000112_1AL Triticum_aestivum_CS42_TGACv1_TRIAE4565_Augustus exon 204336 205303 . + . ID=TRIAE4565_1AL_Aug_0024630.1.exon1;Parent=TRIAE4565_1AL_Aug_0024630.1
Triticum_aestivum_CS42_TGACv1_scaffold_000112_1AL Triticum_aestivum_CS42_TGACv1_TRIAE4565_Augustus five_prime_UTR 204336 204546 . + . ID=TRIAE4565_1AL_Aug_0024630.1.five_prime_UTR1;Parent=TRIAE4565_1AL_Aug_0024630.1
Triticum_aestivum_CS42_TGACv1_scaffold_000112_1AL Triticum_aestivum_CS42_TGACv1_TRIAE4565_Augustus CDS 204547 205303 . + 0 ID=TRIAE4565_1AL_Aug_0024630.1.CDS1;Parent=TRIAE4565_1AL_Aug_0024630.1
Triticum_aestivum_CS42_TGACv1_scaffold_000112_1AL Triticum_aestivum_CS42_TGACv1_TRIAE4565_Augustus CDS 206227 207040 . + 2 ID=TRIAE4565_1AL_Aug_0024630.1.CDS2;Parent=TRIAE4565_1AL_Aug_0024630.1
Triticum_aestivum_CS42_TGACv1_scaffold_000112_1AL Triticum_aestivum_CS42_TGACv1_TRIAE4565_Augustus exon 206227 207040 . + . ID=TRIAE4565_1AL_Aug_0024630.1.exon2;Parent=TRIAE4565_1AL_Aug_0024630.1"""
lines = [
parsers.GFF.GffLine("\t".join(_.split()))
for _ in lines.split("\n")
]
transcript = loci.Transcript(lines[0], logger=self.logger)
transcript.add_exons(lines[1:])
with self.assertLogs("augustus", level="WARNING") as cm_out:
transcript.finalize()
self.assertTrue(
any("The transcript TRIAE4565_1AL_Aug_0024630.1 has coordinates 204336:224434"
in _ for _ in cm_out.output))
self.assertTrue(transcript.is_coding)
def test_invalid_three_truncated(self):
lines = """Triticum_aestivum_CS42_TGACv1_scaffold_000112_1AL Triticum_aestivum_CS42_TGACv1_TRIAE4565_Augustus mRNA 204336 225434 . + . ID=TRIAE4565_1AL_Aug_0024630.1;Parent=TRIAE4565_1AL_Aug_0024630;Name=TRIAE4565_1AL_Aug_0024630.1
Triticum_aestivum_CS42_TGACv1_scaffold_000112_1AL Triticum_aestivum_CS42_TGACv1_TRIAE4565_Augustus exon 204336 205303 . + . ID=TRIAE4565_1AL_Aug_0024630.1.exon1;Parent=TRIAE4565_1AL_Aug_0024630.1
Triticum_aestivum_CS42_TGACv1_scaffold_000112_1AL Triticum_aestivum_CS42_TGACv1_TRIAE4565_Augustus five_prime_UTR 204336 204546 . + . ID=TRIAE4565_1AL_Aug_0024630.1.five_prime_UTR1;Parent=TRIAE4565_1AL_Aug_0024630.1
Triticum_aestivum_CS42_TGACv1_scaffold_000112_1AL Triticum_aestivum_CS42_TGACv1_TRIAE4565_Augustus CDS 204547 205303 . + 0 ID=TRIAE4565_1AL_Aug_0024630.1.CDS1;Parent=TRIAE4565_1AL_Aug_0024630.1
Triticum_aestivum_CS42_TGACv1_scaffold_000112_1AL Triticum_aestivum_CS42_TGACv1_TRIAE4565_Augustus CDS 206227 207042 . + 2 ID=TRIAE4565_1AL_Aug_0024630.1.CDS2;Parent=TRIAE4565_1AL_Aug_0024630.1
Triticum_aestivum_CS42_TGACv1_scaffold_000112_1AL Triticum_aestivum_CS42_TGACv1_TRIAE4565_Augustus exon 206227 207042 . + . ID=TRIAE4565_1AL_Aug_0024630.1.exon2;Parent=TRIAE4565_1AL_Aug_0024630.1
Triticum_aestivum_CS42_TGACv1_scaffold_000112_1AL Triticum_aestivum_CS42_TGACv1_TRIAE4565_Augustus exon 208227 210040 . + . ID=TRIAE4565_1AL_Aug_0024630.1.exon2;Parent=TRIAE4565_1AL_Aug_0024630.1"""
