def read_smiles( self, smiles_string, atoms_to_ignore=None):
self.smiles_string = smiles_string.strip()
self.structure = smiles.text_to_mol( smiles_string, calc_coords=False)
if atoms_to_ignore:
self.atoms_to_ignore = [self.structure.vertices[x-1] for x in atoms_to_ignore]
else:
self.atoms_to_ignore = []
def test_rings_in_disconnected_mol():
import smiles
sc = smiles.converter()
mol = smiles.text_to_mol( "c1ccccc1.c1ccccc1.c1ccccc1CC=C")
mol.remove_zero_order_bonds()
print mol, mol.is_connected()
print [len( c) for c in mol.get_smallest_independent_cycles_e()]
def test_CIP_2():
import smiles
m = smiles.text_to_mol("HC(CC)(O)C")
from atom import atom
a = m.atoms[1]
dg = m.create_CIP_digraph(a)
print dg
def test_CIP_2():
import smiles
m = smiles.text_to_mol( "HC(CC)(O)C")
from atom import atom
a = m.atoms[1]
dg = m.create_CIP_digraph( a)
print dg
def test_rings_in_disconnected_mol():
import smiles
sc = smiles.converter()
mol = smiles.text_to_mol("c1ccccc1.c1ccccc1.c1ccccc1CC=C")
mol.remove_zero_order_bonds()
print mol, mol.is_connected()
print[len(c) for c in mol.get_smallest_independent_cycles_e()]
def test_CIP():
import smiles
m = smiles.text_to_mol( "HC(C(CCC)CCC)(C1CC1C)C2CC2")
from atom import atom
a = m.atoms[1]
print a.is_chiral()
print [m.atoms.index( x) for x in a.get_neighbors_CIP_sorted()]
def test_CIP():
import smiles
m = smiles.text_to_mol("HC(C(CCC)CCC)(C1CC1C)C2CC2")
from atom import atom
a = m.atoms[1]
print a.is_chiral()
print[m.atoms.index(x) for x in a.get_neighbors_CIP_sorted()]
def test_sssr2():
import smiles
string = "C1CCCC1C2CCC2"
string = "C36C1C5C4C2C6C7CCC2CCC4CCC5CCC1CCC3CC7"
string = "c1=%31c%25c8c%23c%19c%18c7c8c%17c%25c%29C=%21C=%31c%12c2-c%11c=%21c%20c%24c=4c%11C=6c2c9c(c5%28)c%12c1c%23c5c%19c3c%16c%18c%14c7c(c%17c%10c%20%29)c%22c%10c%24c%26c-%13c%22c%14c(c-%13c%15=C%27C=4%26)c%16c(c%15=%30)=c3c%28=C9C=%30C=6%27"
string = "C12C34C5C24C135"
mol = smiles.text_to_mol( string, calc_coords=False, localize_aromatic_bonds=False)
print map( len, mol.get_smallest_independent_cycles())
def test_new_ring_perception():
import smiles
mol = smiles.text_to_mol( "C2369C478C56C179C34C1258", calc_coords=False, localize_aromatic_bonds=False)
t = time()
for i, ring in enumerate( mol.get_all_cycles()):
print len( ring),
print
print i, time()-t
def test1(self): mol = smiles.text_to_mol( "CCCO") rc = reaction.reaction_component( mol, 2) self.assertEqual( rc.stoichiometry, 2) self.assertRaises( Exception, reaction.reaction_component, mol, "x") self.assertRaises( Exception, rc._set_stoichiometry, "x") self.assertRaises( Exception, reaction.reaction_component, 2, 2) self.assertRaises( Exception, rc._set_molecule, "x")
def test1(self):
mol = smiles.text_to_mol("CCCO")
rc = reaction.reaction_component(mol, 2)
self.assertEqual(rc.stoichiometry, 2)
self.assertRaises(Exception, reaction.reaction_component, mol, "x")
self.assertRaises(Exception, rc._set_stoichiometry, "x")
self.assertRaises(Exception, reaction.reaction_component, 2, 2)
self.assertRaises(Exception, rc._set_molecule, "x")
def _testformula(self, num):
l = linear_formula.linear_formula()
