def test_bit_ops(self):
"""PackedBases xor and bitcount should give correct # differences"""
p = PackedBases('UCAGU')
q = PackedBases('CAGGA')
self.assertEqual((p ^ q).bitcount(), 5)
r = PackedBases('CAAG')
self.assertEqual((r ^ q).bitcount(), 1)
def test_str(self):
"""PackedBases str should respect RNA/DNA"""
p = PackedBases('UCAGu')
self.assertEqual(str(p), 'UCAGU')
p.Rna = False
self.assertEqual(str(p), 'TCAGT')
p.Rna = True
self.assertEqual(str(p), 'UCAGU')
q = PackedBases('ucagu', Rna=False)
self.assertEqual(str(q), 'TCAGT')
p = PackedBases('T'*100, Rna=False)
self.assertEqual(str(p), 'T'*100)
p.Rna = True
self.assertEqual(str(p), 'U'*100)
def test_str(self):
"""PackedBases str should respect RNA/DNA"""
p = PackedBases("UCAGu")
self.assertEqual(str(p), "UCAGU")
p.Rna = False
self.assertEqual(str(p), "TCAGT")
p.Rna = True
self.assertEqual(str(p), "UCAGU")
q = PackedBases("ucagu", Rna=False)
self.assertEqual(str(q), "TCAGT")
p = PackedBases("T" * 100, Rna=False)
self.assertEqual(str(p), "T" * 100)
p.Rna = True
self.assertEqual(str(p), "U" * 100)
def test_init(self):
"""PackedBases init should allow sequence recovery"""
p = PackedBases()
self.assertEqual(str(p), '')
self.assertEqual(len(p), 0)
p = PackedBases('uCaGGCAU')
self.assertEqual(len(p), 16)
self.assertEqual(str(p), 'UCAGGCAU')
p = PackedBases('aaaAaaAaa')
self.assertEqual(str(p), 'AAAAAAAAA')
self.assertEqual(len(p), 18)
for base in 'ucagUCAGtT':
p = PackedBases(base)
self.assertEqual(len(p), 2)
self.assertEqual(str(p), base.upper().replace('T', 'U'))
def __call__(self, mismatches):
"""Consolidates ModuleInstances in KFinder.ModuleInstances into Modules.
- mismatches accounts for the difference between two ModuleInstances
in terms of purine vs pyrimidine or strong vs weak bonding.
"""
#New list to hold consolidated modules
consolidated_list = []
#Bind module_dict and module_order locally
module_dict = self.KFinder.ModuleDict
module_order = self.KFinder.ModuleOrder
#Check that dict is not empty
if module_dict:
#Iterate through modules in order
for pattern in module_order:
#Create a Bitvector representation of pattern
pat_vec = PackedBases(pattern)
added = False
#Iterate through consolidated_list
for curr_module, curr_vec in consolidated_list:
#If pat_vec and curr_vec are in the allowed mismatch cutoff
if sum(pat_vec ^ curr_vec) <= mismatches:
#Add module information to curr_module
curr_module.update(module_dict[pattern])
added = True
break
if not added:
#Add new module to consolidated list
consolidated_list.append([module_dict[pattern], pat_vec])
#self.Modules should have only the list of modules
self.Modules = [i[0] for i in consolidated_list]
for mod in self.Modules:
mod.Template = str(mod)
def test_str(self):
"""PackedBases str should respect RNA/DNA"""
p = PackedBases('UCAGu')
self.assertEqual(str(p), 'UCAGU')
p.Rna = False
self.assertEqual(str(p), 'TCAGT')
p.Rna = True
self.assertEqual(str(p), 'UCAGU')
q = PackedBases('ucagu', Rna=False)
self.assertEqual(str(q), 'TCAGT')
p = PackedBases('T' * 100, Rna=False)
self.assertEqual(str(p), 'T' * 100)
p.Rna = True
self.assertEqual(str(p), 'U' * 100)