def list_hb(selection,
selection2=None,
cutoff=3.2,
angle=55,
mode=1,
hb_list_name='hbonds'):
"""
USAGE
list_hb selection, [selection2 (default=None)], [cutoff (default=3.2)],
[angle (default=55)], [mode (default=1)],
[hb_list_name (default='hbonds')]
The script automatically adds a requirement that atoms in the
selection (and selection2 if used) must be either of the elements N or
O.
If mode is set to 0 instead of the default value 1, then no angle
cutoff is used, otherwise the angle cutoff is used and defaults to 55
degrees.
e.g.
To get a list of all H-bonds within chain A of an object
list_hb 1abc & c. a &! r. hoh, cutoff=3.2, hb_list_name=abc-hbonds
To get a list of H-bonds between chain B and everything else:
list_hb 1tl9 & c. b, 1tl9 &! c. b
"""
cutoff = float(cutoff)
angle = float(angle)
mode = float(mode)
# ensure only N and O atoms are in the selection
selection = selection + " & e. n+o"
if not selection2:
hb = cmd.find_pairs(selection,
selection,
mode=mode,
cutoff=cutoff,
angle=angle)
else:
selection2 = selection2 + " & e. n+o"
hb = cmd.find_pairs(selection,
selection2,
mode=mode,
cutoff=cutoff,
angle=angle)
# sort the list for easier reading
hb.sort(lambda x, y: (cmp(x[0][1], y[0][1])))
for pairs in hb:
cmd.iterate("%s and index %s" % (pairs[0][0], pairs[0][1]),
'print "%1s/%3s`%s/%-4s " % (chain,resn,resi,name),')
cmd.iterate("%s and index %s" % (pairs[1][0], pairs[1][1]),
'print "%1s/%3s`%s/%-4s " % (chain,resn,resi,name),')
print "%.2f" % cmd.distance(
hb_list_name, "%s and index %s" %
(pairs[0][0], pairs[0][1]), "%s and index %s" %
(pairs[1][0], pairs[1][1]))
def testFindPairs(self):
# mode 0
cmd.fragment("gly")
pairs = cmd.find_pairs("hydro", "elem O")
pairs_ref = [
(('gly', 5), ('gly', 4)),
(('gly', 6), ('gly', 4)),
(('gly', 7), ('gly', 4)),
]
self.assertEqual(sorted(pairs), pairs_ref)
# mode 1
cmd.fab("GGGGG", "m2", ss=1)
pairs = cmd.find_pairs("m2 & donor", "m2 & acceptor", mode=1)
self.assertEqual(pairs, [(('m2', 29), ('m2', 4))])
def get_dehydrons():
cmd.delete('dehydrons')
cmd.delete('DH_pairs')
cmd.hide()
angle = float(angle_value.get())
cutoff = float(dist_cutoff_value.get())
desolv = float(desolv_sphere.get())
min_wrappers = float(min_value.get())
selection = 'name n or name o and not resn hoh'
hb = cmd.find_pairs("((byres "+selection+") and n. n)","((byres "+selection+") and n. o)",mode=1,cutoff=cutoff,angle=angle)
# sort the list for easier reading
hb.sort(lambda x,y:(cmp(x[0][1],y[0][1])))
print "------------------------------------------------\n----------------dehydron Results-----------------\n------------------------------------------------\n Donor | Aceptor | \nChain Residue | Chain Residue | # dehydrons"
sel = []
wra = 0
for pairs in hb:
cmd.iterate("%s and index %s" % (pairs[0][0], pairs[0][1]), 'stored.nitro = chain, resi, resn') # extracts the nitrogen
cmd.iterate("%s and index %s" % (pairs[1][0], pairs[1][1]), 'stored.oxy = chain, resi, resn') # extracts the oxygen
wrappers = cmd.select('wrap', '(((chain %s and name ca and resi %s) around %f) or ((chain %s and name ca and resi %s) around %f)) and (not ((neighbor name n*+o*) or (name n*+o*+h*)))' % (stored.nitro[0], stored.nitro[1], desolv, stored.oxy[0], stored.oxy[1], desolv)) #Identifies the putative dehydrons
if wrappers < min_wrappers:
wra = 1
cmd.distance('Dehydrons',"%s and index %s" % (pairs[0][0],pairs[0][1]),"%s and index %s" % (pairs[1][0],pairs[1][1]))
print ' %s%7s%5d | %s%7s%5d |%7s' % (stored.nitro[0], stored.nitro[2], int(stored.nitro[1]), stored.oxy[0], stored.oxy[2], int(stored.oxy[1]), wrappers)
if stored.nitro[1] not in sel:
sel.append(stored.nitro[1])
if stored.oxy[1] not in sel:
sel.append(stored.oxy[1])
if wra == 1:
cmd.select('DH_pairs', 'resi %s' % ('+').join(sel))
cmd.show('lines', 'DH_pairs')
cmd.disable('DH_pairs')
cmd.hide('labels')
cmd.delete('wrap')
cmd.show('cartoon')
cmd.show('dashes')
def dehydron(selection='all', angle_range=40, max_distance=3.5, desolv=6.5, min_wrappers=19, quiet=0):
'''
DESCRIPTION
dehydron calculator
USAGE
dehydron [ selection [, angle_range [, max_distance [, desolv [, min_wrappers ]]]]]
'''