linear, smile, start_valency, end_valency = self.formulas[num]
m1 = l.parse_text(linear,
start_valency=start_valency,
end_valency=end_valency)
m2 = smiles.text_to_mol(smile)
self.assert_(molecule.equals(m1, m2, level=3))
def read_cdml(text):
"""returns the last molecule for now"""
doc = dom.parseString(text)
#if doc.childNodes()[0].nodeName == 'svg':
# path = "/svg/cdml/molecule"
#else:
# path = "/cdml/molecule"
path = "//molecule"
do_not_continue_this_mol = 0
for mol_el in dom_ext.simpleXPathSearch(doc, path):
atom_id_remap = {}
mol = molecule()
groups = []
for atom_el in dom_ext.simpleXPathSearch(mol_el, "atom"):
name = atom_el.getAttribute('name')
if not name:
#print "this molecule has an invalid symbol"
do_not_continue_this_mol = 1
break
pos = dom_ext.simpleXPathSearch(atom_el, 'point')[0]
x = cm_to_float_coord(pos.getAttribute('x'))
y = cm_to_float_coord(pos.getAttribute('y'))
z = cm_to_float_coord(pos.getAttribute('z'))
if name in PT:
# its really an atom
a = atom(symbol=name,
charge=atom_el.getAttribute('charge')
and int(atom_el.getAttribute('charge')) or 0,
coords=(x, y, z))
mol.add_vertex(v=a)
elif name in cdml_to_smiles:
# its a known group
group = smiles.text_to_mol(cdml_to_smiles[name], calc_coords=0)
a = group.vertices[0]
a.x = x
a.y = y
a.z = z
mol.insert_a_graph(group)
atom_id_remap[atom_el.getAttribute('id')] = a
if do_not_continue_this_mol:
break
for bond_el in dom_ext.simpleXPathSearch(mol_el, "bond"):
type = bond_el.getAttribute('type')
if type[1] == u'0':
# we ignore bonds with order 0
continue
v1 = atom_id_remap[bond_el.getAttribute('start')]
v2 = atom_id_remap[bond_el.getAttribute('end')]
e = bond(order=int(type[1]), type=type[0])
mol.add_edge(v1, v2, e=e)
if mol.is_connected():
# this is here to handle diborane and similar weird things
yield mol
else:
for comp in mol.get_disconnected_subgraphs():
yield comp
def read_smiles(self, smiles_string, atoms_to_ignore=None):
self.smiles_string = smiles_string.strip()
self.structure = smiles.text_to_mol(smiles_string, calc_coords=False)
if atoms_to_ignore:
self.atoms_to_ignore = [
self.structure.vertices[x - 1] for x in atoms_to_ignore
]
else:
self.atoms_to_ignore = []
def is_edge_a_bridge_speed():
mol = smiles.text_to_mol("CCCC(CCC)CCCC1CC2CC1C2")
t1 = time()
for i in range(100):
b = 0
for e in mol.edges:
b += mol.is_edge_a_bridge(e)
print b
return time() - t1
def is_edge_a_bridge_speed():
mol = smiles.text_to_mol( "CCCC(CCC)CCCC1CC2CC1C2")
t1 = time()
for i in range( 100):
b = 0
for e in mol.edges:
b += mol.is_edge_a_bridge( e)
print b
return time() - t1
def read_cdml( text):
"""returns the last molecule for now"""
doc = dom.parseString( text)
#if doc.childNodes()[0].nodeName == 'svg':
# path = "/svg/cdml/molecule"
#else:
# path = "/cdml/molecule"
path = "//molecule"
do_not_continue_this_mol = 0
for mol_el in dom_ext.simpleXPathSearch( doc, path):
atom_id_remap = {}
mol = molecule()
groups = []
for atom_el in dom_ext.simpleXPathSearch( mol_el, "atom"):
name = atom_el.getAttribute( 'name')
if not name:
#print "this molecule has an invalid symbol"
do_not_continue_this_mol = 1
break
pos = dom_ext.simpleXPathSearch( atom_el, 'point')[0]
