def test_transcript_start_codon():
"""
test_transcript_start_codon : Check that fields Transcript
(for transcript named CTNNBIP1-004) matches known values.
"""
CTNNBIP1_004_transcript = ensembl_grch38.transcript_by_id(
CTNNBIP1_004_transcript_id)
assert Locus.__eq__(CTNNBIP1_004_locus, CTNNBIP1_004_transcript), \
"Expected locus %s but got %s" % (
CTNNBIP1_004_locus, Locus.__str__(CTNNBIP1_004_transcript))
start_offsets = CTNNBIP1_004_transcript.start_codon_spliced_offsets
assert len(start_offsets) == 3, \
"Wrong length for start codon: %d (%s)" % (
len(start_offsets), start_offsets)
assert all(isinstance(i, int) for i in start_offsets), \
"Wrong type %s for beginning start codon offset" % (
[type(i) for i in start_offsets],)
expected_start_codon_offset = len(CTNNBIP1_004_UTR5)
start_codon_offset = min(start_offsets)
assert start_codon_offset == expected_start_codon_offset, \
"Incorrect start codon offset, expected %d but got %d" % (
expected_start_codon_offset, start_codon_offset)
def test_transcript_exons():
"""
test_transcript_exons : Ensure that properties of CTTNBIP1-004's
Exon objects match known values.
"""
transcript = ensembl_grch38.transcript_by_id(CTNNBIP1_004_transcript_id)
exons = transcript.exons
assert isinstance(exons, list), \
"Expected list of Exon objects, got %s : %s" % (exons, type(exons))
# CTTNBIP1-004 has 5 exons
assert len(exons) == len(CTTNNIP1_004_exon_lengths), \
"Expected %d exons but got %d" % (
len(CTTNNIP1_004_exon_lengths), len(exons))
for i, exon in enumerate(exons):
expected_id = CTTNNIP1_004_exon_ids[i]
assert exon.id == expected_id, \
"Expected exon #%d of %s to have ID %s but got %s" % (
i + 1, transcript, expected_id, exon.id)
expected_length = CTTNNIP1_004_exon_lengths[i]
assert len(exon) == expected_length, \
"Expected exon #%d of %s (%s) to have length %d but got %d" % (
i + 1, transcript, exon, expected_length, len(exon))
def test_transcript_exons():
"""
test_transcript_exons : Ensure that properties of CTTNBIP1-004's
Exon objects match known values.
"""
transcript = ensembl_grch38.transcript_by_id(CTNNBIP1_004_transcript_id)
exons = transcript.exons
assert isinstance(exons, list), \
"Expected list of Exon objects, got %s : %s" % (exons, type(exons))
# CTTNBIP1-004 has 5 exons
assert len(exons) == len(CTTNNIP1_004_exon_lengths), \
"Expected %d exons but got %d" % (
len(CTTNNIP1_004_exon_lengths), len(exons))
for i, exon in enumerate(exons):
expected_id = CTTNNIP1_004_exon_ids[i]
assert exon.id == expected_id, \
"Expected exon #%d of %s to have ID %s but got %s" % (
i + 1, transcript, expected_id, exon.id)
expected_length = CTTNNIP1_004_exon_lengths[i]
assert len(exon) == expected_length, \
"Expected exon #%d of %s (%s) to have length %d but got %d" % (
i + 1, transcript, exon, expected_length, len(exon))
def test_transcript_cds_CTNNIP1_004():
transcript = ensembl_grch38.transcript_by_id(CTNNBIP1_004_transcript_id)
cds = transcript.coding_sequence
expected_cds_length = len(CTNNBIP1_004_CDS)
eq_(len(cds), expected_cds_length,
"Expected CDS length %d, got %d" % (expected_cds_length, len(cds)))
eq_(cds, CTNNBIP1_004_CDS)
def test_transcript_start_codon():
"""
test_transcript_start_codon : Check that fields Transcript
(for transcript named CTNNBIP1-004) matches known values.