angle, max_distance = float(angle_range), float(max_distance)
desolv, min_wrappers = float(desolv), int(min_wrappers)
quiet = int(quiet)
name = cmd.get_legal_name('DH_%s' % selection)
cmd.delete(name)
selection_hb = '((%s) and polymer)' % (selection)
hb = cmd.find_pairs("((byres "+selection_hb+") and n. n)","((byres "+selection_hb+") and n. o)",mode=1,cutoff=max_distance,angle=angle_range)
if not quiet:
hb.sort(lambda x,y:(cmp(x[0][1],y[0][1])))
print "--------------------------------------------------------------------"
print "--------------------------Dehydron Results--------------------------"
print "--------------------------------------------------------------------"
print " Donor | Aceptor |"
print " Object Chain Residue | Object Chain Residue | # wrappers"
cmd.select('_nonpolar', '(elem C) and not (solvent or (elem N+O) extend 1)', 0)
try:
cmd.select('_selection', '%s' % selection, 0)
except:
pass
sel = []
for pairs in hb:
wrappers = cmd.count_atoms('((%s and _nonpolar and _selection) within %f of byca (%s`%d %s`%d))' %
((pairs[0][0], desolv) + pairs[0] + pairs[1]))
if wrappers < min_wrappers:
cmd.distance(name, pairs[0], pairs[1])
if not quiet:
cmd.iterate(pairs[0], 'stored.nitro = chain, resi, resn')
cmd.iterate(pairs[1], 'stored.oxy = chain, resi, resn')
print ' %12s%4s%6s%5d | %12s%4s%6s%5d |%7s' % (pairs[0][0], stored.nitro[0], stored.nitro[2], int(stored.nitro[1]), pairs[1][0], stored.oxy[0], stored.oxy[2], int(stored.oxy[1]), wrappers)
sel.append(pairs[0])
sel.append(pairs[1])
cmd.delete('_nonpolar')
cmd.delete('_selection')
if len(sel) > 0:
cmd.show_as('dashes', name)
elif not quiet and len(hb) != 0:
print ' - no dehydrons were found - '
else:
print ' - no hydrogen bonds were found - '
def print_hb(selection):
hb = cmd.find_pairs("((byres "+selection+") and n;n)","((byres "+selection+") and n;o)",mode=1,cutoff=3.7,angle=55)
pair1_list = []
pair2_list = []
dist_list = []
for pairs in hb:
cmd.iterate("%s and ID %s" % (pairs[0][0],pairs[0][1]), 'print "%s/%3s`%s/%s " % (chain,resn,resi,name),')
cmd.iterate("%s and ID %s" % (pairs[1][0],pairs[1][1]), 'print "%s/%3s`%s/%s " % (chain,resn,resi,name),')
print "%.2f" % cmd.dist("%s and ID %s" % (pairs[0][0],pairs[0][1]),"%s and ID %s" % (pairs[1][0],pairs[1][1]))
def list_hb(selection,selection2=None,cutoff=3.2,angle=55,mode=1,hb_list_name='hbonds'):
"""
USAGE
list_hb selection, [selection2 (default=None)], [cutoff (default=3.2)],
[angle (default=55)], [mode (default=1)],
[hb_list_name (default='hbonds')]
The script automatically adds a requirement that atoms in the
selection (and selection2 if used) must be either of the elements N or
O.
If mode is set to 0 instead of the default value 1, then no angle
cutoff is used, otherwise the angle cutoff is used and defaults to 55
degrees.
e.g.
To get a list of all H-bonds within chain A of an object
list_hb 1abc & c. a &! r. hoh, cutoff=3.2, hb_list_name=abc-hbonds
To get a list of H-bonds between chain B and everything else:
list_hb 1tl9 & c. b, 1tl9 &! c. b
"""
cutoff=float(cutoff)
angle=float(angle)
mode=float(mode)
# ensure only N and O atoms are in the selection
selection = selection + " & e. n+o"
if not selection2:
hb = cmd.find_pairs(selection,selection,mode=mode,cutoff=cutoff,angle=angle)
else:
selection2 = selection2 + " & e. n+o"
hb = cmd.find_pairs(selection,selection2,mode=mode,cutoff=cutoff,angle=angle)
# sort the list for easier reading
hb.sort(lambda x,y:(cmp(x[0][1],y[0][1])))
for pairs in hb:
cmd.iterate("%s and index %s" % (pairs[0][0],pairs[0][1]), 'print "%1s/%3s`%s/%-4s " % (chain,resn,resi,name),')
cmd.iterate("%s and index %s" % (pairs[1][0],pairs[1][1]), 'print "%1s/%3s`%s/%-4s " % (chain,resn,resi,name),')
print "%.2f" % cmd.distance(hb_list_name,"%s and index %s" % (pairs[0][0],pairs[0][1]),"%s and index %s" % (pairs[1][0],pairs[1][1]))
def polarpairs(sel1, sel2, cutoff=4.0, angle=63.0, name='', state=1, quiet=1):
'''
ARGUMENTS
sel1, sel2 = string: atom selections
cutoff = float: distance cutoff
angle = float: h-bond angle cutoff in degrees. If angle="default", take
"h_bond_max_angle" setting. If angle=0, do not detect h-bonding.
