def test_cds_regions(self):
transcript = Transcript()
record = {
'strand': '+',
'exons': '10000-20000,30000-40000,50000-60000',
'coding_start': '12000',
'coding_end': '53000'
}
transcript.read_from_database_record(record)
cds_regions = transcript.cds_regions()
assert cds_regions[0] == (12000, 20000)
assert cds_regions[1] == (30000, 40000)
assert cds_regions[2] == (50000, 53001)
transcript = Transcript()
record = {
'strand': '-',
'exons': '50-60, 30-40, 10-20',
'coding_start': '55',
'coding_end': '15'
}
transcript.read_from_database_record(record)
cds_regions = transcript.cds_regions()
assert cds_regions[0] == (50, 56)
assert cds_regions[1] == (30, 40)
assert cds_regions[2] == (15, 20)
def test_add(self):
transcript = Transcript(id='xyz',
chrom='11',
strand='+',
start=130,
end=580)
transcript.exons = [Exon('100-200'), Exon('300-400'), Exon('500-600')]
self.tdb_writer.add(transcript)
assert self.tdb_writer._records['11'][0] == [
'xyz', '11', '100-200,300-400,500-600', 130, 580
]
def test_finalize(self):
transcript = Transcript(strand='+', coding_start=16, coding_end=53)
transcript.exons = [Exon('10-20'), Exon('30-40'), Exon('50-60')]
transcript.finalize()
assert transcript.cdna_length == 30
assert transcript.prot_length == 5
assert transcript.start == 10
assert transcript.end == 60
transcript = Transcript(strand='-', coding_start=55, coding_end=15)
transcript.exons = [Exon('50-60'), Exon('30-40'), Exon('10-20')]
transcript.finalize()
assert transcript.cdna_length == 30
assert transcript.prot_length == 6
assert transcript.start == 10
assert transcript.end == 60
def test_finalize(self):
t1 = Transcript(id='1',
chrom='8',
strand='+',
start=130,
end=580,
exons=[])
t2 = Transcript(id='2',
chrom='8',
strand='+',
start=800,
end=900,
exons=[])
t3 = Transcript(id='3',
chrom='8',
strand='+',
start=800,
end=880,
exons=[])
t4 = Transcript(id='4',
chrom='8',
strand='+',
start=30,
end=40,
exons=[])
self.tdb_writer.add(t1)
self.tdb_writer.add(t2)
self.tdb_writer.add(t3)
self.tdb_writer.add(t4)
self.tdb_writer.finalize()
assert os.path.isfile(self.fn + '.gz')
assert os.path.isfile(self.fn + '.gz.tbi')
order = []
for line in gzip.open(self.fn + '.gz'):
line = line.strip()
if line.startswith('#'):
continue
cols = line.split('\t')
order.append(int(cols[-1]))
assert order == [40, 580, 880, 900]
def test_set_info(self):
transcript = Transcript(strand='-', start=10000, end=19600)
transcript.exons = [Exon('1-2'), Exon('3-4'), Exon('5-6')]
transcript.cdna_length = 8100
transcript.prot_length = 1200
transcript.set_info()
assert transcript.info == '-/9.6kb/3/8.1kb/1200'
def setUp(self):
self.fn = str(uuid.uuid4())
tdb_writer = TranscriptDBWriter(
self.fn,
source='xyz',
build='GRCh37',
columns=['id', 'chrom', 'strand', 'start', 'end'])
tdb_writer.add(
Transcript(id='t1', chrom='8', strand='+', start=130, end=580))
tdb_writer.add(
Transcript(id='t2', chrom='8', strand='+', start=800, end=900))
tdb_writer.add(
Transcript(id='t3', chrom='8', strand='+', start=800, end=880))
tdb_writer.add(
Transcript(id='t4', chrom='8', strand='+', start=30, end=40))
tdb_writer.finalize()
self.tdb = TranscriptDB(self.fn + '.gz')
def test_get_protein_length(self):
transcript = Transcript()
record = {
'strand': '+',
'exons': '10-20,30-40,50-60',
'coding_start': '16',
'coding_end': '53'
}
transcript.read_from_database_record(record)
assert transcript.get_protein_length() == 5
transcript = Transcript()
record = {
'strand': '-',
'exons': '50-60,30-40,10-20',
'coding_start': '55',
'coding_end': '15'
}
transcript.read_from_database_record(record)
