def amber99(selection="(all)",quiet=0,_self=cmd):
cmd=_self
result = 1
# first, set all parameters to zero
cmd.alter(selection,"partial_charge=0")
cmd.alter(selection,"elec_radius=0.0")
cmd.alter(selection,"text_type=''")
# next, flag all atoms so that we'll be able to detect what we miss
cmd.flag(23,selection,'set')
# get the amber99 dictionary
if not hasattr(champ,'amber99_dict'):
from chempy.champ.amber99 import amber99_dict
champ.amber99_dict = amber99_dict
# iterate through the residue dictionary matching each residue based on chemistry
# and generating the expressions for reassigning formal charges
alter_list = []
for resn in champ.amber99_dict.keys():
if cmd.select(tmp_sele1,"(%s) and resn %s"%(selection,resn))>0:
entry = champ.amber99_dict[resn]
for rule in entry:
model = cmd.get_model(tmp_sele1)
ch = Champ()
model_pat = ch.insert_model(model)
ch.pattern_detect_chirality(model_pat)
assn_pat = ch.insert_pattern_string(rule[0])
ch.pattern_clear_tags(model_pat)
if ch.match_1v1_n(assn_pat,model_pat,10000,2)>0:
result = ch.pattern_get_ext_indices_with_tags(model_pat)
for atom_tag in result[0]: # just iterate over atom tags
if len(atom_tag[1])==1: # one and only one match
tag = atom_tag[1][0]
prop_list = rule[1][tag]
# the following expression both changes the formal charge and resets flag 23
alter_list.append([atom_tag[0],
"name='''%s''';text_type='''%s''';partial_charge=%f;elec_radius=%f;flags=flags&-8388609"%prop_list])
# now evaluate all of these expressions efficiently en-masse
cmd.alter_list(selection,alter_list)
# see if we missed any atoms
missed_count = cmd.count_atoms("("+selection+") and flag 23")
if missed_count>0:
if not quiet:
# looks like we did, so alter the user
print " WARNING: %d atoms did not have properties assigned"%missed_count
result = 0
# remove the temporary selection we used to select appropriate residues
cmd.delete(tmp_sele1)
return result
def load():
cmd.set("valence")
r = 0
list = glob("pdb/*/*")
# list = ["pdb/06/pdb406d"]
# while list[0]!="pdb/f8/pdb1f8u":
# list.pop(0)
for file in list:
cmd.delete('pdb')
cmd.load(file,'pdb')
cmd.remove("not alt ''+A")
cmd.fix_chemistry("all","all")
cmd.h_add()
sys.__stderr__.write(file)
sys.__stderr__.flush()
ch = Champ()
model = cmd.get_model('pdb')
idx = ch.insert_model(model)
ch.pattern_orient_bonds(idx)
print " %5d"%cmd.count_atoms(),"%5d"%len(ch.pattern_get_string(idx)),
ch.pattern_detect_chirality(idx)
pat = ch.pattern_get_string(idx)
print "%5d"%len(pat),pat[0:22]+"..."+pat[-10:]
def missing_c_termini(selection="(all)", quiet=0, _self=cmd):
cmd = _self
# assumes that hydogens are not present!
sele_list = []
ch = Champ()
model = cmd.get_model(selection)
model_pat = ch.insert_model(model)
assn_pat = ch.insert_pattern_string("[N+0+1]C[C;D2]<0>(=O)")
ch.pattern_clear_tags(model_pat)
if ch.match_1v1_n(assn_pat, model_pat, 10000, 2) > 0:
result = ch.pattern_get_ext_indices_with_tags(model_pat)
for atom_tag in result[0]: # just iterate over atom tags
if len(atom_tag[1]) == 1: # one and only one match
if atom_tag[1][0] == 0:
sele_list.append(atom_tag[0])
cmd.select_list(tmp_sele1, selection, sele_list, mode='index')
while cmd.pop(tmp_sele2, tmp_sele1) > 0: # complete the carboxy terminus
cmd.edit(tmp_sele2)
cmd.attach("O", 1, 1, "OXT", quiet=1)
cmd.unpick()
cmd.delete(tmp_sele1)
def missing_c_termini(selection="(all)",quiet=0,_self=cmd):
