def test_get_mol_wt(self):
dna1 = core.DnaSpeciesType(id='dna6', sequence_path=self.sequence_path)
gene1 = eukaryote_schema.GeneLocus(polymer=dna1, start=1, end=6)
rna1 = eukaryote_schema.PreRnaSpeciesType(gene=gene1)
exon1 = eukaryote_schema.ExonLocus(start=1, end=1)
transcript1 = eukaryote_schema.TranscriptSpeciesType(rna=rna1,
exons=[exon1])
exp_mol_wt = \
+ Bio.SeqUtils.molecular_weight(transcript1.get_seq()) \
- (transcript1.get_len() + 1) * mendeleev.element('H').atomic_weight
self.assertAlmostEqual(transcript1.get_mol_wt(), exp_mol_wt, places=1)
exon2 = eukaryote_schema.ExonLocus(start=3, end=3)
transcript2 = eukaryote_schema.TranscriptSpeciesType(rna=rna1,
exons=[exon2])
exp_mol_wt = \
+ Bio.SeqUtils.molecular_weight(transcript2.get_seq()) \
- (transcript2.get_len() + 1) * mendeleev.element('H').atomic_weight
self.assertAlmostEqual(transcript2.get_mol_wt(), exp_mol_wt, places=1)
exon3 = eukaryote_schema.ExonLocus(start=5, end=5)
transcript3 = eukaryote_schema.TranscriptSpeciesType(rna=rna1,
exons=[exon3])
exp_mol_wt = \
+ Bio.SeqUtils.molecular_weight(transcript3.get_seq()) \
- (transcript3.get_len() + 1) * mendeleev.element('H').atomic_weight
self.assertAlmostEqual(transcript3.get_mol_wt(), exp_mol_wt, places=1)
def test_get_seq(self):
dna1 = core.DnaSpeciesType(id='dna2', sequence_path=self.sequence_path)
gene1 = eukaryote_schema.GeneLocus(polymer=dna1,
start=1,
end=15,
strand=core.PolymerStrand.positive)
rna1 = eukaryote_schema.PreRnaSpeciesType(gene=gene1)
exon1 = eukaryote_schema.ExonLocus(start=1, end=4)
exon2 = eukaryote_schema.ExonLocus(start=7, end=8)
transcript1 = eukaryote_schema.TranscriptSpeciesType(
rna=rna1, exons=[exon1, exon2])
gene2 = eukaryote_schema.GeneLocus(polymer=dna1,
start=4,
end=18,
strand=core.PolymerStrand.negative)
rna2 = eukaryote_schema.PreRnaSpeciesType(gene=gene2)
exon1 = eukaryote_schema.ExonLocus(start=4, end=10)
exon2 = eukaryote_schema.ExonLocus(start=14, end=16)
transcript2 = eukaryote_schema.TranscriptSpeciesType(
rna=rna2, exons=[exon1, exon2])
self.assertEqual(transcript1.get_seq(), 'ACUGUU')
self.assertEqual(transcript2.get_seq(), 'ACGGUAACUC')
def test_constructor(self):
dna1 = core.DnaSpeciesType(id='dna1', sequence_path=self.sequence_path)
gene1 = eukaryote_schema.GeneLocus(polymer=dna1, start=1, end=15)
rna1 = eukaryote_schema.PreRnaSpeciesType(gene=gene1)
transcript1 = eukaryote_schema.TranscriptSpeciesType(
id='t1', name='transcript1', rna=rna1, half_life=2)
self.assertEqual(transcript1.id, 't1')
self.assertEqual(transcript1.name, 'transcript1')
self.assertEqual(transcript1.rna, rna1)
self.assertEqual(transcript1.half_life, 2)
self.assertEqual(transcript1.exons, [])
self.assertEqual(transcript1.comments, '')
self.assertEqual(transcript1.references, [])
self.assertEqual(transcript1.database_references, [])
exon1 = eukaryote_schema.ExonLocus(start=1, end=1)
exon2 = eukaryote_schema.ExonLocus(start=2, end=2)
transcript1.exons = [exon1, exon2]
transcript2 = eukaryote_schema.TranscriptSpeciesType(
id='t2', name='transcript2', rna=rna1, exons=[exon2])
