def changeGly(fn, gapinch):
"""
Change Gly to be ACE or NHE
"""
inpdb = fn + "_protein_proc5.pdb"
outpdb = fn + "_protein_proc6.pdb"
nhe = [gapinch[2 * i] + 'A' for i in range(len(gapinch) / 2)]
ace = [gapinch[2 * i + 1] + 'A' for i in range(len(gapinch) / 2)]
f = open(outpdb, "w")
for lines in fileinput.input(inpdb):
if pdbinfo.isAtom(lines) == 1 and lines[22:27] in nhe:
if pdbinfo.atmn(lines) == ' N ':
lines = lines[:17] + 'NHE' + lines[20:]
else:
continue
elif pdbinfo.isAtom(lines) == 1 and lines[22:27] in ace:
if pdbinfo.atmn(lines) == ' C ' or pdbinfo.atmn(lines) == ' O ':
lines = lines[:17] + 'ACE' + lines[20:]
elif pdbinfo.atmn(lines) == ' CA ':
lines = lines[:17] + 'ACE' + lines[20:]
lines = lines[:12] + ' CH3' + lines[16:]
else:
continue
f.write(lines)
fileinput.close()
f.close()
Hg2toFlag(outpdb)
outpdb2 = fn + "_protein_proc7.pdb"
cmd = "pdb4amber -i " + outpdb + " -o " + outpdb2 + " --nohyd 2> pdb4amber3.log"
os.system(cmd)
FlagtoHg2(outpdb)
FlagtoHg2(outpdb2)
gapinch = checkGap2(fn)
return gapinch
def checkGap2(fn):
gap = []
inpdb = fn + "_protein_proc7.pdb"
for lines in fileinput.input("pdb4amber3.log"):
if lines[0:3] == "gap":
line = lines.split()
#id1 = line[-3].split("_")[1]
#id2 = line[-1].split("_")[1]
### change when using in prepare pair-test ###
id1 = line[6]
id2 = line[-1]
id1 = "%4d" % (int(id1))
id2 = "%4d" % (int(id2))
gap.append(id1)
gap.append(id2)
gapb = copy.copy(gap)
gapinch = []
fileinput.close()
if len(gap) > 0:
gapchid = [i for i in range(len(gap))]
for lines in fileinput.input(inpdb):
if pdbinfo.isAtom(lines) == 1 and pdbinfo.resi(lines) in gap:
tmpid = gap.index(pdbinfo.resi(lines))
gapchid[tmpid] = pdbinfo.chid(lines)
gap[tmpid] = 0
fileinput.close()
for i in range(len(gapb) / 2):
if gapchid[2 * i] == gapchid[
2 * i + 1] and int(gapb[2 * i + 1]) - int(gapb[2 * i]) > 1:
gapinch.append(gapb[2 * i])
gapinch.append(gapb[2 * i + 1])
return gapinch
def PCA(fn, residue_PCA):
"""
get the name of files which have PCA
"""
inputfile = open(fn + "_protein.pdb")
for line in inputfile:
if pdbinfo.isAtom(line) == 1 and pdbinfo.resn(
line).split()[0] == "PCA":
residue_PCA.append(fn)
def addTER(fn, gapinch):
inpdb = fn + "_protein_proc_se.pdb"
outpdb = fn + "_protein_proc4.pdb"
halfgap = [gapinch[2 * i + 1] for i in range(len(gapinch) / 2)]
f = open(outpdb, "w")
for lines in fileinput.input(inpdb):
if pdbinfo.isAtom(lines) == 1 and pdbinfo.resi(lines) in halfgap:
f.write("TER \n")
halfgap.remove(pdbinfo.resi(lines))
f.write(lines)
fileinput.close()
f.close()
def Hg2toFlag(filename):
"""
change Hg2+ ion atom name to be FLAG
"""
f = open("tmp", "w")
for lines in fileinput.input(filename):
if pdbinfo.isAtom(lines) == 1 and \
pdbinfo.resn(lines).split()[0] == 'HG':
lines = lines[0:12] + "FLAG" + lines[16::]
f.write(lines)
fileinput.close()
f.close()
os.system("mv tmp " + filename)
def assignPDB1(fn, res):
chid = res.keys()
inpdb = fn + "_protein_proc8_noCYX.pdb"
outpdb = fn + "_protein_proc8_assign1.pdb"
f = open(outpdb, "w")
for lines in fileinput.input(inpdb):
if pdbinfo.isAtom(lines) == 1:
resid = pdbinfo.resi(lines).split()[0]
if resid in chid:
lines = lines[:17] + res[resid] + lines[20:]
f.write(lines)
fileinput.close()
f.close()
def fixFe2(fn):
"""
Change residue FE2 atom name to be FE2
