def test_get_seq(self):
dna1 = core.DnaSpeciesType(id='dna1', sequence_path=self.sequence_path)
tu1 = prokaryote.TranscriptionUnitLocus(id='tu1',
polymer=dna1,
start=1,
end=15)
rna1 = prokaryote.RnaSpeciesType(id='rna1',
name='rna1',
transcription_units=[tu1])
self.assertEqual(rna1.get_seq(), dna1.get_seq().transcribe())
dna1 = core.DnaSpeciesType(id='dna2', sequence_path=self.sequence_path)
tu1 = prokaryote.TranscriptionUnitLocus(id='tu1',
polymer=dna1,
start=1,
end=1)
rna1 = prokaryote.RnaSpeciesType(id='rna1',
name='rna1',
transcription_units=[tu1])
self.assertEqual(rna1.get_seq(), dna1.get_seq().transcribe())
dna1 = core.DnaSpeciesType(id='dna7', sequence_path=self.sequence_path)
tu1 = prokaryote.TranscriptionUnitLocus(id='tu1',
polymer=dna1,
start=1,
end=8)
rna1 = prokaryote.RnaSpeciesType(id='rna1',
name='rna1',
transcription_units=[tu1])
self.assertEqual(rna1.get_seq(), dna1.get_seq().transcribe())
def test_get_empirical_formula(self):
dna1 = core.DnaSpeciesType(id='dna2', sequence_path=self.sequence_path)
gene1 = eukaryote_schema.GeneLocus(polymer=dna1, start=1, end=1)
rna1 = eukaryote_schema.PreRnaSpeciesType(gene=gene1)
self.assertEqual(rna1.get_empirical_formula(),
chem.EmpiricalFormula('C10H12N5O7P'))
gene2 = eukaryote_schema.GeneLocus(polymer=dna1, start=2, end=2)
rna2 = eukaryote_schema.PreRnaSpeciesType(gene=gene2)
self.assertEqual(rna2.get_empirical_formula(),
chem.EmpiricalFormula('C9H12N3O8P'))
gene3 = eukaryote_schema.GeneLocus(polymer=dna1, start=3, end=3)
rna3 = eukaryote_schema.PreRnaSpeciesType(gene=gene3)
self.assertEqual(rna3.get_empirical_formula(),
chem.EmpiricalFormula('C10H12N5O8P'))
gene4 = eukaryote_schema.GeneLocus(polymer=dna1, start=4, end=4)
rna4 = eukaryote_schema.PreRnaSpeciesType(gene=gene4)
self.assertEqual(rna4.get_empirical_formula(),
chem.EmpiricalFormula('C9H11N2O9P'))
dna2 = core.DnaSpeciesType(id='dna3', sequence_path=self.sequence_path)
gene5 = eukaryote_schema.GeneLocus(polymer=dna2, start=1, end=2)
rna5 = eukaryote_schema.PreRnaSpeciesType(gene=gene5)
self.assertEqual(rna5.get_empirical_formula(),
chem.EmpiricalFormula('C20H23N10O13P2'))
def test_get_empirical_formula(self):
dna1 = core.DnaSpeciesType(id='dna2', sequence_path=self.sequence_path)
tu1 = prokaryote.TranscriptionUnitLocus(id='tu1',
polymer=dna1,
start=1,
end=1)
rna1 = prokaryote.RnaSpeciesType(id='rna1',
name='rna1',
transcription_units=[tu1])
self.assertEqual(rna1.get_empirical_formula(),
chem.EmpiricalFormula('C10H12N5O7P'))
dna1 = core.DnaSpeciesType(id='dna3', sequence_path=self.sequence_path)
tu1 = prokaryote.TranscriptionUnitLocus(id='tu1',
polymer=dna1,
start=1,
end=1)
rna1 = prokaryote.RnaSpeciesType(id='rna1',
name='rna1',
transcription_units=[tu1])
self.assertEqual(rna1.get_empirical_formula(),
chem.EmpiricalFormula('C9H12N3O8P'))
dna1 = core.DnaSpeciesType(id='dna4', sequence_path=self.sequence_path)
tu1 = prokaryote.TranscriptionUnitLocus(id='tu1',
polymer=dna1,
start=1,
end=1)
rna1 = prokaryote.RnaSpeciesType(id='rna1',
name='rna1',
transcription_units=[tu1])
self.assertEqual(rna1.get_empirical_formula(),
chem.EmpiricalFormula('C10H12N5O8P'))
