#filesPDBRoot ='C:/Dev/Github/ProteinDataFiles/pdb_data/'
#filesADJRoot ='C:/Dev/Github/ProteinDataFiles/pdb_out/Fov2_ADJ/' #adjusted on Fo at 3 degrees thevenaz
#loadPath = 'C:/Dev/Github/BbkProject/PhDThesis/5.Chapters/1_Summer/CSV/'
#printPath = 'C:/Dev/Github/BbkProject/PhDThesis/5.Chapters/1_Summer/Data/'
geos = [
'TAU', 'TAU+1', 'TAU-1', 'CA:C:O', 'O:C:N+1', 'CA-1:CA:CA+1', 'N:CA:O',
'CA:O:N+1', 'O-1:N:CA', 'O-1:C-1', 'C-1:N', 'N:CA', 'CA:C', 'C:O', 'C:N+1',
'N+1:CA+1', 'CA+1:C+1', 'C+1:O+1', 'PHI', 'PSI', 'OMEGA', 'CA-1:C-1:N:CA',
'CA-1:CA', 'CA:CA+1', 'C-1:C', 'C:C+1', 'N-1:N', 'N:N+1', 'CA-1:N',
'CA-1:O-1', 'O-1:N', 'C-1:CA', 'N:C', 'CA:O', 'CA:N+1', 'O:N+1', 'C:CA+1',
'N+1:C+1', 'O-1:CA', 'N:O', 'O:CA+1', 'N+1:O+1', 'N-1:O-1'
]
print('### CREATING cut csv file ###')
pdbListIn = help.getPDBList()
print("---- Getting bad atom list--------")
badAtoms = help.getBadAtomsListFromFile(
) # Get the bad atoms list we will use to reduce the list further
print("---- Making unrestricted--------")
#dataPdbRes = help.makeCsv('PDB', pdbListIn, geos, [],False)
dataPdbRes = pd.read_csv(help.loadPath + "bb_restricted_a.csv")
dataPdbRes.to_csv(help.loadPath + "bb_restricted_a.csv", index=False)
dataPdbRes = help.applyRestrictions(dataPdbRes, True, True, True, True, False)
dataPdbRes.to_csv(help.loadPath + "bb_restricted_b.csv", index=False)
dataPdbRes = help.embellishCsv(dataPdbRes)
print("---- Save to", help.loadPath + "bb_restricted.csv", '-------')
import pandas as pd
import Ch000_Functions as help
from PsuGeometry import GeoReport as psu
pdblist = help.getPDBList100()
pdblist.sort()
#pdblist = pdblist[:10]
hueList = ['aa', 'rid', 'bfactor', 'pdbCode', 'bfactorRatio', 'disordered','occupancy','dssp']
dsspPrintPath = '../../PdbLists/'
georep = psu.GeoReport(pdblist, help.pdbDataPathLx, help.edDataPath, dsspPrintPath, ed=False, dssp=True, includePdbs=False, keepDisordered=True)
datacsv = georep.getGeoemtryCsv(['N:CA'],hueList)
datacsv = datacsv[['pdbCode','chain','rid','aa','dssp']]
print(datacsv)
if False:#don;t accidentally run this and replace it
datacsv.to_csv(dsspPrintPath + 'dssp.csv', index=False)
print(datacsv)
import pandas as pd
import Ch000_Functions as help
from PsuGeometry import GeoPdb as geopdb
from PsuGeometry import CloseContact as geocc
from PsuGeometry import GeoReport as psu
pdbListIn = help.getPDBList()
contactslist = []
for pdb in pdbListIn:
print(pdb)
try:
import os.path
iscc = os.path.isfile((help.loadPath + "CloseContacts/CloseContacts_" +
pdb + ".csv").lower())
if iscc:
ccdata = pd.read_csv(help.loadPath +
"CloseContacts/CloseContacts_" + pdb + ".csv")
ccdata['ridA'] = ccdata['ridA'].astype(str)
ccdata['ChRid'] = ccdata['chainA'] + ccdata['ridA']
cc = ccdata[['pdbCode', 'ChRid']].groupby('ChRid').agg('count')
cc['ChRid'] = cc.index
cc.columns = ['Contacts', 'ChRid']
cc['pdbCode'] = pdb
cc['CID'] = cc['pdbCode'] + cc['ChRid']
contactslist.append(cc)
except:
print('Error with', pdb)
