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 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_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_get_charge(self):
dna1 = core.DnaSpeciesType(id='dna6', 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_charge(), -2)
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_charge(), -3)
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 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.TranscriptionUnitLocus(
id='tu_{}_{}'.format(i_chr + 1, i_trn + 1))
trn.type = random.choice([
'WC:mRNA', 'WC:sRNA', 'WC:tRNA', 'WC:rRNA',
'WC:intergenic', 'WC:mixed'
])
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_constructor(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],
type=1)
# make sure that only TU can be created that have valid length
# These should throw errors:
#tu2 = prokaryote.TranscriptionUnitLocus(id='tu1', polymer=dna1, start=1, end=20)
#tu2 = prokaryote.TranscriptionUnitLocus(id='tu1', polymer=dna1, start=-3, end=20)
self.assertEqual(rna1.id, 'rna1')
self.assertEqual(rna1.name, 'rna1')
self.assertEqual(rna1.transcription_units, [tu1])
self.assertEqual(rna1.type, 1)
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.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(core_path,
self.kb,
seq_path=seq_path,
data_repo_metadata=False)
def test_get_mol_wt(self):
dna1 = core.DnaSpeciesType(id='dna7', 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])
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.TranscriptionUnitLocus(id='tu1',
polymer=dna1,
start=3,
end=3)
rna1 = prokaryote.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.TranscriptionUnitLocus(id='tu1',
polymer=dna1,
start=5,
end=5)
rna1 = prokaryote.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)
# Adding cases that have ,multiple nucleotides
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])
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='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])
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)