dna1 = core.DnaSpeciesType(id='dna5', sequence_path=self.sequence_path)
tu1 = prokaryote.TranscriptionUnitLocus(id='tu1',
polymer=dna1,
start=1,
end=1)
rna1 = prokaryote.RnaSpeciesType(id='rna1',
name='rna1',
transcription_units=[tu1])
self.assertEqual(rna1.get_empirical_formula(),
chem.EmpiricalFormula('C9H11N2O9P'))
dna1 = core.DnaSpeciesType(id='dna6', sequence_path=self.sequence_path)
tu1 = prokaryote.TranscriptionUnitLocus(id='tu1',
polymer=dna1,
start=1,
end=2)
rna1 = prokaryote.RnaSpeciesType(id='rna1',
name='rna1',
transcription_units=[tu1])
self.assertEqual(rna1.get_empirical_formula(),
chem.EmpiricalFormula('C20H23N10O13P2'))
def test_observable_coefficient(self):
cell = core.Cell()
comp1 = core.Compartment(id='c')
met1 = core.MetaboliteSpeciesType(id='met1')
dna1 = core.DnaSpeciesType(id="dna1")
species1 = core.Species(species_type=met1, compartment=comp1)
species2 = core.Species(species_type=dna1, compartment=comp1)
speciesCoefficient1 = core.SpeciesCoefficient(species=species1,
coefficient=2.5)
speciesCoefficient2 = core.SpeciesCoefficient(species=species2,
coefficient=3)
observable1 = core.Observable(
id='test',
cell=cell,
species=[speciesCoefficient1, speciesCoefficient2])
observableCoefficient1 = core.ObservableCoefficient(
observable=observable1, coefficient=2.3)
self.assertIsInstance(observableCoefficient1,
core.ObservableCoefficient)
self.assertIsInstance(observableCoefficient1.observable,
core.Observable)
self.assertIsInstance(observableCoefficient1.coefficient, float)
self.assertEqual(observableCoefficient1.observable.id, 'test')
def test_constructor(self):
dna1 = core.DnaSpeciesType(circular=False, double_stranded=False)
gene1 = eukaryote.GeneLocus(polymer=dna1, start=9, end=15)
gene2 = eukaryote.GeneLocus(polymer=dna1, start=17, end=18)
promoter1 = 'ENSR00000172399'
promoter2 = 'ENSR00000309980'
tf1 = eukaryote.ProteinSpeciesType(id='tf1')
tf2 = eukaryote.ProteinSpeciesType(id='tf2')
reg_module1 = eukaryote.RegulatoryModule(
gene=gene1,
promoter=promoter1,
activity=eukaryote.ActivityLevel.active,
type=eukaryote.RegulationType.proximal,
transcription_factor_regulation=[
eukaryote.TranscriptionFactorRegulation(
transcription_factor=tf1,
direction=eukaryote.RegulatoryDirection.activation),
eukaryote.TranscriptionFactorRegulation(
transcription_factor=tf2,
direction=eukaryote.RegulatoryDirection.repression)
])
reg_module2 = eukaryote.RegulatoryModule(
gene=gene1,
promoter=promoter1,
activity=eukaryote.ActivityLevel.active,
type=eukaryote.RegulationType.distal,
transcription_factor_regulation=[eukaryote.TranscriptionFactorRegulation(
transcription_factor=tf1,
direction=eukaryote.RegulatoryDirection.repression)])
reg_module3 = eukaryote.RegulatoryModule(
id='rm3',
name='reg_module3',
activity=eukaryote.ActivityLevel.inactive,
gene=gene2,
promoter=promoter2)
self.assertEqual(reg_module1.gene, gene1)
self.assertEqual(reg_module1.promoter, promoter1)
self.assertEqual(reg_module1.activity.name, 'active')
self.assertEqual(reg_module1.type.value, 1)
self.assertEqual(sorted([i.transcription_factor.id for i in reg_module1.transcription_factor_regulation]),
['tf1', 'tf2'])
