def computeDistMeansForComplex(cid,N,pdbpklpath,pppath):
"""
code for getting distance and auc information
"""
L=myPDB.loader(os.path.join(pdbpklpath,cid+'_l_u.pdb.pkl'))
R=myPDB.loader(os.path.join(pdbpklpath,cid+'_r_u.pdb.pkl'))
if type(pppath)==type(''):
(pauc,Mv,Ml,lseq,rseq,lauc,rauc)=readFile(pppath+cid+'.pairpred.txt',usePDBidx=False)
else:
(pauc,Mv,Ml,lseq,rseq,lauc,rauc)=pppath
lauc=None
rauc=None
try:
(_,_,lauc)=roc.roc(list(np.array(lauc.values())[:,0]),list(np.array(lauc.values())[:,1]))
(_,_,rauc)=roc.roc(list(np.array(rauc.values())[:,0]),list(np.array(rauc.values())[:,1]))
except:
pass
Mlx=np.random.random(Ml.shape)
Mlx[Ml<0]=-1
(r,c,v)=sortScores(Mlx)
lD=getDistMat(getCoords(L.R))
rD=getDistMat(getCoords(R.R))
#pdb.set_trace()
M=20
return pauc,lauc,rauc,getDistMean(lD,r,top=True,M=M), getDistMean(lD,r,top=False,M=M), getDistMean(rD,c,top=True,M=M), getDistMean(rD,c,top=False,M=M)
def computeDistMeansForComplex(cid, N, pdbpklpath, pppath):
"""
code for getting distance and auc information
"""
L = myPDB.loader(os.path.join(pdbpklpath, cid + '_l_u.pdb.pkl'))
R = myPDB.loader(os.path.join(pdbpklpath, cid + '_r_u.pdb.pkl'))
if type(pppath) == type(''):
(pauc, Mv, Ml, lseq, rseq, lauc,
rauc) = readFile(pppath + cid + '.pairpred.txt', usePDBidx=False)
else:
(pauc, Mv, Ml, lseq, rseq, lauc, rauc) = pppath
lauc = None
rauc = None
try:
(_, _, lauc) = roc.roc(list(np.array(lauc.values())[:, 0]),
list(np.array(lauc.values())[:, 1]))
(_, _, rauc) = roc.roc(list(np.array(rauc.values())[:, 0]),
list(np.array(rauc.values())[:, 1]))
except:
pass
Mlx = np.random.random(Ml.shape)
Mlx[Ml < 0] = -1
(r, c, v) = sortScores(Mlx)
lD = getDistMat(getCoords(L.R))
rD = getDistMat(getCoords(R.R))
#pdb.set_trace()
M = 20
return pauc, lauc, rauc, getDistMean(lD, r, top=True, M=M), getDistMean(
lD, r, top=False, M=M), getDistMean(rD, c, top=True,
M=M), getDistMean(rD,
c,
top=False,
M=M)
def getAUCs(mx,dx,dd,dthr=6.0):
lx=2*(dd<dthr)-1
mxf=mx.flatten()
dxf=dx.flatten()
lxf=lx.flatten()
nanidx=~(np.isnan(mxf)+np.isnan(lxf)+np.isnan(dxf))
lxf=list(lxf[nanidx])
mxf=list(mxf[nanidx])
dxf=list(dxf[nanidx])
(_,_,aa_mi)=roc.roc(mxf,lxf)
(_,_,aa_di)=roc.roc(dxf,lxf)
return aa_mi,aa_di
def getAUCs(mx, dx, dd, dthr=6.0):
lx = 2 * (dd < dthr) - 1
mxf = mx.flatten()
dxf = dx.flatten()
lxf = lx.flatten()
nanidx = ~(np.isnan(mxf) + np.isnan(lxf) + np.isnan(dxf))
lxf = list(lxf[nanidx])
mxf = list(mxf[nanidx])
dxf = list(dxf[nanidx])
(_, _, aa_mi) = roc.roc(mxf, lxf)
(_, _, aa_di) = roc.roc(dxf, lxf)