cmd=_self
# assumes that hydogens are not present!
sele_list = []
ch=Champ()
model = cmd.get_model(selection)
model_pat = ch.insert_model(model)
assn_pat = ch.insert_pattern_string("[N+0+1]C[C;D2]<0>(=O)")
ch.pattern_clear_tags(model_pat)
if ch.match_1v1_n(assn_pat,model_pat,10000,2)>0:
result = ch.pattern_get_ext_indices_with_tags(model_pat)
for atom_tag in result[0]: # just iterate over atom tags
if len(atom_tag[1])==1: # one and only one match
if atom_tag[1][0]==0:
sele_list.append(atom_tag[0])
cmd.select_list(tmp_sele1,selection,sele_list, mode='index')
while cmd.pop(tmp_sele2,tmp_sele1)>0: # complete the carboxy terminus
cmd.edit(tmp_sele2)
cmd.attach("O",1,1,"OXT",quiet=1)
cmd.unpick()
cmd.delete(tmp_sele1)
from chempy.champ import Champ
# see if we can read-in and read-out all of the NCI
# database SMILES strings without a hitch
import re
num_re = re.compile("[0-9]")
pnum_re = re.compile(r"\%[0-9][0-9]")
ch = Champ()
f = open("nci.smi")
c = 1
lst = []
while 1:
l = f.readline()
if not l: break
l = string.strip(l)
if len(l):
if 1000*(c/1000)==c:
print c
c = c + 1
# print l
idx = ch.insert_pattern_string(l)
# ch.pattern_dump(idx)
o = ch.get_pattern_string(idx)
if len(o) != len(l): # same length?
print "orig: ",l
print "champ: ",o
ch.pattern_dump(idx)
def formal_charges(selection="(all)", quiet=0, _self=cmd):
cmd = _self
result = 1
# assumes that hydogens are not present!
# first, set all formal charges to zero
cmd.alter(selection, "formal_charge=0")
# next, flag all atoms so that we'll be able to detect what we miss
cmd.flag(23, selection, 'set')
# get the residue dictionary for formal charges
if not hasattr(champ, 'formal_charge_dict'):
from chempy.champ.formal_charges import formal_charge_dict
champ.formal_charge_dict = formal_charge_dict
# iterate through the residue dictionary matching each residue based on chemistry
# and generating the expressions for reassigning formal charges
alter_list = []
for resn in champ.formal_charge_dict.keys():
if cmd.select(tmp_sele1, "(%s) and resn %s" % (selection, resn)) > 0:
entry = champ.formal_charge_dict[resn]
for rule in entry:
model = cmd.get_model(tmp_sele1)
ch = Champ()
model_pat = ch.insert_model(model)
assn_pat = ch.insert_pattern_string(rule[0])
ch.pattern_clear_tags(model_pat)
if ch.match_1v1_n(assn_pat, model_pat, 10000, 2) > 0:
result = ch.pattern_get_ext_indices_with_tags(model_pat)
for atom_tag in result[0]: # just iterate over atom tags
if len(atom_tag[1]) == 1: # one and only one match
tag = atom_tag[1][0]
formal_charge = rule[1][tag]
# the following expression both changes the formal charge and resets flag 23
alter_list.append([
atom_tag[0],
"formal_charge=%d;flags=flags&-8388609" %
formal_charge
])
if 1: # n-terminal amine
# non-proline
ch = Champ()
model = cmd.get_model(selection)
model_pat = ch.insert_model(model)
assn_pat = ch.insert_pattern_string("[N;D1]<0>CC(=O)")
ch.pattern_clear_tags(model_pat)