x = cm_to_float_coord( pos.getAttribute('x'))
y = cm_to_float_coord( pos.getAttribute('y'))
z = cm_to_float_coord( pos.getAttribute('z'))
if name in PT:
# its really an atom
a = atom( symbol=name,
charge=atom_el.getAttribute( 'charge') and int( atom_el.getAttribute( 'charge')) or 0,
coords=( x, y, z))
mol.add_vertex( v=a)
elif name in cdml_to_smiles:
# its a known group
group = smiles.text_to_mol( cdml_to_smiles[ name], calc_coords=0)
a = group.vertices[0]
a.x = x
a.y = y
a.z = z
mol.insert_a_graph( group)
atom_id_remap[ atom_el.getAttribute( 'id')] = a
if do_not_continue_this_mol:
break
for bond_el in dom_ext.simpleXPathSearch( mol_el, "bond"):
type = bond_el.getAttribute( 'type')
if type[1] == u'0':
# we ignore bonds with order 0
continue
v1 = atom_id_remap[ bond_el.getAttribute( 'start')]
v2 = atom_id_remap[ bond_el.getAttribute( 'end')]
e = bond( order=int( type[1]), type=type[0])
mol.add_edge( v1, v2, e=e)
if mol.is_connected():
# this is here to handle diborane and similar weird things
yield mol
else:
for comp in mol.get_disconnected_subgraphs():
yield comp
def test_new_ring_perception():
import smiles
mol = smiles.text_to_mol("C2369C478C56C179C34C1258",
calc_coords=False,
localize_aromatic_bonds=False)
t = time()
for i, ring in enumerate(mol.get_all_cycles()):
print len(ring),
print
print i, time() - t
def test_sssr2():
import smiles
string = "C1CCCC1C2CCC2"
string = "C36C1C5C4C2C6C7CCC2CCC4CCC5CCC1CCC3CC7"
string = "c1=%31c%25c8c%23c%19c%18c7c8c%17c%25c%29C=%21C=%31c%12c2-c%11c=%21c%20c%24c=4c%11C=6c2c9c(c5%28)c%12c1c%23c5c%19c3c%16c%18c%14c7c(c%17c%10c%20%29)c%22c%10c%24c%26c-%13c%22c%14c(c-%13c%15=C%27C=4%26)c%16c(c%15=%30)=c3c%28=C9C=%30C=6%27"
string = "C12C34C5C24C135"
mol = smiles.text_to_mol(string,
calc_coords=False,
localize_aromatic_bonds=False)
print map(len, mol.get_smallest_independent_cycles())
def test_multimol_molfile2():
import molfile, smiles
mols = [smiles.text_to_mol( t) for t in ["CCC(=O)[O-].[K+]"]]
for mol in mols:
mol.remove_zero_order_bonds()
m = molfile.converter()
text = m.mols_to_text( mols)
f = file("multi2.mol","w")
f.write( text)
f.close()
f = file("prase.sdf","r")
for mol in m.read_text( text):
print smiles.mol_to_text( mol)
f.close()
def test_sssr():
import smiles
string = "C1CCCC1C2CCC2"
string = "C36C1C5C4C2C6C7CCC2CCC4CCC5CCC1CCC3CC7"
string = "c1=%31c%25c8c%23c%19c%18c7c8c%17c%25c%29C=%21C=%31c%12c2-c%11c=%21c%20c%24c=4c%11C=6c2c9c(c5%28)c%12c1c%23c5c%19c3c%16c%18c%14c7c(c%17c%10c%20%29)c%22c%10c%24c%26c-%13c%22c%14c(c-%13c%15=C%27C=4%26)c%16c(c%15=%30)=c3c%28=C9C=%30C=6%27"
string = "C12C3C2C13"
string = "C12C34C5C24C135"
mol = smiles.text_to_mol( string, calc_coords=False, localize_aromatic_bonds=False)
print "AAA"
for i,v in enumerate( mol.vertices):
for rings in mol._get_smallest_cycles_for_vertex( v, to_reach=v):
if rings:
print map( len, rings)
break
def test_multimol_molfile2():
import molfile, smiles
mols = [smiles.text_to_mol(t) for t in ["CCC(=O)[O-].[K+]"]]
for mol in mols:
mol.remove_zero_order_bonds()
m = molfile.converter()
text = m.mols_to_text(mols)
f = file("multi2.mol", "w")