return aa_mi, aa_di
def getAUC4Protein(lrV):
vl = map(list, zip(*lrV.values()))
vv = vl[0]
ll = vl[1]
(_, _, a) = roc.roc(vv, ll)
vv = np.array(vv)
ll = np.array(ll)
return (a, vv, ll)
def getTP_RFPP(Mv,Ml):
"""
Returns the number of true positives in the top 50 predictions and the index of the first positive prediction detected
"""
nnan=~(np.isnan(Mv)+np.isnan(Ml))
Mv=Mv[nnan]
Ml=Ml[nnan]
rfpp=np.argmax(Ml[np.argsort(-Mv)]==1);
(fpr,tpr,r)=roc.roc(list(Mv),list(Ml),50,normalize=False);
ntp=np.max(tpr);
return (ntp,rfpp)
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
def getTP_RFPP(Mv, Ml):
"""
Returns the number of true positives in the top 50 predictions and the index of the first positive prediction detected
"""
nnan = ~(np.isnan(Mv) + np.isnan(Ml))
Mv = Mv[nnan]
Ml = Ml[nnan]
rfpp = np.argmax(Ml[np.argsort(-Mv)] == 1)
(fpr, tpr, r) = roc.roc(list(Mv), list(Ml), 50, normalize=False)
ntp = np.max(tpr)
return (ntp, rfpp)
def roc_score(data, targetClass, otherClass, **args):
rocN = None
if 'rocN' in args:
rocN = args['rocN']
s = numpy.zeros(data.numFeatures, numpy.float_)
for i in range(data.numFeatures):
featureValues = data.getFeature(i)
auc = roc.roc(featureValues, data.labels.Y)[2]
s[i] = max(auc, 1 - auc)
return s
def roc_score(data, targetClass, otherClass, **args) :
rocN = None
if 'rocN' in args :
rocN = args['rocN']
s = numpy.zeros(data.numFeatures, numpy.float_)
for i in range(data.numFeatures) :
featureValues = data.getFeature(i)
auc = roc.roc(featureValues, data.labels.Y)[2]
s[i] = max(auc, 1-auc)
return s
def plotROC(self, filename=None, fold = None, **args) :
rocN = None
if 'rocN' in args :
rocN = args['rocN']
if self.numFolds == 1 :
# if the results are for a single split
labels = self.getGivenClass()
dvals = self.getDecisionFunction()
rocFP, rocTP, area = roc_module.roc(dvals, labels, rocN)
elif fold is None :
# get an averaged ROC curve
labels = self.getGivenClass()
dvals = self.getDecisionFunction()
folds = [(dvals[i], labels[i]) for i in range(len(labels))]
rocFP, rocTP, area = roc_module.roc_VA(folds, rocN)
else :
# plot an ROC plot for the given fold
if fold > self.numFolds :
raise ValueError, 'foldNum too large'
labels = self.getGivenClass(fold)
dvals = self.getDecisionFunction(fold)
rocFP, rocTP, area = roc_module.roc(dvals, labels, rocN)
roc_module.plotROC(rocFP, rocTP, filename)
def plotROC(self, filename=None, fold = None, **args) :
rocN = None
if 'rocN' in args :
rocN = args['rocN']
if self.numFolds == 1 :