name = string: If given, also create a distance object for visual representation
SEE ALSO
cmd.find_pairs, cmd.distance
'''
cutoff = float(cutoff)
quiet = int(quiet)
state = int(state)
if angle == 'default':
angle = cmd.get('h_bond_max_angle', cmd.get_object_list(sel1)[0])
angle = float(angle)
mode = 1 if angle > 0 else 0
x = cmd.find_pairs('(%s) and donors' % sel1, '(%s) and acceptors' % sel2,
state, state,
cutoff=cutoff, mode=mode, angle=angle) + \
cmd.find_pairs('(%s) and acceptors' % sel1, '(%s) and donors' % sel2,
state, state,
cutoff=cutoff, mode=mode, angle=angle)
x = sorted(set(x))
if not quiet:
print 'Settings: cutoff=%.1fangstrom angle=%.1fdegree' % (cutoff,
angle)
print 'Found %d polar contacts' % (len(x))
if len(name) > 0:
for p in x:
cmd.distance(name, '(%s`%s)' % p[0], '(%s`%s)' % p[1])
return x
def polarpairs(sel1, sel2, cutoff=4.0, angle=63.0, name='', state=1, quiet=1):
'''
ARGUMENTS
sel1, sel2 = string: atom selections
cutoff = float: distance cutoff
angle = float: h-bond angle cutoff in degrees. If angle="default", take
"h_bond_max_angle" setting. If angle=0, do not detect h-bonding.
name = string: If given, also create a distance object for visual representation
SEE ALSO
cmd.find_pairs, cmd.distance
'''
cutoff = float(cutoff)
quiet = int(quiet)
state = int(state)
if angle == 'default':
angle = cmd.get('h_bond_max_angle', cmd.get_object_list(sel1)[0])
angle = float(angle)
mode = 1 if angle > 0 else 0
x = cmd.find_pairs('(%s) and donors' % sel1, '(%s) and acceptors' % sel2,
state, state,
cutoff=cutoff, mode=mode, angle=angle) + \
cmd.find_pairs('(%s) and acceptors' % sel1, '(%s) and donors' % sel2,
state, state,
cutoff=cutoff, mode=mode, angle=angle)
x = sorted(set(x))
if not quiet:
print 'Settings: cutoff=%.1fangstrom angle=%.1fdegree' % (cutoff, angle)
print 'Found %d polar contacts' % (len(x))
if len(name) > 0:
for p in x:
cmd.distance(name, '(%s`%s)' % p[0], '(%s`%s)' % p[1])
return x
def list_hb(selection,cutoff=3.2,angle=55,hb_list_name='hbonds'):
"""
USAGE
list_hb selection, [cutoff (default=3.2)], [angle (default=55)], [hb_list_name]
e.g.
list_hb 1abc & c. a &! r. hoh, cutoff=3.2, hb_list_name=abc-hbonds
"""
cutoff=float(cutoff)
angle=float(angle)
hb = cmd.find_pairs("((byres "+selection+") and n;n)","((byres "+selection+") and n;o)",mode=1,cutoff=cutoff,angle=angle)
# sort the list for easier reading
hb.sort(lambda x,y:(cmp(x[0][1],y[0][1])))
for pairs in hb:
for ind in [0,1]:
cmd.iterate("%s and index %s" % (pairs[ind][0],pairs[ind][1]), 'print "%s/%3s`%s/%s/%s " % (chain,resn,resi,name,index),')
print "%.2f" % cmd.distance(hb_list_name,"%s and index %s" % (pairs[0][0],pairs[0][1]),"%s and index %s" % (pairs[1][0],pairs[1][1]))
def pmf(key,
cutoff=7.0,
selection1='(name CB)',
selection2='',
state=1,
quiet=1):
'''
DESCRIPTION
Potential of Mean Force
ARGUMENTS
key = string: aaindex key
cutoff = float: distance cutoff {default: 7.0}
cutoff = (float, float): distance shell
selection1 = string: atom selection {default: (name CB)}
selection2 = string: atom selection {default: selection1}
NOTES
Does also support a list of keys and a list of cutoffs to deal with
multiple distance shells.