self.assertEqual(transcript1.exons, [exon1, exon2])
self.assertEqual(transcript2.exons, [exon2])
def test_ComplexSpeciesType(self):
self.tmp_dirname = tempfile.mkdtemp()
sequence_path = os.path.join(self.tmp_dirname, 'test_seq.fasta')
with open(sequence_path, 'w') as f:
f.write(
'>dna1\nTTTATGAARGTNCTCATHAAYAARAAYGARCTCTAGTTTATGAARTTYAARTTYCTCCTCACNCCNCTCTAATTT\n'
)
dna1 = core.DnaSpeciesType(id='dna1', sequence_path=sequence_path)
# Protein subunit 1
gene1 = eukaryote_schema.GeneLocus(polymer=dna1, start=1, end=36)
rna1 = eukaryote_schema.PreRnaSpeciesType(gene=gene1)
exon1 = eukaryote_schema.ExonLocus(start=4, end=36)
transcript1 = eukaryote_schema.TranscriptSpeciesType(rna=rna1,
exons=[exon1])
cds1 = eukaryote_schema.CdsLocus(start=4, end=36)
prot1 = eukaryote_schema.ProteinSpeciesType(transcript=transcript1,
coding_region=cds1)
# Protein subunit 2
gene2 = eukaryote_schema.GeneLocus(polymer=dna1, start=37, end=75)
rna2 = eukaryote_schema.PreRnaSpeciesType(gene=gene2)
exon2 = eukaryote_schema.ExonLocus(start=40, end=72)
transcript2 = eukaryote_schema.TranscriptSpeciesType(rna=rna2,
exons=[exon2])
cds2 = eukaryote_schema.CdsLocus(start=40, end=72)
prot2 = eukaryote_schema.ProteinSpeciesType(transcript=transcript2,
coding_region=cds2)
# Complex formation: (2) prot1 + (3) prot2 ==> complex1
species_coeff1 = core.SpeciesTypeCoefficient(species_type=prot1,
coefficient=2)
species_coeff2 = core.SpeciesTypeCoefficient(species_type=prot2,
coefficient=3)
complex1 = core.ComplexSpeciesType(
subunits=[species_coeff1, species_coeff2])
self.assertEqual(complex1.get_charge(), 8)
self.assertAlmostEqual(
complex1.get_mol_wt(),
(2 * prot1.get_mol_wt() + 3 * prot2.get_mol_wt()))
self.assertEqual(complex1.get_empirical_formula(),
chem.EmpiricalFormula('C292H492N64O66S5'))
shutil.rmtree(self.tmp_dirname)
def test_get_charge(self):
dna1 = core.DnaSpeciesType(id='dna5', sequence_path=self.sequence_path)
gene1 = eukaryote_schema.GeneLocus(polymer=dna1, start=1, end=1)
rna1 = eukaryote_schema.PreRnaSpeciesType(gene=gene1)
exon1 = eukaryote_schema.ExonLocus(start=1, end=1)
transcript1 = eukaryote_schema.TranscriptSpeciesType(rna=rna1,
exons=[exon1])
self.assertEqual(transcript1.get_charge(), -2)
gene2 = eukaryote_schema.GeneLocus(polymer=dna1, start=2, end=4)
rna2 = eukaryote_schema.PreRnaSpeciesType(gene=gene2)
exon2_1 = eukaryote_schema.ExonLocus(start=2, end=2)
exon2_2 = eukaryote_schema.ExonLocus(start=4, end=4)
transcript2 = eukaryote_schema.TranscriptSpeciesType(
rna=rna2, exons=[exon2_1, exon2_2])
self.assertEqual(transcript2.get_charge(), -3)
def test_constructor(self):
exon = eukaryote_schema.ExonLocus(id='e1',
name='exon1',
start=21,
end=30,
comments='No comment')
self.assertEqual(exon.id, 'e1')
self.assertEqual(exon.name, 'exon1')
self.assertEqual(exon.start, 21)
self.assertEqual(exon.end, 30)
self.assertEqual(exon.comments, 'No comment')
self.assertEqual(exon.references, [])
self.assertEqual(exon.database_references, [])
def setUp(self):
self.tmp_dirname = tempfile.mkdtemp()
sequence_path = os.path.join(self.tmp_dirname, 'test_seq.fasta')