# if the results are for a single split
labels = self.getGivenClass()
dvals = self.getDecisionFunction()
rocFP, rocTP, area = roc_module.roc(dvals, labels, rocN)
elif fold is None :
# get an averaged ROC curve
labels = self.getGivenClass()
dvals = self.getDecisionFunction()
folds = [(dvals[i], labels[i]) for i in range(len(labels))]
rocFP, rocTP, area = roc_module.roc_VA(folds, rocN)
else :
# plot an ROC plot for the given fold
if fold > self.numFolds :
raise ValueError, 'foldNum too large'
labels = self.getGivenClass(fold)
dvals = self.getDecisionFunction(fold)
rocFP, rocTP, area = roc_module.roc(dvals, labels, rocN)
roc_module.plotROC(rocFP, rocTP, filename, **args)
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 rasaPlot(rAsa,Dxx,Lxx,Np=10):
#nb=getSamplePoints(rAsa,Np)
nb=np.linspace(np.min(rAsa),np.max(rAsa),Np)
R=np.zeros(len(nb)-1)
R.fill(np.nan)
xx=np.zeros(len(nb)-1)
pp=np.zeros(len(nb)-1)
nn=np.zeros(len(nb)-1)
for idx in range(len(nb)-1):
vidx=np.logical_and(rAsa>=nb[idx], rAsa<nb[idx+1])
v=Dxx[vidx]
l=Lxx[vidx]
xx[idx]=(nb[idx]+nb[idx+1])/2.0
pp[idx]=np.sum(l==+1)
nn[idx]=np.sum(l!=+1)
if(pp[idx]>10 and nn[idx]>10):
try:
(_,_,R[idx])=roc.roc(list(v),list(l))
except:
continue
naidx=~np.isnan(R)
print "Correlation Coefficient: ", pearsonr(xx[naidx],R[naidx])
#PLOTTING ONLY CODE
stat="$\Delta$rASA"
ww=np.diff(nb)
plt.figure(0)
plt.plot(xx,R,'-o')
plt.xlabel(stat)
plt.ylabel("AUC")
plt.title('AUC vs $\Delta$rASA')
plt.grid()
plt.savefig('../figures/fig_A2.eps', format='eps', dpi=1200)
plt.figure(1)
plt.plot(nb[:-1],pp,'r-^',label="Interacting residues")
plt.plot(nb[:-1],nn,'k-v',label="Not-Interacting residues")
# plt.bar(nb[:-1],pp,color='r',width=ww,label="+1")
# plt.bar(nb[:-1],nn,color='k',width=ww,bottom=pp,label="-1")
plt.xlabel(stat)
plt.ylabel("Counts")
plt.legend(loc=0)
plt.title('Number of residues vs. $\Delta$rASA')
plt.grid()
plt.savefig('../figures/fig_A3.eps', format='eps', dpi=1200)
def computeNTP(ifile, top=200, freader=None):
"""
Given a result file name ifile and its reader function freader=parseShandarFiles, it computes
auc: The auc score
ttp: Number of true positives in top
fpi: index of the first true positive
dntp: Distance to the nearest true positive for each top example
la: auc of ligand
ra: auc of receptor
pp: number of positive examples
nn: number of negative examples
Mvx: flattened matrix of prediction scores
Mlx: flattened matrix of labels
on input auc (not used, recomputed from prediction scores and labels, kept for compatability to file reader)
