def validGeometry_DHAB(self, tags1, tags2, reslines1,
reslines2): ## implement in subclasses
## D and H coordinates from reslines1
Dcrd, Hcrds = self.DHcrd(reslines1, tags1)
## A and B coordinates from reslines2
Acrd, Bcrd, Aatomname, Batomname = None, None, None, None
for tat in tags2:
if tat.tag == 'A': Aatomname = tat.atn
if tat.tag == 'B': Batomname = tat.atn
for rl in reslines2:
if Aatomname == line2atomname(rl): Acrd = line2crd(rl)
if Batomname == line2atomname(rl): Bcrd = line2crd(rl)
## limit checks
tag2points = {}
tag2points['D'] = Dcrd
tag2points['A'] = Acrd
tag2points['B'] = Bcrd
if len(Hcrds) == 0:
Hcrds = [
(1e6, 1e6, 1e6)
] ## probably hydrogens have no role in this intxn, thats why they were not discovered
for hcrd in Hcrds:
tag2points['H'] = hcrd
all_lims_satisfied = 1
for l in self.lims:
#print tag2points
if not l.check(tag2points):
all_lims_satisfied = 0
break
if all_lims_satisfied == 1: return pymol_line(Dcrd, Acrd)
return None
def validGeometry_DHAB(self, tags1, tags2, reslines1, reslines2) : ## implement in subclasses
## D and H coordinates from reslines1
Dcrd, Hcrds = self.DHcrd(reslines1, tags1)
## A and B coordinates from reslines2
Acrd, Bcrd, Aatomname, Batomname = None, None, None, None
for tat in tags2 :
if tat.tag == 'A' : Aatomname = tat.atn
if tat.tag == 'B' : Batomname = tat.atn
for rl in reslines2 :
if Aatomname == line2atomname(rl) : Acrd = line2crd(rl)
if Batomname == line2atomname(rl) : Bcrd = line2crd(rl)
## limit checks
tag2points = {}
tag2points['D'] = Dcrd
tag2points['A'] = Acrd
tag2points['B'] = Bcrd
if len(Hcrds) == 0 : Hcrds = [(1e6,1e6,1e6)] ## probably hydrogens have no role in this intxn, thats why they were not discovered
for hcrd in Hcrds :
tag2points['H'] = hcrd
all_lims_satisfied = 1
for l in self.lims :
#print tag2points
if not l.check(tag2points) :
all_lims_satisfied = 0
break
if all_lims_satisfied == 1 : return pymol_line(Dcrd, Acrd)
return None
def validGeometry_contact(self, tags1, tags2, reslines1, reslines2,
atomnbrs): ## implement in subclasses
contact = None
for an1 in tags1:
if contact: break
for an2 in tags2:
if contact: break
if (an1.atn, an2.atn) in atomnbrs: contact = 1
if not contact: return None
c1, c2, H1crd, H2crd = 0, 0, [
0.,
0.,
0.,
], [
0.,
0.,
0.,
]
for rl in reslines1:
for an in tags1:
if line2atomname(rl) == an.atn:
H1crd = vec_add(H1crd, line2crd(rl))
c1 = c1 + 1
for rl in reslines2:
for an in tags2:
if line2atomname(rl) == an.atn:
H2crd = vec_add(H2crd, line2crd(rl))
c2 = c2 + 1
H1crd = vec_scale(H1crd, 1. / c1)
H2crd = vec_scale(H2crd, 1. / c2)
return pymol_line(H1crd, H2crd)
def DHcrd(self, reslines, tags) : Datomname = None for tat in tags : if tat.tag == 'D' : Datomname = tat.atn Hatomname = '.H' + Datomname[2:4] Dcrd, Hcrds = None, [] for rl in reslines : if re.compile(Hatomname).search(line2atomname(rl)) : Hcrds.append(line2crd(rl)) if Datomname == line2atomname(rl) : Dcrd = line2crd(rl) return Dcrd, Hcrds
def DHcrd(self, reslines, tags):
Datomname = None
for tat in tags:
if tat.tag == 'D': Datomname = tat.atn
Hatomname = '.H' + Datomname[2:4]
Dcrd, Hcrds = None, []
for rl in reslines:
if re.compile(Hatomname).search(line2atomname(rl)):
Hcrds.append(line2crd(rl))
if Datomname == line2atomname(rl): Dcrd = line2crd(rl)
return Dcrd, Hcrds
def fixCNSop(pdbfile) :
from pdbr import isPdbAAline, isPdbAtomLine, line2atomname, line2resn
lines = []
for l in open(pdbfile, 'r').readlines() :
if not isPdbAAline(l) : lines.append(l)
elif line2resn(l) == "ILE" and line2atomname(l) == " CD " : lines.append(re.sub(" CD ", " CD1", l))
elif line2atomname(l) == " OT1" : lines.append(re.sub(" OT1", " O ", l))
elif line2atomname(l) == " OXT" : continue
else : lines.append(l)
op = open(pdbfile, 'w')
for l in lines : op.write(l)
op.close()
def validPartners(self, reslines1, reslines2, atomnbrs, justOnePerPair=1):
a1, a2 = [], []
res1, res2 = line2resid(reslines1[0]), line2resid(reslines2[0])
resn1, resn2 = line2resn(reslines1[0]), line2resn(reslines2[0])
print "Checking " + self.name + "-" + res1 + "-" + res2 + "-"
for l in reslines1:
assert line2resid(l) == res1
a1.append(line2atomname(l))
for l in reslines2:
assert line2resid(l) == res2
a2.append(line2atomname(l))
## does res1 qualify to be D-partner in this interaction ?
tags1 = self.acceptableResidue(resn1, 'D', a1)
if not tags1: print res1, 'doesnt qualify as D'
## does res2 qualify to be A-partner in this interaction ?
tags2 = self.acceptableResidue(resn2, 'A', a2)
if not tags2: print res2, 'doesnt qualify as A'
if not tags1 or not tags2: return None
lines = []
## check if tags1, tags2 are voronoi nbrs
for t1 in tags1:
atn1 = []
for t in t1:
atn1.append(t.atn)
for t2 in tags2:
atn2 = []
for t in t2:
atn2.append(t.atn)
vornbrs = None
for an1, an2 in atomnbrs:
if an1 in atn1 and an2 in atn2:
vornbrs = 1
break
if not vornbrs:
print "Reqd atoms are not voronoi nbrs"
continue
ret = None
if self.type == 'DHAB':
ret = self.validGeometry_DHAB(t1, t2, reslines1, reslines2)
elif self.type == 'DHR':
ret = self.validGeometry_DHR(t1, t2, reslines1, reslines2)
elif self.type == 'RR':
ret = self.validGeometry_RR(t1, t2, reslines1, reslines2)
elif self.type == 'contact':
ret = self.validGeometry_contact(t1, t2, reslines1,
reslines2, atomnbrs)
else:
assert 1 == 0
if ret:
if justOnePerPair: return [ret]
else: lines.append(ret)
if len(lines) > 0: return lines
return None
def validPartners(self, reslines1, reslines2, atomnbrs, justOnePerPair=1) : a1, a2 = [], [] res1, res2 = line2resid(reslines1[0]), line2resid(reslines2[0]) resn1, resn2 = line2resn(reslines1[0]), line2resn(reslines2[0]) print "Checking " + self.name + "-" + res1 + "-" + res2 + "-" for l in reslines1 : assert line2resid(l) == res1 a1.append(line2atomname(l)) for l in reslines2 : assert line2resid(l) == res2 a2.append(line2atomname(l)) ## does res1 qualify to be D-partner in this interaction ? tags1 = self.acceptableResidue(resn1, 'D', a1) if not tags1 : print res1, 'doesnt qualify as D' ## does res2 qualify to be A-partner in this interaction ? tags2 = self.acceptableResidue(resn2, 'A', a2) if not tags2 : print res2, 'doesnt qualify as A' if not tags1 or not tags2 : return None lines = [] ## check if tags1, tags2 are voronoi nbrs for t1 in tags1 : atn1 = [] for t in t1 : atn1.append(t.atn) for t2 in tags2 : atn2 = [] for t in t2 : atn2.append(t.atn) vornbrs = None for an1,an2 in atomnbrs : if an1 in atn1 and an2 in atn2 : vornbrs = 1 break if not vornbrs : print "Reqd atoms are not voronoi nbrs" continue ret = None if self.type == 'DHAB' : ret = self.validGeometry_DHAB(t1, t2, reslines1, reslines2) elif self.type == 'DHR' : ret = self.validGeometry_DHR(t1, t2, reslines1, reslines2) elif self.type == 'RR' : ret = self.validGeometry_RR(t1, t2, reslines1, reslines2) elif self.type == 'contact' : ret = self.validGeometry_contact(t1, t2, reslines1, reslines2, atomnbrs) else : assert 1==0 if ret : if justOnePerPair : return [ret] else : lines.append(ret) if len(lines) > 0 : return lines return None
def keepMClinesOnly2(pdbfn,pdbout) :
from pdbr import isPdbAAline, isPdbAtomLine, line2atomname
lines = []
for l in open(pdbfn, 'r').readlines() :
if not isPdbAtomLine(l) : lines.append(l)
elif isPdbAAline(l) and line2atomname(l) in [" N "," CA "," C "," O "," CB "] : lines.append(l)
ofp = open(pdbout, 'w')
for l in lines : ofp.write(l)
ofp.close()
def fixCNSop(pdbfile) :
from pdbr import isPdbAAline, isPdbAtomLine, line2atomname, line2resn, changeResn, changeAtomname
lines = []
if (os.path.isfile(pdbfile)==False) :
print "Cannot find file %s "%pdbfile
print "No file in directory ", os.getcwd()
sys.exit()
for l in open(pdbfile, 'r').readlines() :
if not isPdbAtomLine(l) : lines.append(l)
elif line2resn(l) == "CU " : lines.append( changeResn(l, " CU") )
elif line2resn(l) == "MSE" and line2atomname(l) == " SE " : lines.append( changeAtomname(l, "SE ") )
elif line2resn(l) == "ILE" and line2atomname(l) == " CD " : lines.append(re.sub(" CD ", " CD1", l))
elif line2atomname(l) == " OT1" : lines.append(re.sub(" OT1", " O ", l))
elif line2atomname(l) == " OXT" : continue
else : lines.append(l)
op = open(pdbfile, 'w')
for l in lines : op.write(l)
op.close()
def changeBfacs(filename, bfacs) :
from pdbr import isPdbAAline, line2atomname, line2occu, changeBfactorOccupancy
lines = []
for l in open(filename, 'r').readlines() :
if isPdbAAline(l) :
if line2atomname(l) in [" N "," CA "," C "," O "] : l = changeBfactorOccupancy(l, bfacs[0], line2occu(l))
else : l = changeBfactorOccupancy(l, bfacs[1], line2occu(l))
lines.append(l)
fp = open(filename, 'w')
for l in lines : fp.write(l)
fp.close()
def adjustBfac2(pdbfile, refpdb,nativeBfac, mcBfac, scBfac) :
print "Copy Bfactors from", refpdb, "to", pdbfile
from pdbr import line2bfac, isPdbAtomLine, line2bfac, line2atomid, changeBfactor, line2crdstr
id2bo = {} # read in crd, bfac, for each atom-id
if (os.path.isfile(refpdb)==False) :
print "Cannot find file %s "%refpdb
print "No file in directory ", os.getcwd()
sys.exit()
if (os.path.isfile(pdbfile)==False) :
print "Cannot find file %s "%pdbfile