"""
pdbin = fn + "_protein_proc2.pdb"
pdbout = fn + "_protein_proc2_fixFe2.pdb"
f = open(pdbout, "w")
for lines in fileinput.input(pdbin):
if pdbinfo.isAtom(lines) == 1 and pdbinfo.resn(lines) == 'FE2':
lines = lines[0:12] + ' FE2' + lines[16:]
f.write(lines)
f.close()
fileinput.close()
os.system("mv " + pdbout + " " + pdbin)
def rmChain(fn):
"""
remove chains outside 12 A
"""
pktpdb = fn + "_protein_pocket_12.pdb"
protpdb = fn + "_protein_proc1.pdb"
outpdb = fn + "_protein_proc2.pdb"
chidlist = []
for lines in fileinput.input(pktpdb):
if pdbinfo.isAtom(lines) == 1:
if pdbinfo.chid(lines) in chidlist:
continue
else:
chidlist.append(pdbinfo.chid(lines))
fileinput.close()
f = open(outpdb, "w")
for lines in fileinput.input(protpdb):
if pdbinfo.isAtom(lines) == 1 and pdbinfo.chid(lines) not in chidlist:
continue
else:
f.write(lines)
fileinput.close()
f.close()
def rmPCA(fn):
"""
remove PCA from these files
"""
inputfile = open(fn + "_protein.pdb")
outputfile = open(fn + "_protein_tmp.pdb", "w")
for line in inputfile:
if pdbinfo.isAtom(line) == 1 and pdbinfo.resn(
line).split()[0] == "PCA":
continue
else:
outputfile.write(line)
outputfile.close()
os.system("mv " + fn + "_protein_tmp.pdb " + fn + "_protein.pdb")
os.system("rm " + fn + "_tmp.pdb")
def changeRes(fn, res1, res2):
inpdb = fn + "_protein_proc8.pdb"
outpdb = fn + "_protein_prep.pdb"
chid1 = res1.keys()
chid2 = res2.keys()
f = open(outpdb, "w")
for lines in fileinput.input(inpdb):
if pdbinfo.isAtom(lines) == 1:
resid = pdbinfo.resi(lines).split()[0]
if resid in chid1:
lines = lines[:17] + res1[resid] + lines[20:]
elif resid in chid2:
lines = lines[:17] + res2[resid] + lines[20:]
f.write(lines)
fileinput.close()
f.close()
def getProton(fn):
inpdb = fn + "_protein_proc8_assign1.pqr"
proton = {}
for lines in fileinput.input(inpdb):
if pdbinfo.isAtom(lines) == 1:
resn = pdbinfo.resn(lines)
if resn == 'HIS':
resi = pdbinfo.resi(lines).split()[0]
atmn = pdbinfo.atmn(lines)
if resi in proton.keys() and atmn in [' HD1', ' HE2']:
proton[resi][1].append(atmn)
elif resi not in proton.keys():
proton[resi] = [resn, []]
if atmn in [' HD1', 'HE2']:
proton[resi][1].append(atmn)
res = checkProtonState(proton)
return res
def checkGap(fn):
"""
Check the gap information from the pdb4amber22.log file
"""
gap = []
for lines in fileinput.input("pdb4amber22.log"):
if lines[0:3] == "gap":
line = lines.split()
#id1 = line[-3].split("_")[1]
#id2 = line[-1].split("_")[1]
### change when using in prepare pair-test ###
id1 = line[6]
id2 = line[-1]
id1 = "%4d" % (int(id1))
id2 = "%4d" % (int(id2))
gap.append(id1)
gap.append(id2)
gapb = copy.copy(gap)
gapinch = [] # for gap within one chain
fileinput.close()
inpdb = fn + "_protein_proc_se.pdb"
if len(gap) > 0:
gapchid = [i for i in range(len(gap))]
for lines in fileinput.input(inpdb):
if pdbinfo.isAtom(lines) == 1 and pdbinfo.resi(lines) in gap:
tmpid = gap.index(pdbinfo.resi(lines))
gapchid[tmpid] = pdbinfo.chid(lines)
gap[tmpid] = 0
fileinput.close()
for i in range(len(gapb) / 2):
if gapchid[2 * i] == gapchid[2 * i + 1] and int(
gapb[2 * i + 1]
) - int(
gapb[2 * i]
) == 1: # the residues form the gap are close residues in same chain
gapinch.append(gapb[2 * i])
gapinch.append(gapb[2 * i + 1])
return gapinch
