import sys
sys.path.append('/home/tc/svn/tc_sandbox/pdb')
import parse_mmCIF, mmCIF2coords
sys.path.append('/home/tc/svn/GoodVibes')
import NMA, visualization
d_mmCIF = parse_mmCIF.main('2lzm',)
d_coords, l_coords_alpha = mmCIF2coords.main('2lzm',d_mmCIF)
cutoff = 10
matrix_hessian = NMA.hessian_calculation(l_coords_alpha, cutoff)
eigenvectors, eigenvalues = NMA.diagonalize_hessian(matrix_hessian,)
visualization.vmd_trajectory('2lzm',l_coords_alpha,eigenvectors)
def parse_GoodVibes_exclude_flexible(
pdb,
path,
):
##
## calculate amplitudes
##
d_mmCIF = parse_mmCIF.main(pdb[:4], )
d_coords, l_coords_alpha = mmCIF2coords.main(pdb[:4],
d_mmCIF,
query_chain=pdb[-1])
print len(l_coords_alpha)
##
## eigenvector
##
cutoff = 10
matrix_hessian = NMA.hessian_calculation(
l_coords_alpha,
cutoff,
)
eigenvectors, eigenvalues = NMA.diagonalize_hessian(matrix_hessian)
l_amplitudes = [
math.sqrt(eigenvectors[6][i]**2 + eigenvectors[6][i + 1]**2 +
eigenvectors[6][i + 2]**2)
for i in range(0, len(eigenvectors[6]), 3)
]
## ## write pdb (color by bfactor)
## l_bfactors = [100*(l_amplitudes[i]-min(l_amplitudes))/(max(l_amplitudes)-min(l_amplitudes)) for i in range(len(l_amplitudes))]
## fd = open('output/%s/%s_%s_probe.pdb' %(path,pdb[:4],pdb[-1],),'r')
## lines = fd.readlines()
## fd.close()
## index = [-1,None,]
## lines_out = []
## for line in lines:
## record = line[:6].strip()
## if record != 'ATOM':
## lines_out += [line]
## else:
## res_no = int(line[22:26])
## if res_no != index[1]:
## index = [index[0]+1,res_no,]
## bfactor = l_bfactors[index[0]]
## line_out = '%s%6.2f%s' %(line[:60],bfactor,line[66:],)
## lines_out += [line_out]
## fd = open('output/%s/%s_%s_probe_color_by_amplitude.pdb' %(path,pdb[:4],pdb[-1],),'w')
## fd.writelines(lines_out)
## fd.close()
## average amplitude
average = sum(l_amplitudes) / len(l_amplitudes)
average, stddev = statistics.do_stddev(l_amplitudes)
##
l_coords_rigid = []
for i in range(len(l_coords_alpha)):
if l_amplitudes[i] < average:
l_coords_rigid += [l_coords_alpha[i]]
l_coords_flexible = []
for i in range(len(l_coords_alpha)):
if l_amplitudes[i] > average + 0.5 * stddev:
l_coords_flexible += [l_coords_alpha[i]]
## parse output
fd = open('output/%s/%s_%s_probe.pdb' % (
path,
pdb[:4],
pdb[-1],
), 'r')
lines = fd.readlines()
fd.close()
max_bfactor = None
coord = None
for line in lines:
record = line[:6].strip()
if record not in [
'ATOM',
'HETATM',
]:
continue
res_name = line[17:20]
if res_name != 'EXT':
continue
bfactor = float(line[60:66])
if bfactor > max_bfactor:
x = float(line[30:38])
y = float(line[38:46])
z = float(line[46:54])
## coord_tmp = numpy.array([x,y,z,])
## bool_vicinal_to_rigid = False
## for coord_rigid in l_coords_rigid:
## dist_from_rigid = math.sqrt(sum((coord_rigid-coord_tmp)**2))
## if dist_from_rigid < 6:
## bool_vicinal_to_rigid = True
## break
## if bool_vicinal_to_rigid == False:
## continue
## bool_vicinal_to_flexible = False
## for coord_flexible in l_coords_flexible:
## dist_from_flexible = math.sqrt(sum((coord_flexible-coord_tmp)**2))
## if dist_from_flexible < 6:
## bool_vicinal_to_flexible = True
## break
## if bool_vicinal_to_flexible == True:
## continue
## min_dist = [1000.,None,]
## for i_coord_alpha in range(len(l_coords_alpha)):
## coord_alpha = l_coords_alpha[i_coord_alpha]
## dist_from_alpha = math.sqrt(sum((coord_alpha-coord_tmp)**2))
## if dist_from_alpha < min_dist[0]:
## min_dist = [dist_from_alpha,i_coord_alpha,]
## if l_amplitudes[min_dist[1]] > average+stddev:
## continue
coord = numpy.array([
