cutoff = 0
reloadPDB = False
reloadCSV = False
extraTag = '3_50'
pdbs = help.getList('70', cutoff, pdbSet + '_ADJ')
#pdbs = ['1ucs','4zm7']
realCsv, badRealCsv, occRealCsv = help.getMaximaDiffs(pdbSet, pdbs, False)
badAtoms = help.getBadList(realCsv, badRealCsv, occRealCsv, 0.05)
if not reloadCSV:
dataPdbUn = help.getCsv('UNRESTRICTED',
pdbs, [], [],
reloadPDB,
reloadCSV,
aa='ALL',
includeCis=False,
allAtoms=True,
bFactorFactor=-1,
cutoff=cutoff)
dataPdb = help.getCsv('RESTRICTED',
pdbs, [], [],
reloadPDB,
reloadCSV,
aa='ALL',
includeCis=False,
allAtoms=False,
bFactorFactor=1.3,
cutoff=cutoff)
dataPdbCut = help.getCsv('RESTRICTED_CUT',
pdbs, [], [],
def createGeosFile(pdbSet,pdbs, badAtoms, cutOff, tag):
print('----------start create geos csv----------')
startx = time.time()
printPath = help.rootPath + '/BbkProject/PhDThesis/0.Papers/3.DefensibleGeometry/EvidencedSet/DataA/'
print('Running CreateGeosFile on',pdbSet)
allAtoms = False
bFactorFactor = 1.3
if pdbSet == 'UNRESTRICTED':
allAtoms = True
bFactorFactor = -1
geos = ['N:CA', 'CA:C', 'C:O', 'C-1:N', 'C:N+1']
print('Create csv 1', pdbSet)
if pdbSet == 'UNRESTRICTED' or pdbSet == 'RESTRICTED':
csv1 = help.getCsv('PDB', pdbs,geos,badAtoms,True, True,aa='ALL',includeCis=False,allAtoms=allAtoms, bFactorFactor=bFactorFactor,cutoff=cutOff)
else:
csv1 = help.getCsv(pdbSet, pdbs, geos, badAtoms, True, True, aa='ALL', includeCis=False, allAtoms=allAtoms,bFactorFactor=bFactorFactor, cutoff=cutOff)
csv1.to_csv(printPath + 'CsvGeos_BEST_' + 'Set1BONDALL_' + pdbSet + tag + '.csv', index=False)
geos = ['TAU', 'C-1:N:CA', 'CA:C:N+1', 'CA:C:O', 'O:C:N+1', 'CA:C:N+1']
print('Create csv 2', pdbSet)
if pdbSet == 'UNRESTRICTED' or pdbSet == 'RESTRICTED':
csv2 = help.getCsv('PDB', pdbs,geos,badAtoms, False, True, aa='ALL', includeCis=False, allAtoms=allAtoms, bFactorFactor=bFactorFactor, cutoff=cutOff)
else:
csv2 = help.getCsv(pdbSet, pdbs, geos, badAtoms, False, True, aa='ALL', includeCis=False, allAtoms=allAtoms,bFactorFactor=bFactorFactor, cutoff=cutOff)
csv2.to_csv(printPath + 'CsvGeos_BEST_' + 'Set2ANGSALL_' + pdbSet + tag + '.csv', index=False)
geos = ['PHI', 'PSI', 'OMEGA', 'CA-1:C-1:N:CA']
print('Create csv 3', pdbSet)
if pdbSet == 'UNRESTRICTED' or pdbSet == 'RESTRICTED':
csv3 = help.getCsv('PDB', pdbs,geos,badAtoms, False, True, aa='ALL', includeCis=False, allAtoms=allAtoms, bFactorFactor=bFactorFactor, cutoff=cutOff)
else:
csv3 = help.getCsv(pdbSet, pdbs, geos, badAtoms, False, True, aa='ALL', includeCis=False, allAtoms=allAtoms, bFactorFactor=bFactorFactor, cutoff=cutOff)
csv3.to_csv(printPath + 'CsvGeos_BEST_' + 'Set3DIHSALL_' + pdbSet + tag + '.csv', index=False)
geos = ['N:N+1', 'N:C']
print('Create csv 4', pdbSet)
if pdbSet == 'UNRESTRICTED' or pdbSet == 'RESTRICTED':
csv4 = help.getCsv('PDB', pdbs,geos,badAtoms, False, True, aa='ALL', includeCis=False, allAtoms=allAtoms,bFactorFactor=bFactorFactor, cutoff=cutOff)
else:
csv4 = help.getCsv(pdbSet, pdbs, geos, badAtoms, False, True, aa='ALL', includeCis=False, allAtoms=allAtoms, bFactorFactor=bFactorFactor, cutoff=cutOff)
csv4.to_csv(printPath + 'CsvGeos_BEST_' + 'Set4DISTALL_' + pdbSet + tag + '.csv', index=False)
geos = ['N:O-2', 'C:O-2', 'N:CA:C:O-2', 'N:CA:N+1:O-2']
print('Create csv 5', pdbSet)
if pdbSet == 'UNRESTRICTED' or pdbSet == 'RESTRICTED':