self.assertEqual(sorted([i.direction.name for i in reg_module1.transcription_factor_regulation]),
['activation', 'repression'])
self.assertEqual(reg_module2.gene, gene1)
self.assertEqual(reg_module2.promoter, promoter1)
self.assertEqual(reg_module2.activity.name, 'active')
self.assertEqual(reg_module2.type.value, 2)
self.assertEqual(reg_module2.transcription_factor_regulation[0].transcription_factor, tf1)
self.assertEqual(reg_module2.transcription_factor_regulation[0].direction.name, 'repression')
self.assertEqual(reg_module3.id, 'rm3')
self.assertEqual(reg_module3.activity.name, 'inactive')
self.assertEqual(reg_module3.name, 'reg_module3')
self.assertEqual(reg_module3.promoter, promoter2)
def test_constructor(self):
dna1 = core.DnaSpeciesType(id='dna1', sequence_path=self.sequence_path)
gene1 = eukaryote.GeneLocus(polymer=dna1, start=1, end=15)
transcript1 = eukaryote.TranscriptSpeciesType(
id='t1',
name='transcript1',
gene=gene1,
type=eukaryote.TranscriptType.mRna)
self.assertEqual(transcript1.id, 't1')
self.assertEqual(transcript1.name, 'transcript1')
self.assertEqual(transcript1.gene, gene1)
self.assertEqual(transcript1.type.name, 'mRna')
self.assertEqual(transcript1.exons, [])
self.assertEqual(transcript1.comments, '')
self.assertEqual(transcript1.references, [])
self.assertEqual(transcript1.identifiers, [])
exon1 = eukaryote.GenericLocus(start=1, end=1)
exon2 = eukaryote.GenericLocus(start=2, end=2)
transcript1.exons = [exon1, exon2]
transcript2 = eukaryote.TranscriptSpeciesType(id='t2',
name='transcript2',
gene=gene1,
exons=[exon2])
self.assertEqual(transcript1.exons, [exon1, exon2])
self.assertEqual(transcript2.exons, [exon2])
def setUp(self):
# Mycoplasma Genintalium Genome
dna1 = core.DnaSpeciesType(
id='chromosome', sequence_path='tests/fixtures/prokaryote_seq.fna')
cell1 = dna1.cell = core.Cell()
cell1.knowledge_base = core.KnowledgeBase(
translation_table=4) # Table 4 is for mycoplasma
# MPN001
self.prot1 = prokaryote.ProteinSpeciesType(id='prot1', cell=cell1)
gene1 = prokaryote.GeneLocus(id='gene1',
cell=cell1,
proteins=self.prot1,
polymer=dna1,
start=692,
end=1834)
tu1 = prokaryote.TranscriptionUnitLocus(id='tu1',
genes=[gene1],
polymer=dna1)
# MPN011
self.prot2 = prokaryote.ProteinSpeciesType(id='prot2', cell=cell1)
gene2 = prokaryote.GeneLocus(id='gene2',
cell=cell1,
proteins=self.prot2,
polymer=dna1,
start=12838,
end=13533,
strand=core.PolymerStrand.negative)
tu2 = prokaryote.TranscriptionUnitLocus(id='tu2',
genes=[gene2],
polymer=dna1)
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 setUp(self):
self.dir = tempfile.mkdtemp()
self.seq_path = os.path.join(self.dir, 'seq.fna')
self.kb = kb = core.KnowledgeBase(id='genus_species', name='Genus species', version='0.0.1')
cell = kb.cell = core.Cell(id='genus_species_cell')
dna_seqs = []
for i_chr in range(5):
dna = core.DnaSpeciesType(id='chr_{}'.format(i_chr + 1), sequence_path=self.seq_path)
cell.species_types.append(dna)
seq_len = random.randint(100, 200)
bases = 'ACGT'
seq = ''
for i_nt in range(seq_len):
seq += bases[random.randint(0, 3)]
dna_seqs.append(Bio.SeqRecord.SeqRecord(
Bio.Seq.Seq(seq), dna.id))
for i_trn in range(5):