x,
y,
z,
])
max_bfactor = bfactor
return coord
import sys
sys.path.append('/home/tc/svn/tc_sandbox/pdb')
import parse_mmCIF, mmCIF2coords
sys.path.append('/home/tc/svn/GoodVibes')
import NMA, visualization
d_mmCIF = parse_mmCIF.main('2lzm', )
d_coords, l_coords_alpha = mmCIF2coords.main('2lzm', d_mmCIF)
cutoff = 10
matrix_hessian = NMA.hessian_calculation(l_coords_alpha, cutoff)
eigenvectors, eigenvalues = NMA.diagonalize_hessian(matrix_hessian, )
visualization.vmd_trajectory('2lzm', l_coords_alpha, eigenvectors)
'1czfA', '1thgA', '1booA', '1iu4A', '1bqcA', '206lA', '1cdeA', '1snzA',
'1gq8A', '1aqlA', '1ps1A', '1s95A', '1pylA', '1ra2A', '1b6bA', '1pntA',
'1e1aA', '2f9rA', '1v04A', '2nlrA', '1n29A', '1pbgA', '5cpaA', '1agmA',
'1byaA', '1r76A', '1u5uA', '1vidA', '1h4gA', '1akdA', '1fy2A', '1xqdA',
'1d6oA', '1qv0A', '1qjeA', '1fvaA', '1bp2A', '1ah7A', '2pthA', '2engA',
'2acyA', '1qazA', '2a0nA', '1dl2A', '1gp5A', '1onrA', '1cwyA', '1pudA',
'1bs9A', '1dinA', '1xyzA', '1bwlA', '1eugA', '1idjA', '1g24A', '1oygA',
'1hzfA', '9papA', '1eb6A', '1ghsA', '1rbnA', '1bixA', '1bs4A', '1celA',
'1hkaA', '1b02A', '1qibA', '1u3fA', '1agyA', '1zioA', '1pa9A', '2tpsA',
'2plcA', '1qk2A', '1j53A', '1m21A',
]
cutoff = 10
for pdb in l_pdbs:
pdb = pdb[:4]
d = parse_mmCIF.main(pdb,)
d_coords, l_coords = mmCIF2coords.main(pdb, d, query_chain = pdb[4:])
matrix_hessian = NMA.hessian_calculation(l_coords, cutoff, verbose = False)
eigenvectors, eigenvalues = NMA.diagonalize_hessian(matrix_hessian, verbose = False)
visualization.vmd_arrows(pdb, l_coords, eigenvectors)
print pdb
stop
def main():
set_pdbs = exclude_include()
l_pdbs_remove = [
'4a3h','2wf5','1arl','1ee3', ## incorrect _struct_ref_seq.pdbx_db_accession
'1uyd','1uye','1uyf','2byh','2byi', ## remediation _struct_ref_seq_dif
'2xdu','3dn8','3dna','1ps3','1ouf','1l35','2eun','1rtc','1zon', ## _struct_ref_seq_dif missing
'1pwl','1pwm','2fz8','2fz9', ## remediation incorrect _struct_ref.pdbx_seq_one_letter_code
]
set_pdbs.remove('1f92') ## remediation _struct_ref_seq_dif incorrect residue number
set_pdbs.remove('2f6f') ## remediation _pdbx_poly_seq_scheme.auth_mon_id wrong
set_pdbs.remove('3a5j') ## remediation _struct_ref_seq_dif.db_mon_id is ? but should be MET
set_pdbs.remove('2rhx') ## remediation _struct_ref_seq_dif.db_mon_id is ? but should be SER
set_pdbs.remove('2fzb') ## remediation incorrect _struct_ref.pdbx_seq_one_letter_code
set_pdbs.remove('2fzd') ## remediation incorrect _struct_ref.pdbx_seq_one_letter_code
set_pdbs.remove('3dn5') ## remediation incorrect _struct_ref.pdbx_seq_one_letter_code
set_pdbs.remove('1x96') ## remediation incorrect _struct_ref.pdbx_seq_one_letter_code
set_pdbs.remove('1x97') ## remediation incorrect _struct_ref.pdbx_seq_one_letter_code
set_pdbs.remove('1x98') ## remediation incorrect _struct_ref.pdbx_seq_one_letter_code
set_pdbs.remove('1z3n') ## GenBank DBref - not an error...
