def msai2resi():
if len(sys.argv) < 4:
print 'msai2resi: output the mapping between msa position index and pdb residue number'
print 'example:python utils_msa.py msai2resi PF07714_full.fa BTK_HUMAN 1k2p.pdb\n'
print 'output: PF07714_full.fa.1k2p.pdb.map'
return
msafile = sys.argv[2]
target = sys.argv[3]
pdbfile = sys.argv[4]
outfile = msafile+'.'+pdbfile+'.map'
print 'msafile: %s\ntarget header: %s\npdbfile: %s\noutput file: %s' % (msafile, target, pdbfile, outfile)
m = msa(msafile)
p = protein(pdbfile)
rtmap = m.getResiTargetMap(p, target)
if len(rtmap) < 1:
print 'error occoured in generating rtmap'
return
#print '%s: %s' % (tvar, repr(rtmap[tvar]))
# construct trmap from rtmap
# 3128: (B641, 'R')
trmap = {}
#trmap = {v: k for k, v in rtmap.iteritems()}
fout = open(outfile ,'w')
for k in rtmap:
msai, resn = rtmap[k]
if msai in trmap:
print 'error. duplicate key [%d] in rtmap' % msai
return
trmap[msai] = (k, resn)
fout.write('%d %d %d' % (msai, k, resn))
fout.close()
def main():
if len(sys.argv)< 2:
print "Usage: proc_spectralFilter.py pdb(tip)file >> tip_clusters.txt"
return
p=protein(sys.argv[1], 'v4',center='TIP')
p.spectralClustering(6)
def main():
if len(sys.argv) < 2:
print "Usage python proc_extractDomain.py domain_desc_file"
return
fin = open(sys.argv[1], 'r')
for line in fin.readlines():
line = line.strip()
strArr = line.split(',')
tip_filename = strArr[0]
start = int(strArr[1])
end = int(strArr[2])
print tip_filename+'.domain'
fo = open(tip_filename+'.domain', 'w')
p = protein('a'+tip_filename+'.tip', 'alpha',center='TIP')
for a in p.atoms:
if a.resSeq >= start and a.resSeq <= end:
fo.write(a.writeAtom())
fo.close()
fin.close()
def main():
if len(sys.argv)< 2:
print "Usage: proc_SinglePDBFilter.py pdb(tip)file >> tip_clusters.txt"
return
p=protein(sys.argv[1], 'v3',center='TIP')
p.filterClusters()
def writencg(): if len(sys.argv) < 4: print 'writencg(): write non parametric contact group matrix for a (coarse-grained) pdb with size cutoff' print 'writencg(): python utils_ncg.py writencg 1t3r.pdb 3' return pdbfile = sys.argv[2] size = int(sys.argv[3]) outfile = pdbfile+'.ncg' print 'writencg(): pdbfile: %s' % pdbfile print 'writencg(): ncg size: %d' % size print 'writencg(): output: %s' % outfile ncgArray = [] p = protein(pdbfile) for a in p.atoms: c = ncg(a, size) ncgArray.append(c) fout = open(outfile, 'w') for c in ncgArray: c.grow(p.atoms) fout.write(c.outStr()+'\n') fout.close()
def main():
if len(sys.argv)< 3:
print "Usage: proc_N-mer.py tip_file cluster_file n_mer dist_cutoff >> n_mer_outfile"
return
infile = sys.argv[1]
infile2 = sys.argv[2]
n_mer = int(sys.argv[3])
cutoff = float(sys.argv[4])
p = protein(infile, center='TIP')
p.initCGResiMap()
with open(infile2) as fp:
for line in fp:
cg = cgroup(line.strip())
if cg.getSize() == n_mer:
if p.cgResiGroupFilter(cg, cutoff) == True:
print cg.getString()
elif cg.getSize() < n_mer:
continue
else:
# generate combinations
for idx in list(itertools.combinations(range(cg.getSize()),n_mer)):
sub_cg = cgroup()
sub_cg.pdb = cg.pdb
sub_cg.chain = cg.chain
for i in idx: # iterate all the tuples
sub_cg.AAgroup = sub_cg.AAgroup + cg.AAgroup[i]
sub_cg.resi.append(cg.resi[i])
if p.cgResiGroupFilter(sub_cg, cutoff) == True:
print sub_cg.getString()