f.write(text)
f.close()
f = file("prase.sdf", "r")
for mol in m.read_text(text):
print smiles.mol_to_text(mol)
f.close()
def cairo_out_test2():
import smiles
#mol = smiles.text_to_mol( "COC(=O)CNC(C1=CC=CC=C1)C2=C(C=CC(=C2)Br)NC(=O)C3=CC(=CC=C3)Cl")
#mol = smiles.text_to_mol( "c1nccc2c1cncn2")
mol = smiles.text_to_mol( "CCC=CC(=O)C.CCCC")
import cairo_out
mol.normalize_bond_length( 30)
mol.remove_unimportant_hydrogens()
c = cairo_out.cairo_out( color_bonds=True, color_atoms=True) #, background_color=(0.4,1,0.5,0.8))
c.show_hydrogens_on_hetero = True
c.font_size = 20
mols = list( mol.get_disconnected_subgraphs())
c.mols_to_cairo( mols, "test.pdf", format="pdf")
c.mols_to_cairo( mols, "test.png")
c.mols_to_cairo( mols, "test.svg", format="svg")
def test_sssr():
import smiles
string = "C1CCCC1C2CCC2"
string = "C36C1C5C4C2C6C7CCC2CCC4CCC5CCC1CCC3CC7"
string = "c1=%31c%25c8c%23c%19c%18c7c8c%17c%25c%29C=%21C=%31c%12c2-c%11c=%21c%20c%24c=4c%11C=6c2c9c(c5%28)c%12c1c%23c5c%19c3c%16c%18c%14c7c(c%17c%10c%20%29)c%22c%10c%24c%26c-%13c%22c%14c(c-%13c%15=C%27C=4%26)c%16c(c%15=%30)=c3c%28=C9C=%30C=6%27"
string = "C12C3C2C13"
string = "C12C34C5C24C135"
mol = smiles.text_to_mol(string,
calc_coords=False,
localize_aromatic_bonds=False)
print "AAA"
for i, v in enumerate(mol.vertices):
for rings in mol._get_smallest_cycles_for_vertex(v, to_reach=v):
if rings:
print map(len, rings)
break
def test_fullerene_lockdown():
import inchi
import smiles
from time import time
t = time()
#mol = inchi.text_to_mol( "InChI=1/C60/c1-2-5-6-3(1)8-12-10-4(1)9-11-7(2)17-21-13(5)23-24-14(6)22-18(8)28-20(12)30-26-16(10)15(9)25-29-19(11)27(17)37-41-31(21)33(23)43-44-34(24)32(22)42-38(28)48-40(30)46-36(26)35(25)45-39(29)47(37)55-49(41)51(43)57-52(44)50(42)56(48)59-54(46)53(45)58(55)60(57)59")
string = "C12=C3C4=C5C6=C1C7=C8C9=C1C%10=C%11C(=C29)C3=C2C3=C4C4=C5C5=C9C6=C7C6=C7C8=C1C1=C8C%10=C%10C%11=C2C2=C3C3=C4C4=C5C5=C%11C%12=C(C6=C95)C7=C1C1=C%12C5=C%11C4=C3C3=C5C(=C81)C%10=C23"
#string = "C12C3C2C13"
string = "c1=%31c%25c8c%23c%19c%18c7c8c%17c%25c%29C=%21C=%31c%12c2-c%11c=%21c%20c%24c=4c%11C=6c2c9c(c5%28)c%12c1c%23c5c%19c3c%16c%18c%14c7c(c%17c%10c%20%29)c%22c%10c%24c%26c-%13c%22c%14c(c-%13c%15=C%27C=4%26)c%16c(c%15=%30)=c3c%28=C9C=%30C=6%27"
mol = smiles.text_to_mol(string, calc_coords=True)
print time() - t
t = time()
#print mol.get_all_cycles()
print smiles.mol_to_text(mol)
print time() - t
print mol
def test_fullerene_lockdown():
import inchi
import smiles
from time import time
t = time()
#mol = inchi.text_to_mol( "InChI=1/C60/c1-2-5-6-3(1)8-12-10-4(1)9-11-7(2)17-21-13(5)23-24-14(6)22-18(8)28-20(12)30-26-16(10)15(9)25-29-19(11)27(17)37-41-31(21)33(23)43-44-34(24)32(22)42-38(28)48-40(30)46-36(26)35(25)45-39(29)47(37)55-49(41)51(43)57-52(44)50(42)56(48)59-54(46)53(45)58(55)60(57)59")
string = "C12=C3C4=C5C6=C1C7=C8C9=C1C%10=C%11C(=C29)C3=C2C3=C4C4=C5C5=C9C6=C7C6=C7C8=C1C1=C8C%10=C%10C%11=C2C2=C3C3=C4C4=C5C5=C%11C%12=C(C6=C95)C7=C1C1=C%12C5=C%11C4=C3C3=C5C(=C81)C%10=C23"
#string = "C12C3C2C13"