lines = [
parsers.GFF.GffLine("\t".join(_.split()))
for _ in lines.split("\n")
]
transcript = loci.Transcript(lines[0], logger=self.logger)
transcript.add_exons(lines[1:])
with self.assertLogs("augustus", level="WARNING") as cm_out:
transcript.finalize()
self.assertTrue(
any("The transcript TRIAE4565_1AL_Aug_0024630.1 has coordinates 204336:225434"
in _ for _ in cm_out.output))
# self.assertTrue(any(
# "strip_cds" in _ for
# _ in cm_out.output))
self.assertFalse(transcript.is_coding)
def test_valid_three_truncated(self):
"""
Picked from the EnsEMBL Human GTF (v. 70)
:return:
"""
lines = """11\tnonsense_mediated_decay\texon\t134177086\t134177102\t.\t+\t.\tgene_id "ENSG00000166105"; transcript_id "ENST00000455971"; exon_number "1"; gene_name "GLB1L3"; gene_biotype "protein_coding"; transcript_name "GLB1L3-006"; exon_id "ENSE00002461794";
11\tnonsense_mediated_decay\tCDS\t134177086\t134177102\t.\t+\t2\tgene_id "ENSG00000166105"; transcript_id "ENST00000455971"; exon_number "1"; gene_name "GLB1L3"; gene_biotype "protein_coding"; transcript_name "GLB1L3-006"; protein_id "ENSP00000397929";
11\tnonsense_mediated_decay\texon\t134179522\t134179657\t.\t+\t.\tgene_id "ENSG00000166105"; transcript_id "ENST00000455971"; exon_number "2"; gene_name "GLB1L3"; gene_biotype "protein_coding"; transcript_name "GLB1L3-006"; exon_id "ENSE00002147723";
11\tnonsense_mediated_decay\tCDS\t134179522\t134179657\t.\t+\t0\tgene_id "ENSG00000166105"; transcript_id "ENST00000455971"; exon_number "2"; gene_name "GLB1L3"; gene_biotype "protein_coding"; transcript_name "GLB1L3-006"; protein_id "ENSP00000397929";
11\tnonsense_mediated_decay\texon\t134180465\t134180545\t.\t+\t.\tgene_id "ENSG00000166105"; transcript_id "ENST00000455971"; exon_number "3"; gene_name "GLB1L3"; gene_biotype "protein_coding"; transcript_name "GLB1L3-006"; exon_id "ENSE00001278318";
11\tnonsense_mediated_decay\tCDS\t134180465\t134180545\t.\t+\t2\tgene_id "ENSG00000166105"; transcript_id "ENST00000455971"; exon_number "3"; gene_name "GLB1L3"; gene_biotype "protein_coding"; transcript_name "GLB1L3-006"; protein_id "ENSP00000397929";
11\tnonsense_mediated_decay\texon\t134180958\t134181064\t.\t+\t.\tgene_id "ENSG00000166105"; transcript_id "ENST00000455971"; exon_number "4"; gene_name "GLB1L3"; gene_biotype "protein_coding"; transcript_name "GLB1L3-006"; exon_id "ENSE00001140726";
11\tnonsense_mediated_decay\tCDS\t134180958\t134181064\t.\t+\t2\tgene_id "ENSG00000166105"; transcript_id "ENST00000455971"; exon_number "4"; gene_name "GLB1L3"; gene_biotype "protein_coding"; transcript_name "GLB1L3-006"; protein_id "ENSP00000397929";
