def parallelRun(N,pdbpklpath,pppath,ofname=None,comm=None,myid=0,nprocs=1):
"""
Wrapper for running computeDistMeansForComplex in parallel
"""
cids=incids
csize=int(np.ceil(len(cids)/float(nprocs)))
gclist=list(chunks(cids,csize))
mycids=gclist[myid]
A={}
for cid in mycids:
print "Processing",cid
try:
A[cid]=computeDistMeansForComplex(cid,N,pdbpklpath,pppath)
except Exception as ee:
print "Error processing", cid,ee, traceback.format_exc()
continue
Ascores=None
if(myid!=0):
comm.send(A, dest=0)
if(myid==0):
gcK=[A]
for p in range(1,nprocs):
gcK.append(comm.recv(source=p))
Ascores=mergeDicts(gcK)
if ofname is not None:
Pickle.dump(ofname,Ascores)
print "Saved scores file:",ofname
return Ascores
def onFileTriggered(self, event):
if str(event.text()) == "Save":
Pickle.dump(self.view, "current.pkl")
if str(event.text()) == "Open":
self.view.scene.clear()
self.setMode("free")
Pickle.load(self.view, "current.pkl")
def onFileTriggered(self, event):
if str(event.text()) == "Save":
Pickle.dump(self.view, "current.pkl")
if str(event.text()) == "Open":
self.view.scene.clear()
self.setMode("free")
Pickle.load(self.view, "current.pkl")
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 parallelRun(N,
pdbpklpath,
pppath,
ofname=None,
comm=None,
myid=0,
nprocs=1):
"""
Wrapper for running computeDistMeansForComplex in parallel
"""
cids = incids
csize = int(np.ceil(len(cids) / float(nprocs)))
gclist = list(chunks(cids, csize))
mycids = gclist[myid]
A = {}
for cid in mycids:
print "Processing", cid
try:
A[cid] = computeDistMeansForComplex(cid, N, pdbpklpath, pppath)
except Exception as ee:
print "Error processing", cid, ee, traceback.format_exc()
continue
Ascores = None
if (myid != 0):
comm.send(A, dest=0)
if (myid == 0):
gcK = [A]
for p in range(1, nprocs):
gcK.append(comm.recv(source=p))
Ascores = mergeDicts(gcK)
if ofname is not None:
Pickle.dump(ofname, Ascores)
print "Saved scores file:", ofname
return Ascores
lD=getDistMat(getCoords(L.R))
rD=getDistMat(getCoords(R.R))
lM=np.max(lD)
rM=np.max(rD)
lD=lD/lM
rD=rD/rM
D=[]
for k0,(l0,r0) in enumerate(pex):
for l1,r1 in pex[k0+1:]:
d=np.max((lD[l0,l1],rD[r0,r1]))
D.append(d)
C=C+np.histogram(D,bins)[0]
except Exception as e:
print "Error",e
continue
mPickle.dump(ofname,(bins,C))
else:
(bins,C)=mPickle.load(ofname)
bb=(bins[1:]+bins[:-1])/2
idx=bb<=1
bb=bb[idx]
C=C[idx]
plt.plot(bb,C,'b',linewidth=2);plt.grid();
plt.xlabel('Normalized pairwise distance (d)');
plt.ylabel('Number of pairs of simultaneosuly interacting residue pairs',color='b');
ax1=plt.gca()
ax2 = ax1.twinx()
ax2.plot(bb, np.cumsum(C)/np.sum(C), 'r.-',linewidth=2)
ax2.set_ylabel('Cumulative proporion of pairs of simultaneosuly interacting residue pairs', color='r')
plt.show()
def saveMIFile(M, ofile):
"""
save the MI variables in a zipped pickle binary file
"""
cPickle.dump(ofile, M)
lD = getDistMat(getCoords(L.R))
rD = getDistMat(getCoords(R.R))
lM = np.max(lD)
rM = np.max(rD)