string = "c1=%31c%25c8c%23c%19c%18c7c8c%17c%25c%29C=%21C=%31c%12c2-c%11c=%21c%20c%24c=4c%11C=6c2c9c(c5%28)c%12c1c%23c5c%19c3c%16c%18c%14c7c(c%17c%10c%20%29)c%22c%10c%24c%26c-%13c%22c%14c(c-%13c%15=C%27C=4%26)c%16c(c%15=%30)=c3c%28=C9C=%30C=6%27"
mol = smiles.text_to_mol( string, calc_coords=True)
print time()-t
t = time()
#print mol.get_all_cycles()
print smiles.mol_to_text( mol)
print time()-t
print mol
def cairo_out_test2():
import smiles
#mol = smiles.text_to_mol( "COC(=O)CNC(C1=CC=CC=C1)C2=C(C=CC(=C2)Br)NC(=O)C3=CC(=CC=C3)Cl")
#mol = smiles.text_to_mol( "c1nccc2c1cncn2")
mol = smiles.text_to_mol("CCC=CC(=O)C.CCCC")
import cairo_out
mol.normalize_bond_length(30)
mol.remove_unimportant_hydrogens()
c = cairo_out.cairo_out(
color_bonds=True,
color_atoms=True) #, background_color=(0.4,1,0.5,0.8))
c.show_hydrogens_on_hetero = True
c.font_size = 20
mols = list(mol.get_disconnected_subgraphs())
c.mols_to_cairo(mols, "test.pdf", format="pdf")
c.mols_to_cairo(mols, "test.png")
c.mols_to_cairo(mols, "test.svg", format="svg")
def sssr():
mol = smiles.text_to_mol( sssr_smiles)
t1 = time()
cs = mol.get_smallest_independent_cycles_e_new()
print len( cs)
return time() - t1
dump = ssm.structures.get_graphviz_text_dump()
f = file("dump.dot", "w")
f.write(dump)
f.close()
print "Graphviz dump: %.1fms" % (1000 * (time.time() - t))
t = time.time()
def print_tree(x, l):
print l * " ", x #, x.children
for ch in x.children:
print_tree(ch, l + 2)
#for tree in ssm._compute_search_trees():
# print_tree( tree, 0)
#"c1cccc2c1cccc2
#text = "COc5ccc4c2sc(cc2nc4c5)-c(cc1nc3c6)sc1c3ccc6OC"
text = 'C(=O)OCC'
#text2 = 'C(=O)[O-]'
mol = smiles.text_to_mol(text, calc_coords=False)
#m2 = smiles.text_to_mol( text2, calc_coords=False)
#print "XXXX", mol.contains_substructure( m2)
subs = ssm.find_substructures_in_mol(mol)
for sub in subs:
print sub
print "Substructure search: %.1fms" % (1000 * (time.time() - t))
t = time.time()
def _testformula(self, num): smile1, smile2, result = self.formulas[num] m1 = smiles.text_to_mol( smile1) m2 = smiles.text_to_mol( smile2) self.assert_(m1.contains_substructure(m2)==result)
def _testformula(self, num): l = linear_formula.linear_formula() linear, smile, start_valency, end_valency = self.formulas[num] m1 = l.parse_text( linear, start_valency=start_valency, end_valency=end_valency) m2 = smiles.text_to_mol( smile) self.assert_(molecule.equals(m1,m2,level=3))
def aromaticity():
mol = smiles.text_to_mol("C1=C[CH][CH]C=C1")
#print [v.multiplicity for v in mol.vertices]
mol.mark_aromatic_bonds()
print[e.aromatic for e in mol.edges]
def _testformula(self, num): smile1, smile2, result = self.formulas[num] m1 = smiles.text_to_mol( smile1) m2 = smiles.text_to_mol( smile2) self.assert_(molecule.equals(m1,m2,level=3)==result)
#sm = "CP(c1ccccc1)(c2ccccc2)c3ccccc3" #sm = 'C1CC2C1CCCC3C2CC(CCC4)C4C3' #sm = "C\C=C/CC#CCCCC\C=C=C=C/CC" sm = "C/C(Cl)=C(\O)C" #sm = "C1CCC1C/C=C\CCCCC" #sm = "C25C1C3C5C4C2C1C34" #sm = 'C1CC2CCC1CC2' #sm = 'C1CC5(CC(C)CC5)CC(C)C12CC(CC(C(C)(C)CCCC)CCC)CC23C(CC)CC3' #sm = 'CCCC(C)(CCC)CCC(Cl)C(CCCCC)CCC(C)CCC' print "oasa::coords_generator DEMO" print "generating coords for following smiles" print " %s" % sm mol = smiles.text_to_mol( sm, calc_coords=False) import time #cg = coords_generator() t = time.time() calculate_coords( mol, force=1) print "generation time: %.3f ms" % ((time.time()-t)*1000) show_mol( mol) ################################################## # TODO # when an atom with degree 4 is created not as part of the backbone the neighbors are