fp.close()
def ncg2sdiicol():
if len(sys.argv)<7:
print 'ncg2sdiicol: write selected MSA column into .sdiicol file'
print 'python utils_msa.py ncg2sdiicol 1aps_A_1_97.rpdb.tip 1aps_A_1_97.rpdb.tip.ncg PF00708_full.txt.rseq PF00708_full.txt.all_2_sdiii ACYP2_HORSE 2'
return
pdbfile = sys.argv[2] # pdb name
ncgfile = sys.argv[3] # hcg
msafile = sys.argv[4] # msa (full or reduced)
sdiifile = sys.argv[5] # sdii
target = sys.argv[6] # target name
orderlist = [int(i) for i in sys.argv[7].split(',')]
outfile = pdbfile[0:4]+'_'+msafile[0:7]+'.sdiicol'# new substitution matrix
print 'pdbfile :%s' % pdbfile
print 'ncgfile :%s' % ncgfile
print 'msafile :%s' % msafile
print 'sdiifile :%s' % sdiifile
print 'uniprot name :%s' % target
print 'ncg order list : [%s]' % repr(orderlist)
print 'outfile: %s' % outfile
# get msa in matrix format
m = msa(msafile)
msaMatrix = np.array([list(s[1]) for s in m.msaArray]) # matrix format of msa
#for i in xrange(0, len(seqs)):
# print seqs[i]
print 'msa matrix: ' + repr(msaMatrix.shape)
# get resi -> msai map
p = protein(pdbfile)
rtmap = m.getResiTargetMap(p, target) # ('A9', (14, 'V')) : (resi+chain, (MSA index, resn))
sdiidict = loadsdii(sdiifile) # key: 39-140-210, value = 0.0788593466276019
msaGroupArray = ncg2msa(ncgfile, rtmap) # unsorted [[86, 83, 198, 127, 120], [138, 76, 82, 127, 132]]
# output msa column set
colset = set()
for i in orderlist:
for g in msaGroupArray:
rg = g[0:i] # get ith order contact group
rg.sort() # for generating key
sdiikey = '-'.join([str(r) for r in rg])
if sdiikey not in sdiidict:
#print 'ncg2sdiicol(): discard group: %s for low sdii' % sdiikey
continue
print (sdiikey, sdiidict[sdiikey])
for resi in rg: # for significant ncg, add corresponding MSA column index
colset.add(resi)
print 'ncg2sdiicol():writing %s: %s' % (outfile, repr(colset))
fout = open(outfile, 'w')
fout.write(' '.join([str(c) for c in colset]))
fout.close()
def getresset(): if len(sys.argv) < 2: print 'getresset(): python utils_sdii.py getresset result_sdii' return pdbfile = sys.argv[2] chain = sys.argv[3] p = protein(pdbfile, chain) print p.seq
def main():
fin = open('pdblist.txt', 'r')
lines = fin.readlines()
fin.close()
for i in xrange(0,len(lines)):
line = lines[i].strip()
# pdb_filename=line+'.pdb'
pdb_filename=line+'.tip'
p=protein(pdb_filename,'fasta')
p.writeSeq(line+'.fa')
pass
def main():
fin = open('pdblist.txt', 'r')
lines = fin.readlines()
fin.close()
for i in xrange(0,len(lines)):
line = lines[i].strip()
pdb_filename=line+'.pdb'
print pdb_filename
p=protein(pdb_filename,'CA_A')
p.writeChainACA('ca_'+line+'.pdb')
pass
def sdii2resi():
if len(sys.argv) < 5:
print 'resi2target: given a residue number output the corresponding position in target msa'
print 'example:python utils_msa.py sdii2resi PF07714_full.fa.r50 BTK_HUMAN 1k2p.pdb PF07714_full.fa.r50.3128_3_sdii\n'
print 'output: PF07714_full.fa.r50.3128_3_sdii_resi'
return
msafile = sys.argv[2]
target = sys.argv[3]
pdbfile = sys.argv[4]
sdiifile = sys.argv[5]
print 'msafile: %s\ntarget header: %s\npdbfile: %s\nsdii file: %s' % (msafile, target, pdbfile, sdiifile)
m = msa(msafile)
p = protein(pdbfile)
rtmap = m.getResiTargetMap(p, target)
if len(rtmap) < 1:
print 'error occoured in generating rtmap'
return