print "No file in directory ", os.getcwd()
sys.exit()
for l in open(refpdb, 'r').readlines() :
if not isPdbAtomLine(l) : continue
if id2bo.has_key(line2atomid(l)) : continue
id2bo[line2atomid(l)] = [line2bfac(l), line2crdstr(l)]
newlines = []
if nativeBfac == 1:
for l in open(pdbfile, 'r').readlines() :
if not isPdbAtomLine(l) : newlines.append(l) ; continue
bfac, crdstr = id2bo[ line2atomid(l) ]
l = changeBfactor(l, bfac)
newlines.append(l)
else :
for l in open(pdbfile, 'r').readlines() :
if not isPdbAtomLine(l) : newlines.append(l) ; continue
bfac, crdstr = id2bo[ line2atomid(l) ]
if crdstr == line2crdstr(l) :
l = changeBfactor(l, bfac)
else :
if line2atomname(l) in [' N ',' CA ',' C ',' O '] :
l = changeBfactor(l, mcBfac)
else :
l = changeBfactor(l, scBfac)
newlines.append(l)
op = open(pdbfile, 'w')
for l in newlines : op.write(l)
op.close()
def pdbCopy(pdbfrom, pdbto) :
from pdbr import isPdbAtomLine, line2atomid, isPdbAAline, line2atomname, changeBfactorOccupancy
op = open(pdbto, 'w')
idsSofar = []
for l in open(pdbfrom, 'r').readlines() :
if not isPdbAtomLine(l) : op.write(l) ; continue
if line2atomid(l) in idsSofar : continue
idsSofar.append(line2atomid(l))
bfactor = 30
if isPdbAAline(l) and line2atomname(l) in [' N ',' CA ',' C ',' O '] : bfactor = 20
l = changeBfactorOccupancy(l, bfactor, 1)
op.write(l)
op.close()
def validGeometry_contact(self, tags1, tags2, reslines1, reslines2, atomnbrs) : ## implement in subclasses contact = None for an1 in tags1 : if contact : break for an2 in tags2 : if contact : break if (an1.atn,an2.atn) in atomnbrs : contact = 1 if not contact : return None c1,c2, H1crd, H2crd = 0,0, [0.,0.,0.,], [0.,0.,0.,] for rl in reslines1 : for an in tags1 : if line2atomname(rl) == an.atn : H1crd = vec_add(H1crd, line2crd(rl)) c1 = c1 + 1 for rl in reslines2 : for an in tags2 : if line2atomname(rl) == an.atn : H2crd = vec_add(H2crd, line2crd(rl)) c2 = c2 + 1 H1crd = vec_scale(H1crd, 1./c1) H2crd = vec_scale(H2crd, 1./c2) return pymol_line(H1crd, H2crd)
def Rcrd(self, reslines, tags) : Ratomnames = [] for tat in tags : if tat.tag == 'R' : Ratomnames.append(tat.atn) Rcrd, AMcrd, ANcrd = [], [0.,0.,0.], [] for rl in reslines : if line2atomname(rl) in Ratomnames : Rcrd.append(line2crd(rl)) assert len(Rcrd) >= 3 for rc in Rcrd : AMcrd = vec_add(AMcrd, rc) AMcrd = vec_scale(AMcrd, 1./len(Rcrd)) AN = cross_product(vec_diff(Rcrd[0], Rcrd[1]), vec_diff(Rcrd[2], Rcrd[1])) ANcrd.append(vec_add(AMcrd, AN)) ANcrd.append(vec_diff(AMcrd, AN)) return AMcrd, ANcrd
def Rcrd(self, reslines, tags):
Ratomnames = []
for tat in tags:
if tat.tag == 'R': Ratomnames.append(tat.atn)
Rcrd, AMcrd, ANcrd = [], [0., 0., 0.], []
for rl in reslines:
if line2atomname(rl) in Ratomnames: Rcrd.append(line2crd(rl))
assert len(Rcrd) >= 3
for rc in Rcrd:
AMcrd = vec_add(AMcrd, rc)
AMcrd = vec_scale(AMcrd, 1. / len(Rcrd))
AN = cross_product(vec_diff(Rcrd[0], Rcrd[1]),
vec_diff(Rcrd[2], Rcrd[1]))
ANcrd.append(vec_add(AMcrd, AN))
ANcrd.append(vec_diff(AMcrd, AN))
return AMcrd, ANcrd