EXAMPLES
# distance dependent c-beta contact potentials
pmf SIMK990101, 5, /2x19//A//CB
pmf SIMK990102, [5, 7.5], /2x19//A//CB
pmf [SIMK990101, SIMK990102, SIMK990103], [0, 5, 7.5, 10], /2x19//A//CB
# interface potential
sidechaincenters 2x19_scc, 2x19
pmf KESO980102, 7.0, /2x19_scc//A, /2x19_scc//B
distance /2x19_scc//A, /2x19_scc//B, cutoff=7.0
'''
from pymol import cmd, stored
from chempy import cpv
if cmd.is_string(key):
if key.lstrip().startswith('['):
key = cmd.safe_alpha_list_eval(key)
else:
key = [key]
if cmd.is_string(cutoff):
cutoff = eval(cutoff)
if not cmd.is_sequence(cutoff):
cutoff = [cutoff]
if len(cutoff) == len(key):
cutoff = [0.0] + list(cutoff)
if len(cutoff) != len(key) + 1:
print 'Error: Number of keys and number of cutoffs inconsistent'
return
state = int(state)
quiet = int(quiet)
if len(selection2) == 0:
selection2 = selection1
if not quiet and len(key) > 1:
print 'Distance shells:'
for i in range(len(key)):
print '%s %.1f-%.1f' % (key[i], cutoff[i], cutoff[i + 1])
idmap = dict()
cmd.iterate_state(state,
'(%s) or (%s)' % (selection1, selection2),
'idmap[model,index] = [(resn,name),(x,y,z)]',
space={'idmap': idmap})
twoN = cmd.count_atoms(selection1) + cmd.count_atoms(selection2)
pairs = cmd.find_pairs(selection1,
selection2,
cutoff=max(cutoff),
state1=state,
state2=state)
if len(pairs) == 0:
print 'Empty pair list'
return 0.0
matrix = map(get, key)
for i in matrix:
assert isinstance(i, MatrixRecord)
i_list = range(len(key))
u_sum = 0
count = 0
for id1, id2 in pairs:
a1 = idmap[id1]
a2 = idmap[id2]
r = cpv.distance(a1[1], a2[1])
for i in i_list:
if cutoff[i] <= r and r < cutoff[i + 1]:
try:
aa1 = to_one_letter_code[a1[0][0]]
aa2 = to_one_letter_code[a2[0][0]]
u_sum += matrix[i].get(aa1, aa2)
count += 1
except:
print 'Failed for', a1[0], a2[0]
value = float(u_sum) / twoN
if not quiet:
print 'PMF: %.4f (%d contacts, %d residues)' % (value, count, twoN)
return value
def dehydron(selection='all',
angle_range=40.,
max_distance=3.5,
desolv=6.5,
min_wrappers=19,
max_wrappers=35,
quiet=0):
'''
DESCRIPTION
dehydron calculator
USAGE
wrappy [ selection [, angle_range [, max_distance [, desolv [, min_wrappers [, max_wrappers ]]]]]]
'''
angle, max_distance = float(angle_range), float(max_distance)
desolv, min_wrappers, max_wrappers = float(desolv), int(min_wrappers), int(
max_wrappers)
quiet = int(quiet)
DH_name = cmd.get_legal_name('DH_%s' % selection)
cmd.delete(DH_name)
HBA_name = cmd.get_legal_name('HBA_%s' % selection)
cmd.delete(HBA_name)
HBO_name = cmd.get_legal_name('HBO_%s' % selection)
cmd.delete(HBO_name)
selection_hb = '((%s) and polymer)' % (selection)
hb = cmd.find_pairs("((byres " + selection_hb + ") and n. n)",
"((byres " + selection_hb + ") and n. o)",
mode=1,
cutoff=max_distance,
angle=angle_range)
cmd.select('_nonpolar',
'(elem C) and not (solvent or (elem N+O) extend 1)', 0)
try:
cmd.select('_selection', '%s' % selection, 0)
except:
pass
low_sel = []
mean_sel = []
high_sel = []
total_wrappers = 0
for pairs in hb:
wrappers = cmd.count_atoms(
'((%s and _nonpolar and _selection) within %f of byca (%s`%d %s`%d))'
% ((pairs[0][0], desolv) + pairs[0] + pairs[1]))
total_wrappers = total_wrappers + wrappers
cmd.iterate(pairs[0], 'stored.donor = chain, resi, resn')
cmd.iterate(pairs[1], 'stored.aceptor = chain, resi, resn')
if wrappers < min_wrappers:
cmd.distance(DH_name, pairs[0], pairs[1])
line = (wrappers,
'%12s%4s%6s%6s | %12s%4s%6s%6s |%7s below' %
(pairs[0][0], stored.donor[0], stored.donor[2],
stored.donor[1], pairs[1][0], stored.aceptor[0],
stored.aceptor[2], stored.aceptor[1], wrappers))
low_sel.append(line)
elif wrappers < max_wrappers:
cmd.distance(HBA_name, pairs[0], pairs[1])
line = (wrappers,
'%12s%4s%6s%6s | %12s%4s%6s%6s |%7s average' %
(pairs[0][0], stored.donor[0], stored.donor[2],
stored.donor[1], pairs[1][0], stored.aceptor[0],
stored.aceptor[2], stored.aceptor[1], wrappers))
mean_sel.append(line)
else:
cmd.distance(HBO_name, pairs[0], pairs[1])
line = (wrappers,
'%12s%4s%6s%6s | %12s%4s%6s%6s |%7s over' %
(pairs[0][0], stored.donor[0], stored.donor[2],
stored.donor[1], pairs[1][0], stored.aceptor[0],
stored.aceptor[2], stored.aceptor[1], wrappers))
high_sel.append(line)
cmd.delete('_nonpolar')
cmd.delete('_selection')