csv5 = help.getCsv('PDB', pdbs,geos,badAtoms, False, True, aa='ALL', includeCis=False, allAtoms=allAtoms,bFactorFactor=bFactorFactor, cutoff=cutOff)
else:
csv5 = help.getCsv(pdbSet, pdbs, geos, badAtoms, False, True, aa='ALL', includeCis=False, allAtoms=allAtoms, bFactorFactor=bFactorFactor, cutoff=cutOff)
csv5.to_csv(printPath + 'CsvGeos_BEST_' + 'Set5HBALL_' + pdbSet + tag + '.csv', index=False)
geos = ['N:O-3', 'C:O-3', 'N:CA:C:O-3', 'N:CA:N+1:O-3']
print('Create csv 6', pdbSet)
if pdbSet == 'UNRESTRICTED' or pdbSet == 'RESTRICTED':
csv6 = help.getCsv('PDB', pdbs,geos,badAtoms, False, True, aa='ALL', includeCis=False, allAtoms=allAtoms,bFactorFactor=bFactorFactor, cutoff=cutOff)
else:
csv6 = help.getCsv(pdbSet, pdbs, geos, badAtoms, False, True, aa='ALL', includeCis=False, allAtoms=allAtoms, bFactorFactor=bFactorFactor, cutoff=cutOff)
csv6.to_csv(printPath + 'CsvGeos_BEST_' + 'Set6HBALL_' + pdbSet + tag + '.csv', index=False)
print('----------Finished----------')
endx = time.time()
time_diff = endx - startx
timestring = str(int(time_diff / 60)) + "m " + str(int(time_diff % 60)) + "s"
print(timestring)
#create.createGeosFile(pdbSet,0)
# B. Merge the csv files together for comparative analaysis
#merge.mergeCsvs(pdbSet)
'''
Engh&Huber Comparisons
'''
# C. Compare distributions with E&H values
#compare.EHCompare(pdbSet)
'''
SCATTERS AND HISTOGRAMS
'''
# I. Scatters
geos = ['C:N+1', 'N:N+1','TAU', 'PSI', 'PHI', 'C:O','O:C:N+1','CA:C:N+1','CA:C:O']
pdbs = help.getList('TOP20',0)
data = help.getCsv(pdbSet, pdbs,geos,True,True,aa='ALL',includeCis=False,allAtoms=False, bFactorFactor=1.3,cutoff=0)
print(data)
geoTrios = [['PHI', 'PSI', 'TAU'],
['PSI', 'N:N+1', 'TAU'],
['C:O', 'C:N+1', 'PHI'],
['C:O', 'C:N+1', 'PSI'],
['C:O', 'C:N+1', 'TAU'],
['PSI', 'C:N+1', 'TAU'],
['PSI', 'C:N+1', 'PHI'],
['PSI', 'C:O', 'TAU'],
['PSI', 'C:O', 'PHI'],
['PHI', 'C:N+1', 'TAU'],
['PHI', 'C:N+1', 'PSI'],
['PHI', 'C:O', 'TAU'],
['PHI', 'C:O', 'PSI'],
['C:N+1', 'C:O', 'O:C:N+1'],
['N:CA'],
['CA:C'],
['C:O'],
['C:N+1'],
['TAU'],
['CA:C:N+1'],
['CA:C:O'],
['O:C:N+1'],
['C-1:N:CA'],
]
dataPdbUn = help.getCsv('PDB',
pdbs,
geos, [],
True,
True,
aa='ALL',
includeCis=False,
allAtoms=True,
bFactorFactor=-1,
cutoff=0)
dataPdb = help.getCsv('PDB',
pdbs,
geos, [],
True,
True,
aa='ALL',
includeCis=False,
allAtoms=False,
bFactorFactor=1.3,
cutoff=0)
dataPdbCut = help.getCsv('PDB',
scatter.scatterReports(pdbSet,data,geoTrios,pdbSet+'_CYS_tst')
'''
# J. Stats compare
stats.statsCompare(pdbSet, 'RESTRICTED')
#stats.statsCompare(pdbSet, 'UNRESTRICTED')
# K. Stats summary
# geos = ['CA:CB', 'CB:SG', 'N:CA:CB', 'CB:CA:C', 'CA:CB:SG', 'SG:{SG}']
# summary.statsSummary(pdbSet, data, geos, '_DISULFIDE')
geos = [
'N:CA', 'CA:C', 'C:O', 'C:N+1', 'TAU', 'CA:C:N+1', 'CA:C:O', 'O:C:N+1',
'C-1:N:CA'
]
data = help.getCsv(pdbSet, geos, False, True, 'ALL')
summary.statsSummary(pdbSet, data, geos, 'EH')
for pdbSet in pdbSets:
'''
ELECTRON DENSITY
'''
# F. Create density slices for the rejected density
# if pdbSet not in ['RESTRICTED', 'UNRESTRICTED']:
# bad.createBadDensitySlices(pdbSet, 'CA', 'N', 'C')
# bad.createBadDensitySlices(pdbSet, 'C', 'CA', 'O')
# G. Create density slcies for the good outliers
# geoset = []
# geoset.append([['CA', 'N', 'C'],['N:CA', 'CA:C', 'TAU']])
# geoset.append([['C', 'CA', 'O'], ['C:O', 'CA:C:O']])