def mols_to_png(mols, filename, **kw):
c = cairo_out(**kw)
c.mols_to_cairo(mols, filename)
def mol_to_cairo(mol, filename, format, **kw):
c = cairo_out(**kw)
c.mol_to_cairo(mol, filename, format=format)
def mols_to_cairo(mols, filename, format, **kw):
c = cairo_out(**kw)
c.mols_to_cairo(mols, filename, format=format)
if __name__ == "__main__":
import smiles
mol = smiles.text_to_mol("FCCSCl", calc_coords=30)
#mol.vertices[0].properties_['show_hydrogens'] = False
#mol.vertices[1].properties_['show_symbol'] = False
#mol.vertices[2].properties_['show_symbol'] = True
mol_to_png(mol, "output.png", show_hydrogens_on_hetero=True, scaling=2)
## import inchi
## mol = inchi.text_to_mol( "1/C7H6O2/c8-7(9)6-4-2-1-3-5-6/h1-5H,(H,8,9)", include_hydrogens=False, calc_coords=30)
## mol_to_png( mol, "output.png")
def _testformula(self, num):
smile1, smile2, result = self.formulas[num]
m1 = smiles.text_to_mol(smile1)
m2 = smiles.text_to_mol(smile2)
self.assert_(m1.contains_substructure(m2) == result)
print "f**k", rad_to_deg( ang1), rad_to_deg( ang2), rad_to_deg( dang)
else:
#rint "good", rad_to_deg( ang1), rad_to_deg( ang2), rad_to_deg( dang)
pass
return gx1, gy1, gx2, gy2
if __name__ == "__main__":
import smiles
import time
mol = smiles.text_to_mol( 'CC(C)C(C)CCCC')
print [(v.x,v.y) for v in mol.vertices]
opt = coords_optimizer()
t = time.time()
ok = opt.optimize_coords( mol, bond_length=0.9)
print "converged:", ok
print "%d iterations, RMS grad %f, max grad %f" % (opt.i, opt.rms_grad, opt.max_grad)
print "time %.1f ms" % ((time.time() - t) * 1000)
print [(v.x,v.y) for v in mol.vertices]
import coords_generator
def _testformula(self, num):
smile1, smile2, result = self.formulas[num]
m1 = smiles.text_to_mol(smile1)
m2 = smiles.text_to_mol(smile2)
self.assert_(molecule.equals(m1, m2, level=3) == result)
from optparse import OptionParser
op = OptionParser(usage="python %prog -c command [options] [structure file]")
op.add_option( "-c", "--command", action="store",
dest="command", default="test",
help="command - what to do; one of 'test','update','rebuild','synonyms'")
op.add_option( "-s", "--synonyms", action="store",
dest="synonyms", default="",
help="file containing synonyms")
(options, args) = op.parse_args()
if options.command == "test":
print get_compounds_from_database( inchi="1/C4H10/c1-3-4-2/h3-4H2,1-2H3")
print get_compounds_from_database( smiles="O")
import smiles
print find_molecule_in_database( smiles.text_to_mol("C1CCC=CC1"))
print find_molecule_in_database( smiles.text_to_mol("c1ccccc1C"))
print get_compounds_from_database( synonym="toluene")
elif options.command in ('update','rebuild','synonyms'):
if not options.command == 'synonyms':
if len( args) >= 1:
fname = args[0]
else:
print >> sys.stderr, "You must supply a valid filename of a file containing structures to be read."