# compute the z_scores. Useful for protein structure validation.
stored.ResiduesNames = []
cmd.iterate('(name ca)', 'stored.ResiduesNames.append((resn))')
total_residues = float(len(stored.ResiduesNames))
z_score_wrappers = ((total_wrappers / total_residues) - 17) / 2
z_score_hb = ((len(hb) / total_residues) - 0.62) / 0.06
if len(low_sel) > 0:
cmd.show_as('dashes', DH_name)
cmd.color('red', DH_name)
low_sel.sort()
if len(mean_sel) > 0:
cmd.show_as('dashes', HBA_name)
cmd.color('yellow', HBA_name)
mean_sel.sort()
if len(high_sel) > 0:
cmd.show_as('dashes', HBO_name)
cmd.color('green', HBO_name)
high_sel.sort()
if not quiet:
hb.sort()
print "--------------------------------------------------------------------"
print "------------------------------Results ------------------------------"
print "--------------------------------------------------------------------"
print " Donor | Aceptor |"
print " Object Chain Residue | Object Chain Residue | # wrappers wrapping"
for line in low_sel:
print line[1]
for line in mean_sel:
print line[1]
for line in high_sel:
print line[1]
print '\nProtein global statistics:'
print '\nz-score wrappers = %6.2f\nz-score hydrogen bonds = %6.2f\n' % (
z_score_wrappers, z_score_hb)
elif not quiet and len(hb) != 0:
print '\n - no dehydrons were found - '
print '\nz-score hydrogen bonds = %6.2f\n' % (z_score_hb)
else:
print '\n - no hydrogen bonds were found - '
def dehydron(selection='all', angle_range=40., max_distance=3.5, desolv=6.5, min_wrappers=19, max_wrappers=35, quiet=0):
'''
DESCRIPTION
dehydron calculator
USAGE
wrappy [ selection [, angle_range [, max_distance [, desolv [, min_wrappers [, max_wrappers ]]]]]]
'''
angle, max_distance = float(angle_range), float(max_distance)
desolv, min_wrappers, max_wrappers = float(desolv), int(min_wrappers), int(max_wrappers)
quiet = int(quiet)
DH_name = cmd.get_legal_name('DH_%s' % selection)
cmd.delete(DH_name)
HBA_name = cmd.get_legal_name('HBA_%s' % selection)
cmd.delete(HBA_name)
HBO_name = cmd.get_legal_name('HBO_%s' % selection)
cmd.delete(HBO_name)
selection_hb = '((%s) and polymer)' % (selection)
hb = cmd.find_pairs("((byres " + selection_hb + ") and n. n)", "((byres " + selection_hb + ") and n. o)", mode=1, cutoff=max_distance, angle=angle_range)
cmd.select('_nonpolar', '(elem C) and not (solvent or (elem N+O) extend 1)', 0)
try:
cmd.select('_selection', '%s' % selection, 0)
except:
pass
low_sel = []
mean_sel = []
high_sel = []
total_wrappers = 0
for pairs in hb:
wrappers = cmd.count_atoms('((%s and _nonpolar and _selection) within %f of byca (%s`%d %s`%d))' %
((pairs[0][0], desolv) + pairs[0] + pairs[1]))
total_wrappers = total_wrappers + wrappers
cmd.iterate(pairs[0], 'stored.donor = chain, resi, resn')
cmd.iterate(pairs[1], 'stored.aceptor = chain, resi, resn')
if wrappers < min_wrappers:
cmd.distance(DH_name, pairs[0], pairs[1])
line = (wrappers, '%12s%4s%6s%6s | %12s%4s%6s%6s |%7s below' % (pairs[0][0], stored.donor[0], stored.donor[2], stored.donor[1], pairs[1][0], stored.aceptor[0], stored.aceptor[2], stored.aceptor[1], wrappers))
low_sel.append(line)
elif wrappers < max_wrappers:
cmd.distance(HBA_name, pairs[0], pairs[1])
line = (wrappers, '%12s%4s%6s%6s | %12s%4s%6s%6s |%7s average' % (pairs[0][0], stored.donor[0], stored.donor[2], stored.donor[1], pairs[1][0], stored.aceptor[0], stored.aceptor[2], stored.aceptor[1], wrappers))
mean_sel.append(line)
else:
cmd.distance(HBO_name, pairs[0], pairs[1])
line = (wrappers, '%12s%4s%6s%6s | %12s%4s%6s%6s |%7s over' % (pairs[0][0], stored.donor[0], stored.donor[2], stored.donor[1], pairs[1][0], stored.aceptor[0], stored.aceptor[2], stored.aceptor[1], wrappers))
high_sel.append(line)
cmd.delete('_nonpolar')
cmd.delete('_selection')
# compute the z_scores. Useful for protein structure validation.
stored.ResiduesNames = []
cmd.iterate('(name ca)', 'stored.ResiduesNames.append((resn))')
total_residues = float(len(stored.ResiduesNames))
z_score_wrappers = ((total_wrappers / total_residues) - 17) / 2
z_score_hb = ((len(hb) / total_residues) - 0.62) / 0.06
if len(low_sel) > 0:
cmd.show_as('dashes', DH_name)
cmd.color('red', DH_name)
low_sel.sort()
if len(mean_sel) > 0:
cmd.show_as('dashes', HBA_name)
cmd.color('yellow', HBA_name)
mean_sel.sort()
if len(high_sel) > 0:
cmd.show_as('dashes', HBO_name)
cmd.color('green', HBO_name)
high_sel.sort()
if not quiet:
hb.sort()
print "--------------------------------------------------------------------"
print "------------------------------Results ------------------------------"
print "--------------------------------------------------------------------"
print " Donor | Aceptor |"
print " Object Chain Residue | Object Chain Residue | # wrappers wrapping"
for line in low_sel:
print line[1]
for line in mean_sel:
print line[1]
for line in high_sel:
print line[1]
print '\nProtein global statistics:'
print '\nz-score wrappers = %6.2f\nz-score hydrogen bonds = %6.2f\n' % (z_score_wrappers, z_score_hb)
elif not quiet and len(hb) != 0:
print '\n - no dehydrons were found - '
print '\nz-score hydrogen bonds = %6.2f\n' % (z_score_hb)
else:
print '\n - no hydrogen bonds were found - '
def dehydron(selection='all',
angle_range=40,
max_distance=3.5,
desolv=6.5,
min_wrappers=19,
quiet=0):
'''
DESCRIPTION
dehydron calculator
USAGE
dehydron [ selection [, angle_range [, max_distance [, desolv [, min_wrappers ]]]]]
'''
angle, max_distance = float(angle_range), float(max_distance)
desolv, min_wrappers = float(desolv), int(min_wrappers)
quiet = int(quiet)
name = cmd.get_legal_name('DH_%s' % selection)
cmd.delete(name)
selection_hb = '((%s) and polymer)' % (selection)
hb = cmd.find_pairs("((byres " + selection_hb + ") and n. n)",
"((byres " + selection_hb + ") and n. o)",
mode=1,
cutoff=max_distance,
angle=angle_range)
if not quiet:
hb.sort(lambda x, y: (cmp(x[0][1], y[0][1])))
print "--------------------------------------------------------------------"
print "--------------------------Dehydron Results--------------------------"
print "--------------------------------------------------------------------"
print " Donor | Aceptor |"
print " Object Chain Residue | Object Chain Residue | # wrappers"
cmd.select('_nonpolar',
'(elem C) and not (solvent or (elem N+O) extend 1)', 0)
try:
cmd.select('_selection', '%s' % selection, 0)
except:
pass
sel = []
total_wrappers = 0
for pairs in hb:
wrappers = cmd.count_atoms(
'((%s and _nonpolar and _selection) within %f of byca (%s`%d %s`%d))'
% ((pairs[0][0], desolv) + pairs[0] + pairs[1]))
total_wrappers = total_wrappers + wrappers
if wrappers < min_wrappers:
cmd.distance(name, pairs[0], pairs[1])
if not quiet:
cmd.iterate(pairs[0], 'stored.nitro = chain, resi, resn')
cmd.iterate(pairs[1], 'stored.oxy = chain, resi, resn')
print ' %12s%4s%6s%6s | %12s%4s%6s%6s |%7s' % (
pairs[0][0], stored.nitro[0], stored.nitro[2],
stored.nitro[1], pairs[1][0], stored.oxy[0], stored.oxy[2],
stored.oxy[1], wrappers)
sel.append(pairs[0])
sel.append(pairs[1])
cmd.delete('_nonpolar')
cmd.delete('_selection')
#compute the z_scores for validation porpoises.
stored.ResiduesNames = []
cmd.iterate('(name ca)', 'stored.ResiduesNames.append((resn))')
total_residues = float(len(stored.ResiduesNames))
z_score_wrappers = ((total_wrappers / total_residues) - 17) / 2
z_score_hb = ((len(hb) / total_residues) - 0.62) / 0.06
if len(sel) > 0:
cmd.show_as('dashes', name)
print '\nz-score wrappers = %6.2f\nz-score hydrogen bonds = %6.2f\n' % (
z_score_wrappers, z_score_hb)
elif not quiet and len(hb) != 0:
print '\n - no dehydrons were found - '
print '\nz-score hydrogen bonds = %6.2f\n' % (z_score_hb)
else:
print '\n - no hydrogen bonds were found - '
def peptide_rebuild(name, selection='all', cycles=1000, state=1, quiet=1):
'''
DESCRIPTION
Rebuild the peptide from selection. All atoms which are present in
selection will be kept fixed, while atoms missing in selection are
placed by sculpting.
USAGE
peptide_rebuild name [, selection [, cycles [, state ]]]
SEE ALSO
stub2ala, add_missing_atoms, peptide_rebuild_modeller
'''
from chempy import fragments, feedback, models
cycles, state, quiet = int(cycles), int(state), int(quiet)
# suppress feedback for model merging
feedback['actions'] = False
# work with named selection
namedsele = cmd.get_unused_name('_')
cmd.select(namedsele, selection, 0)
identifiers = []
cmd.iterate(namedsele + ' and polymer and guide and alt +A',
'identifiers.append([segi,chain,resi,resv,resn])', space=locals())
model = models.Indexed()
for (segi,chain,resi,resv,resn) in identifiers:
try:
fname = resn.lower() if resn != 'MSE' else 'met'
frag = fragments.get(fname)
except IOError:
print(' Warning: unknown residue: ' + resn)
continue
for a in frag.atom:
a.segi = segi
a.chain = chain
a.resi = resi
a.resi_number = resv
a.resn = resn
model.merge(frag)
if not quiet:
print(' Loading model...')
cmd.load_model(model, name, 1, zoom=0)
if cmd.get_setting_boolean('auto_remove_hydrogens'):
cmd.remove(name + ' and hydro')
cmd.protect(name + ' in ' + namedsele)
cmd.sculpt_activate(name)
cmd.update(name, namedsele, 1, state)
cmd.delete(namedsele)
if not quiet:
print(' Sculpting...')
cmd.set('sculpt_field_mask', 0x003, name) # bonds and angles only
cmd.sculpt_iterate(name, 1, int(cycles / 4))
cmd.set('sculpt_field_mask', 0x09F, name) # local + torsions
cmd.sculpt_iterate(name, 1, int(cycles / 4))
cmd.set('sculpt_field_mask', 0x0FF, name) # ... + vdw
cmd.sculpt_iterate(name, 1, int(cycles / 2))
cmd.sculpt_deactivate(name)
cmd.deprotect(name)
cmd.unset('sculpt_field_mask', name)
if not quiet:
print(' Connecting peptide...')
pairs = cmd.find_pairs(name + ' and name C', name + ' and name N', 1, 1, 2.0)
for pair in pairs:
cmd.bond(*pair)
cmd.h_fix(name)
if not quiet:
print(' peptide_rebuild: done')
def peptide_rebuild(name, selection='all', cycles=1000, state=1, quiet=1):
'''
DESCRIPTION
Rebuild the peptide from selection. All atoms which are present in
selection will be kept fixed, while atoms missing in selection are
placed by sculpting.