trn = prokaryote_schema.TranscriptionUnitLocus(id='tu_{}_{}'.format(i_chr + 1, i_trn + 1))
trn.cell = cell
dna.loci.append(trn)
trn.start = random.randint(100, 200)
trn.end = ((trn.start + random.randint(1, 200) - 1) % seq_len) + 1
trn.strand = core.PolymerStrand.positive
with open(self.seq_path, 'w') as file:
writer = Bio.SeqIO.FastaIO.FastaWriter(
file, wrap=70, record2title=lambda record: record.id)
writer.write_file(dna_seqs)
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_mol_wt(self):
dna1 = core.DnaSpeciesType(id='dna6', sequence_path=self.sequence_path)
gene1 = eukaryote.GeneLocus(polymer=dna1, start=1, end=6)
exon1 = eukaryote.GenericLocus(start=1, end=1)
transcript1 = eukaryote.TranscriptSpeciesType(gene=gene1, 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.GenericLocus(start=3, end=3)
transcript2 = eukaryote.TranscriptSpeciesType(gene=gene1, 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.GenericLocus(start=5, end=5)
transcript3 = eukaryote.TranscriptSpeciesType(gene=gene1, 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)
# Test using input sequence
test_trans = eukaryote.TranscriptSpeciesType()
exp_mol_wt = \
+ Bio.SeqUtils.molecular_weight(transcript1.get_seq()) \
- (transcript1.get_len() + 1) * mendeleev.element('H').atomic_weight
self.assertAlmostEqual(test_trans.get_mol_wt(seq_input=Bio.Seq.Seq('A')), 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_get_charge(self):
dna1 = core.DnaSpeciesType(id='dna3', sequence_path=self.sequence_path)
gene1 = eukaryote_schema.GeneLocus(polymer=dna1, start=1, end=1)
rna1 = eukaryote_schema.PreRnaSpeciesType(gene=gene1)
self.assertEqual(rna1.get_charge(), -2)
gene2 = eukaryote_schema.GeneLocus(polymer=dna1, start=2, end=3)
rna2 = eukaryote_schema.PreRnaSpeciesType(gene=gene2)
self.assertEqual(rna2.get_charge(), -3)
def test_get_empirical_formula(self):
dna1 = core.DnaSpeciesType(id='dna3', sequence_path=self.sequence_path)
gene1 = eukaryote.GeneLocus(polymer=dna1, start=1, end=4)
exon1 = eukaryote.GenericLocus(start=1, end=1)
transcript1 = eukaryote.TranscriptSpeciesType(gene=gene1,
exons=[exon1])
self.assertEqual(transcript1.get_empirical_formula(),
chem.EmpiricalFormula('C10H12N5O7P'))
exon2 = eukaryote.GenericLocus(start=2, end=2)
transcript2 = eukaryote.TranscriptSpeciesType(gene=gene1,
exons=[exon2])
self.assertEqual(transcript2.get_empirical_formula(),
chem.EmpiricalFormula('C9H12N3O8P'))
exon3 = eukaryote.GenericLocus(start=3, end=3)
transcript3 = eukaryote.TranscriptSpeciesType(gene=gene1,
exons=[exon3])
self.assertEqual(transcript3.get_empirical_formula(),
chem.EmpiricalFormula('C10H12N5O8P'))
exon4 = eukaryote.GenericLocus(start=4, end=4)
transcript4 = eukaryote.TranscriptSpeciesType(gene=gene1,
exons=[exon4])
self.assertEqual(transcript4.get_empirical_formula(),
chem.EmpiricalFormula('C9H11N2O9P'))
dna2 = core.DnaSpeciesType(id='dna4', sequence_path=self.sequence_path)
gene2 = eukaryote.GeneLocus(polymer=dna2, start=1, end=4)
exon5_1 = eukaryote.GenericLocus(start=1, end=1)
exon5_2 = eukaryote.GenericLocus(start=3, end=3)
transcript5 = eukaryote.TranscriptSpeciesType(gene=gene2,
exons=[exon5_1, exon5_2])
self.assertEqual(transcript5.get_empirical_formula(),