def readProtRes(prot) :
res, resids, resnums, resnames, chids, resics, crds = {}, {}, {}, {}, {}, {}, []
for ri in range(len(prot.reslines)) :
start, stop = prot.reslines[ri]
resids[ri] = line2resid( prot.atomlines[start] )
resnames[ri] = line2resn( prot.atomlines[start] )
resnums[ri] = line2resnum( prot.atomlines[start] )
chids[ri] = line2chid( prot.atomlines[start] )
resics[ri] = line2resic( prot.atomlines[start] )
res[ri] = {}
for ai in range(start, stop) :
crd = line2crd( prot.atomlines[ai] )
aname = line2atomname( prot.atomlines[ai] )
crds.append(crd)
res[ri][aname] = len(crds)-1
return res, resids, resnums, resnames, chids, resics, crds
def changeBfacs(filename, bfacs) :
from pdbr import isPdbAAline, line2atomname, line2occu, changeBfactorOccupancy
lines = []
if (os.path.isfile(filename)==False) :
print "Cannot find file %s "%filename
print "No file in directory ", os.getcwd()
sys.exit()
for l in open(filename, 'r').readlines() :
if isPdbAAline(l) :
if line2atomname(l) in [" N "," CA "," C "," O "] : l = changeBfactorOccupancy(l, bfacs[0], line2occu(l))
else : l = changeBfactorOccupancy(l, bfacs[1], line2occu(l))
lines.append(l)
fp = open(filename, 'w')
for l in lines : fp.write(l)
fp.close()
def pdbCopy(pdbfrom, pdbto) :
from pdbr import isPdbAtomLine, line2atomid, isPdbAAline, line2atomname, changeBfactorOccupancy
op = open(pdbto, 'w')
idsSofar = []
if (os.path.isfile(pdbfrom)==False) :
print "Cannot find file %s "%pdbfrom
print "No file in directory ", os.getcwd()
sys.exit()
for l in open(pdbfrom, 'r').readlines() :
if not isPdbAtomLine(l) : op.write(l) ; continue
if line2atomid(l) in idsSofar : continue
idsSofar.append(line2atomid(l))
bfactor = 30
if isPdbAAline(l) and line2atomname(l) in [' N ',' CA ',' C ',' O '] : bfactor = 20
l = changeBfactorOccupancy(l, bfactor, 1)
op.write(l)
op.close()
def readProtRes(prot) :
res, resids, resnums, resnames, chids, resics, crds = {}, {}, {}, {}, {}, {}, []
for ri in range(len(prot.reslines)) :
start, stop = prot.reslines[ri]
if start == 0 and stop == 0:
print "No ATOM records found in file"
continue
resids[ri] = line2resid( prot.atomlines[start] )
resnames[ri] = line2resn( prot.atomlines[start] )
resnums[ri] = line2resnum( prot.atomlines[start] )
chids[ri] = line2chid( prot.atomlines[start] )
resics[ri] = line2resic( prot.atomlines[start] )
res[ri] = {}
for ai in range(start, stop) :
crd = line2crd( prot.atomlines[ai] )
aname = line2atomname( prot.atomlines[ai] )
crds.append(crd)
res[ri][aname] = len(crds)-1
if len(res.keys()) == 0 and start ==0 and stop ==0:
print "Coordinate file corrupted, pleas check file format. Unable to read coordinae file"
import sys ; sys.exit()
return res, resids, resnums, resnames, chids, resics, crds
def readProtRes3(prot) :
res, resids, resnums, resnames, chids, resics, crds, hetids = {}, {}, {}, {}, {}, {}, [] , {}
for ri in range(len(prot.reslines)) :
# print prot.reslines[ri]
start, stop = prot.reslines[ri]
# print prot.atomlines[start]
resids[ri] = line2resid( prot.atomlines[start] )