USAGE
peptide_rebuild name [, selection [, cycles [, state ]]]
SEE ALSO
stub2ala, add_missing_atoms, peptide_rebuild_modeller
'''
from chempy import fragments, feedback, models
cycles, state, quiet = int(cycles), int(state), int(quiet)
# suppress feedback for model merging
feedback['actions'] = False
# work with named selection
namedsele = cmd.get_unused_name('_')
cmd.select(namedsele, selection, 0)
identifiers = []
cmd.iterate(namedsele + ' and polymer and guide and alt +A',
'identifiers.append([segi,chain,resi,resv,resn])', space=locals())
model = models.Indexed()
for (segi,chain,resi,resv,resn) in identifiers:
try:
fname = resn.lower() if resn != 'MSE' else 'met'
frag = fragments.get(fname)
except IOError:
print(' Warning: unknown residue:', resn)
continue
for a in frag.atom:
a.segi = segi
a.chain = chain
a.resi = resi
a.resi_number = resv
a.resn = resn
model.merge(frag)
if not quiet:
print(' Loading model...')
cmd.load_model(model, name, 1, zoom=0)
if cmd.get_setting_boolean('auto_remove_hydrogens'):
cmd.remove(name + ' and hydro')
cmd.protect(name + ' in ' + namedsele)
cmd.sculpt_activate(name)
cmd.update(name, namedsele, 1, state)
cmd.delete(namedsele)
if not quiet:
print(' Sculpting...')
cmd.set('sculpt_field_mask', 0x003, name) # bonds and angles only
cmd.sculpt_iterate(name, 1, int(cycles / 4))
cmd.set('sculpt_field_mask', 0x09F, name) # local + torsions
cmd.sculpt_iterate(name, 1, int(cycles / 4))
cmd.set('sculpt_field_mask', 0x0FF, name) # ... + vdw
cmd.sculpt_iterate(name, 1, int(cycles / 2))
cmd.sculpt_deactivate(name)
cmd.deprotect(name)
cmd.unset('sculpt_field_mask', name)
if not quiet:
print(' Connecting peptide...')
pairs = cmd.find_pairs(name + ' and name C', name + ' and name N', 1, 1, 2.0)
for pair in pairs:
cmd.bond(*pair)
cmd.h_fix(name)
if not quiet:
print(' peptide_rebuild: done')
def hydro_pairs(selection, cut_off):
"""
Find hydrogen bonds for a given selection
"""
states = cmd.count_states(selection)
hb = []
for i in range(1, states+1):
hb.append(cmd.find_pairs("%s and (name O* and neighbor elem H) or (name N* and neighbor elem H)"%(selection),
"%s and name N* or name O*"%(selection),
cutoff = 3.5, mode=1, angle=40, state1=i, state2=i))
seen = {}
for state in hb:
for pairs in state:
if pairs in seen:
seen[pairs] = seen[pairs] + 1
else:
seen[pairs] = 1
occurrence = seen.items()
occurrence.sort(key=lambda x:x[1], reverse=True)
fd = open("Hydrogen_bonds.dat", "w")
fd.write("--------------------------------------------------------------------\n")
fd.write("-----------------------------Results--------------------------------\n")
fd.write("--------------------------------------------------------------------\n")
fd.write(" Donor | Aceptor |\n")
fd.write(" Object Residue Atom Index| Object Residue Atom Index| % occurrence\n")
stored.donors = []
stored.aceptors = []
sub = []
occurrence_list = []
for i in range (len(occurrence)):
cmd.iterate("index %s"%(occurrence[i][0][0][1]),
"stored.donors.append((resn, elem))")
cmd.iterate("index %s"%(occurrence[i][0][1][1]),
"stored.aceptors.append((resn, elem))")
if (occurrence[i][1]*100/states) >= cut_off:
fd.write( "%8s%8s%6s%8s|%8s%8s%6s%8s|%5s\n" % (occurrence[i][0][0][0],
stored.donors[i][0],
stored.donors[i][1],
occurrence[i][0][0][1],
occurrence[i][0][1][0],
stored.aceptors[i][0],
stored.aceptors[i][1],
occurrence[i][0][1][1],
"%.2f"%(occurrence[i][1]*100/states)))
occurrence_list.append(occurrence[i][0])
fd.close()
cmd.set('suspend_updates', 'on')
for state, bonds in enumerate(hb):
for bond in bonds:
if bond in occurrence_list:
cmd.distance('HB', 'index %s' % bond[0][1], 'index %s' % bond[1][1], state=state, cutoff=3.5)
cmd.hide("labels","HB")
cmd.set('suspend_updates', 'off')
print "Check working directory for Hydrogen bonds text file report"
def pmf(key, cutoff=7.0, selection1='(name CB)', selection2='', state=1, quiet=1):
'''
DESCRIPTION
Potential of Mean Force
ARGUMENTS
key = string: aaindex key
cutoff = float: distance cutoff {default: 7.0}
cutoff = (float, float): distance shell
selection1 = string: atom selection {default: (name CB)}
selection2 = string: atom selection {default: selection1}
NOTES
Does also support a list of keys and a list of cutoffs to deal with
multiple distance shells.