chem.EmpiricalFormula('C20H23N10O13P2'))
# Test using input sequence
test_trans = eukaryote.TranscriptSpeciesType()
self.assertEqual(
test_trans.get_empirical_formula(seq_input=Bio.Seq.Seq('AA')),
chem.EmpiricalFormula('C20H23N10O13P2'))
def test_get_charge(self):
dna1 = core.DnaSpeciesType(id='dna6', sequence_path=self.sequence_path)
tu1 = prokaryote_schema.TranscriptionUnitLocus(id='tu1',
polymer=dna1,
start=1,
end=1)
rna1 = prokaryote_schema.RnaSpeciesType(id='rna1',
name='rna1',
transcription_units=[tu1])
self.assertEqual(rna1.get_charge(), -2)
dna1 = core.DnaSpeciesType(id='dna6', sequence_path=self.sequence_path)
tu1 = prokaryote_schema.TranscriptionUnitLocus(id='tu1',
polymer=dna1,
start=1,
end=2)
rna1 = prokaryote_schema.RnaSpeciesType(id='rna1',
name='rna1',
transcription_units=[tu1])
self.assertEqual(rna1.get_charge(), -3)
def test_ComplexSpeciesType(self):
# Test constructor
complex1 = core.ComplexSpeciesType()
# Generate test proteins from Mycoplasma Genintalium Genome
dna1 = core.DnaSpeciesType(id='chromosome',
sequence_path='tests/fixtures/seq.fna')
cell1 = dna1.cell = core.Cell()
cell1.knowledge_base = core.KnowledgeBase(
translation_table=4) # Table 4 is for mycoplasma
# Protein 1, MPN001
gene1 = prokaryote_schema.GeneLocus(id='gene1',
cell=cell1,
polymer=dna1,
start=692,
end=1834)
tu1 = prokaryote_schema.TranscriptionUnitLocus(id='tu1',
genes=[gene1],
polymer=dna1)
prot1 = prokaryote_schema.ProteinSpeciesType(id='prot1',
gene=gene1,
cell=cell1)
# Protein 2, MPN011
gene2 = prokaryote_schema.GeneLocus(id='gene2',
cell=cell1,
polymer=dna1,
start=12838,
end=13533,
strand=core.PolymerStrand.negative)
tu2 = prokaryote_schema.TranscriptionUnitLocus(id='tu2',
genes=[gene2],
polymer=dna1)
prot2 = prokaryote_schema.ProteinSpeciesType(id='prot2',
gene=gene2,
cell=cell1)
# Test adding complexation
# Add formation reaction: (2) prot1 + (3) prot2 ==> complex1
species_coeff1 = core.SpeciesTypeCoefficient(species_type=prot1,
coefficient=2)
species_coeff2 = core.SpeciesTypeCoefficient(species_type=prot2,
coefficient=3)
complex1.subunits = [species_coeff1, species_coeff2]
self.assertEqual(complex1.get_charge(), 38)
self.assertAlmostEqual(
complex1.get_mol_wt(),
(2 * prot1.get_mol_wt() + 3 * prot2.get_mol_wt()))
self.assertEqual(complex1.get_empirical_formula(),
chem.EmpiricalFormula('C7698H12076N1938O2248S23'))
def test_reader_error_no_cell(self):
kb = core.KnowledgeBase(id='kb', name='kb1', version='0.0.1')
dna = core.DnaSpeciesType(id='chr')
core_path = os.path.join(self.dir, 'core.xlsx')
obj_model.io.WorkbookWriter().run(core_path, [kb, dna], io.PROKARYOTE_MODEL_ORDER, include_all_attributes=False)
seq_path = os.path.join(self.dir, 'test_seq.fna')
with open(seq_path, 'w') as file:
pass
with self.assertRaisesRegex(ValueError, 'cannot contain instances'):
io.Reader().run(core_path, seq_path)
def test_get_mol_wt(self):
dna1 = core.DnaSpeciesType(id='dna7', sequence_path=self.sequence_path)
tu1 = prokaryote_schema.TranscriptionUnitLocus(id='tu1',
polymer=dna1,
start=1,
end=1)
rna1 = prokaryote_schema.RnaSpeciesType(id='rna1',
name='rna1',
transcription_units=[tu1])
exp_mol_wt = \