#print '%s: %s' % (tvar, repr(rtmap[tvar]))
# construct trmap from rtmap
# 3128: (B641, 'R')
trmap = {}
#trmap = {v: k for k, v in rtmap.iteritems()}
for k in rtmap:
msai, resn = rtmap[k]
if msai in trmap:
print 'error. duplicate key [%d] in rtmap' % msai
return
trmap[msai] = (k, resn)
#print trmap
# read sdii file
with open(sdiifile) as f:
sdiilines = f.readlines()
outfile = sdiifile + '_resi'
fout = open(outfile, 'w')
# 52 [pid:20029] 926-3089-3128 0.001106226720675
count = 0
for line in sdiilines:
count += 1
print '%d/%d processed ...' % (count, len(sdiilines))
strArr = line.strip().split(' ')
msailist = strArr[2].split('-')
sdiivalue = strArr[3]
fout.write('%s %s\n' % ('-'.join([repr(trmap[int(i)]) for i in msailist]), sdiivalue))
fout.close()
print 'done.\noutput file: [%s]' % outfile
def writeseq(): if len(sys.argv) < 3: print 'writeseq(): write pdb sequence' print 'writeseq(): python utils_protein.py writeseq 1t3r.pdb' print 'writeseq(): output: 1t3r.pdb.seq' return pdbfile = sys.argv[2] outfile = sys.argv[2]+'.seq' print 'writeseq(): pdbfile: %s' % pdbfile print 'writeseq(): outfile: %s' % outfile p = protein(pdbfile) fout = open(outfile, 'w') fout.write(p.seq+'\n') fout.close()
def searchpdbseq(): if len(sys.argv) < 2: print 'searchpdbseq: locate pdb sequence in MSA' print 'example: python utils_msa.py searchpdbseq PF07714_full.fa 1T49_A.pdb\n' return msafile = sys.argv[2] target = sys.argv[3] print 'msa file: %s' % msafile print 'pdb target: %s' % target m = msa(msafile) p = protein(target) if m.searchTargetPDB(p)==0: print 'cannot locate pdb sequence in MSA'
def main():
if len(sys.argv) < 2:
print 'Usage: proc_getTip.py pdblist'
return
pdblist = sys.argv[1]
fin = open(pdblist, 'r')
lines = fin.readlines()
fin.close()
for i in xrange(0,len(lines)):
line = lines[i].strip()
#pdb_filename=line+'.pdb'
pdb_filename=line
print pdb_filename
p=protein(pdb_filename)
p.writeChainATips('AAtips.def',line+'.tip')
pass
def resi2target(): if len(sys.argv) < 5: print 'resi2target: given a residue number output the corresponding position in target msa' print 'example:python utils_msa.py resi2target PF07714_full.fa.r50 BTK_HUMAN 1k2p.pdb B641\n' return msafile = sys.argv[2] target = sys.argv[3] pdbfile = sys.argv[4] tvar = sys.argv[5] print 'msafile: %s\ntarget header: %s\npdbfile: %s\ntarget variable: %s' % (msafile, target, pdbfile, tvar) m = msa(msafile) p = protein(pdbfile) print p.resDict[tvar] rtmap = m.getResiTargetMap(p, target) if len(rtmap) < 1: return print 'map %s: %s' % (tvar, repr(rtmap[tvar])) return (tvar, rtmap[tvar][0], rtmap[tvar][1])
def resi2msai(): if len(sys.argv) < 5: print 'resi2target: given a residue number output the corresponding position in target msa' print 'python utils_msa.py resi2msai PF00014_full.txt BPT1_BOVIN 5pti_pf.pdb A6' return msafile = sys.argv[2] target = sys.argv[3] pdbfile = sys.argv[4] tvar = sys.argv[5] print 'msafile: %s\ntarget header: %s\npdbfile: %s\ntarget variable: %s' % (msafile, target, pdbfile, tvar) m = msa(msafile) p = protein(pdbfile) print p.resDict[tvar] rtmap = m.getResiTargetMap(p, target) if len(rtmap) < 1: return print 'map %s: %s' % (tvar, repr(rtmap[tvar])) return (tvar, rtmap[tvar][0], rtmap[tvar][1])
def pdbcut():
if len(sys.argv) < 5:
print 'pdbcut(): write pdb by residue segment'
print 'pdbcut(): python utils_protein.py pdbcut 1t3r.pdb A 5-15'
print 'pdbcut(): python utils_protein.py pdbcut 1t3r.pdb all 5-15'
return
pdbfile = sys.argv[2]
chain = sys.argv[3]
rangeStr = sys.argv[4]
rangeArray = rangeStr.split('-')
rBegin = int(rangeArray[0])
rEnd = int(rangeArray[1])
pdbname = pdbfile[0:4]
outfile = '%s_%s_%d-%d.rpdb' % (pdbname, chain, rBegin, rEnd)
print 'pdbcut():pdbfile: %s' % pdbfile
print 'pdbcut():pdb: %s' % pdbname
print 'pdbcut():chain: %s' % chain
print 'pdbcut():residue range: %d - %d' % (rBegin, rEnd)
p = protein(pdbfile)
out = []
if chain == 'all':
for a in p.atoms:
if a.resSeq <= rEnd and a.resSeq >= rBegin:
out.append(a)
else:
for a in p.atoms:
if (a.resSeq <= rEnd and a.resSeq >= rBegin and a.chainID.lower() == chain.lower()):
out.append(a)
fout = open(outfile, 'w')
print 'pdbcut():output: %s' % outfile
print 'pdbcut():%d atoms written.' % len(out)
for a in out:
fout.write(a.writeAtom())
fout.close()
def resn2bfactor():
if len(sys.argv) < 3:
print 'resn2bfactor(): replace b factor values with residue type.'
print 'resn2bfactor(): used for pymol spectrum b'
return
scoreValue = {
'X':0,'-': 0,'.': 0,'A': 1,'C': 2,'D': 3,'E': 4,'F': 5,'G': 6,'H': 7,'I': 8,'K': 9,
'L': 10,'M': 11,'N': 12,'P': 13,'Q': 14,'R': 15,'S': 16,'T': 17,'V': 18,'W': 19,'Y': 20, 'B': 3
}
aamap = AAmap()
pdbfile = sys.argv[2]
p = protein(pdbfile)
outfile = '%s_rb.pdb' % pdbfile[:-4]
fout = open(outfile, 'w')
for a in p.atoms:
newBFactor = scoreValue[aamap.getAAmap(a.resName)]
print 'new b-factor: [%s : %s] -> %d' % (a.resName, aamap.getAAmap(a.resName), newBFactor)
a.tempFactor = newBFactor
fout.write(a.writeAtom())
fout.close()
print 'Output file: %s' % outfile
def main():
if len(sys.argv) < 3:
print 'python proc_dendrogram.py preffix cutoff'
exit
preffix = sys.argv[1]
cutoff = float(sys.argv[2])
# load tip pdb file
pr = protein(preffix)
aamap = AAmap()
n = len(pr.atoms)
resimap = {}
print 'writing %s.resimap ...' % (preffix)
fr = open(preffix+'.resimap', 'w')
px = []
count = 0
for a in pr.atoms:
px.append((a.x, a.y, a.z))
resimap[count] = ('%s%d' % (a.chainID, a.resSeq), aamap.getAAmap(a.resName))
fr.write('%d %s%d %s\n' % (count, a.chainID, a.resSeq, aamap.getAAmap(a.resName)))
count+=1
fr.close()
x = np.array(px)
# calculate pairwised distance
pdist = {}
print 'writing %s.pdist ...' % (preffix)
fo=open(preffix+'.pdist','w')
for i in xrange(0,len(x)):
for j in xrange(i+1,len(x)):
dist = np.linalg.norm(x[i]-x[j])
pdist['%d-%d' % (i,j)] = dist
fo.write('%d-%d : %f\n' % (i,j,dist))
fo.close()
# for hc extraction
hcdict = {}
hclist = []
existdict = {}
#linkage_matrix = linkage(x, "single")
linkage_matrix = linkage(x, "complete")
#ddata = augmented_dendrogram(linkage_matrix, color_threshold=1)
#plt.show()
print 'writing %s.hcluster ...' % (preffix)
fo1 = open(preffix+'.hcluster', 'w')
m = linkage_matrix
for i in xrange(0,len(m)):
#print '%d %d %d %f %d' % (n+i,m[i,0],m[i,1],m[i,2],m[i,3])
fo1.write('%d %d %d %f %d\n' % (n+i,m[i,0],m[i,1],m[i,2],m[i,3]))
hcline = '%d %d %d %f %d' % (n+i,m[i,0],m[i,1],m[i,2],m[i,3])
h = hc(hcline, n)
hcdict[h.clusterID] = h
hclist.append(h)
fo1.close()
# resolve leaves for each cluster
print 'resolving leaves ...'