11\tnonsense_mediated_decay\texon\t134182243\t134182383\t.\t+\t.\tgene_id "ENSG00000166105"; transcript_id "ENST00000455971"; exon_number "5"; gene_name "GLB1L3"; gene_biotype "protein_coding"; transcript_name "GLB1L3-006"; exon_id "ENSE00003177017";
11\tnonsense_mediated_decay\tCDS\t134182243\t134182383\t.\t+\t0\tgene_id "ENSG00000166105"; transcript_id "ENST00000455971"; exon_number "5"; gene_name "GLB1L3"; gene_biotype "protein_coding"; transcript_name "GLB1L3-006"; protein_id "ENSP00000397929";
11\tnonsense_mediated_decay\texon\t134182710\t134182781\t.\t+\t.\tgene_id "ENSG00000166105"; transcript_id "ENST00000455971"; exon_number "6"; gene_name "GLB1L3"; gene_biotype "protein_coding"; transcript_name "GLB1L3-006"; exon_id "ENSE00003096760";
11\tnonsense_mediated_decay\tCDS\t134182710\t134182781\t.\t+\t0\tgene_id "ENSG00000166105"; transcript_id "ENST00000455971"; exon_number "6"; gene_name "GLB1L3"; gene_biotype "protein_coding"; transcript_name "GLB1L3-006"; protein_id "ENSP00000397929";
11\tnonsense_mediated_decay\texon\t134183835\t134183922\t.\t+\t.\tgene_id "ENSG00000166105"; transcript_id "ENST00000455971"; exon_number "7"; gene_name "GLB1L3"; gene_biotype "protein_coding"; transcript_name "GLB1L3-006"; exon_id "ENSE00003040614";
11\tnonsense_mediated_decay\tCDS\t134183835\t134183837\t.\t+\t0\tgene_id "ENSG00000166105"; transcript_id "ENST00000455971"; exon_number "7"; gene_name "GLB1L3"; gene_biotype "protein_coding"; transcript_name "GLB1L3-006"; protein_id "ENSP00000397929";
11\tnonsense_mediated_decay\tstop_codon\t134183838\t134183840\t.\t+\t0\tgene_id "ENSG00000166105"; transcript_id "ENST00000455971"; exon_number "7"; gene_name "GLB1L3"; gene_biotype "protein_coding"; transcript_name "GLB1L3-006";
11\tnonsense_mediated_decay\texon\t134184224\t134184335\t.\t+\t.\tgene_id "ENSG00000166105"; transcript_id "ENST00000455971"; exon_number "8"; gene_name "GLB1L3"; gene_biotype "protein_coding"; transcript_name "GLB1L3-006"; exon_id "ENSE00003002659";
11\tnonsense_mediated_decay\texon\t134188525\t134188641\t.\t+\t.\tgene_id "ENSG00000166105"; transcript_id "ENST00000455971"; exon_number "9"; gene_name "GLB1L3"; gene_biotype "protein_coding"; transcript_name "GLB1L3-006"; exon_id "ENSE00003191545";
11\tnonsense_mediated_decay\texon\t134188771\t134189178\t.\t+\t.\tgene_id "ENSG00000166105"; transcript_id "ENST00000455971"; exon_number "10"; gene_name "GLB1L3"; gene_biotype "protein_coding"; transcript_name "GLB1L3-006"; exon_id "ENSE00001441085";"""
lines = [
parsers.GTF.GtfLine("\t".join(_.split("\t")))
for _ in lines.split("\n")
]
assert all([line.header is False for line in lines])
transcript = loci.Transcript(lines[0], logger=self.logger)
transcript.add_exons(lines[1:])
with self.assertLogs("augustus", level="DEBUG") as cm_out:
transcript.finalize()
self.assertTrue(transcript.is_coding)
self.assertEqual(