lD = lD / lM
rD = rD / rM
D = []
for k0, (l0, r0) in enumerate(pex):
for l1, r1 in pex[k0 + 1:]:
d = np.max((lD[l0, l1], rD[r0, r1]))
D.append(d)
C = C + np.histogram(D, bins)[0]
except Exception as e:
print "Error", e
continue
mPickle.dump(ofname, (bins, C))
else:
(bins, C) = mPickle.load(ofname)
bb = (bins[1:] + bins[:-1]) / 2
idx = bb <= 1
bb = bb[idx]
C = C[idx]
plt.plot(bb, C, 'b', linewidth=2)
plt.grid()
plt.xlabel('Normalized pairwise distance (d)')
plt.ylabel('Number of pairs of simultaneosuly interacting residue pairs',
color='b')
ax1 = plt.gca()
ax2 = ax1.twinx()
ax2.plot(bb, np.cumsum(C) / np.sum(C), 'r.-', linewidth=2)
SPECIAL = chars.copy()
for c in NORMAL:
if c in chars:
SPECIAL.pop(c)
SPECIAL = list(SPECIAL.keys())
TOT = { c:i for i, c in enumerate(['\n'] + NORMAL) }
TOT.update( {c:len(TOT) for c in SPECIAL} )
else:
TOT = { c:i for i, c in enumerate(['\n'] + list(chars.keys())) }
#####################################
# WRITE CHARS MAP ON FILE
CM_OUT = os.path.join(HOME, 'charmap.pickle')
myPickle.dump(CM_OUT, TOT)
#####################################
# CONVERT PASSWORDS IN INDEX
X = [string2index(x, MAX_LEN, TOT) for x in X]
#####################################
# CREATE WRITE TEST IN FILE
TEST_OUT = os.path.join(HOME, 'rfX')
Xtest = np.array(X)
Xtest = np.squeeze(Xtest)
rank = np.array(rank)[:, None]
rfX = np.concatenate((rank, F[:, None], Xtest), 1)
np.save(TEST_OUT, rfX)
#####################################
for p in range(1,nprocs):
(DNTP_p,dsA_p,LV_p,LVP_p,TPS_p)=comm.recv(source=p)
dsAr.append(dsA_p)
DNTP.extend(DNTP_p)
LV.extend(LV_p)
LVP.extend(LVP_p)
TPS.extend(TPS_p)
dsA=mergeDicts(dsAr)
print 'Number of complexes',len(dsA)
#print 'Complex wise AUC = ',np.mean(dA.values())
p12=map(list,zip(*dsA.values()));pa=p12[0];p1=p12[1];p2=p12[2];ps=p1;ps.extend(p2);
print 'Complex Wise AUC =',np.mean(pa),'Protein Wise AUC =',np.mean(ps)
if not auconly:
(fplv,tplv,auclv)=roc.roc_VA(LV)
(fplvp,tplvp,auclvp)=roc.roc_VA(LVP)
mkl.dump(ofname,((fplv,tplv,auclv),(fplvp,tplvp,auclvp),dsA))
print "Results file saved",ofname
print "AUC = ",auclv
"""
plt.hist(np.array(DNTP).flatten(),[0,1,2,3,4,5,6,1000],cumulative=True);plt.grid();plt.xlabel('sequence distance');plt.ylabel('counts');plt.title('Number of top 200 predictions vs. sequence distance from nearest true positive');plt.show()
[np.sum(dn<2.0) for dn in DNTP]
cids=[getFileParts(getFileParts(ifile)[1])[1] for ifile in fs]
[dsA[cid] for cid in cids]
[dAo[cid] for cid in cids]
"""
#DISTRIBUTION PLOT
dthresh=[0,1,2,3,4] # sequence distance threshold
XX=calcRFPP(np.array(TPS)[:,1]+1,DNTP,dthresh=dthresh)
if doplot:
plt.figure();plt.plot(fplv,tplv);plt.xlabel('FP');plt.ylabel('TP');plt.grid();plt.title('ROC Curve: AUC = %1.2f' % (auclv*100))
plt.figure();plt.boxplot(tuple(XX),bootstrap=1000,positions=dthresh);plt.xlabel('Sequence Distance (D) from a TP'); plt.ylabel('Minimum rank of a prediction within distance D of a TP' );plt.title('Results of soft sequence distance threshold');plt.grid();plt.yticks(range(0,201,10));