sys.exit()
if options.command == 'rebuild':
if os.path.exists( Config.database_file):
try:
os.remove( Config.database_file)
except Exception, e:
print >> sys.stderr, "Old database file could not be removed. Reason: %s" % e
def parse_form( self, text, start_valency=0, mol=None, reverse=False):
form = text
# the code itself
if not mol:
mol = Config.create_molecule()
# create the dummy atom
if start_valency:
last_atom = mol.create_vertex()
last_atom.valency = start_valency
mol.add_vertex( last_atom)
else:
last_atom = None
# check if there are branches in the formula
if "(" not in form:
# there are no subbranches
chunks = re.split( "([A-Z][a-z]?[0-9]?[+-]?)", form)
if reverse:
chunks = reverse_chunks( chunks)
for chunk in chunks:
if chunk:
atms = self.chunk_to_atoms( chunk, mol)
if atms == None:
return None
last_atom = self.get_last_free_atom( mol)
for a in atms:
mol.add_vertex( a)
if last_atom:
max_val = min( last_atom.free_valency, a.free_valency, 3)
if max_val <= 0 and last_atom.free_valency <= 0:
if last_atom.raise_valency():
max_val = min( last_atom.free_valency, a.free_valency, 3)
b = mol.create_edge()
b.order = max_val
mol.add_edge( last_atom, a, b)
else:
last_atom = a
else:
for chunk, count in gen_formula_fragments( form, reverse=reverse):
if chunk:
last_atom = self.get_last_free_atom( mol)
do_linear = False # should we string the fragments rather than adding them all to the last atom
if last_atom and last_atom.free_valency < count:
do_linear = True
for j in range( count):
if chunk[0] == "!":
# the form should be a smiles
m = smiles.text_to_mol( chunk[1:], calc_coords=0)
m.add_missing_hydrogens()
hs = [v for v in m.vertices[0].neighbors if v.symbol == 'H']
m.disconnect( hs[0], m.vertices[0])
m.remove_vertex( hs[0])
smile = True
else:
val = last_atom and 1 or 0
m = self.parse_form( chunk, start_valency=val, mol=mol.create_graph())
smile = False
if not m:
return None
if not last_atom:
# !!! this should not happen in here
mol.insert_a_graph( m)
# if there are multiple chunks without a previous atom, we should create a linear fragment
#last_atom = [v for v in mol.vertices if v.free_valency > 0][-1]
else:
if not smile:
m.remove_vertex( m.vertices[0]) # remove the dummy
mol.insert_a_graph( m)
b = mol.create_edge()
mol.add_edge( last_atom, m.vertices[0], b)
if do_linear:
last_atom = m.vertices[0]
return mol
def sssr():
mol = smiles.text_to_mol(sssr_smiles)
t1 = time()
cs = mol.get_smallest_independent_cycles_e_new()
print len(cs)
return time() - t1
c.mol_to_cairo( mol, filename) def mols_to_png( mols, filename, **kw): c = cairo_out( **kw) c.mols_to_cairo( mols, filename) def mol_to_cairo( mol, filename, format, **kw): c = cairo_out( **kw) c.mol_to_cairo( mol, filename, format=format) def mols_to_cairo( mols, filename, format, **kw): c = cairo_out( **kw) c.mols_to_cairo( mols, filename, format=format) if __name__ == "__main__": import smiles mol = smiles.text_to_mol( "FCCSCl", calc_coords=30) #mol.vertices[0].properties_['show_hydrogens'] = False #mol.vertices[1].properties_['show_symbol'] = False #mol.vertices[2].properties_['show_symbol'] = True mol_to_png( mol, "output.png", show_hydrogens_on_hetero=True, scaling=2) ## import inchi ## mol = inchi.text_to_mol( "1/C7H6O2/c8-7(9)6-4-2-1-3-5-6/h1-5H,(H,8,9)", include_hydrogens=False, calc_coords=30) ## mol_to_png( mol, "output.png")
def aromaticity():
mol = smiles.text_to_mol( "C1=C[CH][CH]C=C1")
#print [v.multiplicity for v in mol.vertices]
mol.mark_aromatic_bonds()
print [e.aromatic for e in mol.edges]
