def test_generate_fraggle_fragmentation(self):
mol = Chem.MolFromSmiles('COc1cc(CN2CCC(CC2)NC(=O)c2cncc(C)c2)c(OC)c2ccccc12')
frags = FraggleSim.generate_fraggle_fragmentation(mol)
self.assertEqual(len(frags), 16)
expected = (
'[*]C(=O)NC1CCN(Cc2cc(OC)c3ccccc3c2OC)CC1',
'[*]C(=O)c1cncc(C)c1.[*]C1CCN(Cc2cc(OC)c3ccccc3c2OC)CC1',
'[*]C(=O)c1cncc(C)c1.[*]c1cc(OC)c2ccccc2c1OC', '[*]C1CCN(Cc2cc(OC)c3ccccc3c2OC)CC1',
'[*]C(=O)c1cncc(C)c1.[*]Cc1cc(OC)c2ccccc2c1OC',
'[*]Cc1cc(OC)c2ccccc2c1OC.[*]NC(=O)c1cncc(C)c1', '[*]Cc1cc(OC)c2ccccc2c1OC.[*]c1cncc(C)c1',
'[*]NC(=O)c1cncc(C)c1.[*]c1cc(OC)c2ccccc2c1OC', '[*]NC1CCN(Cc2cc(OC)c3ccccc3c2OC)CC1',
'[*]NC1CCN(Cc2cc(OC)c3ccccc3c2OC)CC1.[*]c1cncc(C)c1',
'[*]c1c(CN2CCC(NC(=O)c3cncc(C)c3)CC2)cc(OC)c2ccccc12',
'[*]c1c(OC)cc(CN2CCC(NC(=O)c3cncc(C)c3)CC2)c(OC)c1[*]',
'[*]c1cc(CN2CCC(NC(=O)c3cncc(C)c3)CC2)c(OC)c2ccccc12',
'[*]N1CCC(NC(=O)c2cncc(C)c2)CC1.[*]c1cc(OC)c2ccccc2c1OC',
'[*]C1CCN(Cc2cc(OC)c3ccccc3c2OC)CC1.[*]c1cncc(C)c1', '[*]c1cc(OC)c2ccccc2c1OC.[*]c1cncc(C)c1')
expected = [_of(s) for s in expected]
for smi in frags:
self.assertTrue(_of(smi) in expected)
# Test case for fragments that contain a cyclic and acyclic component
mol = Chem.MolFromSmiles('c12c(CCC)cccc2cccc1')
frags = FraggleSim.generate_fraggle_fragmentation(mol)
expected = ['[*]CCC.[*]c1ccccc1[*]', '[*]Cc1cccc2ccccc12', '[*]c1cccc(CCC)c1[*]',
'[*]c1cccc2ccccc12', '[*]c1ccccc1[*]']
expected = [_of(s) for s in expected]
for smi in frags:
self.assertTrue(_of(smi) in expected)
def test_generate_fraggle_fragmentation(self):
mol = Chem.MolFromSmiles('COc1cc(CN2CCC(CC2)NC(=O)c2cncc(C)c2)c(OC)c2ccccc12')
frags = FraggleSim.generate_fraggle_fragmentation(mol)
self.assertEqual(len(frags), 16)
expected = (
'[*]C(=O)NC1CCN(Cc2cc(OC)c3ccccc3c2OC)CC1',
'[*]C(=O)c1cncc(C)c1.[*]C1CCN(Cc2cc(OC)c3ccccc3c2OC)CC1',
'[*]C(=O)c1cncc(C)c1.[*]c1cc(OC)c2ccccc2c1OC', '[*]C1CCN(Cc2cc(OC)c3ccccc3c2OC)CC1',
'[*]C(=O)c1cncc(C)c1.[*]Cc1cc(OC)c2ccccc2c1OC',
'[*]Cc1cc(OC)c2ccccc2c1OC.[*]NC(=O)c1cncc(C)c1', '[*]Cc1cc(OC)c2ccccc2c1OC.[*]c1cncc(C)c1',
'[*]NC(=O)c1cncc(C)c1.[*]c1cc(OC)c2ccccc2c1OC', '[*]NC1CCN(Cc2cc(OC)c3ccccc3c2OC)CC1',
'[*]NC1CCN(Cc2cc(OC)c3ccccc3c2OC)CC1.[*]c1cncc(C)c1',
'[*]c1c(CN2CCC(NC(=O)c3cncc(C)c3)CC2)cc(OC)c2ccccc12',
'[*]c1c(OC)cc(CN2CCC(NC(=O)c3cncc(C)c3)CC2)c(OC)c1[*]',