if ch.match_1v1_n(assn_pat, model_pat, 10000, 2) > 0:
result = ch.pattern_get_ext_indices_with_tags(model_pat)
for atom_tag in result[0]: # just iterate over atom tags
if len(atom_tag[1]) == 1: # one and only one match
if atom_tag[1][0] == 0:
# the following expression both changes the formal charge and resets flag 23
alter_list.append([
atom_tag[0], "formal_charge=1;flags=flags&-8388609"
])
# proline residues
ch = Champ()
model = cmd.get_model(selection)
model_pat = ch.insert_model(model)
assn_pat = ch.insert_pattern_string("C1CC[N;D2]<0>C1C(=O)")
ch.pattern_clear_tags(model_pat)
if ch.match_1v1_n(assn_pat, model_pat, 10000, 2) > 0:
result = ch.pattern_get_ext_indices_with_tags(model_pat)
for atom_tag in result[0]: # just iterate over atom tags
if len(atom_tag[1]) == 1: # one and only one match
if atom_tag[1][0] == 0:
# the following expression both changes the formal charge and resets flag 23
alter_list.append([
atom_tag[0], "formal_charge=1;flags=flags&-8388609"
])
if 1: # c-terminal acid
ch = Champ()
model = cmd.get_model(selection)
model_pat = ch.insert_model(model)
assn_pat = ch.insert_pattern_string("NCC(=O<0>)[O;D1]<1>")
ch.pattern_clear_tags(model_pat)
if ch.match_1v1_n(assn_pat, model_pat, 10000, 2) > 0:
result = ch.pattern_get_ext_indices_with_tags(model_pat)
for atom_tag in result[0]: # just iterate over atom tags
if len(atom_tag[1]) == 1: # one and only one match
if atom_tag[1][0] == 1:
# the following expression both changes the formal charge and resets flag 23
alter_list.append([
atom_tag[0],
"formal_charge=-1;flags=flags&-8388609"
])
# now evaluate all of these expressions efficiently en-masse
cmd.alter_list(selection, alter_list)
# see if we missed any atoms
missed_count = cmd.count_atoms("(" + selection + ") and flag 23")
if missed_count > 0:
if not quiet:
# looks like we did, so alter the user
print(" WARNING: %d atoms did not have formal charges assigned" %
missed_count)
result = 0
# remove the temporary selection we used to select appropriate residues
cmd.delete(tmp_sele1)
return result
import string
print '''# NOTE: This file was autogenerated
formal_charge_dict = {
'''
for res in ('ala', 'arg', 'asp', 'asn', 'cys', 'gln', 'glu', 'gly', 'his',
'hip', 'hie', 'hid', 'ile', 'leu', 'lys', 'met', 'phe', 'pro',
'ser', 'thr', 'trp', 'tyr', 'val'):
stored.fc_dict = {}
print "'" + string.upper(res) + "': ["
print " ("
ch = Champ()
cmd.fragment(res, "tmp")
cmd.iterate("tmp", "stored.fc_dict[name]=formal_charge", quiet=1)
cmd.alter("all", "formal_charge=0", quiet=1)
cmd.remove("hydro", quiet=1)
model = cmd.get_model("tmp")
cmd.delete("tmp")
m1 = ch.insert_model(model)
ch.pattern_detect_chirality(m1)
ch.pattern_orient_bonds(m1)
pat1 = ch.pattern_get_string_with_names(m1)
ch.pattern_detect_chirality(m1)
pat2 = ch.pattern_get_string_with_names(m1)
# confirm that CHAMP handles this pattern well...
def formal_charges(selection="(all)",quiet=0,_self=cmd):