"""
if type(ifile) == type(''):
assert freader is not None
(_, Mv, Ml, lseq, rseq, lrV, rrV) = freader(ifile, usePDBidx=False)
else: #expects tuple
(_, Mv, Ml, lseq, rseq, lrV, rrV) = ifile
(la, lv, ll) = getAUC4Protein(lrV)
(ra, rv, rl) = getAUC4Protein(rrV)
Mvx = Mv.ravel()
Mlx = Ml.ravel()
nidx = ~np.isnan(Mvx) & ~np.isnan(Mlx)
(_, _, auc) = roc.roc(list(Mvx[nidx]), list(Mlx[nidx]))
Mvx[~nidx] = -np.inf
(ttp, fpi, dntp) = findNTPinTop(Mvx, Mlx, Mv.shape, top=top)
Mvx = Mvx[nidx]
Mlx = Mlx[nidx]
#yard.ROCCurve(yard.BinaryClassifierData(zip(Mvx,Mlx)))#PrecisionRecallCurve
#zxA=yard.ROCCurve(yard.BinaryClassifierData(zip(Mvx,Mlx)))
#zxR=yard.ROCCurve(yard.BinaryClassifierData(zip(rv,rl)))
#zxL=yard.ROCCurve(yard.BinaryClassifierData(zip(lv,ll)))
#pdb.set_trace()
pp = np.sum(Mlx == 1) # total number of positives
nn = len(Mlx) - pp #total number of negatives
#pdb.set_trace()
return (auc, ttp, fpi, dntp, la, ra, pp, nn, Mvx, Mlx, lv, ll, rv, rl)
def computeNTP(ifile,top=200,freader=None):
"""
Given a result file name ifile and its reader function freader=parseShandarFiles, it computes
auc: The auc score
ttp: Number of true positives in top
fpi: index of the first true positive
dntp: Distance to the nearest true positive for each top example
la: auc of ligand
ra: auc of receptor
pp: number of positive examples
nn: number of negative examples
Mvx: flattened matrix of prediction scores
Mlx: flattened matrix of labels
on input auc (not used, recomputed from prediction scores and labels, kept for compatability to file reader)
"""
if type(ifile)==type(''):
assert freader is not None
(_,Mv,Ml,lseq,rseq,lrV,rrV)=freader(ifile,usePDBidx=False)
else: #expects tuple
(_,Mv,Ml,lseq,rseq,lrV,rrV)=ifile
(la,lv,ll)=getAUC4Protein(lrV)
(ra,rv,rl)=getAUC4Protein(rrV)
Mvx=Mv.ravel()
Mlx=Ml.ravel()
nidx=~np.isnan(Mvx) & ~np.isnan(Mlx)
(_,_,auc)=roc.roc(list(Mvx[nidx]),list(Mlx[nidx]))
Mvx[~nidx]=-np.inf
(ttp,fpi,dntp)=findNTPinTop(Mvx,Mlx,Mv.shape,top=top)
Mvx=Mvx[nidx]
Mlx=Mlx[nidx]
#yard.ROCCurve(yard.BinaryClassifierData(zip(Mvx,Mlx)))#PrecisionRecallCurve
#zxA=yard.ROCCurve(yard.BinaryClassifierData(zip(Mvx,Mlx)))
#zxR=yard.ROCCurve(yard.BinaryClassifierData(zip(rv,rl)))
#zxL=yard.ROCCurve(yard.BinaryClassifierData(zip(lv,ll)))
#pdb.set_trace()
pp=np.sum(Mlx==1) # total number of positives
nn=len(Mlx)-pp #total number of negatives
#pdb.set_trace()
return (auc,ttp,fpi,dntp,la,ra,pp,nn,Mvx,Mlx,lv,ll,rv,rl)
def getAUC(s):
if type(s)==type(''):