'[*]c1cc(CN2CCC(NC(=O)c3cncc(C)c3)CC2)c(OC)c2ccccc12',
'[*]N1CCC(NC(=O)c2cncc(C)c2)CC1.[*]c1cc(OC)c2ccccc2c1OC',
'[*]C1CCN(Cc2cc(OC)c3ccccc3c2OC)CC1.[*]c1cncc(C)c1', '[*]c1cc(OC)c2ccccc2c1OC.[*]c1cncc(C)c1')
expected = [_of(s) for s in expected]
for smi in frags:
self.assertTrue(_of(smi) in expected)
# Test case for fragments that contain a cyclic and acyclic component
mol = Chem.MolFromSmiles('c12c(CCC)cccc2cccc1')
frags = FraggleSim.generate_fraggle_fragmentation(mol)
expected = ['[*]CCC.[*]c1ccccc1[*]', '[*]Cc1cccc2ccccc12', '[*]c1cccc(CCC)c1[*]',
'[*]c1cccc2ccccc12', '[*]c1ccccc1[*]']
expected = [_of(s) for s in expected]
for smi in frags:
self.assertTrue(_of(smi) in expected)
def testFragmentation(self):
"""
"""
mol = Chem.MolFromSmiles(
'COc1cc(CN2CCC(CC2)NC(=O)c2cncc(C)c2)c(OC)c2ccccc12')
frags = FraggleSim.generate_fraggle_fragmentation(mol)
self.assertEqual(len(frags), 16)
expected = ('[*]C(=O)NC1CCN(Cc2cc(OC)c3ccccc3c2OC)CC1',
'[*]C(=O)c1cncc(C)c1.[*]C1CCN(Cc2cc(OC)c3ccccc3c2OC)CC1',
'[*]C(=O)c1cncc(C)c1.[*]c1cc(OC)c2ccccc2c1OC',
'[*]C1CCN(Cc2cc(OC)c3ccccc3c2OC)CC1',
'[*]C(=O)c1cncc(C)c1.[*]Cc1cc(OC)c2ccccc2c1OC',
'[*]Cc1cc(OC)c2ccccc2c1OC.[*]NC(=O)c1cncc(C)c1',
'[*]Cc1cc(OC)c2ccccc2c1OC.[*]c1cncc(C)c1',
'[*]NC(=O)c1cncc(C)c1.[*]c1cc(OC)c2ccccc2c1OC',
'[*]NC1CCN(Cc2cc(OC)c3ccccc3c2OC)CC1',
'[*]NC1CCN(Cc2cc(OC)c3ccccc3c2OC)CC1.[*]c1cncc(C)c1',
'[*]c1c(CN2CCC(NC(=O)c3cncc(C)c3)CC2)cc(OC)c2ccccc12',
'[*]c1c(OC)cc(CN2CCC(NC(=O)c3cncc(C)c3)CC2)c(OC)c1[*]',
'[*]c1cc(CN2CCC(NC(=O)c3cncc(C)c3)CC2)c(OC)c2ccccc12',
'[*]N1CCC(NC(=O)c2cncc(C)c2)CC1.[*]c1cc(OC)c2ccccc2c1OC',
'[*]C1CCN(Cc2cc(OC)c3ccccc3c2OC)CC1.[*]c1cncc(C)c1',
'[*]c1cc(OC)c2ccccc2c1OC.[*]c1cncc(C)c1')
for smi in frags:
self.assertTrue(smi in expected)
def testFragmentation(self):
"""
"""
mol = Chem.MolFromSmiles('COc1cc(CN2CCC(CC2)NC(=O)c2cncc(C)c2)c(OC)c2ccccc12')
frags = FraggleSim.generate_fraggle_fragmentation(mol)
self.failUnlessEqual(len(frags),16)
expected=('[*]C(=O)NC1CCN(Cc2cc(OC)c3ccccc3c2OC)CC1',
'[*]C(=O)c1cncc(C)c1.[*]C1CCN(Cc2cc(OC)c3ccccc3c2OC)CC1',
'[*]C(=O)c1cncc(C)c1.[*]c1cc(OC)c2ccccc2c1OC',
'[*]C1CCN(Cc2cc(OC)c3ccccc3c2OC)CC1',
'[*]Cc1cc(OC)c2ccccc2c1OC.[*]C(=O)c1cncc(C)c1',
'[*]Cc1cc(OC)c2ccccc2c1OC.[*]NC(=O)c1cncc(C)c1',
'[*]Cc1cc(OC)c2ccccc2c1OC.[*]c1cncc(C)c1',
'[*]NC(=O)c1cncc(C)c1.[*]c1cc(OC)c2ccccc2c1OC',