set_pdbs.remove('1z8a') ## GenBank DBref - not an error...
set_pdbs.remove('1z89') ## GenBank DBref - not an error...
set_pdbs.remove('2pf8') ## stupid use of alt_ids (C for highest occupancy and only altloc)
set_pdbs.remove('2pyr') ## stupid use of alt_ids (G and R)
set_pdbs.remove('3pdn') ## stupid use of alt_ids (B and C)
set_pdbs.remove('2v4c') ## alt_id B used for 100% occupancy atoms
set_pdbs.remove('1jxt') ## weird alt_id microheterogeneity...
set_pdbs.remove('1jxu') ## weird alt_id microheterogeneity...
set_pdbs.remove('1jxw') ## weird alt_id microheterogeneity...
set_pdbs.remove('1jxx') ## weird alt_id microheterogeneity...
set_pdbs.remove('1jxy') ## weird alt_id microheterogeneity...
## set_pdbs.remove('1ac4') ## multiple strains and taxonomy ids but all same organism (S. cerevisiae)...
## set_pdbs.remove('1ac8') ## multiple strains and taxonomy ids but all same organism (S. cerevisiae)...
## set_pdbs.remove('1aeb') ## multiple strains and taxonomy ids but all same organism (S. cerevisiae)...
## set_pdbs.remove('2rbt') ## multiple strains and taxonomy ids but all same organism (S. cerevisiae)... UNP A7A026, TAX 307796, STRAIN YJM789
## set_pdbs.remove('2rbu') ## multiple strains and taxonomy ids but all same organism (S. cerevisiae)... UNP A7A026, TAX 307796, STRAIN YJM789
## set_pdbs.remove('2rbv') ## multiple strains and taxonomy ids but all same organism (S. cerevisiae)... UNP A7A026, TAX 307796, STRAIN YJM789
for pdb in l_pdbs_remove:
set_pdbs.remove(pdb)
fd = open('%s/bc-100.out' %(path_mmCIF),'r')
lines = fd.readlines()
fd.close()
for i_line in range(len(lines)):
cluster = i_line
if cluster < 4816:
continue
## if cluster not in [5,]:
## continue
line = lines[i_line]
l_pdbs = line.lower().split()
l_pdbs.sort()
for i_pdb in range(len(l_pdbs)):
l_pdbs[i_pdb] = l_pdbs[i_pdb][:4]
for i_pdb1 in range(0,len(l_pdbs)-1):
pdb1 = l_pdbs[i_pdb1]