for h in hclist:
h.getChildren(hcdict)
#h.dump()
print 'iterating clusters for largest proximity contact ...'
for i in xrange(0, n):
leafstr = '%d %d %d 0.0 1' % (i, i, i)
h = hc(leafstr, n)
h.leaves = [i]
hcdict[i] = h
#hcdict[i].dump()
# add single leaf in
for i in xrange(0, n):
existdict[i]= True
for h in hclist:
if h.dist <= cutoff:
if h.c1 in existdict and h.c2 in existdict: # both been checked before
#print '1AA'
if existdict[h.c1] == True and existdict[h.c2] == True:
ret = checkProximity2(hcdict[h.c1], hcdict[h.c2], pdist, cutoff)
existdict[h.clusterID] = ret
if ret == True: # combine both and delete sub cluster in the dict
existdict[h.c1] = False
existdict[h.c2] = False
elif existdict[h.c1] == False or existdict[h.c2] == False:
existdict[h.clusterID] = False
elif h.c1 in existdict and h.c2 not in existdict:
#print '1AB'
if existdict[h.c1] == False: # c1 is not a contact; get h
existdict[h.clusterID] = False
existdict[h.c2] = checkProximity(hcdict[h.c2], pdist, cutoff) # get c2
elif existdict[h.c1] == True: # c1 is a contact; get c2 then get h = c1 and c2
ret = checkProximity(hcdict[h.c2], pdist, cutoff) # get c2
existdict[h.c2] = ret
if ret == False:
existdict[h.clusterID] = False
elif ret == True: # h.c2 is a contact
ret1 = checkProximity2(hcdict[h.c1], hcdict[h.c2], pdist, cutoff)
existdict[h.clusterID] = ret1
if ret1 == True:
existdict[h.c1] = False
existdict[h.c2] = False
elif h.c1 not in existdict and h.c2 in existdict:
#print '1BA'
if existdict[h.c2] == False: # c2 is not a contact; get h
existdict[h.clusterID] = False
existdict[h.c1] = checkProximity(hcdict[h.c1], pdist, cutoff) # get c1
elif existdict[h.c2] == True: # c2 is a contact; get c1 then get h = c1 and c2
ret = checkProximity(hcdict[h.c1], pdist, cutoff) # get c1
existdict[h.c1] = ret
if ret == False:
existdict[h.clusterID] = False
elif ret == True: # h.c1 is a contact
ret1 = checkProximity2(hcdict[h.c1], hcdict[h.c2], pdist, cutoff)
existdict[h.clusterID] = ret1
if ret1 == True:
existdict[h.c1] = False
existdict[h.c2] = False
elif h.c1 not in existdict and h.c2 not in existdict:
#print '1BB'
r1 = checkProximity(hcdict[h.c1], pdist, cutoff)
existdict[h.c1] = r1
r2 = checkProximity(hcdict[h.c2], pdist, cutoff)
existdict[h.c2] = r2
if r1 == False or r2 == False:
existdict[h.clusterID] = False
elif r1 == True and r2 == True:
ret = checkProximity2(hcdict[h.c1], hcdict[h.c2], pdist, cutoff)
if ret == True:
existdict[h.c1] = False
existdict[h.c2] = False
elif h.dist > cutoff:
#print '0XX'
existdict[h.clusterID] = False
if h.c1 not in existdict:
existdict[h.c1] = checkProximity(hcdict[h.c1], pdist, cutoff)
if h.c2 not in existdict:
existdict[h.c2] = checkProximity(hcdict[h.c2], pdist, cutoff)
# print out the result
print 'writing result into %s.hcg' % preffix
fout = open(preffix+'.hcg', 'w')
count=0
for hid in existdict:
#if hid >= N and existdict[hid] == True:
if existdict[hid] == True:
#fout.write('%d: %r, %s' % (hid, existdict[hid], hcdict[hid].writeString()))
fout.write('%s,%s\n' % (preffix, hcdict[hid].writeLeaves(resimap)))
count+=len(hcdict[hid].leaves)
print '%d leaves in total\n' % count
def ncg2blossum():