ccall = pd.concat(contactslist)
ccall.to_csv(help.loadPath + "Contacts_List.csv", index=False)
print('Merging')
#printPath = 'C:/Dev/Github/BbkProject/PhDThesis/5.Chapters/1_Summer/Data/'
geos = [
'TAU', 'TAU+1', 'TAU-1', 'CA:C:O', 'O:C:N+1', 'CA-1:CA:CA+1', 'N:CA:O',
'CA:O:N+1', 'O-1:N:CA', 'O-1:C-1', 'C-1:N', 'N:CA', 'CA:C', 'C:O', 'C:N+1',
'N+1:CA+1', 'CA+1:C+1', 'C+1:O+1', 'PHI', 'PSI', 'OMEGA', 'CA-1:C-1:N:CA',
'CA-1:CA', 'CA:CA+1', 'C-1:C', 'C:C+1', 'N-1:N', 'N:N+1', 'CA-1:N',
'CA-1:O-1', 'O-1:N', 'C-1:CA', 'N:C', 'CA:O', 'CA:N+1', 'O:N+1', 'C:CA+1',
'N+1:C+1', 'O-1:CA', 'N:O', 'O:CA+1', 'N+1:O+1', 'N-1:O-1'
]
title = 'Backbone Report'
fileName = 'backbone'
print('### CREATING csv files ###')
pdbListIn = help.getPDBList()
#we want to look at ALL adjusted without the bad list
print("---- Making adjusted--------")
dataPdbAdj = help.makeCsv('ADJUSTED', pdbListIn, geos, [], False)
dataPdbAdj = help.applyRestrictions(dataPdbAdj)
dataPdbAdj = help.embellishCsv(dataPdbAdj)
# embellish with dssp - the dssp file was created ages ago from the linux laptop
pdbdssp = pd.read_csv(
'C:/Dev/Github/BbkProject/PhDThesis/5.Chapters/1_Summer/CSV/CsvGeos_BEST_Set0DSSPALL.csv'
)
pdbdata = pd.read_csv('../../PdbLists/Pdbs_100.csv')
#embellish with dssp, resolution and software
import pandas as pd
import Ch000_Functions as help
import matplotlib
print(matplotlib.__version__)
geos = [
'TAU', 'TAU+1', 'TAU-1', 'CA:C:O', 'O:C:N+1', 'CA-1:CA:CA+1', 'N:CA:O',
'CA:O:N+1', 'O-1:N:CA', 'O-1:C-1', 'C-1:N', 'N:CA', 'CA:C', 'C:O', 'C:N+1',
'N+1:CA+1', 'CA+1:C+1', 'C+1:O+1', 'PHI', 'PSI', 'OMEGA', 'CA-1:C-1:N:CA',
'CA-1:CA', 'CA:CA+1', 'C-1:C', 'C:C+1', 'N-1:N', 'N:N+1', 'CA-1:N',
'CA-1:O-1', 'O-1:N', 'C-1:CA', 'N:C', 'CA:O', 'CA:N+1', 'O:N+1', 'C:CA+1',
'N+1:C+1', 'O-1:CA', 'N:O', 'O:CA+1', 'N+1:O+1', 'N-1:O-1'
]
print('### CREATING csv files ###')
pdbListIn = help.getPDBList()
print("---- Getting bad atom list--------")
badAtoms = help.getBadAtomsListFromFile(
) # Get the bad atoms list we will use to reduce the list further
print("---- Making adjusted--------")
dataPdbAdj = help.makeCsv('ADJUSTEDLAP', pdbListIn, geos, badAtoms, False)
#dataPdbAdj = pd.read_csv(help.loadPath + "bblap_adjusted_a.csv")
dataPdbAdj.to_csv(help.loadPath + "bblap_adjusted_a.csv", index=False)
dataPdbAdj = help.embellishCsv(dataPdbAdj)
dataPdbAdj = help.applyRestrictions(dataPdbAdj, True, True, True, True, False)
dataPdbAdj.to_csv(help.loadPath + "bblap_adjusted_b.csv", index=False)
print("---- Save to", help.loadPath + "bblap_adjusted.csv", '-------')
In this file we compare individual geos
to see if any pdbs are problematic
'''
import pandas as pd
import Ch000_Functions as help
from PsuGeometry import GeoReport as psu
print('### LOADING csv files ###')
dataPdbUn = pd.read_csv(help.loadPath + "bb_unrestricted.csv")
dataPdbRes = pd.read_csv(help.loadPath + "bb_restricted.csv")
dataPdbCut = pd.read_csv(help.loadPath + "bb_reduced.csv")
dataPdbAdj = pd.read_csv(help.loadPath + "bbden_adjusted.csv")