## if pdb1 != '1t49': ## tmp!!!
## continue
if not pdb1 in set_pdbs:
continue
print pdb1
stop
d_mmCIF1 = parse_mmCIF.main(pdb1,)
bool_monomeric = check_monomeric(d_mmCIF1)
if bool_monomeric == False:
if i_pdb1 == 0:
break
else:
continue
bool_remediation_modres = check_modres(d_mmCIF1,pdb1,)
if bool_remediation_modres == True:
continue
if '_struct_ref_seq_dif.details' in d_mmCIF1.keys():
if 'DELETION' in d_mmCIF1['_struct_ref_seq_dif.details']:
continue
for i_entity in range(len(d_mmCIF1['_entity.id'])):
if d_mmCIF1['_entity.type'][i_entity] == 'polymer':
if int(d_mmCIF1['_entity.pdbx_number_of_molecules'][i_entity]) != 1:
print d_mmCIF1['_entity.pdbx_number_of_molecules']
print pdb1, cluster
stop
SG1 = d_mmCIF1['_symmetry.space_group_name_H-M']
for i_pdb2 in range(i_pdb1+1,len(l_pdbs)):
pdb2 = l_pdbs[i_pdb2]
## if pdb2 != '2pf8': ## tmp!!!
## continue
## if pdb1 != '3fui' or pdb2 != '3fuj':
## continue
if not pdb2 in set_pdbs:
continue
d_mmCIF2 = parse_mmCIF.main(pdb2,)
bool_monomeric = check_monomeric(d_mmCIF2)
if bool_monomeric == False:
continue
bool_remediation_modres = check_modres(d_mmCIF2,pdb2,)
if bool_remediation_modres == True:
continue
if '_struct_ref_seq_dif.seq_num' in d_mmCIF2.keys():
if 'DELETION' in d_mmCIF2['_struct_ref_seq_dif.details']:
continue
## biounit monomeric?
for i_entity in range(len(d_mmCIF2['_entity.id'])):
if d_mmCIF2['_entity.type'][i_entity] == 'polymer':
if int(d_mmCIF2['_entity.pdbx_number_of_molecules'][i_entity]) != 1:
continue
SG2 = d_mmCIF2['_symmetry.space_group_name_H-M']
if SG1 != SG2:
continue
## parse coordinates again after being shortened in previous loop
try:
d_coords1, l_coords_alpha1 = mmCIF2coords.main(pdb1, d_mmCIF1)
except:
fd = open('remediation_atom_site.label_alt_id.txt','a')
fd.write('%s\n' %(pdb1,))
fd.close()
try:
d_coords2, l_coords_alpha2 = mmCIF2coords.main(pdb2, d_mmCIF2)
except:
fd = open('remediation_atom_site.label_alt_id.txt','a')
fd.write('%s\n' %(pdb2,))
fd.close()
## align sequences/coordinates
try:
l_coords_alpha1, l_coords_alpha2 = create_apo_holo_dataset.sequential_alignment_of_coordinates(
l_coords_alpha1, l_coords_alpha2,
d_mmCIF1, d_mmCIF2,
pdb1, pdb2,
)
except:
fd = open('remediation_struct_ref_seq_dif.txt','a')
fd.write(
'%s %s %s %s\n' %(
pdb1,pdb2,
d_mmCIF1['_struct_ref_seq.pdbx_db_accession'],
d_mmCIF2['_struct_ref_seq.pdbx_db_accession'],
)
)
fd.close()
continue
if len(l_coords_alpha1) != len(l_coords_alpha2):
print d_mmCIF1['_pdbx_poly_seq_scheme.pdb_mon_id']
print d_mmCIF2['_pdbx_poly_seq_scheme.pdb_mon_id']
print 'coords', len(l_coords_alpha1), len(l_coords_alpha2)
print 'seq', len(d_mmCIF1['_pdbx_poly_seq_scheme.pdb_mon_id'])
print 'seq', len(d_mmCIF2['_pdbx_poly_seq_scheme.pdb_mon_id'])
print pdb1, pdb2
d_coords1, l_coords_alpha1 = mmCIF2coords.main(pdb1, d_mmCIF1)
d_coords1, l_coords_alpha2 = mmCIF2coords.main(pdb1, d_mmCIF2)