assert transcript.get_protein_length() == 6
def test_read_from_database_record(self):
record = {
'one': 'x',
'two': 'y',
'start': '12345',
'exons': '10000-20000,30000-40000'
}
transcript = Transcript()
transcript.read_from_database_record(record)
for key in record:
assert key in transcript.__dict__
assert transcript.one == 'x'
assert transcript.two == 'y'
assert transcript.start == 12345
for exon in transcript.exons:
assert type(exon) == Exon
assert transcript.exons[0].start == 10000
assert transcript.exons[1].end == 40000
def test_sort_records(self):
t1 = Transcript(id='1',
chrom='8',
strand='+',
start=130,
end=580,
exons=[])
t2 = Transcript(id='2',
chrom='8',
strand='+',
start=800,
end=900,
exons=[])
t3 = Transcript(id='3',
chrom='8',
strand='+',
start=800,
end=880,
exons=[])
t4 = Transcript(id='4',
chrom='8',
strand='+',
start=30,
end=40,
exons=[])
self.tdb_writer.add(t1)
self.tdb_writer.add(t2)
self.tdb_writer.add(t3)
self.tdb_writer.add(t4)
self.tdb_writer._sort_records()
assert self.tdb_writer._records['8'][0][-1] == 40
assert self.tdb_writer._records['8'][1][-1] == 580
assert self.tdb_writer._records['8'][2][-1] == 880
def test_all_have_same_cds(self):
t1 = Transcript()
record = {
'strand': '+',
'exons': '10000-20000,30000-40000,50000-60000',
'coding_start': '12000',
'coding_end': '53000'
}
t1.read_from_database_record(record)
t2 = Transcript()
record = {
'strand': '+',
'exons': '9000-20000,30000-40000,50000-68000',
'coding_start': '12000',
'coding_end': '53000'
}
t2.read_from_database_record(record)
t3 = Transcript()
record = {
'strand': '+',
'exons': '3000-20000,30000-40000,50000-68000',
'coding_start': '12000',
'coding_end': '53000'
}
t3.read_from_database_record(record)
t4 = Transcript()
record = {
'strand': '+',
'exons': '10000-20000,30000-40000,50000-60000',
'coding_start': '12500',
'coding_end': '53000'
}
t4.read_from_database_record(record)
assert not helper.all_have_same_cds([t1, t2, t3, t4])
assert helper.all_have_same_cds([t1, t2, t3])
def test_utr5_regions(self):
transcript = Transcript()
record = {
'strand': '+',
'exons': '10000-20000,25000-26000,30000-40000,50000-60000',
'coding_start': '25500',
'coding_end': '53000'
}
transcript.read_from_database_record(record)
utr5_regions = transcript.utr5_regions()
assert len(utr5_regions) == 2
assert utr5_regions[0] == (10000, 20000)
assert utr5_regions[1] == (25000, 25500)
transcript = Transcript()
record = {
'strand': '+',
'exons': '10000-20000,30000-40000,50000-60000',
'coding_start': '10000',
'coding_end': '35000'
}
transcript.read_from_database_record(record)
assert transcript.utr5_regions() == []
transcript = Transcript()
record = {
'strand': '-',
'exons': '70-80, 50-60, 30-40, 10-20',
'coding_start': '55',
'coding_end': '15'
}
transcript.read_from_database_record(record)
utr5_regions = transcript.utr5_regions()
assert len(utr5_regions) == 2
assert utr5_regions[0] == (70, 80)
assert utr5_regions[1] == (56, 60)
transcript = Transcript()
record = {
'strand': '-',
'exons': '50-60, 30-40, 10-20',
'coding_start': '59',
'coding_end': '15'
}
transcript.read_from_database_record(record)
assert transcript.utr5_regions() == []
def test_any_unset(self):
transcript = Transcript()
assert transcript._any_unset(['start', 'end'])
transcript.start = 1
transcript.end = 2
assert not transcript._any_unset(['start', 'end'])
def test_get_cdna_length(self):
transcript = Transcript()
record = {'strand': '+', 'exons': '10-20,100-200,1000-2000'}
transcript.read_from_database_record(record)
assert transcript.get_cdna_length() == 1110