dataPdbLap = pd.read_csv(help.loadPath + "bblap_adjusted.csv")
# ensure data is correctly restricted
dataPdbUn = help.applyRestrictions(dataPdbUn, True, False, False, False, False)
dataPdbRes = help.applyRestrictions(dataPdbRes, True, True, True, True, False)
dataPdbCut = help.applyRestrictions(dataPdbCut, True, True, True, True, True)
dataPdbAdj = help.applyRestrictions(dataPdbAdj, True, True, True, False, True)
dataPdbLap = help.applyRestrictions(dataPdbLap, True, True, True, False, True)
tag = ''
#SHale we cut on bfactor factor?
BFactorFactor = True
if BFactorFactor:
tag = '_bff'
dataPdbRes = dataPdbRes.query('bfactorRatio <= 1.2')
dataPdbCut = dataPdbCut.query('bfactorRatio <= 1.2')
dataPdbAdj = dataPdbAdj.query('bfactorRatio <= 1.2')
dsspList = dataPdbUn["dssp"].unique()
'C-1:C', 'C:C+1', 'N-1:N', 'N:N+1', 'CA-1:N', 'CA-1:O-1', 'O-1:N',
'C-1:CA', 'N:C', 'CA:O', 'CA:N+1', 'O:N+1', 'C:CA+1', 'N+1:C+1', 'O-1:CA',
'N:O', 'O:CA+1', 'N+1:O+1', 'N-1:O-1'
]
title = 'Finding evidential residues'
fileName = 'evidential'
print('### LOADING csv files ###'
) # bit rubbish but we didn;t change the object references with dssp
dataPdbCut = pd.read_csv(help.loadPath + "bb_reduced.csv")
dataPdbAdj = pd.read_csv(help.loadPath + "bbden_adjusted.csv")
dataPdbLap = pd.read_csv(help.loadPath + "bblap_adjusted.csv")
# Find restrictions
#Reduced On lap-diff <0.02
ev1DataPdbCut = help.applyRestrictions(dataPdbCut, True, True, True, True,
True)
ev1DataPdbAdj = help.applyRestrictions(dataPdbAdj, True, True, True, False,
True)
ev1DataPdbLap = help.applyRestrictions(dataPdbLap, True, True, True, False,
True)
#Reduced on resolution
ev2DataPdbCut = ev1DataPdbCut.query('RES < 0.85')
ev2DataPdbAdj = ev1DataPdbAdj.query('RES < 0.85')
ev2DataPdbLap = ev1DataPdbLap.query('RES < 0.85')
print('### Creating scatter files ###')
georep = psu.GeoReport([],
"",
"",
help.printPath,
'C-1:CA', 'N:C', 'CA:O', 'CA:N+1', 'O:N+1', 'C:CA+1', 'N+1:C+1', 'O-1:CA',
'N:O', 'O:CA+1', 'N+1:O+1', 'N-1:O-1'
]
title = 'Backbone Report'
fileName = 'backbone'
print('### LOADING csv files ###'
) # bit rubbish but we didn;t change the object references with dssp
dataPdbUn = pd.read_csv(help.loadPath + "bb_unrestricted.csv")
dataPdbRes = pd.read_csv(help.loadPath + "bb_restricted.csv")
dataPdbCut = pd.read_csv(help.loadPath + "bb_reduced.csv")
dataPdbAdj = pd.read_csv(help.loadPath + "bbden_adjusted.csv")
dataPdbLap = pd.read_csv(help.loadPath + "bblap_adjusted.csv")
# ensure data is correctly restricted
dataPdbUn = help.applyRestrictions(dataPdbUn, True, False, False, False, False)
dataPdbRes = help.applyRestrictions(dataPdbRes, True, True, True, True, False)
dataPdbCut = help.applyRestrictions(dataPdbCut, True, True, True, True, True)
dataPdbAdj = help.applyRestrictions(dataPdbAdj, True, True, True, False, True)
dataPdbLap = help.applyRestrictions(dataPdbLap, True, True, True, False, True)
tag = '_lap'
#SHale we cut on bfactor factor?