560, transcript.selected_cds_length,
sum(_[1][1] - _[1][0] + 1 for _ in transcript.selected_internal_orf
if _[0] == "CDS"))
class PhaseChecker(unittest.TestCase):
logger = create_default_logger("pcheck")
logger.setLevel("DEBUG")
def setUp(self):
lines = """Triticum_aestivum_CS42_TGACv1_scaffold_434051_5DL TGACv1 mRNA 40282 46004 . - . ID=TRIAE_CS42_5DL_TGACv1_434051_AA1427960.2;Parent=TRIAE_CS42_5DL_TGACv1_434051_AA1427960;Name=TRIAE_CS42_5DL_TGACv1_434051_AA1427960.2;aed=0.0;note=TRIAE_CS42_5DL_TGACv1_434051_AA1427960;confidence=High;has_start=True;has_stop=True;original_stop=True;protein_rank=P1;transcript_rank=T2
Triticum_aestivum_CS42_TGACv1_scaffold_434051_5DL TGACv1 exon 40282 40933 . - . ID=TRIAE_CS42_5DL_TGACv1_434051_AA1427960.2.exon1;Parent=TRIAE_CS42_5DL_TGACv1_434051_AA1427960.2
Triticum_aestivum_CS42_TGACv1_scaffold_434051_5DL TGACv1 three_prime_UTR 40282 40720 . - . ID=TRIAE_CS42_5DL_TGACv1_434051_AA1427960.2.three_prime_UTR1;Parent=TRIAE_CS42_5DL_TGACv1_434051_AA1427960.2
Triticum_aestivum_CS42_TGACv1_scaffold_434051_5DL TGACv1 CDS 40721 40933 . - 0 ID=TRIAE_CS42_5DL_TGACv1_434051_AA1427960.2.CDS1;Parent=TRIAE_CS42_5DL_TGACv1_434051_AA1427960.2
Triticum_aestivum_CS42_TGACv1_scaffold_434051_5DL TGACv1 CDS 41018 41111 . - 1 ID=TRIAE_CS42_5DL_TGACv1_434051_AA1427960.2.CDS2;Parent=TRIAE_CS42_5DL_TGACv1_434051_AA1427960.2
Triticum_aestivum_CS42_TGACv1_scaffold_434051_5DL TGACv1 exon 41018 41111 . - . ID=TRIAE_CS42_5DL_TGACv1_434051_AA1427960.2.exon2;Parent=TRIAE_CS42_5DL_TGACv1_434051_AA1427960.2
Triticum_aestivum_CS42_TGACv1_scaffold_434051_5DL TGACv1 CDS 41227 41468 . - 0 ID=TRIAE_CS42_5DL_TGACv1_434051_AA1427960.2.CDS3;Parent=TRIAE_CS42_5DL_TGACv1_434051_AA1427960.2
Triticum_aestivum_CS42_TGACv1_scaffold_434051_5DL TGACv1 exon 41227 41468 . - . ID=TRIAE_CS42_5DL_TGACv1_434051_AA1427960.2.exon3;Parent=TRIAE_CS42_5DL_TGACv1_434051_AA1427960.2
Triticum_aestivum_CS42_TGACv1_scaffold_434051_5DL TGACv1 CDS 41673 41831 . - 0 ID=TRIAE_CS42_5DL_TGACv1_434051_AA1427960.2.CDS4;Parent=TRIAE_CS42_5DL_TGACv1_434051_AA1427960.2
Triticum_aestivum_CS42_TGACv1_scaffold_434051_5DL TGACv1 exon 41673 41831 . - . ID=TRIAE_CS42_5DL_TGACv1_434051_AA1427960.2.exon4;Parent=TRIAE_CS42_5DL_TGACv1_434051_AA1427960.2
Triticum_aestivum_CS42_TGACv1_scaffold_434051_5DL TGACv1 CDS 41946 42820 . - 2 ID=TRIAE_CS42_5DL_TGACv1_434051_AA1427960.2.CDS5;Parent=TRIAE_CS42_5DL_TGACv1_434051_AA1427960.2
Triticum_aestivum_CS42_TGACv1_scaffold_434051_5DL TGACv1 exon 41946 42820 . - . ID=TRIAE_CS42_5DL_TGACv1_434051_AA1427960.2.exon5;Parent=TRIAE_CS42_5DL_TGACv1_434051_AA1427960.2
Triticum_aestivum_CS42_TGACv1_scaffold_434051_5DL TGACv1 CDS 42905 42913 . - 2 ID=TRIAE_CS42_5DL_TGACv1_434051_AA1427960.2.CDS6;Parent=TRIAE_CS42_5DL_TGACv1_434051_AA1427960.2