EXAMPLES
# distance dependent c-beta contact potentials
pmf SIMK990101, 5, /2x19//A//CB
pmf SIMK990102, [5, 7.5], /2x19//A//CB
pmf [SIMK990101, SIMK990102, SIMK990103], [0, 5, 7.5, 10], /2x19//A//CB
# interface potential
sidechaincenters 2x19_scc, 2x19
pmf KESO980102, 7.0, /2x19_scc//A, /2x19_scc//B
distance /2x19_scc//A, /2x19_scc//B, cutoff=7.0
'''
from pymol import cmd, stored
from chempy import cpv
if cmd.is_string(key):
if key.lstrip().startswith('['):
key = cmd.safe_alpha_list_eval(key)
else:
key = [key]
if cmd.is_string(cutoff):
cutoff = eval(cutoff)
if not cmd.is_sequence(cutoff):
cutoff = [cutoff]
if len(cutoff) == len(key):
cutoff = [0.0] + list(cutoff)
if len(cutoff) != len(key) + 1:
print('Error: Number of keys and number of cutoffs inconsistent')
return
state = int(state)
quiet = int(quiet)
if len(selection2) == 0:
selection2 = selection1
if not quiet and len(key) > 1:
print('Distance shells:')
for i in range(len(key)):
print('%s %.1f-%.1f' % (key[i], cutoff[i], cutoff[i + 1]))
idmap = dict()
cmd.iterate_state(state, '(%s) or (%s)' % (selection1, selection2),
'idmap[model,index] = [(resn,name),(x,y,z)]', space={'idmap': idmap})
twoN = cmd.count_atoms(selection1) + cmd.count_atoms(selection2)
pairs = cmd.find_pairs(selection1, selection2, cutoff=max(cutoff),
state1=state, state2=state)
if len(pairs) == 0:
print('Empty pair list')
return 0.0
matrix = list(map(get, key))
for i in matrix:
assert isinstance(i, MatrixRecord)
i_list = list(range(len(key)))
u_sum = 0
count = 0
for id1, id2 in pairs:
a1 = idmap[id1]
a2 = idmap[id2]
r = cpv.distance(a1[1], a2[1])
for i in i_list:
if cutoff[i] <= r and r < cutoff[i + 1]:
try:
aa1 = to_one_letter_code[a1[0][0]]
aa2 = to_one_letter_code[a2[0][0]]
u_sum += matrix[i].get(aa1, aa2)
count += 1
except:
print('Failed for', a1[0], a2[0])
value = float(u_sum) / twoN
if not quiet:
print('PMF: %.4f (%d contacts, %d residues)' % (value, count, twoN))
return value
def hydro_pairs(selection, cut_off):
"""
Find hydrogen bonds for a given selection
"""
states = cmd.count_states(selection)
if states:
hb = []
for i in range(1, states + 1):
p = cmd.find_pairs("%s and (name O* and neighbor elem H) or"
"(name N* and neighbor elem H)" % selection,
"%s and name N* or name O*" % selection,
cutoff=3.5,
mode=1,
angle=40,
state1=i,
state2=i)
hb.append(p)
if any([j for i in hb for j in i]):
seen = {}
for state in hb:
for pairs in state:
if pairs in seen:
seen[pairs] = seen[pairs] + 1
else:
seen[pairs] = 1
occurrence = seen.items()
occurrence = sorted(occurrence, key=lambda x: x[1], reverse=True)
fd = open("Hydrogen_bonds.dat", "w")
fd.write("--------------------------------------------------------"
"------------\n")
fd.write("-----------------------------Results--------------------"
"------------\n")
fd.write("--------------------------------------------------------"
"------------\n")
fd.write(" Donor |"
" Aceptor |\n")
fd.write(" Object Residue Atom Index|"
" Object Residue Atom Index| % occurrence\n")
stored.donors = []
stored.aceptors = []
sub = []
occurrence_list = []
for i in range(len(occurrence)):
cmd.iterate("index %s" % (occurrence[i][0][0][1]),
"stored.donors.append((resn, elem))")
cmd.iterate("index %s" % (occurrence[i][0][1][1]),
"stored.aceptors.append((resn, elem))")
if (occurrence[i][1] * 100 / states) >= cut_off:
fd.write("%8s%8s%6s%8s|%8s%8s%6s%8s|%5s\n" %
(occurrence[i][0][0][0], stored.donors[i][0],
stored.donors[i][1], occurrence[i][0][0][1],
occurrence[i][0][1][0], stored.aceptors[i][0],
stored.aceptors[i][1], occurrence[i][0][1][1],
"%.2f" % (occurrence[i][1] * 100 / states)))
occurrence_list.append(occurrence[i][0])
fd.close()
cmd.set('suspend_updates', 'on')
for state, bonds in enumerate(hb):
for bond in bonds:
if bond in occurrence_list:
cmd.distance('HB',
'index %s' % bond[0][1],
'index %s' % bond[1][1],
state=state,
cutoff=3.5)
cmd.hide("labels", "HB")
cmd.set('suspend_updates', 'off')
print(
"Check working directory for hydrogen bonds text file report")
else:
print("No hydrogen bonds detected for this selection")