resnames[ri] = line2resn( prot.atomlines[start] )
resnums[ri] = line2resnum( prot.atomlines[start] )
chids[ri] = line2chid( prot.atomlines[start] )
resics[ri] = line2resic( prot.atomlines[start] )
if isHetAtomLine( prot.atomlines[start] ) :
hetids[ri] = 1
else :
hetids[ri] = 0
res[ri] = {}
for ai in range(start, stop) :
crd = line2crd( prot.atomlines[ai] )
aname = line2atomname( prot.atomlines[ai] )
crds.append(crd)
res[ri][aname] = len(crds)-1
return res, resids, resnums, resnames, chids, resics, crds , hetids
if not isPdbAAline(prot.atomlines[prot.reslines[i][0]]): continue
resid1 = line2resid(prot.atomlines[prot.reslines[i][0]])
for j in range(len(prot.reslines)):
if not isPdbAAline(prot.atomlines[prot.reslines[j][0]]): continue
resid2 = line2resid(prot.atomlines[prot.reslines[j][0]])
vornbrs[(resid1, resid2)] = []
for l in vorface_lines[1:]: #ignore 1st line of output
flds = l.split()[1:] #ignore first field of each line
a0, a1 = string.atoi(flds[0]), string.atoi(flds[1])
if a0 >= len(prot.atomlines) or a1 >= len(prot.atomlines): continue
if not isPdbAAline(prot.atomlines[a0]) or not isPdbAAline(
prot.atomlines[a1]):
continue
resid1 = line2resid(prot.atomlines[a0])
resid2 = line2resid(prot.atomlines[a1])
an1 = line2atomname(prot.atomlines[a0])
an2 = line2atomname(prot.atomlines[a1])
vornbrs[(resid1, resid2)].append((an1, an2))
vornbrs[(resid2, resid1)].append((an2, an1))
## reduce pdb file
pdbfile = mkstemp(suffix=".pdb")[1]
print pdbfile
proc_run_exitOnError('reduce %s > %s' % (options.pdbin, pdbfile), [],
[256])
prot = protein(pdbfile, read_hydrogens=1, read_waters=0,
read_hets=0) ## pdb file here
os.unlink(pdbfile)
# read interactions from xml file
reader = xml.sax.make_parser()
vornbrs = {}
for i in range(len(prot.reslines)) :
if not isPdbAAline(prot.atomlines[ prot.reslines[i][0] ]) : continue
resid1 = line2resid( prot.atomlines[prot.reslines[i][0]] )
for j in range(len(prot.reslines)) :
if not isPdbAAline(prot.atomlines[ prot.reslines[j][0] ]) : continue
resid2 = line2resid( prot.atomlines[prot.reslines[j][0]] )
vornbrs[(resid1,resid2)] = []
for l in vorface_lines[1:] : #ignore 1st line of output
flds = l.split()[1:] #ignore first field of each line
a0, a1 = string.atoi(flds[0]), string.atoi(flds[1])
if a0 >= len(prot.atomlines) or a1 >= len(prot.atomlines) : continue
if not isPdbAAline(prot.atomlines[a0]) or not isPdbAAline(prot.atomlines[a1]) : continue
resid1 = line2resid(prot.atomlines[a0])
resid2 = line2resid(prot.atomlines[a1])
an1 = line2atomname(prot.atomlines[a0])
an2 = line2atomname(prot.atomlines[a1])
vornbrs[(resid1,resid2)].append((an1,an2))
vornbrs[(resid2,resid1)].append((an2,an1))
## reduce pdb file
pdbfile = mkstemp(suffix = ".pdb")[1]
print pdbfile
proc_run_exitOnError('reduce %s > %s' % (options.pdbin, pdbfile), [], [256])
prot = protein(pdbfile, read_hydrogens=1, read_waters=0, read_hets=0) ## pdb file here
os.unlink(pdbfile)
# read interactions from xml file
reader = xml.sax.make_parser()
ih = IntxHandler()
reader.setContentHandler(ih)