(r,dkey)=cPickle.load(open(s, "rb" ) )
else:
(r,dkey)=s
patid=combineList(r.getPatternID())
vkey=dict(zip(patid,range(len(patid))))
decfn=combineList(r.getDecisionFunction())
lblid=combineList(r.getGivenLabels())
cids=dkey.keys()
D=[[] for i in cids]
L=[[] for i in cids]
A=[[] for i in cids]
try:
R=getRMSDDict('shandar_rmsd.txt')
except:
R=None
Rx=[[] for i in cids]
for i,cid in enumerate(cids):
cidx=dkey[cid]
if type(cidx) is tuple: #backward compatability to old results objects
cidx=cidx[0]
for e in cidx:
try:
n=vkey[e]
except KeyError:
pdb.set_trace()
D[i].append(decfn[n])
L[i].append(lblid[n])
(_,_,a)=roc.roc(D[i],L[i])
A[i]=a
if R is not None:
Rx[i]=R[cid]
(fp,tp,auc)=roc.roc_VA(zip(D,L))
return (auc,(fp,tp),(A,Rx,D,L,cids,r,dkey))
def getAUC(s):
if type(s) == type(''):
(r, dkey) = cPickle.load(open(s, "rb"))
else:
(r, dkey) = s
patid = combineList(r.getPatternID())
vkey = dict(zip(patid, range(len(patid))))
decfn = combineList(r.getDecisionFunction())
lblid = combineList(r.getGivenLabels())
cids = dkey.keys()
D = [[] for i in cids]
L = [[] for i in cids]
A = [[] for i in cids]
try:
R = getRMSDDict('shandar_rmsd.txt')
except:
R = None
Rx = [[] for i in cids]
for i, cid in enumerate(cids):
cidx = dkey[cid]
if type(cidx) is tuple: #backward compatability to old results objects
cidx = cidx[0]
for e in cidx:
try:
n = vkey[e]
except KeyError:
pdb.set_trace()
D[i].append(decfn[n])
L[i].append(lblid[n])
(_, _, a) = roc.roc(D[i], L[i])
A[i] = a
if R is not None:
Rx[i] = R[cid]
(fp, tp, auc) = roc.roc_VA(zip(D, L))
return (auc, (fp, tp), (A, Rx, D, L, cids, r, dkey))
from myPDB import *
from getExamplesDBD_breakup import *
from PyML.evaluators.roc import roc
E = getExamplesDBD.loader(
os.path.join('../../DBD4CSPKL/PKL', 'ENS_15_35_50.lbl.pkl'))
pdbdir = '../../DBD4CSPKL/PDB_all_'
pkldir = '../../DBD4CSPKL/PKL'
F = list(
set([
getFileParts(g)[1].split('.')[0]
for g in glob.glob(os.path.join(pkldir, '*.pdb.pkl'))
]))
A = {}
for fid in F:
print fid
X = myPDB.loader(os.path.join(pkldir, fid + '.pdb.pkl'))
C = np.max(X.pssm, axis=0)
#C=X.rasa#np.sum(.psfm,axis=0)
#C=JSON2ConsScore(ipdbfile, jfile)
fcids = [k for k in E.Pex.keys() if (fid in k)]
fPi = []
for c in fcids:
fPi.extend([i[int(c[0] != fid)] for i in E.Pex[c][0]])
fPi = np.unique(np.array(fPi))
if len(fPi):
L = np.zeros(len(C))
L[fPi] = 1.0
A[fid] = roc(list(C), list(L))[-1]
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
dd = []
ld = []
md = []
for p in E.Pex[cid][0]:
if p in mx:
#myEdata.append([cid,p[0],p[1],1,mx[p],dx[p]])
