def calcRMSD_pymol(uf, bf):
"""
Given two pdb files of the same protein, this function calculates the
rmsd, asa for each and the molecular weight of each using Pymol
"""
# Call the function below before using any PyMOL modules.
#time.sleep(random.random())
cmd.set("dot_solvent", 1)
cmd.load(uf)
cmd.load(bf)
#cmd.h_add()
#cmd.remove('het')
_, un, _ = getFileParts(uf)
_, bn, _ = getFileParts(bf)
asa_u = cmd.get_area(un)
asa_b = cmd.get_area(bn)
umass = cmd.get_model(un).get_mass()
bmass = cmd.get_model(bn).get_mass()
#rms=cmd.super(un,bn,transform=1)[0]
#time.sleep(random.random())
bv0 = []
cmd.iterate('all', 'bv0.append(b)', space=locals())
cmd.do('run colorbyrmsd.py; colorbyrmsd \'' + un + '\',\'' + bn +
'\',guide = 0,doAlign=1, doPretty=1')
while True: # synchronization
bv1 = []
cmd.iterate('all', 'bv1.append(b)', space=locals())
if bv0 != bv1:
time.sleep(0.1)
break
out_file = tempfile.NamedTemporaryFile(suffix='.pdb')
out_file.close()
tmp_pdb = out_file.name
updb = tmp_pdb + 'u'
bpdb = tmp_pdb + 'b'
cmd.save(updb, un)
cmd.save(bpdb, bn)
(_, uR, _, _, _) = readPDB(updb)
urmsd = getBvalues(uR)
os.remove(updb)
(_, bR, _, _, _) = readPDB(bpdb)
brmsd = getBvalues(bR)
os.remove(bpdb)
rms = np.sqrt(np.mean(
np.array([v for V in urmsd for v in V if v >= 0])**2))
#(_,urx,_,_,_)=readPDB(uf); ux=getBvalues(urx);
# if np.abs(rms-rmsd)>0.1:
# print "RMSD =",rms,rmsd
# pdb.set_trace()
cmd.reinitialize()
pdb.set_trace()
return rms, asa_u, asa_b, umass, bmass, urmsd, brmsd
def batchExtract(pkldir, bdir, ofname):
"""
Running the information required for all files
"""
import glob
flist = glob.glob(pkldir + '*.pdb.pkl')
TT = len(flist) + 0.0
if os.path.isfile(ofname) is False:
fdict = {}
else:
fdict = myPickle.load(ofname)
for cnt, f in enumerate(flist):
print '% Done =', cnt / TT
(_, k, _) = getFileParts(getFileParts(f)[1])
#pdb.set_trace()
k = k[:-2]
if k not in fdict:
print "Processing", f
try:
U = myPDB.loader(pkldir + k + '_u.pdb.pkl')
B = myPDB.loader(pkldir + k + '_b.pdb.pkl')
except:
continue
pdb.set_trace()
#rmsd,Uidx,Bidx=calcRMSD(U,B)
try:
rpymol = calcRMSD_pymol(bdir + k + '_u.pdb',
bdir + k + '_b.pdb')
except:
print "Error processing", k
cmd.reinitialize()
time.sleep(0.1)
continue
#pdb.set_trace()
#useq=''.join([three_to_one(U.R[i].get_resname()) for i in Uidx])
#bseq=''.join([three_to_one(B.R[i].get_resname()) for i in Bidx])
#a_useq=ProteinAnalysis(U.seq)
#a_bseq=ProteinAnalysis(B.seq)
#asa_u=np.sum([U.ASA[i] for i in Uidx])
#asa_b=np.sum([B.ASA[i] for i in Bidx])
fdict[
k] = rpymol #+(BN.nanmean(U.B),BN.nanmean(B.B),BN.nanmedian(U.B),BN.nanmedian(B.B),BN.nanmax(U.B),BN.nanmax(B.B))
#pdb.set_trace()
myPickle.dump(ofname, fdict)
print k, rpymol[0]
else:
print "Already found", f
return fdict
def parse1SVM(ifile, auconly=False, **kwargs): #,E,Asgl
exfname = 'EP_6N.lbl.pkl'
sglfile = 'result.sgl.pkl'
try:
E
except NameError:
E = getExamplesDBD.loader(exfname)
try:
Asgl
except NameError:
Asgl = cPickle.load(open(sglfile, "rb"))
cid = getFileParts(getFileParts(ifile)[1])[1][:4]
(la, ra, lrV, rrV) = Asgl[cid]
I = []
J = []
V = []
L = []
Mv = np.zeros((len(lrV), len(rrV)))
Ml = np.zeros(Mv.shape)
for lidx, xr in enumerate(lrV.keys()):
for ridx, xc in enumerate(rrV.keys()):
if (xr, xc) in E.Pex[cid][0]:
l = +1.0
else:
l = -1.0
I.append(xr)
J.append(xc)
v = lrV[xr][0] + rrV[xc][0]
V.append(v)
L.append(l)
Mv[lidx, ridx] = v
Ml[lidx, ridx] = l
#pdb.set_trace()
# for idx in range(len(I)):
# Mv[I[idx],J[idx]]=V[idx]
# Ml[I[idx],J[idx]]=L[idx]
(_, _, auc) = roc.roc(list(Mv.flatten()), list(Ml.flatten()))
if auconly:
return auc
return (auc, Mv, Ml, None, None, lrV, rrV) #auc,Mvm,Mlm,None,None,lrV,rrV
def parse1SVM(ifile,auconly=False,**kwargs):#,E,Asgl
exfname='EP_6N.lbl.pkl'
sglfile='result.sgl.pkl'
try:
E
except NameError:
E=getExamplesDBD.loader(exfname)
try:
Asgl
except NameError:
Asgl=cPickle.load(open(sglfile, "rb" ))
cid=getFileParts(getFileParts(ifile)[1])[1][:4]
(la,ra,lrV,rrV)=Asgl[cid]
I=[]
J=[]
V=[]
L=[]
Mv=np.zeros((len(lrV),len(rrV)))
Ml=np.zeros(Mv.shape)
for lidx,xr in enumerate(lrV.keys()):
for ridx,xc in enumerate(rrV.keys()):
if (xr,xc) in E.Pex[cid][0]:
l=+1.0
else:
l=-1.0
I.append(xr)
J.append(xc)
v=lrV[xr][0]+rrV[xc][0]
V.append(v)
L.append(l)
Mv[lidx,ridx]=v
Ml[lidx,ridx]=l
#pdb.set_trace()
# for idx in range(len(I)):
# Mv[I[idx],J[idx]]=V[idx]
# Ml[I[idx],J[idx]]=L[idx]
(_,_,auc)=roc.roc(list(Mv.flatten()),list(Ml.flatten()))
if auconly:
return auc
return (auc,Mv,Ml,None,None,lrV,rrV) #auc,Mvm,Mlm,None,None,lrV,rrV
def parseShandarFiles(ifile,auconly=False,**kwargs): #(auc,Mv,Ml,lseq,rseq,lrV,rrV)
"""
Reads shandar's output files with labels (made on the same pattern as analyzePredFile.readFile)
"""
def parseContLine(ln):
# ['A', '#5', 'ASN:7', 'N', '::', 'B', '#5', 'HIS:6', 'H:', '0', '53.61']
# 0 1 2 3 4 5 6 7 8 9 10
lns=ln.split()
lidx=lns[0]+lns[1]
ridx=lns[5]+lns[6]
lbl=int(lns[9])
return (lidx,ridx,lbl)
loopath,cid,_=getFileParts(ifile)
lcids=cid.split('_')[1]
rcids=cid.split('_')[2]
Mlidx={}
Mridx={}
Mlv=[]
l=0
r=0
with open(os.path.join(loopath,cid+'.preds')) as fp,open(os.path.join(loopath,cid+'.cont')) as fc:
for lnp,lnc in zip(fp,fc):
(lidx,ridx,lbl)=parseContLine(lnc)
if lidx[0] in lcids and ridx[0] in rcids:
try:
lx=Mlidx[lidx]
except:
Mlidx[lidx]=l
lx=l
l=l+1
try:
rx=Mridx[ridx]
except:
Mridx[ridx]=r
rx=r
r=r+1
p=float(lnp)
Mlv.append((lx,rx,lbl,p))
Mvm=np.zeros((l,r))
Mvm.fill(np.nan)
Mlm=np.zeros((l,r))
for i in range(len(Mlv)):
Mlm[Mlv[i][0],Mlv[i][1]]=Mlv[i][2]
Mvm[Mlv[i][0],Mlv[i][1]]=Mlv[i][3]
(_,_,auc)=roc.roc(list(Mvm.flatten()),list(Mlm.flatten()))
if auconly:
return auc
#construct lrV,rrV
lrV=dict(zip(range(Mvm.shape[0]),zip(np.max(Mvm,axis=1),np.max(Mlm,axis=1))))
rrV=dict(zip(range(Mvm.shape[1]),zip(np.max(Mvm,axis=0),np.max(Mlm,axis=0))))
return auc,Mvm,Mlm,None,None,lrV,rrV
except ImportError:
print "Failure importing MPI4py: Not using MPI parallelization."