'[*]NC1CCN(Cc2cc(OC)c3ccccc3c2OC)CC1',
'[*]NC1CCN(Cc2cc(OC)c3ccccc3c2OC)CC1.[*]c1cncc(C)c1',
'[*]c1c(CN2CCC(NC(=O)c3cncc(C)c3)CC2)cc(OC)c2ccccc12',
'[*]c1c([*])c(OC)c(CN2CCC(NC(=O)c3cncc(C)c3)CC2)cc1OC',
'[*]c1cc(CN2CCC(NC(=O)c3cncc(C)c3)CC2)c(OC)c2ccccc12',
'[*]c1cc(OC)c2ccccc2c1OC.[*]N1CCC(NC(=O)c2cncc(C)c2)CC1',
'[*]c1cncc(C)c1.[*]C1CCN(Cc2cc(OC)c3ccccc3c2OC)CC1',
'[*]c1cncc(C)c1.[*]c1cc(OC)c2ccccc2c1OC')
for smi in frags:
self.failUnless(smi in expected)
def frag(
mol: Chem.Mol,
remove_parent: bool = False,
sanitize: bool = True,
fix: bool = True,
):
"""Generate all possible fragmentation of a molecule.
Args:
mol: a molecule.
remove_parent: Remove parent from the fragments.
sanitize: Wether to sanitize the fragments.
fix: Wether to fix the fragments.
"""
frags = FraggleSim.generate_fraggle_fragmentation(mol)
smiles = set([])
for seq in frags:
smiles |= {s.strip() for s in seq.split(".")}
smiles = list(sorted(smiles, reverse=True))
frags = [dm.to_mol(s) for s in smiles]
if fix:
frags = [dm.fix_mol(x) for x in frags]
if sanitize:
frags = [dm.sanitize_mol(x) for x in frags]
frags = [x for x in frags if x is not None]
if remove_parent:
return frags
return [mol] + frags
def testFragmentation2(self):
mol = Chem.MolFromSmiles('COc1cc(CN2CCC(NC(=O)c3ccccc3)CC2)c(OC)c2ccccc12')
frags = FraggleSim.generate_fraggle_fragmentation(mol)
self.assertEqual(len(frags), 13)
expected = (
'[*]C(=O)c1ccccc1.[*]C1CCN(Cc2cc(OC)c3ccccc3c2OC)CC1',
'[*]C(=O)c1ccccc1.[*]Cc1cc(OC)c2ccccc2c1OC', '[*]C(=O)c1ccccc1.[*]c1cc(OC)c2ccccc2c1OC',
'[*]C1CCN(Cc2cc(OC)c3ccccc3c2OC)CC1.[*]c1ccccc1',
'[*]Cc1cc(OC)c2ccccc2c1OC.[*]NC(=O)c1ccccc1', '[*]Cc1cc(OC)c2ccccc2c1OC.[*]c1ccccc1',
'[*]N1CCC(NC(=O)c2ccccc2)CC1.[*]c1cc(OC)c2ccccc2c1OC',
'[*]NC(=O)c1ccccc1.[*]c1cc(OC)c2ccccc2c1OC',
'[*]NC1CCN(Cc2cc(OC)c3ccccc3c2OC)CC1.[*]c1ccccc1',
'[*]c1c(CN2CCC(NC(=O)c3ccccc3)CC2)cc(OC)c2ccccc12',
'[*]c1c(OC)cc(CN2CCC(NC(=O)c3ccccc3)CC2)c(OC)c1[*]',
'[*]c1cc(CN2CCC(NC(=O)c3ccccc3)CC2)c(OC)c2ccccc12', '[*]c1cc(OC)c2ccccc2c1OC.[*]c1ccccc1')
expected = [_of(s) for s in expected]
for smi in frags:
self.assertIn(_of(smi), expected)
def testFragmentation2(self):
mol = Chem.MolFromSmiles('COc1cc(CN2CCC(NC(=O)c3ccccc3)CC2)c(OC)c2ccccc12')
frags = FraggleSim.generate_fraggle_fragmentation(mol)
self.assertEqual(len(frags), 13)