dd.append(dx[p])
ld.append(+1)
md.append(mx[p])
for n in E.getNegEx(cid):
if n in mx:
#myEdata.append([cid,n[0],n[1],-1,mx[n],dx[n]])
dd.append(dx[n])
md.append(mx[n])
ld.append(-1)
(_, _, aa_di) = roc.roc(dd, ld)
(_, _, aa_mi) = roc.roc(md, ld)
Xauc.append([aa_mi, aa_di])
print cid, ncs, lstats[0].shape[0], rstats[0].shape[0], Xauc[
-1], Xuauc[-1], Lauc[-2:]
#pdb.set_trace()
if (myid != 0):
comm.send(myEdata, dest=0)
else:
"""
for p in range(1,nprocs):
myEdata.extend(comm.recv(source=p))
output = open(ofname, 'wb')
cPickle.dump(myEdata, output,-1)
output.close()
if evalROC:
'2A5T', '3CPH', '1ZHH', '2ABZ', '1LFD', '2OUL', '1JIW', '2B4J', '1SYX',
'1FLE', '1JTG', '2AYO', '4CPA', '1CLV', '1OC0', '1XU1', '1R6Q', '2O3B',
'1US7', '3D5S', '1JZD', '1HCF', '1OYV', '2OZA', '1H9D', '2A9K', '2J0T',
'2Z0E', '3BP8', '2IDO', '1WDW', '1ZLI', '2VDB', '1RV6', '1FFW', '1F6M',
'BOYV', '1JWH', '2OOR', '1MQ8', '1GL1', '1PVH', '2I9B', '1OFU', '1GXD',
'3SGQ', '1JK9', '1ZM4', '1FCC', '2G77', '2J7P', '2FJU'
]
fs = f3 + f4
E = getExamplesDBD.loader(efile)
A = {}
for cid in fs:
print cid
L = myPDB.loader(bdir + cid + '_l_u.pdb.pkl')
R = myPDB.loader(bdir + cid + '_r_u.pdb.pkl')
V = []
Y = []
for p in E.Pex[cid][0]:
v = L.B[p[0]] + R.B[p[
1]] #np.abs(L.ASA[p[0]]-L.asa[p[0]])+np.abs(R.ASA[p[1]]-R.asa[p[1]])
if ~np.isnan(v):
V.append(v)
Y.append(+1)
for n in E.getNegEx(cid):
v = L.B[n[0]] + R.B[n[
1]] #np.abs(L.ASA[n[0]]-L.asa[n[0]])+np.abs(R.ASA[n[1]]-R.asa[n[1]])
if ~np.isnan(v):
V.append(v)
Y.append(-1)
(_, _, auc) = roc.roc(V, Y)
A[cid] = auc
efile=bdir+'E_125PN_15_35_50.lbl.pkl'
#fs=glob.glob(bdir+'*_u.pdb.pkl')
f3=['1SBB', '1JPS', '2HMI', '1GHQ', '1KTZ', '1K74', '1D6R', '2SIC', '1GPW', '1XD3', '1EAW', '1VFB', '7CEI', '1E4K', '1I4D', '1H1V', '2PCC', '1FQ1', '2HLE', '1FQJ', '1S1Q', '2OOB', '1UDI', '1KLU', '1WQ1', '1CGI', '1ATN', '1N2C', '1GP2', '1FAK', '1NW9', '1GLA', '1GRN', '2HRK', '1AZS', '1JMO', '1PXV', '1EWY', '1RLB', '1DQJ', '2BTF', '2I25', '1I2M', '1BUH', '1BGX', '1ML0', '1EFN', '1DFJ', '1Y64', '2UUY', '1MAH', '1BVK', '1BVN', '1EER', '1MLC', '1NSN', '1AK4', '1A2K', '1QFW', '2H7V', '1T6B', '1KAC', '1YVB', '1J2J', '1QA9', '1AHW', '2OT3', '2FD6', '2AJF', '1K4C', '1NCA', '1OPH', '1XQS', '1B6C', '1PPE', '2O8V', '1HIA', '1Z0K', '1R0R', '1WEJ', '1ACB', '1KXP', '1KXQ', '1R8S', '1IRA', '1GCQ', '1F51', '2B42', '2HQS', '1AKJ', '2JEL', '1KKL', '1FC2', '1E96', '1N8O', '2MTA', '2VIS', '1IB1', '1E6J', '1Z5Y', '1EZU', '1TMQ', '2C0L', '1E6E', '1IQD', '1ZHI', '1M10', '2NZ8', '1AY7', '1HE8', '1IJK', '1HE1', '1FSK', '1F34', '2SNI', '1BJ1', '2CFH', '1BKD', '1DE4', '1IBR', '1I9R', '1K5D', '1AVX']
