def array_rep_from_smiles(smiles):
"""Precompute everything we need from MolGraph so that we can free the memory asap."""
molgraph = graph_from_smiles_tuple(smiles)
arrayrep = {
'atom_features': molgraph.feature_array('atom'),
'bond_features': molgraph.feature_array('bond'),
'atom_list': molgraph.neighbor_list('molecule',
'atom'), # List of lists.
'rdkit_ix': molgraph.rdkit_ix_array()
} # For plotting only.
#print "atom_features", len(arrayrep['atom_features']),len(arrayrep['atom_features'][0])
#print arrayrep['atom_features']
#print "bond_features", len(arrayrep['bond_features']), len(arrayrep['bond_features'][0])
#print arrayrep['bond_features']
#print "atom_list", len(arrayrep['bond_features']), len(arrayrep['bond_features'][0])
#print arrayrep['atom_list']
#print "rdkit_ix", len(arrayrep['bond_features']), len(arrayrep['bond_features'][0])
#print arrayrep['rdkit_ix']
#import pdb;pdb.set_trace()
for degree in degrees:
arrayrep[('atom_neighbors', degree)] = \
np.array(molgraph.neighbor_list(('atom', degree), 'atom'), dtype=int)
arrayrep[('bond_neighbors', degree)] = \
np.array(molgraph.neighbor_list(('atom', degree), 'bond'), dtype=int)
return arrayrep
def main():
print "This is the file"
mol_smile = [('OCC3OC(OCC2OC(OC(C#N)c1ccccc1)C(O)C(O)C2O)C(O)C(O)C3O'),('c1ccsc1')]
# mol_smile = mol_smile[1]
# m = Chem.MolFromSmiles(mol_smile)
# alist = m.GetAtoms()
# a = alist[0]
print mol_smile
molgraph = graph_from_smiles_tuple(mol_smile)
arrayrep = {'atom_features' : molgraph.feature_array('atom'),
'bond_features' : molgraph.feature_array('bond'),
'atom_list' : molgraph.neighbor_list('molecule', 'atom'), # List of lists.
'rdkit_ix' : molgraph.rdkit_ix_array()} # For plotting only.
for degree in degrees:
# import pdb; pdb.set_trace()
arrayrep[('atom_neighbors', degree)] = \
np.array(molgraph.neighbor_list(('atom', degree), 'atom'), dtype=int) #V: The degree of an atom is defined to be its number of directly-bonded neighbors.
arrayrep[('bond_neighbors', degree)] = \
np.array(molgraph.neighbor_list(('atom', degree), 'bond'), dtype=int)
# pdb.set_trace()
filename = 'varun_visualize_atoms'
molecule_idx = 1
highlight_atom_nodes = arrayrep['atom_list'][molecule_idx]
highlight_list_rdkit = [arrayrep['rdkit_ix'][our_ix] for our_ix in highlight_atom_nodes]
pdb.set_trace()
draw_molecule_with_highlights(filename, mol_smile[molecule_idx],highlight_list_rdkit[0:3])
def array_rep_from_smiles(smiles):
"""extract features from molgraph"""
molgraph = graph_from_smiles_tuple(smiles)
arrayrep = {'atom_features' : molgraph.feature_array('atom'),
'bond_features' : molgraph.feature_array('bond'),
'atom_list' : molgraph.neighbor_list('molecule', 'atom'), # List of lists.
'rdkit_ix' : molgraph.rdkit_ix_array()} # For plotting only.
for degree in degrees:
arrayrep[('atom_neighbors', degree)] = \
np.array(molgraph.neighbor_list(('atom', degree), 'atom'), dtype=int)
arrayrep[('bond_neighbors', degree)] = \
np.array(molgraph.neighbor_list(('atom', degree), 'bond'), dtype=int)
return arrayrep
def array_rep_from_smiles(smiles):
"""Precompute everything we need from MolGraph so that we can free the memory asap."""
molgraph = graph_from_smiles_tuple(smiles)
arrayrep = {'atom_features' : molgraph.feature_array('atom'),
'bond_features' : molgraph.feature_array('bond'),
'atom_list' : molgraph.neighbor_list('molecule', 'atom'), # List of lists.
'rdkit_ix' : molgraph.rdkit_ix_array()} # For plotting only.
for degree in degrees:
# import pdb; pdb.set_trace()
arrayrep[('atom_neighbors', degree)] = \
np.array(molgraph.neighbor_list(('atom', degree), 'atom'), dtype=int) #V: The degree of an atom is defined to be its number of directly-bonded neighbors.
arrayrep[('bond_neighbors', degree)] = \
np.array(molgraph.neighbor_list(('atom', degree), 'bond'), dtype=int)
# import pdb; pdb.set_trace()
return arrayrep