expected = (
'[*]C(=O)c1ccccc1.[*]C1CCN(Cc2cc(OC)c3ccccc3c2OC)CC1',
'[*]C(=O)c1ccccc1.[*]Cc1cc(OC)c2ccccc2c1OC', '[*]C(=O)c1ccccc1.[*]c1cc(OC)c2ccccc2c1OC',
'[*]C1CCN(Cc2cc(OC)c3ccccc3c2OC)CC1.[*]c1ccccc1',
'[*]Cc1cc(OC)c2ccccc2c1OC.[*]NC(=O)c1ccccc1', '[*]Cc1cc(OC)c2ccccc2c1OC.[*]c1ccccc1',
'[*]N1CCC(NC(=O)c2ccccc2)CC1.[*]c1cc(OC)c2ccccc2c1OC',
'[*]NC(=O)c1ccccc1.[*]c1cc(OC)c2ccccc2c1OC',
'[*]NC1CCN(Cc2cc(OC)c3ccccc3c2OC)CC1.[*]c1ccccc1',
'[*]c1c(CN2CCC(NC(=O)c3ccccc3)CC2)cc(OC)c2ccccc12',
'[*]c1c(OC)cc(CN2CCC(NC(=O)c3ccccc3)CC2)c(OC)c1[*]',
'[*]c1cc(CN2CCC(NC(=O)c3ccccc3)CC2)c(OC)c2ccccc12', '[*]c1cc(OC)c2ccccc2c1OC.[*]c1ccccc1')
expected = [_of(s) for s in expected]
for smi in frags:
self.assertIn(_of(smi), expected)
if __name__ == '__main__':
import sys, re
if (len(sys.argv) >= 2):
print(
"Program to run the first part of Fraggle. Program splits the molecule\nready for the search\n")
print("USAGE: ./fraggle.py <file_of_smiles")
print("Format of smiles file: SMILES ID (space or comma separated)")
print("Output: whole mol smiles,ID,fraggle split smiles\n")
sys.exit(1)
#read the STDIN
for line in sys.stdin:
line = line.rstrip()
smi, id_ = re.split('\s|,', line)
#print smi,id_
mol = Chem.MolFromSmiles(smi)
if mol is None:
sys.stderr.write("Can't generate mol for: %s\n" % (smi))
continue
out_fragments = FraggleSim.generate_fraggle_fragmentation(mol)
#print out the unique fragments
for x in out_fragments:
#cansmi
temp = Chem.MolFromSmiles(x)
print("%s,%s,%s" % (smi, id_, Chem.MolToSmiles(temp)))
if __name__ =='__main__':
import sys,re
if (len(sys.argv) >= 2):
print "Program to run the first part of Fraggle. Program splits the molecule\nready for the search\n"
print "USAGE: ./fraggle.py <file_of_smiles"
print "Format of smiles file: SMILES ID (space or comma separated)"
print "Output: whole mol smiles,ID,fraggle split smiles\n"
sys.exit(1)
#read the STDIN
for line in sys.stdin:
line = line.rstrip()
smi,id_ = re.split('\s|,',line)
#print smi,id_
mol = Chem.MolFromSmiles(smi)
if mol is None:
sys.stderr.write("Can't generate mol for: %s\n" % (smi) )
continue
out_fragments = FraggleSim.generate_fraggle_fragmentation(mol)
#print out the unique fragments
for x in out_fragments:
#cansmi
temp = Chem.MolFromSmiles(x)
print "%s,%s,%s" % (smi,id_,Chem.MolToSmiles(temp))