f4=['2A5T', '3CPH', '1ZHH', '2ABZ', '1LFD', '2OUL', '1JIW', '2B4J', '1SYX', '1FLE', '1JTG', '2AYO', '4CPA', '1CLV', '1OC0', '1XU1', '1R6Q', '2O3B', '1US7', '3D5S', '1JZD', '1HCF', '1OYV', '2OZA', '1H9D', '2A9K', '2J0T', '2Z0E', '3BP8', '2IDO', '1WDW', '1ZLI', '2VDB', '1RV6', '1FFW', '1F6M', 'BOYV', '1JWH', '2OOR', '1MQ8', '1GL1', '1PVH', '2I9B', '1OFU', '1GXD', '3SGQ', '1JK9', '1ZM4', '1FCC', '2G77', '2J7P', '2FJU']
fs=f3+f4
E=getExamplesDBD.loader(efile)
A={}
for cid in fs:
print cid
L=myPDB.loader(bdir+cid+'_l_u.pdb.pkl')
R=myPDB.loader(bdir+cid+'_r_u.pdb.pkl')
V=[]
Y=[]
for p in E.Pex[cid][0]:
v=L.B[p[0]]+R.B[p[1]]#np.abs(L.ASA[p[0]]-L.asa[p[0]])+np.abs(R.ASA[p[1]]-R.asa[p[1]])
if ~np.isnan(v):
V.append(v)
Y.append(+1)
for n in E.getNegEx(cid):
v=L.B[n[0]]+R.B[n[1]]#np.abs(L.ASA[n[0]]-L.asa[n[0]])+np.abs(R.ASA[n[1]]-R.asa[n[1]])
if ~np.isnan(v):
V.append(v)
Y.append(-1)
(_,_,auc)=roc.roc(V,Y)
A[cid]=auc
from PyML.evaluators import roc
from postProcess import postProcessAvg
#from getExamplesDBD import getPosex
from symmetryProcessing import *
#bdir='../CAPRI/'
bdir='../../g2mers/'
cid='1MLC'
#(_,_,P,_,_)=getPosex(bdir,cid) #get positive examples
P=getPosexFromPDB(bdir,cid,dthr=6.0) # Handles symmetry in the complex
ppfile=bdir+cid+'.pairpred.txt'
(auc,Mv,Ml,lseq,rseq,lrV,rrV)=readFile(ppfile,usePDBidx=False)
#auc0,Mvc0,Mv,Mlc,lseq,rseq,lrV0,lrV,rrV0,rrV=postProcessAvg(cid,bdir,bdir)
#
#Mv[:10,:]=np.nan
#Mv[-10:,:]=np.nan
#Mv[:,:10]=np.nan
#Mv[:,-10:]=np.nan
Mvtbl=np.zeros(Mv.shape)
for (i,j) in P:
Mvtbl[i,j]=1.0
Mvr=Mv.ravel()
Mvtblr=Mvtbl.ravel()
nidx=(~np.isnan(Mvr))
Mvr=Mvr[nidx]
Mvtblr=Mvtblr[nidx]
(fpv,tpv,aucv)=roc.roc(list(Mvr),list(Mvtblr))
print cid,"AUC =",aucv, "RFPP =",np.argmax(Mvtblr[np.argsort(-Mvr)]==1)
(fpl,tpl,auc)=roc.roc(list(np.nanmax(Mv,axis=0)),list(np.nanmax(Mvtbl,axis=0))); print auc
(fpl,tpl,auc)=roc.roc(list(np.nanmax(Mv,axis=1)),list(np.nanmax(Mvtbl,axis=1))); print auc
dd=[]
ld=[]
md=[]
for p in E.Pex[cid][0]:
if p in mx:
#myEdata.append([cid,p[0],p[1],1,mx[p],dx[p]])
dd.append(dx[p])
ld.append(+1)
md.append(mx[p])
for n in E.getNegEx(cid):
if n in mx:
#myEdata.append([cid,n[0],n[1],-1,mx[n],dx[n]])
dd.append(dx[n])
md.append(mx[n])
ld.append(-1)
(_,_,aa_di)=roc.roc(dd,ld)
(_,_,aa_mi)=roc.roc(md,ld)
Xauc.append([aa_mi,aa_di])
print cid,ncs,lstats[0].shape[0],rstats[0].shape[0],Xauc[-1],Xuauc[-1],Lauc[-2:]