BFactorFactor = False
if BFactorFactor:
tag = '_bff'
dataPdbCut = dataPdbCut.query('bfactorRatio <= 1.2')
dataPdbRes = dataPdbRes.query('bfactorRatio <= 1.2')
dataPdbAdj = dataPdbAdj.query('bfactorRatio <= 1.2')
dataPdbLap = dataPdbLap.query('bfactorRatio <= 1.2')
createOrLoad = "CREATE" # CREATE or LOAD
if createOrLoad == "LOAD":
print('### CREATING csv files ###')
pdbdata = pd.read_csv('../../PdbLists/Pdbs_70.csv')
pdbListA = pdbdata['PDB'].tolist()[0:]
pdbListIn = []
for pdb in pdbListA:
import os.path
if os.path.isfile((filesADJRoot + 'pdb' + pdb + '.ent').lower()):
pdbListIn.append(pdb.lower())
else:
print('No file:', (filesADJRoot + 'pdb' + pdb + '.ent').lower())
print(pdbListIn)
print("---- Getting bad atom list--------")
badAtoms = help.getBadAtomsListFromFile(
loadPath, "badatoms.csv"
) # Get the bad atoms list we will use to reduce the list further
print("---- Making unrestricted--------")
dataPdbUn = help.makeCsv('PDB', pdbListIn, geos, [], True)
print("---- Making unrestricted--------")
dataPdbRes = help.makeCsv('PDB', pdbListIn, geos, [], False)
dataPdbRes = help.applyRestrictions(dataPdbRes)
print("---- Making reduced--------")
dataPdbCut = help.makeCsv('PDB', pdbListIn, geos, badAtoms, False)
dataPdbCut = help.applyRestrictions(dataPdbCut)
print("---- Making adjusted--------")
dataPdbAdj = help.makeCsv('ADJUSTED', pdbListIn, geos, badAtoms, False)
dataPdbAdj = help.applyRestrictions(dataPdbAdj)
# embellish with dssp - the dssp file was created ages ago from the linux laptop
pdbdssp = pd.read_csv(
'C:/Dev/Github/BbkProject/PhDThesis/5.Chapters/1_Summer/CSV/CsvGeos_BEST_Set0DSSPALL.csv'
#loadPath = 'C:/Dev/Github/BbkProject/PhDThesis/5.Chapters/1_Summer/CSV/'
#printPath = 'C:/Dev/Github/BbkProject/PhDThesis/5.Chapters/1_Summer/Data/'
title = 'Hydrogen bonding Report'
fileName = 'hydrogenbonding'
print('### LOADING csv files ###'
) # bit rubbish but we didn;t change the object references with dssp
#dataPdbUn = pd.read_csv(help.loadPath + "hb_unrestricted.csv")
#dataPdbRes = pd.read_csv(help.loadPath + "hb_restricted.csv")
dataPdbCut = pd.read_csv(help.loadPath + "hb_reduced.csv")
dataPdbAdj = pd.read_csv(help.loadPath + "hb_adjusted.csv")
# ensure data is correctly restricted
#dataPdbUn = help.applyRestrictions(dataPdbUn,True,False,False,False)
dataPdbCut = help.applyRestrictions(dataPdbCut, True, True, True, True)
#dataPdbRes = help.applyRestrictions(dataPdbRes,True,True,True,True)
dataPdbAdj = help.applyRestrictions(dataPdbAdj, True, True, True, False)
tag = ''
#SHale we cut on bfactor factor?