r=(pap+rp,panp+rnp)#+(100*np.mean(Ml[~np.isnan(Ml)]>0),Mv.shape[0],Mv.shape[1])
#(auc,Mv,Ml,lseq,rseq,lrV,rrV)=readFile(fname)
except Exception as e:
print e
print '-'*60
print '###PROCESSSING FAILED FOR ',cid,e
traceback.print_exc(file=sys.stdout)
print '-'*60
r=np.nan
rfpp.append(r)
print cid,rfpp
R[cid]=rfpp
# (AUC, AUCL, AUCR, NTP,RFP)_post,(AUC, AUCL, AUCR, NTP,RFP)_no_post,pp, percentage of positives, |L|,|R|
myPickle.dump('DBD4_SGD_CENTPW71.res.pkl',R)
#V=np.array([r for r in R.values() if ~np.any(np.isnan(r))])
#import scipy.stats
#scipy.stats.wilcoxon(V[:,0]-V[:,1])
#cc=['1KTZ', '2OOB']
#Ro={};
#for k in R:
# if k not in cc:
# Ro[k]=[]
# for m in range(len(R[k])):
# Ro[k].extend(R[k][m][0]+R[k][m][1])
#
#mV=np.mean(Ro.values(),axis=0)
#print mV
k0 = (three_to_one(Lu.R[a].get_resname()),
three_to_one(Ru.R[b].get_resname()))
k1 = (three_to_one(Ru.R[b].get_resname()),
three_to_one(Lu.R[a].get_resname()))
except KeyError:
continue
Ncnt[k0] = Ncnt[k0] + 1
Ncnt[k1] = Ncnt[k1] + 1
addASA(cid, True, lPex, APcnt, Lu, Lb, Lu2b)
addASA(cid, False, rPex, APcnt, Ru, Rb, Ru2b)
addASA(cid, True, lNex, ANcnt, Lu, Lb, Lu2b)
addASA(cid, False, rNex, ANcnt, Ru, Rb, Ru2b)
#pdb.set_trace()
myPickle.dump(ofname, (Pcnt, Ncnt, APcnt, ANcnt, TAC))
else:
print "Using existing file", ofname
(Pcnt, Ncnt, APcnt, ANcnt, TAC) = myPickle.load(ofname)
Pm = getMtx(Pcnt)
Nm = getMtx(Ncnt)
v = np.atleast_2d(np.sum(Nm, axis=0) + np.sum(Pm, axis=0))
Ex = np.sum(Pm) * ((v * v.T) / np.sum((v * v.T)))
#
pp = ((Pm - Ex)**2) / (Ex)
#pp=(Pm/np.sum(Pm))/(Nm/np.sum(Nm))
pp = np.log2(Pm / Ex)
print categ, calc_gini(pp.flatten())
def saveMIFile(M,ofile):
"""
save the MI variables in a zipped pickle binary file
"""
cPickle.dump(ofile, M)
TPS.extend(TPS_p)
dsA = mergeDicts(dsAr)
print 'Number of complexes', len(dsA)
#print 'Complex wise AUC = ',np.mean(dA.values())
p12 = map(list, zip(*dsA.values()))
pa = p12[0]
p1 = p12[1]
p2 = p12[2]
ps = p1
ps.extend(p2)
print 'Complex Wise AUC =', np.mean(pa), 'Protein Wise AUC =', np.mean(
ps)
if not auconly:
(fplv, tplv, auclv) = roc.roc_VA(LV)
(fplvp, tplvp, auclvp) = roc.roc_VA(LVP)
mkl.dump(ofname,
((fplv, tplv, auclv), (fplvp, tplvp, auclvp), dsA))
print "Results file saved", ofname
print "AUC = ", auclv
"""
plt.hist(np.array(DNTP).flatten(),[0,1,2,3,4,5,6,1000],cumulative=True);plt.grid();plt.xlabel('sequence distance');plt.ylabel('counts');plt.title('Number of top 200 predictions vs. sequence distance from nearest true positive');plt.show()
[np.sum(dn<2.0) for dn in DNTP]
cids=[getFileParts(getFileParts(ifile)[1])[1] for ifile in fs]
[dsA[cid] for cid in cids]
[dAo[cid] for cid in cids]
"""
#DISTRIBUTION PLOT
dthresh = [0, 1, 2, 3, 4] # sequence distance threshold
XX = calcRFPP(np.array(TPS)[:, 1] + 1, DNTP, dthresh=dthresh)
if doplot:
plt.figure()
plt.plot(fplv, tplv)