#pdb.set_trace()
if(myid!=0):
comm.send(myEdata, dest=0)
else:
"""
for p in range(1,nprocs):
myEdata.extend(comm.recv(source=p))
output = open(ofname, 'wb')
cPickle.dump(myEdata, output,-1)
output.close()
if evalROC:
MV=[]
def getROC(self, rocN = None) :
rocTP, rocFP, rocValue = roc_module.roc(self.decisionFunc, self.givenY,
rocN, self.rocNormalization)
return rocValue
def getROC(self, rocN = None) :
rocTP, rocFP, rocValue = roc_module.roc(self.decisionFunc, self.givenY,
rocN, self.rocNormalization)
return rocValue
"""
Created on Wed Nov 27 08:40:33 2013
@author: root
"""
from myPDB import *
from getExamplesDBD_breakup import *
from PyML.evaluators.roc import roc
E=getExamplesDBD.loader(os.path.join('../../DBD4CSPKL/PKL','ENS_15_35_50.lbl.pkl'))
pdbdir='../../DBD4CSPKL/PDB_all_'
pkldir='../../DBD4CSPKL/PKL'
F=list(set([getFileParts(g)[1].split('.')[0] for g in glob.glob(os.path.join(pkldir,'*.pdb.pkl'))]))
A={}
for fid in F:
print fid
X=myPDB.loader(os.path.join(pkldir,fid+'.pdb.pkl'))
C=np.max(X.pssm,axis=0)
#C=X.rasa#np.sum(.psfm,axis=0)
#C=JSON2ConsScore(ipdbfile, jfile)
fcids=[k for k in E.Pex.keys() if (fid in k)]
fPi=[]
for c in fcids:
fPi.extend([i[int(c[0]!=fid)] for i in E.Pex[c][0]])
fPi=np.unique(np.array(fPi))
if len(fPi):
L=np.zeros(len(C))
L[fPi]=1.0
A[fid]=roc(list(C),list(L))[-1]
def getAUC4Protein(lrV):
vl=map(list, zip(*lrV.values()));vv=vl[0];ll=vl[1]
(_,_,a)=roc.roc(vv,ll)
vv=np.array(vv)
ll=np.array(ll)
return (a,vv,ll)
except:
continue
#Get our results
Mo=np.zeros((len(L.S2Ri),len(R.S2Ri)))
Mo.fill(np.nan)
ifile=cdir+'/InterPRed_prediction/2X000.InterPRed.txt'
for ln in open(ifile,'r'):
lns=ln.split()
r=int(lns[3])
c=int(lns[8])
v=float(lns[10])
Mo[r,c]=v
"""
print 'MI1- auc',roc.roc(MI1,trbs)[-1]
print 'Shandar - auc',roc.roc(np.nanmax(M,axis=0),trbs)[-1]
print 'Our - auc',roc.roc(np.nanmax(Mo,axis=0),trbs)[-1]
plotdv(rseqn,trbs)
plotdv(rseqn,np.nanmax(M,axis=0))
plotdv(rseqn,np.nanmax(Mo,axis=0))
#plotdv(rseqn,MI1)
plt.show()
"""
plt.plot([0,1],[0, 1],'k:',linewidth=2.0)
(fp,tp,auc)=roc.roc(list(M.flatten()),list(Mt.flatten()));plt.plot(fp,tp,'r-.',linewidth=2.0);print auc
(fp,tp,auc)=roc.roc(MI1,list(np.nanmax(Mt,axis=0)));plt.plot(fp,tp,'g--',linewidth=2.0);print auc
(fp,tp,auc)=roc.roc(list(Mo.flatten()),list(Mt.flatten()));plt.plot(fp,tp,'b-',linewidth=2.0);print auc
plt.grid()
plt.xlabel('FPR')
plt.ylabel('TPR')
plt.legend(['Random : 50.0','PPiPP : 54.0','MI-1 : 59.6','PAIRPred : 63.8'],loc=0);plt.title('EF-CAM Results');plt.show()