BFactorFactor = False
if BFactorFactor:
tag = '_bff'
dataPdbCut = dataPdbCut.query('bfactorRatio <= 1.2')
#dataPdbRes = dataPdbRes.query('bfactorRatio <= 1.2')
dataPdbAdj = dataPdbAdj.query('bfactorRatio <= 1.2')
print('### Creating scatter files ###')
'''
geos = ['TAU','TAU+1',
descdataPdbCut = pd.read_csv(help.loadPath + "DescribeGeos_Cut.csv")
descdataPdbAdj = pd.read_csv(help.loadPath + "DescribeGeos_AdjustedMax.csv")
descdataPdbLap = pd.read_csv(help.loadPath + "DescribeGeos_AdjustedLap.csv")
print('### Creating scatter files ###')
geoTriosA = [
['C:O mean'],['C:O 50%'],
['N:CA mean'],['N:CA 50%'],
['CA:C mean'],['CA:C 50%'],
['C:N+1 mean'],['C:N+1 50%'],
['TAU mean'],['TAU 50%'],
['C:O mean', 'C:O count', 'C:O 50%', False],
['C:O mean', 'N:CA mean', 'CA:C mean',False],
]
namesCsvs = []
namesCsvs.append(["Unrestricted",descdataPdbUn])
namesCsvs.append(["Restricted",descdataPdbRes])
namesCsvs.append(["Reduced",descdataPdbCut])
namesCsvs.append(["Density Adjusted",descdataPdbAdj])
namesCsvs.append(["Laplacian Adjusted",descdataPdbLap])
help.trioReports(namesCsvs, geoTriosA, title,help.printPath,fileName + "")
import Ch000_Functions as help
import matplotlib
print(matplotlib.__version__)
geos = ['TAU','TAU+1','TAU-1','CA:C:O','O:C:N+1','CA-1:CA:CA+1',
'N:CA:O','CA:O:N+1','O-1:N:CA',
'O-1:C-1','C-1:N','N:CA','CA:C','C:O','C:N+1','N+1:CA+1','CA+1:C+1','C+1:O+1',
'PHI','PSI','OMEGA','CA-1:C-1:N:CA',
'CA-1:CA','CA:CA+1','C-1:C','C:C+1','N-1:N','N:N+1',
'CA-1:N','CA-1:O-1','O-1:N','C-1:CA','N:C','CA:O','CA:N+1','O:N+1','C:CA+1','N+1:C+1',
'O-1:CA','N:O','O:CA+1','N+1:O+1','N-1:O-1']
print('### CREATING cut csv file ###')
pdbListIn = help.getPDBList()
print("---- Getting bad atom list--------")
badAtoms = help.getBadAtomsListFromFile() # Get the bad atoms list we will use to reduce the list further
print("---- Making unrestricted--------")
dataPdbUn = help.makeCsv('PDB', pdbListIn, geos, [],True)
#dataPdbUn = pd.read_csv(help.loadPath + "bb_unrestricted_a.csv")
dataPdbUn.to_csv(help.loadPath + "bb_unrestricted_a.csv", index=False)
dataPdbUn = help.applyRestrictions(dataPdbUn,True,False,False,False,False)
dataPdbUn.to_csv(help.loadPath + "bb_unrestricted_b.csv", index=False)
dataPdbUn = help.embellishCsv(dataPdbUn)
print("---- Save to",help.loadPath + "bb_unrestricted.csv",'-------')
dataPdbUn.to_csv(help.loadPath + "bb_unrestricted.csv", index=False)