def test_reader_error_multiple_kbs(self):
kb1 = core.KnowledgeBase(id='kb1', name='kb1', version='0.0.1')
kb2 = core.KnowledgeBase(id='kb2', name='kb2', version='0.0.1')
core_path = os.path.join(self.dir, 'core.xlsx')
obj_model.io.WorkbookWriter().run(core_path, [kb1, kb2], 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, ' should define one knowledge base'):
io.Reader().run(core_path, seq_path)
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 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_set_git_repo_metadata_from_path(self):
kb = core.KnowledgeBase()
self.assertEqual(kb.url, '')
util.set_git_repo_metadata_from_path(kb, path='.')
self.assertIn(kb.url, [
'https://github.com/KarrLab/wc_kb.git',
'ssh://[email protected]/KarrLab/wc_kb.git',
'[email protected]:KarrLab/wc_kb.git',
])
def test_set_git_repo_metadata_from_path_error(self):
tempdir = tempfile.mkdtemp()
kb = core.KnowledgeBase()
self.assertEqual(kb.url, '')
with self.assertRaisesRegex(ValueError, 'is not a Git repository'):
util.set_git_repo_metadata_from_path(kb, path=tempdir)
self.assertEqual(kb.url, '')
shutil.rmtree(tempdir)
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_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_reader_error_multiple_cells(self):
kb = core.KnowledgeBase(id='kb', name='kb1', version='0.0.1')
cell1 = core.Cell(id='cell1', name='cell1')
cell2 = core.Cell(id='cell2', name='cell2')
core_path = os.path.join(self.dir, 'core.xlsx')
obj_tables.io.WorkbookWriter().run(core_path, [kb, cell1, cell2],
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
with self.assertRaisesRegex(ValueError,
' should define zero or one cells'):
io.Reader().run(core_path, seq_path=seq_path)
def test_constructor(self):
kb = core.KnowledgeBase()
self.assertEqual(kb.cell, None)