cmd=_self
result = 1
# assumes that hydogens are not present!
# first, set all formal charges to zero
cmd.alter(selection,"formal_charge=0")
# next, flag all atoms so that we'll be able to detect what we miss
cmd.flag(23,selection,'set')
# get the residue dictionary for formal charges
if not hasattr(champ,'formal_charge_dict'):
from chempy.champ.formal_charges import formal_charge_dict
champ.formal_charge_dict = formal_charge_dict
# iterate through the residue dictionary matching each residue based on chemistry
# and generating the expressions for reassigning formal charges
alter_list = []
for resn in champ.formal_charge_dict.keys():
if cmd.select(tmp_sele1,"(%s) and resn %s"%(selection,resn))>0:
entry = champ.formal_charge_dict[resn]
for rule in entry:
model = cmd.get_model(tmp_sele1)
ch = Champ()
model_pat = ch.insert_model(model)
assn_pat = ch.insert_pattern_string(rule[0])
ch.pattern_clear_tags(model_pat)
if ch.match_1v1_n(assn_pat,model_pat,10000,2)>0:
result = ch.pattern_get_ext_indices_with_tags(model_pat)
for atom_tag in result[0]: # just iterate over atom tags
if len(atom_tag[1])==1: # one and only one match
tag = atom_tag[1][0]
formal_charge = rule[1][tag]
# the following expression both changes the formal charge and resets flag 23
alter_list.append([atom_tag[0],
"formal_charge=%d;flags=flags&-8388609"%formal_charge])
if 1: # n-terminal amine
# non-proline
ch=Champ()
model = cmd.get_model(selection)
model_pat = ch.insert_model(model)
assn_pat = ch.insert_pattern_string("[N;D1]<0>CC(=O)")
ch.pattern_clear_tags(model_pat)
if ch.match_1v1_n(assn_pat,model_pat,10000,2)>0:
result = ch.pattern_get_ext_indices_with_tags(model_pat)
for atom_tag in result[0]: # just iterate over atom tags
if len(atom_tag[1])==1: # one and only one match
if atom_tag[1][0]==0:
# the following expression both changes the formal charge and resets flag 23
alter_list.append([atom_tag[0],
"formal_charge=1;flags=flags&-8388609"])
# proline residues
ch=Champ()
model = cmd.get_model(selection)
model_pat = ch.insert_model(model)
assn_pat = ch.insert_pattern_string("C1CC[N;D2]<0>C1C(=O)")
ch.pattern_clear_tags(model_pat)
if ch.match_1v1_n(assn_pat,model_pat,10000,2)>0:
result = ch.pattern_get_ext_indices_with_tags(model_pat)
for atom_tag in result[0]: # just iterate over atom tags
if len(atom_tag[1])==1: # one and only one match
if atom_tag[1][0]==0:
# the following expression both changes the formal charge and resets flag 23
alter_list.append([atom_tag[0],
"formal_charge=1;flags=flags&-8388609"])
if 1: # c-terminal acid
ch=Champ()
model = cmd.get_model(selection)
model_pat = ch.insert_model(model)
assn_pat = ch.insert_pattern_string("NCC(=O<0>)[O;D1]<1>")
ch.pattern_clear_tags(model_pat)
if ch.match_1v1_n(assn_pat,model_pat,10000,2)>0:
result = ch.pattern_get_ext_indices_with_tags(model_pat)
for atom_tag in result[0]: # just iterate over atom tags
if len(atom_tag[1])==1: # one and only one match
if atom_tag[1][0]==1:
# the following expression both changes the formal charge and resets flag 23
alter_list.append([atom_tag[0],
"formal_charge=-1;flags=flags&-8388609"])
# now evaluate all of these expressions efficiently en-masse
cmd.alter_list(selection,alter_list)
# see if we missed any atoms
missed_count = cmd.count_atoms("("+selection+") and flag 23")