print len(l_coords_alpha1), len(l_coords_alpha2)
stop
continue
##
## align structure 1 and 2
##
instance_geometry = geometry.geometry()
rmsd = instance_geometry.superpose(l_coords_alpha1,l_coords_alpha2)
tv1 = instance_geometry.fitcenter
rm = instance_geometry.rotation
tv2 = instance_geometry.refcenter
## structural alignment
for i_coord in range(len(l_coords_alpha2)):
l_coords_alpha2[i_coord] = numpy.dot(l_coords_alpha2[i_coord]-tv1,rm)+tv2
##
## vector from structure 1 to 2
##
vector = []
for i in range(len(l_coords_alpha1)):
vector += [
l_coords_alpha1[i][0]-l_coords_alpha2[i][0],
l_coords_alpha1[i][1]-l_coords_alpha2[i][1],
l_coords_alpha1[i][2]-l_coords_alpha2[i][2],
]
vector = numpy.array(vector)
##
## calculate normal modes of structure 1
##
cutoff = 10
try:
matrix_hessian1 = NMA.hessian_calculation(l_coords_alpha1, cutoff, verbose = False)
eigenvectors1, eigenvalues1 = NMA.diagonalize_hessian(matrix_hessian1, verbose = False)
matrix_hessian2 = NMA.hessian_calculation(l_coords_alpha2, cutoff, verbose = False)
eigenvectors2, eigenvalues2 = NMA.diagonalize_hessian(matrix_hessian2, verbose = False)
except:
continue
##
## calculate overlap between normal modes and difference vector
##
eigenvector1 = eigenvectors1[6]
eigenvector2 = eigenvectors2[6]
overlap1 = calc_overlap(eigenvector1,vector)
overlap2 = calc_overlap(eigenvector2,vector)
overlap3a = calc_overlap(eigenvector1,eigenvector2)
overlap3b = calc_overlap(eigenvectors1[6],eigenvectors2[7])
overlap3c = calc_overlap(eigenvectors1[7],eigenvectors2[6])
overlap3 = max(overlap3a,overlap3b,overlap3c)
fd = open('rmsd_v_overlap2/cluster%i.txt' %(i_line),'a')
fd.write('%s %s\n' %(rmsd,overlap1))
fd.close()
fd = open('rmsd_v_overlap2/cluster%i.txt' %(i_line),'a')
fd.write('%s %s\n' %(rmsd,overlap2))
fd.close()
fd = open('rmsd_v_overlap2/cluster%i_ev_v_ev.txt' %(i_line),'a')
fd.write('%s %s\n' %(rmsd,overlap3a))
fd.close()
fd = open('rmsd_v_overlap2/cluster%i_ev_v_ev_max.txt' %(i_line),'a')
fd.write('%s %s\n' %(rmsd,overlap3))
fd.close()
print pdb1, pdb2, 'cluster', i_line, 'size', len(l_pdbs),
print 'overlap', '%4.2f' %(round(overlap1,2)), '%4.2f' %(round(overlap2,2)), '%4.2f' %(round(overlap3,2)), 'rmsd', '%4.2f' %(round(rmsd,2))
return
def parse_GoodVibes_exclude_flexible(pdb,path,):
##
## calculate amplitudes
##
d_mmCIF = parse_mmCIF.main(pdb[:4],)
d_coords, l_coords_alpha = mmCIF2coords.main(pdb[:4],d_mmCIF,query_chain=pdb[-1])
print len(l_coords_alpha)
##
## eigenvector
##
cutoff = 10
matrix_hessian = NMA.hessian_calculation(l_coords_alpha,cutoff,)
eigenvectors, eigenvalues = NMA.diagonalize_hessian(matrix_hessian)
l_amplitudes = [
math.sqrt(
eigenvectors[6][i]**2+eigenvectors[6][i+1]**2+eigenvectors[6][i+2]**2
)
for i in range(0,len(eigenvectors[6]),3)
]