comm=None
myid=0
nprocs=1
csize=int(np.ceil(len(fs)/float(nprocs)))
gclist=list(chunks(fs,csize))
myfs=gclist[myid]
LV=[]
TPS=[]
DNTP=[]
dsA={}
LVP=[]
for i,ifile in enumerate(myfs):
try:
cid=getFileParts(getFileParts(ifile)[1])[1][:4]
if incids is not None and cid not in incids:
continue
print "Processing",cid
if auconly:
auc=readFile(ifile,auconly=True)
dsA[cid]=(auc,np.nan,np.nan)
else:
if postprocess:
pauc,Mvc0,Mvc,Mlc,lseq,rseq,lrV0,lrV,rrV0,rrV=postProcessAvg(cid,pdbpklpath,loopath)
ifile=(pauc,Mvc,Mlc,lseq,rseq,lrV,rrV)
(auc,ttp,fpi,dntp,la,ra,pp,nn,Mvx,Mlx,lv,ll,rv,rl)=computeNTP(ifile,top=200) #lv,ll,rv,rl
TPS.append([ttp,fpi,100.0*ttp/pp,pp,nn,pp+nn])
DNTP.append(dntp)
LV.append((list(Mvx),list(Mlx)))
import glob
import numpy as np
from analyzeLOOCV import computeNTP, calcRFPP
dir1 = './DBD3LOOCVSR/'
dir2 = './DBD3LOOCV/'
fs = glob.glob(dir1 + '*.pairpred.txt')
from BISEPutils import getFileParts
F1 = np.zeros((len(fs), 5))
F2 = np.zeros((len(fs), 5))
DNTP1 = []
DNTP2 = []
for i, f1 in enumerate(fs):
fp = getFileParts(f1)
f2 = dir2 + fp[1] + fp[2]
(auc, ttp, fpi, dntp, la, ra, pp, nn, Mvx, Mlx) = computeNTP(f1)
DNTP1.append(dntp)
print i, f1, auc, ttp, fpi, la, ra
F1[i, :] = [auc, ttp, fpi, la, ra]
(auc, ttp, fpi, dntp, la, ra, pp, nn, Mvx, Mlx) = computeNTP(f2)
DNTP2.append(dntp)
print i, f2, auc, ttp, fpi, la, ra
F2[i, :] = [auc, ttp, fpi, la, ra]
FPI1 = F1[:, 2]
FPI2 = F2[:, 2]
print "RFPP for", dir1
calcRFPP(FPI1, DNTP1)
print "RFPP for", dir2
import myPickle,re
pdbpklpath='../../DBD4CSPKL/PKL/'#'../../DBD4N/PDBPKL4'
#dirs=['../../DBD4_ESR_prop/','../../DBD4_NoESR_prop/','../../DBD4_SGDSVM/','../../DBD_SSVM_3E-6/','../../DBD_SPW_3E-6/']
#dirs=['../DBD4_ESR_prop/']#,'../SGD_DBD4/'
#dirs=['../DBD4_SGDSVM/','../DBD_SPW_3E-8/']
#cids=['2OOB', '1EFN', '1PPE', '1J2J', '1GL1', '1SYX', '1Z0K', '1AY7', '1FFW', '3SGQ', '1S1Q', '1FLE', '7CEI', '2IDO', '1KTZ', '4CPA', '2UUY', '1R6Q', '1D6R', '1OC0', '1CGI', '1R0R', '1EAW', '1GCQ', '1XD3', '1LFD', '2I25', '1CLV', '1H9D', '1ACB', '2SNI', '3D5S', '1Z5Y', '2HRK', '2ABZ', '1UDI', '1PXV', '2J0T']#E.Pex.keys()[20:40]
#dirs=['../../SGD_DBD4/']
dirs=['../../DBD4S_SMO196/','../../DBD4S_SGD196/','../../DBD4S_SGD196_CENT/','../../DBD4S_SGDCENTPW71/']#['../../DBD4_NoESR_prop/']
# FIND THE COMMON SET
cids=None
Re=(r"(\S+)\.",r"(\S+)\#(\S+)\.")