+ Bio.SeqUtils.molecular_weight(rna1.get_seq()) \
- (rna1.get_len() + 1) * mendeleev.element('H').atomic_weight
self.assertAlmostEqual(rna1.get_mol_wt(), exp_mol_wt, places=1)
dna1 = core.DnaSpeciesType(id='dna7', sequence_path=self.sequence_path)
tu1 = prokaryote_schema.TranscriptionUnitLocus(id='tu1',
polymer=dna1,
start=3,
end=3)
rna1 = prokaryote_schema.RnaSpeciesType(id='rna1',
name='rna1',
transcription_units=[tu1])
exp_mol_wt = \
+ Bio.SeqUtils.molecular_weight(rna1.get_seq()) \
- (rna1.get_len() + 1) * mendeleev.element('H').atomic_weight
self.assertAlmostEqual(rna1.get_mol_wt(), exp_mol_wt, places=1)
dna1 = core.DnaSpeciesType(id='dna7', sequence_path=self.sequence_path)
tu1 = prokaryote_schema.TranscriptionUnitLocus(id='tu1',
polymer=dna1,
start=5,
end=5)
rna1 = prokaryote_schema.RnaSpeciesType(id='rna1',
name='rna1',
transcription_units=[tu1])
exp_mol_wt = \
+ Bio.SeqUtils.molecular_weight(rna1.get_seq()) \
- (rna1.get_len() + 1) * mendeleev.element('H').atomic_weight
self.assertAlmostEqual(rna1.get_mol_wt(), exp_mol_wt, places=1)
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'))
def test_reader_no_cell(self):
kb = core.KnowledgeBase(id='kb', name='kb1', version='0.0.1')
dna = core.DnaSpeciesType(id='chr')
core_path = os.path.join(self.dir, 'core.xlsx')
obj_tables.io.WorkbookWriter().run(core_path, [kb, dna],
models=io.PROKARYOTE_MODELS,
include_all_attributes=False)
seq_path = os.path.join(self.dir, 'test_seq.fna')
with open(seq_path, 'w') as file:
pass
io.Reader().run(core_path, seq_path=seq_path)
def test_get_5_prime(self):
dna1 = core.DnaSpeciesType(id='dna1', sequence_path=self.sequence_path)
tu1 = prokaryote.TranscriptionUnitLocus(
id='tu1',
polymer=dna1,
start=1,
end=15,
strand=core.PolymerStrand.positive)
rna1 = prokaryote.RnaSpeciesType(id='rna1',
name='rna1',
transcription_units=[tu1])
self.assertEqual(tu1.get_5_prime(), 1)
dna1 = core.DnaSpeciesType(id='dna1', sequence_path=self.sequence_path)
tu1 = prokaryote.TranscriptionUnitLocus(
id='tu1',
polymer=dna1,
start=1,
end=15,
strand=core.PolymerStrand.negative)
rna1 = prokaryote.RnaSpeciesType(id='rna1',
name='rna1',
transcription_units=[tu1])
self.assertEqual(tu1.get_5_prime(), 15)
def test_get_seq(self):
dna1 = core.DnaSpeciesType(id='dna1', 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)
gene2 = eukaryote_schema.GeneLocus(polymer=dna1,
start=4,
end=18,
strand=core.PolymerStrand.negative)
rna2 = eukaryote_schema.PreRnaSpeciesType(gene=gene2)
self.assertEqual(rna1.get_seq(), 'ACUGAGUUACGUACG')
self.assertEqual(rna2.get_seq(), 'AAACGUACGUAACUC')
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.GeneLocus(polymer=dna1, start=1, end=1)
exon1 = eukaryote.GenericLocus(start=1, end=1)
transcript1 = eukaryote.TranscriptSpeciesType(gene=gene1, exons=[exon1])
self.assertEqual(transcript1.get_charge(), -2)
gene2 = eukaryote.GeneLocus(polymer=dna1, start=2, end=4)
exon2_1 = eukaryote.GenericLocus(start=2, end=2)
exon2_2 = eukaryote.GenericLocus(start=4, end=4)
transcript2 = eukaryote.TranscriptSpeciesType(gene=gene2, exons=[exon2_1, exon2_2])
self.assertEqual(transcript2.get_charge(), -3)