## ## write pdb (color by bfactor)
## l_bfactors = [100*(l_amplitudes[i]-min(l_amplitudes))/(max(l_amplitudes)-min(l_amplitudes)) for i in range(len(l_amplitudes))]
## fd = open('output/%s/%s_%s_probe.pdb' %(path,pdb[:4],pdb[-1],),'r')
## lines = fd.readlines()
## fd.close()
## index = [-1,None,]
## lines_out = []
## for line in lines:
## record = line[:6].strip()
## if record != 'ATOM':
## lines_out += [line]
## else:
## res_no = int(line[22:26])
## if res_no != index[1]:
## index = [index[0]+1,res_no,]
## bfactor = l_bfactors[index[0]]
## line_out = '%s%6.2f%s' %(line[:60],bfactor,line[66:],)
## lines_out += [line_out]
## fd = open('output/%s/%s_%s_probe_color_by_amplitude.pdb' %(path,pdb[:4],pdb[-1],),'w')
## fd.writelines(lines_out)
## fd.close()
## average amplitude
average = sum(l_amplitudes)/len(l_amplitudes)
average,stddev = statistics.do_stddev(l_amplitudes)
##
l_coords_rigid = []
for i in range(len(l_coords_alpha)):
if l_amplitudes[i] < average:
l_coords_rigid += [l_coords_alpha[i]]
l_coords_flexible = []
for i in range(len(l_coords_alpha)):
if l_amplitudes[i] > average+0.5*stddev:
l_coords_flexible += [l_coords_alpha[i]]
## parse output
fd = open('output/%s/%s_%s_probe.pdb' %(path,pdb[:4],pdb[-1],),'r')
lines = fd.readlines()
fd.close()
max_bfactor = None
coord = None
for line in lines:
record = line[:6].strip()
if record not in ['ATOM','HETATM',]:
continue
res_name = line[17:20]
if res_name != 'EXT':
continue
bfactor = float(line[60:66])
if bfactor > max_bfactor:
x = float(line[30:38])
y = float(line[38:46])
z = float(line[46:54])
## coord_tmp = numpy.array([x,y,z,])
## bool_vicinal_to_rigid = False
## for coord_rigid in l_coords_rigid:
## dist_from_rigid = math.sqrt(sum((coord_rigid-coord_tmp)**2))
## if dist_from_rigid < 6:
## bool_vicinal_to_rigid = True
## break
## if bool_vicinal_to_rigid == False:
## continue
## bool_vicinal_to_flexible = False
## for coord_flexible in l_coords_flexible:
## dist_from_flexible = math.sqrt(sum((coord_flexible-coord_tmp)**2))
## if dist_from_flexible < 6:
## bool_vicinal_to_flexible = True
## break
## if bool_vicinal_to_flexible == True:
## continue
## min_dist = [1000.,None,]
## for i_coord_alpha in range(len(l_coords_alpha)):
## coord_alpha = l_coords_alpha[i_coord_alpha]
## dist_from_alpha = math.sqrt(sum((coord_alpha-coord_tmp)**2))
## if dist_from_alpha < min_dist[0]:
## min_dist = [dist_from_alpha,i_coord_alpha,]
## if l_amplitudes[min_dist[1]] > average+stddev:
## continue
coord = numpy.array([x,y,z,])
max_bfactor = bfactor
return coord
'1u3fA',
'1agyA',
'1zioA',
'1pa9A',
'2tpsA',
'2plcA',
'1qk2A',
'1j53A',
'1m21A',
]
cutoff = 10
for pdb in l_pdbs:
pdb = pdb[:4]
d = parse_mmCIF.main(pdb, )
d_coords, l_coords = mmCIF2coords.main(pdb, d, query_chain=pdb[4:])
matrix_hessian = NMA.hessian_calculation(l_coords, cutoff, verbose=False)
eigenvectors, eigenvalues = NMA.diagonalize_hessian(matrix_hessian,
verbose=False)
visualization.vmd_arrows(pdb, l_coords, eigenvectors)
print pdb
stop