for d in dirs:
cids_d=[]
for f in glob.glob(d+'/*.pairpred.txt'):
cx=re.match(Re[int('#' in f)],getFileParts(f)[1]).groups()
if len(cx)==1:
cx=cx[0]
cids_d.append(cx)
if cids is None:
cids=set(cids_d)
else:
cids=cids.intersection(cids_d)
cids=list(cids)
R={}
for cid in cids:
rfpp=[]
for d in dirs:
fname=d+('#'.join(cid))+'.pairpred.txt'
try:
(auc0,Mv0,Mv,Ml,lseq,rseq,lrV0,lrV,rrV0,rrV)=postProcessAvg(cid,pdbpklpath,d)
except ImportError:
print "Failure importing MPI4py: Not using MPI parallelization."
comm = None
myid = 0
nprocs = 1
csize = int(np.ceil(len(fs) / float(nprocs)))
gclist = list(chunks(fs, csize))
myfs = gclist[myid]
LV = []
TPS = []
DNTP = []
dsA = {}
LVP = []
for i, ifile in enumerate(myfs):
try:
cid = getFileParts(getFileParts(ifile)[1])[1][:4]
if incids is not None and cid not in incids:
continue
print "Processing", cid
if auconly:
auc = readFile(ifile, auconly=True)
dsA[cid] = (auc, np.nan, np.nan)
else:
if postprocess:
pauc, Mvc0, Mvc, Mlc, lseq, rseq, lrV0, lrV, rrV0, rrV = postProcessAvg(
cid, pdbpklpath, loopath)
ifile = (pauc, Mvc, Mlc, lseq, rseq, lrV, rrV)
(auc, ttp, fpi, dntp, la, ra, pp, nn, Mvx, Mlx, lv, ll, rv,
rl) = computeNTP(ifile, top=200) #lv,ll,rv,rl
TPS.append([ttp, fpi, 100.0 * ttp / pp, pp, nn, pp + nn])
@author: root
"""
import glob
import numpy as np
from analyzeLOOCV import computeNTP, calcRFPP
dir1='./DBD3LOOCVSR/'
dir2='./DBD3LOOCV/'
fs=glob.glob(dir1+'*.pairpred.txt')
from BISEPutils import getFileParts
F1=np.zeros((len(fs),5))
F2=np.zeros((len(fs),5))
DNTP1=[]
DNTP2=[]
for i,f1 in enumerate(fs):
fp=getFileParts(f1)
f2=dir2+fp[1]+fp[2]
(auc,ttp,fpi,dntp,la,ra,pp,nn,Mvx,Mlx)=computeNTP(f1);
DNTP1.append(dntp)
print i,f1,auc, ttp, fpi,la,ra
F1[i,:]=[auc ,ttp ,fpi ,la ,ra]
(auc,ttp,fpi,dntp,la,ra,pp,nn,Mvx,Mlx)=computeNTP(f2);
DNTP2.append(dntp)
print i,f2,auc, ttp, fpi,la,ra
F2[i,:]=[auc ,ttp ,fpi ,la ,ra]
FPI1=F1[:,2]
FPI2=F2[:,2]
print "RFPP for",dir1
calcRFPP(FPI1,DNTP1)
print "RFPP for",dir2
if __name__ == '__main__':
LV = []
TPS = []
DNTP = []
#auconly=False # whether to calculate the avg. auc of the complexes or do more
#(auc,(fp,tp),(A,Rx,D,L,cids,r,dkey))=getAUC('./Results/result_tppk.res.pkl')
#dAo=dict(zip(cids,A)) #AUCs from the training data set (CV) only
loopath = './Shandar/data-sets/data-sets/' #C:\Users\Afsar\Desktop\pairpred\sequence only\DBD3LOOCVSEQ
fsp = glob.glob(loopath + '*.preds')
dA = {}
dsA = {}
#daoo={}
for i, ifile in enumerate(fsp):
cid = getFileParts(ifile)[1]
print 'cid =', cid, 100 * float(i + 1) / len(fsp), '% done'
(Ml, Mv) = parseShandarFiles(cid, loopath)
#(auc,Mv,Ml,lseq,rseq,lrV,rrV)=readFile(ifile,usePDBidx=False);#(auc,Mv,Ml,lseq,rseq,lrV,rrV)
#(la,lv,ll)=getAUC4Protein(lrV)
#(ra,rv,rl)=getAUC4Protein(rrV)