with open(sequence_path, 'w') as f:
f.write(
'>dna1\nTTTATGAARGTNCTCATHAAYAARAAYGARCTCTAGTTTTTACAGTTYCGGGGTCAGCAGAAATTTTTTCATTTT\n'
)
dna1 = core.DnaSpeciesType(id='dna1', sequence_path=sequence_path)
cell1 = dna1.cell = core.Cell()
gene1 = eukaryote_schema.GeneLocus(polymer=dna1, start=1, end=36)
rna1 = eukaryote_schema.PreRnaSpeciesType(gene=gene1)
exon1 = eukaryote_schema.ExonLocus(start=4, end=36)
transcript1 = eukaryote_schema.TranscriptSpeciesType(rna=rna1,
exons=[exon1])
cds1 = eukaryote_schema.CdsLocus(id='cds1', start=4, end=36)
self.prot1 = eukaryote_schema.ProteinSpeciesType(
id='prot1',
name='protein1',
uniprot='Q12X34',
transcript=transcript1,
coding_region=cds1,
half_life=0.35)
gene2 = eukaryote_schema.GeneLocus(polymer=dna1,
start=30,
end=75,
strand=core.PolymerStrand.negative)
rna2 = eukaryote_schema.PreRnaSpeciesType(gene=gene2)
exon2_1 = eukaryote_schema.ExonLocus(start=32, end=35)
exon2_2 = eukaryote_schema.ExonLocus(start=38, end=45)
exon2_3 = eukaryote_schema.ExonLocus(start=49, end=54)
exon2_4 = eukaryote_schema.ExonLocus(start=55, end=72)
exon2_5 = eukaryote_schema.ExonLocus(start=73, end=74)
transcript2 = eukaryote_schema.TranscriptSpeciesType(
rna=rna2, exons=[exon2_1, exon2_2, exon2_3, exon2_4, exon2_5])
cds2 = eukaryote_schema.CdsLocus(id='cds2', start=40, end=72)
self.prot2 = eukaryote_schema.ProteinSpeciesType(
id='prot2',
name='protein2',
uniprot='P12345',
cell=cell1,
transcript=transcript2,
coding_region=cds2)
def test_get_empirical_formula(self):
dna1 = core.DnaSpeciesType(id='dna3', sequence_path=self.sequence_path)
gene1 = eukaryote_schema.GeneLocus(polymer=dna1, start=1, end=4)
rna1 = eukaryote_schema.PreRnaSpeciesType(gene=gene1)
exon1 = eukaryote_schema.ExonLocus(start=1, end=1)
transcript1 = eukaryote_schema.TranscriptSpeciesType(rna=rna1,
exons=[exon1])
self.assertEqual(transcript1.get_empirical_formula(),
chem.EmpiricalFormula('C10H12N5O7P'))
exon2 = eukaryote_schema.ExonLocus(start=2, end=2)
transcript2 = eukaryote_schema.TranscriptSpeciesType(rna=rna1,
exons=[exon2])
self.assertEqual(transcript2.get_empirical_formula(),
chem.EmpiricalFormula('C9H12N3O8P'))
exon3 = eukaryote_schema.ExonLocus(start=3, end=3)
transcript3 = eukaryote_schema.TranscriptSpeciesType(rna=rna1,
exons=[exon3])
self.assertEqual(transcript3.get_empirical_formula(),
chem.EmpiricalFormula('C10H12N5O8P'))
exon4 = eukaryote_schema.ExonLocus(start=4, end=4)
transcript4 = eukaryote_schema.TranscriptSpeciesType(rna=rna1,
exons=[exon4])
self.assertEqual(transcript4.get_empirical_formula(),
chem.EmpiricalFormula('C9H11N2O9P'))
dna2 = core.DnaSpeciesType(id='dna4', sequence_path=self.sequence_path)
gene2 = eukaryote_schema.GeneLocus(polymer=dna2, start=1, end=4)
rna2 = eukaryote_schema.PreRnaSpeciesType(gene=gene2)
exon5_1 = eukaryote_schema.ExonLocus(start=1, end=1)
exon5_2 = eukaryote_schema.ExonLocus(start=3, end=3)
transcript5 = eukaryote_schema.TranscriptSpeciesType(
rna=rna2, exons=[exon5_1, exon5_2])
self.assertEqual(transcript5.get_empirical_formula(),
chem.EmpiricalFormula('C20H23N10O13P2'))