# Test using input sequence
test_trans = eukaryote.TranscriptSpeciesType()
self.assertEqual(test_trans.get_charge(seq_input=Bio.Seq.Seq('CG')), -3)
def test_write_without_cell_relationships(self):
core_path = os.path.join(self.dir, 'core.xlsx')
seq_path = os.path.join(self.dir, 'test_seq.fna')
with open(seq_path, 'w') as file:
file.write('>chr_x\nACGT\n')
dna = core.DnaSpeciesType(id='chr_x', sequence_path=seq_path)
self.kb.cell.species_types.append(dna)
trn = prokaryote_schema.TranscriptionUnitLocus(id='tu_x_0')
dna.loci.append(trn)
trn.cell = None
writer = io.Writer()
with self.assertRaisesRegex(ValueError, 'must be set to the instance of `Cell`'):
writer.run(self.kb, core_path, seq_path, set_repo_metadata_from_path=False)
def test_constructor(self):
dna1 = core.DnaSpeciesType(id='dna1')
gene1 = eukaryote_schema.GeneLocus(polymer=dna1, start=1, end=15)
rna1 = eukaryote_schema.PreRnaSpeciesType(id='rna1',
name='rna1',
gene=gene1,
type=1,
half_life=2)
self.assertEqual(rna1.id, 'rna1')
self.assertEqual(rna1.name, 'rna1')
self.assertEqual(rna1.gene, gene1)
self.assertEqual(rna1.type, 1)
self.assertEqual(rna1.half_life, 2)
self.assertEqual(rna1.comments, '')
self.assertEqual(rna1.references, [])
self.assertEqual(rna1.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_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):
dna1 = core.DnaSpeciesType(id='dna1', sequence_path=self.sequence_path)
tu1 = prokaryote_schema.TranscriptionUnitLocus(id='tu1',
polymer=dna1,
start=1,
end=15)
rna1 = prokaryote_schema.RnaSpeciesType(id='rna1',
name='rna1',
transcription_units=[tu1],
type=1,
half_life=2)
self.assertEqual(rna1.id, 'rna1')
self.assertEqual(rna1.name, 'rna1')
self.assertEqual(rna1.transcription_units, [tu1])
self.assertEqual(rna1.type, 1)
self.assertEqual(rna1.half_life, 2)
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\nTTTATGAARGTNCTCATHAAYAARAAYGARCTCTAGTTTATGAARTTYAARTTYCTCCTCACNCCNCTCTAATTT\n'
)
dna1 = core.DnaSpeciesType(id='dna1', sequence_path=sequence_path)
cell1 = dna1.cell = core.Cell()
gene1 = eukaryote.GeneLocus(polymer=dna1, start=1, end=36)
exon1 = eukaryote.GenericLocus(start=4, end=36)
transcript1 = eukaryote.TranscriptSpeciesType(gene=gene1,
exons=[exon1])
cds1 = eukaryote.GenericLocus(start=4, end=36)
self.prot1 = eukaryote.ProteinSpeciesType(id='prot1',
name='protein1',
uniprot='Q12X34',
transcript=transcript1,
coding_regions=[cds1])
gene2 = eukaryote.GeneLocus(polymer=dna1,
start=30,
end=75,
strand=core.PolymerStrand.positive)
exon2_1 = eukaryote.GenericLocus(start=32, end=35)
exon2_2 = eukaryote.GenericLocus(start=38, end=45)
exon2_3 = eukaryote.GenericLocus(start=49, end=54)
exon2_4 = eukaryote.GenericLocus(start=55, end=72)
exon2_5 = eukaryote.GenericLocus(start=73, end=74)
transcript2 = eukaryote.TranscriptSpeciesType(
gene=gene2, exons=[exon2_1, exon2_2, exon2_3, exon2_4, exon2_5])
cds2_2 = eukaryote.GenericLocus(start=40, end=45)
cds2_3 = eukaryote.GenericLocus(start=49, end=54)
cds2_4 = eukaryote.GenericLocus(start=55, end=72)
self.prot2 = eukaryote.ProteinSpeciesType(
id='prot2',
name='protein2',
uniprot='P12345',
cell=cell1,
transcript=transcript2,
coding_regions=[cds2_4, cds2_2, cds2_3])