Mvx = Mv.ravel()
Mlx = Ml.ravel()
nidx = ~np.isnan(Mvx) & ~np.isnan(Mlx)
Mvx[~nidx] = -np.inf
(ttp, fpi, dntp) = findNTPinTop(Mvx, Mlx, Mv.shape, top=500)
Mvx = Mvx[nidx]
Mlx = Mlx[nidx]
pp = np.sum(Mlx == 1) # total number of positives
nn = len(Mlx) - pp #total number of negatives
return (Mlm,Mvm)
if __name__=='__main__':
LV=[]
TPS=[]
DNTP=[]
#auconly=False # whether to calculate the avg. auc of the complexes or do more
#(auc,(fp,tp),(A,Rx,D,L,cids,r,dkey))=getAUC('./Results/result_tppk.res.pkl')
#dAo=dict(zip(cids,A)) #AUCs from the training data set (CV) only
loopath='./Shandar/data-sets/data-sets/'#C:\Users\Afsar\Desktop\pairpred\sequence only\DBD3LOOCVSEQ
fsp=glob.glob(loopath+'*.preds')
dA={}
dsA={}
#daoo={}
for i,ifile in enumerate(fsp):
cid=getFileParts(ifile)[1]
print 'cid =',cid,100*float(i+1)/len(fsp),'% done'
(Ml,Mv)=parseShandarFiles(cid,loopath)
#(auc,Mv,Ml,lseq,rseq,lrV,rrV)=readFile(ifile,usePDBidx=False);#(auc,Mv,Ml,lseq,rseq,lrV,rrV)
#(la,lv,ll)=getAUC4Protein(lrV)
#(ra,rv,rl)=getAUC4Protein(rrV)
Mvx=Mv.ravel()
Mlx=Ml.ravel()
nidx=~np.isnan(Mvx) & ~np.isnan(Mlx)
Mvx[~nidx]=-np.inf
(ttp,fpi,dntp)=findNTPinTop(Mvx,Mlx,Mv.shape,top=500)
Mvx=Mvx[nidx]
Mlx=Mlx[nidx]
pp=np.sum(Mlx==1) # total number of positives
nn=len(Mlx)-pp #total number of negatives
def parseShandarFiles(ifile,
auconly=False,
**kwargs): #(auc,Mv,Ml,lseq,rseq,lrV,rrV)
"""
Reads shandar's output files with labels (made on the same pattern as analyzePredFile.readFile)
"""
def parseContLine(ln):
# ['A', '#5', 'ASN:7', 'N', '::', 'B', '#5', 'HIS:6', 'H:', '0', '53.61']
# 0 1 2 3 4 5 6 7 8 9 10
lns = ln.split()
lidx = lns[0] + lns[1]
ridx = lns[5] + lns[6]
lbl = int(lns[9])
return (lidx, ridx, lbl)
loopath, cid, _ = getFileParts(ifile)
lcids = cid.split('_')[1]
rcids = cid.split('_')[2]
Mlidx = {}
Mridx = {}
Mlv = []
l = 0
r = 0
with open(os.path.join(loopath, cid + '.preds')) as fp, open(
os.path.join(loopath, cid + '.cont')) as fc:
for lnp, lnc in zip(fp, fc):
(lidx, ridx, lbl) = parseContLine(lnc)
if lidx[0] in lcids and ridx[0] in rcids:
try:
lx = Mlidx[lidx]
except:
Mlidx[lidx] = l
lx = l
l = l + 1
try:
rx = Mridx[ridx]
except:
Mridx[ridx] = r
rx = r
r = r + 1
p = float(lnp)
Mlv.append((lx, rx, lbl, p))
Mvm = np.zeros((l, r))
Mvm.fill(np.nan)
Mlm = np.zeros((l, r))
for i in range(len(Mlv)):
Mlm[Mlv[i][0], Mlv[i][1]] = Mlv[i][2]
Mvm[Mlv[i][0], Mlv[i][1]] = Mlv[i][3]
(_, _, auc) = roc.roc(list(Mvm.flatten()), list(Mlm.flatten()))
if auconly:
return auc
#construct lrV,rrV
lrV = dict(
zip(range(Mvm.shape[0]), zip(np.max(Mvm, axis=1), np.max(Mlm,
axis=1))))
rrV = dict(
zip(range(Mvm.shape[1]), zip(np.max(Mvm, axis=0), np.max(Mlm,
axis=0))))
return auc, Mvm, Mlm, None, None, lrV, rrV