if missed_count>0:
if not quiet:
# looks like we did, so alter the user
print " WARNING: %d atoms did not have formal charges assigned"%missed_count
result = 0
# remove the temporary selection we used to select appropriate residues
cmd.delete(tmp_sele1)
return result
from chempy.champ import Champ
ch = Champ()
p1 = ch.insert_pattern_string("C(N)(F)O")
ch.pattern_dump(p1)
ch = Champ()
p1 = ch.insert_pattern_string("C1(N)(F).O1")
ch.pattern_dump(p1)
from chempy.champ import Champ
ch = Champ()
# basic validation of stereochemistry handling on the simplest system
IS = [ # implicit patterns (S)
"[C@H](C)(N)O",
"[C@H](N)(O)C",
"[C@H](O)(C)N",
"C[C@H](N)O",
"N[C@H](O)C",
"O[C@H](C)N",
"[C@@H](C)(O)N",
"[C@@H](N)(C)O",
"[C@@H](O)(N)C",
"C[C@@H](O)N",
"N[C@@H](C)O",
"O[C@@H](N)C",
]
IR = [ # implicit patterns (R)
"[C@@H](C)(N)O",
"[C@@H](N)(O)C",
"[C@@H](O)(C)N",
"C[C@@H](N)O",
"N[C@@H](O)C",
"O[C@@H](C)N",
"[C@H](C)(O)N",
"[C@H](N)(C)O",
"[C@H](O)(N)C",
from pymol import cmd
from chempy.champ import Champ
import string
print '''# NOTE: This file was autogenerated
aa_dict = {'
'''
for res in ( 'ala','arg','asp','asn','cys','gln','glu','gly','his','ile','leu','lys','met','phe','pro','ser','thr','trp','tyr','val' ):
print "'"+string.upper(res)+"': ["
ch = Champ()
cmd.fragment(res,"tmp")
model = cmd.get_model("tmp")
cmd.delete("tmp")
m1 = ch.insert_model(model)
ch.pattern_detect_chirality(m1)
ch.pattern_orient_bonds(m1)
pat1 = ch.pattern_get_string_with_names(m1)
ch.pattern_detect_chirality(m1)
pat2 = ch.pattern_get_string_with_names(m1)
# confirm that CHAMP handles this pattern well...
if pat1!=pat2:
print " Chirality Assignment Error!"
from chempy.champ import Champ ch = Champ() # basic validation of stereochemistry handling on the simplest system IS = [ # implicit patterns (S) "[C@H](C)(N)O", "[C@H](N)(O)C", "[C@H](O)(C)N", "C[C@H](N)O", "N[C@H](O)C", "O[C@H](C)N", "[C@@H](C)(O)N", "[C@@H](N)(C)O", "[C@@H](O)(N)C", "C[C@@H](O)N", "N[C@@H](C)O", "O[C@@H](N)C", ] IR = [ # implicit patterns (R) "[C@@H](C)(N)O", "[C@@H](N)(O)C", "[C@@H](O)(C)N", "C[C@@H](N)O",
from chempy.champ import Champ
ch = Champ()
p1 = ch.insert_pattern_string("C(N)(F)O")
ch.pattern_dump(p1)
ch = Champ()
p1 = ch.insert_pattern_string("C1(N)(F).O1")
ch.pattern_dump(p1)
from chempy.champ import Champ ch = Champ() # basic validation of stereochemistry handling on the simplest system IS = [ # implicit patterns (S) "[C@H](C)(N)O", "[C@H](N)(O)C", "[C@H](O)(C)N", "C[C@H](N)O", "N[C@H](O)C", "O[C@H](C)N", "[C@@H](C)(O)N", "[C@@H](N)(C)O", "[C@@H](O)(N)C", "C[C@@H](O)N", "N[C@@H](C)O", "O[C@@H](N)C", ] IR = [ # implicit patterns (R) "[C@@H](C)(N)O", "[C@@H](N)(O)C", "[C@@H](O)(C)N", "C[C@@H](N)O",
from chempy.champ import Champ
ch = Champ()
# basic validation of stereochemistry handling on the simplest system
IS = [ # implicit patterns (S)
"[C@H](C)(N)O",
"[C@H](N)(O)C",
"[C@H](O)(C)N",
"C[C@H](N)O",
"N[C@H](O)C",
"O[C@H](C)N",
"[C@@H](C)(O)N",
"[C@@H](N)(C)O",
"[C@@H](O)(N)C",
"C[C@@H](O)N",
"N[C@@H](C)O",
"O[C@@H](N)C",
]
IR = [ # implicit patterns (R)
"[C@@H](C)(N)O",
"[C@@H](N)(O)C",
"[C@@H](O)(C)N",
"C[C@@H](N)O",
"N[C@@H](O)C",
"O[C@@H](C)N",
"[C@H](C)(O)N",
"[C@H](N)(C)O",
"[C@H](O)(N)C",