# -- ©Rachel Alcraft 2020, PsuGeometry --
from PsuGeometry import GeoReport as geor
from PsuGeometry import GeoPdbLists as geol
import pandas as pd
'''
This script replicates results from Jaskolski et al 2007
'''
pdbDataPath = '/home/rachel/Documents/Bioinformatics/ProteinDataFiles/pdb_data/'
edDataPath = '/home/rachel/Documents/Bioinformatics/ProteinDataFiles/ccp4_data/'
printPath = '/home/rachel/Documents/Bioinformatics/ProteinDataFiles/results_psu/Paper01/'
pdbList = geol.GeoPdbLists().getListJask()
georep = geor.GeoReport(pdbList,
pdbDataPath,
edDataPath,
printPath,
ed=False,
dssp=False,
includePdbs=False)
geoList = ['N:CA', 'CA:C', 'C:O', 'C-1:N']
hueList = ['dssp', 'aa', 'bfactor', 'resolution']
data = georep.getGeoemtryCsv(geoList, hueList)
for pdb in pdbList:
datapdb = data[data['pdbCode'] == pdb]
georep.addHistogram(data=datapdb,
geoX='N:CA',
title=pdb + ' N:CA',
exclusions={'aa': 'PRO,GLY'})
georep.addHistogram(data=datapdb,
# -- ©Rachel Alcraft 2020, PsuGeometry --
from PsuGeometry import GeoReport as psu
from PsuGeometry import GeoPdbLists as geol
import random
'''
TAU correlations
'''
###############################################################################################
myWindowsLaptop = False
keepDisordered = True
bfactorFactor = -1
pdbList1000 = geol.GeoPdbLists().getListPaper()
#random.shuffle(pdbList1000)
#pdbList1000 = pdbList1000[:200]
geoList = [
'N:N+1', 'TAU', 'PHI', 'PSI', 'N:O', 'OMEGA', 'C-1:N:CA', 'CA:C:N+1'
]
hueList = ['dssp', 'aa', 'rid', 'bfactor']
aas = ['GLY']
###################################################################################
pdbDataPath = '/home/rachel/Documents/Bioinformatics/ProteinDataFiles/pdb_data/'
edDataPath = '/home/rachel/Documents/Bioinformatics/ProteinDataFiles/ccp4_data/'
printPath = '/home/rachel/Documents/Bioinformatics/ProteinDataFiles/results_psu/Paper02/'
if myWindowsLaptop:
pdbDataPath = 'F:/Code/ProteinDataFiles/pdb_data/'
edDataPath = 'F:/Code/ProteinDataFiles/ccp4_data/'
printPath = 'F:/Code/ProteinDataFiles/results_psu/Paper02/'
###########################################################################################
georep = psu.GeoReport(pdbList1000,
# -- ©Rachel Alcraft 2020, PsuGeometry -- from PsuGeometry import GeoReport as geor from PsuGeometry import GeoPdbLists as geol ''' This script looks at distributions aournf the carbonyl atom ''' pdbDataPath = '/home/rachel/Documents/Bioinformatics/ProteinDataFiles/pdb_data/' edDataPath = '/home/rachel/Documents/Bioinformatics/ProteinDataFiles/ccp4_data/' printPath = '/home/rachel/Documents/Bioinformatics/ProteinDataFiles/results_psu/' pdbList = geol.GeoPdbLists().getList100() georep = geor.GeoReport(pdbList, pdbDataPath, edDataPath, printPath,ed=False,dssp=False,includePdbs=False) #geoList = ['CA:C','C:O','C:N+1','CA:N+1','O:N+1','CA:O'] #hueList = ['dssp','aa','bfactor','resolution'] #data = georep.getGeoemtryCsv(geoList,hueList) #bond lengths georep.addHistogram(geoX='CA:C', title='CA:C') georep.addHistogram(geoX='C:O', title='C:O') georep.addHistogram(geoX='C:N+1', title='C:N+1') #distances georep.addHistogram(geoX='CA:N+1', title='CA:N+1') georep.addHistogram(geoX='O:N+1', title='O:N+1') georep.addHistogram(geoX='CA:O', title='CA:O') #angles georep.addHistogram(geoX='CA:C:N+1', title='CA:C:N+1') georep.addHistogram(geoX='N+1:C:O', title='N+1:C:O') georep.addHistogram(geoX='O:C:CA', title='O:C:CA') #dihedrals georep.addHistogram(geoX='CA:C:N+1:O', title='CA:C:N+1:O',operation='ABS') georep.addHistogram(geoX='N+1:C:O:CA', title='N+1:C:O:CA',operation='ABS')