Triticum_aestivum_CS42_TGACv1_scaffold_434051_5DL TGACv1 exon 42905 42913 . - . ID=TRIAE_CS42_5DL_TGACv1_434051_AA1427960.2.exon6;Parent=TRIAE_CS42_5DL_TGACv1_434051_AA1427960.2
Triticum_aestivum_CS42_TGACv1_scaffold_434051_5DL TGACv1 CDS 45373 45496 . - 0 ID=TRIAE_CS42_5DL_TGACv1_434051_AA1427960.2.CDS7;Parent=TRIAE_CS42_5DL_TGACv1_434051_AA1427960.2
Triticum_aestivum_CS42_TGACv1_scaffold_434051_5DL TGACv1 exon 45373 45496 . - . ID=TRIAE_CS42_5DL_TGACv1_434051_AA1427960.2.exon7;Parent=TRIAE_CS42_5DL_TGACv1_434051_AA1427960.2
Triticum_aestivum_CS42_TGACv1_scaffold_434051_5DL TGACv1 CDS 45600 45651 . - 1 ID=TRIAE_CS42_5DL_TGACv1_434051_AA1427960.2.CDS8;Parent=TRIAE_CS42_5DL_TGACv1_434051_AA1427960.2
Triticum_aestivum_CS42_TGACv1_scaffold_434051_5DL TGACv1 exon 45600 45651 . - . ID=TRIAE_CS42_5DL_TGACv1_434051_AA1427960.2.exon8;Parent=TRIAE_CS42_5DL_TGACv1_434051_AA1427960.2
Triticum_aestivum_CS42_TGACv1_scaffold_434051_5DL TGACv1 CDS 45726 45726 . - 2 ID=TRIAE_CS42_5DL_TGACv1_434051_AA1427960.2.CDS9;Parent=TRIAE_CS42_5DL_TGACv1_434051_AA1427960.2
Triticum_aestivum_CS42_TGACv1_scaffold_434051_5DL TGACv1 exon 45726 45726 . - . ID=TRIAE_CS42_5DL_TGACv1_434051_AA1427960.2.exon9;Parent=TRIAE_CS42_5DL_TGACv1_434051_AA1427960.2
Triticum_aestivum_CS42_TGACv1_scaffold_434051_5DL TGACv1 CDS 45875 45893 . - 0 ID=TRIAE_CS42_5DL_TGACv1_434051_AA1427960.2.CDS10;Parent=TRIAE_CS42_5DL_TGACv1_434051_AA1427960.2
Triticum_aestivum_CS42_TGACv1_scaffold_434051_5DL TGACv1 exon 45875 46004 . - . ID=TRIAE_CS42_5DL_TGACv1_434051_AA1427960.2.exon10;Parent=TRIAE_CS42_5DL_TGACv1_434051_AA1427960.2
Triticum_aestivum_CS42_TGACv1_scaffold_434051_5DL TGACv1 five_prime_UTR 45894 46004 . - . ID=TRIAE_CS42_5DL_TGACv1_434051_AA1427960.2.five_prime_UTR1;Parent=TRIAE_CS42_5DL_TGACv1_434051_AA1427960.2"""
lines = [GffLine("\t".join(_.split())) for _ in lines.split("\n") if _]
self.transcript = Transcript(lines[0], logger=self.logger)
self.transcript.add_exons(lines[1:])
self.correct_phases = {(40721, 40933): 2,
(41018, 41111): 0,
(41227, 41468): 2,
(41673, 41831): 2,
(41946, 42820): 1,
(42905, 42913): 1,
(45373, 45496): 2,
(45600, 45651): 0,
(45726, 45726): 2,
(45875, 45893): 0}
@unittest.skip
def test_check_phases(self):
self.transcript.finalize()
phases = dict((_[1], _[2]) for _ in self.transcript.internal_orfs[0]
if _[0] == "CDS")
self.assertEqual(self.transcript.combined_cds_start, 45893)
self.assertEqual(phases.keys(),
self.correct_phases.keys(),
list(zip(sorted(phases.keys()),
sorted(self.correct_phases.keys()))))
if self.correct_phases != phases:
for key in sorted(phases.keys(), reverse=True):
self.assertEqual(phases[key], self.correct_phases[key],
(key, phases[key], self.correct_phases[key]))
self.assertEqual(self.correct_phases,
phases,
(self.correct_phases, phases))