"""
CTNNBIP1_004_transcript = ensembl_grch38.transcript_by_id(
CTNNBIP1_004_transcript_id)
assert Locus.__eq__(CTNNBIP1_004_locus, CTNNBIP1_004_transcript), \
"Expected locus %s but got %s" % (
CTNNBIP1_004_locus, Locus.__str__(CTNNBIP1_004_transcript))
start_offsets = CTNNBIP1_004_transcript.start_codon_spliced_offsets
assert len(start_offsets) == 3, \
"Wrong length for start codon: %d (%s)" % (
len(start_offsets), start_offsets)
assert all(isinstance(i, int) for i in start_offsets), \
"Wrong type %s for beginning start codon offset" % (
[type(i) for i in start_offsets],)
expected_start_codon_offset = len(CTNNBIP1_004_UTR5)
start_codon_offset = min(start_offsets)
assert start_codon_offset == expected_start_codon_offset, \
"Incorrect start codon offset, expected %d but got %d" % (
expected_start_codon_offset, start_codon_offset)
def test_transcript_sequence_ensembl_grch38():
# extremely short TRD gene
seq = ensembl_grch38.transcript_sequence("ENST00000448914")
expected = "ACTGGGGGATACG"
eq_(seq, expected)
# now try via a Transcript object
eq_(ensembl_grch38.transcript_by_id("ENST00000448914").sequence, expected)
def test_transcript_utr3_sequence_CTNNIP1_004():
transcript = ensembl_grch38.transcript_by_id(CTNNBIP1_004_transcript_id)
utr3 = transcript.three_prime_utr_sequence
expected_utr3_length = len(CTNNBIP1_004_UTR3)
eq_(
len(utr3), expected_utr3_length, "Expected 3' UTR length %d, got %d" %
(expected_utr3_length, len(utr3)))
eq_(utr3, CTNNBIP1_004_UTR3)
def test_transcript_utr5_sequence_CTNNIP1_004():
transcript = ensembl_grch38.transcript_by_id(CTNNBIP1_004_transcript_id)
utr5 = transcript.five_prime_utr_sequence
expected_utr5_length = len(CTNNBIP1_004_UTR5)
eq_(
len(utr5), expected_utr5_length, "Expected 5' UTR length %d, got %d" %
(expected_utr5_length, len(utr5)))
eq_(utr5, CTNNBIP1_004_UTR5)
def test_transcript_cds_CTNNIP1_004():
transcript = ensembl_grch38.transcript_by_id(CTNNBIP1_004_transcript_id)
cds = transcript.coding_sequence
expected_cds_length = len(CTNNBIP1_004_CDS)
eq_(
len(cds),
expected_cds_length,
"Expected CDS length %d, got %d" % (expected_cds_length, len(cds)))
eq_(cds, CTNNBIP1_004_CDS)
def test_transcript_utr3_sequence_CTNNIP1_004():
transcript = ensembl_grch38.transcript_by_id(CTNNBIP1_004_transcript_id)
utr3 = transcript.three_prime_utr_sequence
expected_utr3_length = len(CTNNBIP1_004_UTR3)
eq_(len(utr3),
expected_utr3_length,
"Expected 3' UTR length %d, got %d" % (
expected_utr3_length, len(utr3)))
eq_(utr3, CTNNBIP1_004_UTR3)
def test_transcript_utr5_sequence_CTNNIP1_004():
transcript = ensembl_grch38.transcript_by_id(CTNNBIP1_004_transcript_id)
utr5 = transcript.five_prime_utr_sequence
expected_utr5_length = len(CTNNBIP1_004_UTR5)
eq_(len(utr5),
expected_utr5_length,
"Expected 5' UTR length %d, got %d" % (
expected_utr5_length, len(utr5)))
eq_(utr5, CTNNBIP1_004_UTR5)