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 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 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 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 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 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 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
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
parser.add_option("--intxml", action='store', type='string', dest="intxml", help='xml file describing interactions to be detected')
parser.add_option("--out", action='store', type='string', dest="out", help='output xml file containing interactions, in a format readable with pymol plugin')
parser.add_option("--reprez", action='store', type='string', dest="reprez", help='pdb file')
(options, args) = parser.parse_args()
intxml = options.intxml
outfn = options.out
## solvate protein and decide voronoi adjacency in un-reduced protein
prot = protein(options.pdbin, read_hydrogens=0, read_waters=1, read_hets=1) ## pdb file here
HOHcrd = makeGridZimmer(prot.allcrds())
vor_in = []
vor_in.append("3")
vor_in.append("%d" % (len(prot.atomlines)+len(HOHcrd)))
for l in prot.atomlines : vor_in.append("%f %f %f" % line2crd(l))
for crd in HOHcrd : vor_in.append("%f %f %f" % crd)
dontcare_estatus,vorface_lines,dontcare_elines = proc_run_exitOnError("qvoronoi Fv", vor_in) # voronoi vertices
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
help='pdb file')
(options, args) = parser.parse_args()
intxml = options.intxml
outfn = options.out
## solvate protein and decide voronoi adjacency in un-reduced protein
prot = protein(options.pdbin, read_hydrogens=0, read_waters=1,
read_hets=1) ## pdb file here
HOHcrd = makeGridZimmer(prot.allcrds())
vor_in = []
vor_in.append("3")
vor_in.append("%d" % (len(prot.atomlines) + len(HOHcrd)))
for l in prot.atomlines:
vor_in.append("%f %f %f" % line2crd(l))
for crd in HOHcrd:
vor_in.append("%f %f %f" % crd)
dontcare_estatus, vorface_lines, dontcare_elines = proc_run_exitOnError(
"qvoronoi Fv", vor_in) # voronoi vertices
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])