if len(sys.argv) < 7:
print 'ncg2blossum: construct new substitution matrix from contact group'
print 'example:python utils_msa.py ncg2blossum 5pti_pf.pdb 5pti_pf.tip.ncg PF00014_full.txt.rseq PF00014_full.txt.sdii BPT1_BOVIN order'
print 'output: a substitution matrix file (same format as BLOSSUM62)'
return
#print sys.argv[0] # utils_msa.py
#print sys.argv[1] # hcg2blossum
pdbfile = sys.argv[2] # pdb name
ncgfile = sys.argv[3] # hcg
msafile = sys.argv[4] # msa (full or reduced)
sdiifile = sys.argv[5] # sdii
target = sys.argv[6] # target name
order = int(sys.argv[7])
outfile = msafile[0:7]+".sm" # new substitution matrix
# get msa in matrix format
m = msa(msafile)
msaMatrix = np.array([list(s[1]) for s in m.msaArray]) # matrix format of msa
#for i in xrange(0, len(seqs)):
# print seqs[i]
print 'msa matrix: ' + repr(msaMatrix.shape)
# get resi -> msai map
p = protein(pdbfile)
rtmap = m.getResiTargetMap(p, target)
sdiidict = loadsdii(sdiifile) # key: 39-140-210, value = 0.0788593466276019
msaGroupArray = ncg2msa(ncgfile, rtmap) # [[210, 215], [106, 211], [73, 95, 166], [109, 124, 139]]
# get non overlapped column indices
colset = set()
for g in msaGroupArray:
rg = g[0:order] # get ith order contact group
rg.sort() # for generating key
sdiikey = '-'.join([str(r) for r in rg])
if sdiikey not in sdiidict:
#print 'ncg2sdiicol(): discard group: %s for low sdii' % sdiikey
continue
print (sdiikey, sdiidict[sdiikey])
for resi in rg: # for significant ncg, add corresponding MSA column index
colset.add(resi)
# init substitution matrix
EBlist = ['A', 'R', 'N', 'D', 'C', 'Q', 'E', 'G', 'H', 'I', 'L', 'K', 'M', 'F', 'P', 'S', 'T', 'W', 'Y', 'V', 'B', 'Z', 'X', '*']
#AAlist = sorted(EBlist)
#AAlist = sorted(['A', 'R', 'N', 'D', 'C', 'Q', 'E', 'G', 'H', 'I', 'L', 'K', 'M', 'F', 'P', 'S', 'T', 'W', 'Y', 'V', 'B', 'Z', 'X', '*'])
AAlist = sorted(['A', 'R', 'N', 'D', 'C', 'Q', 'E', 'G', 'H', 'I', 'L', 'K', 'M', 'F', 'P', 'S', 'T', 'W', 'Y', 'V'])
sm = {}
for i in xrange(0, len(AAlist)):
for j in xrange(i, len(AAlist)):
key = '%s%s' % (AAlist[i], AAlist[j])
sm[key] = 0
print AAlist
print 'Alphabet: %d' % len(AAlist)
print 'AA: %d' % len(sm)
# accumulate substitution matrix AA frequency for all the contact group columns
# Sum the scores for each columns across column
print ''
w = 0 # count column number
for col in colset:
w+=1
calcColSM(sm, msaMatrix, col)
'''
for mg in msaGroupArray:
# form key for co-evolve value
sdiikey = '-'.join([str(i) for i in mg])
if sdiikey not in sdiidict:
print 'hcg2blossum():discard group: %s' % sdiikey
continue
sdiiweight = sdiidict[sdiikey]
print (sdiikey, sdiiweight)
# accumulate SM for each contact group / column group
for col in mg:
w +=1
calcColSM(sm, msaMatrix, col)
print ''
'''
#print repr(sm)
#print ''
n = msaMatrix.shape[0]
T = w*n*(n-1)/2 # normalization term
print 'w: %d' % w # number of columns (contact group)
print 'n: %d' % n # number of sequence
print 'T: %d' % T
# convert cij to qij
# Normalize the pair frequencies so they will sum to 1
for c in sm:
sm[c] = 1.0*sm[c]/T
#print repr(sm)
#print ''
# Calculate the expected probability of occurrence of the ith residue in an (i,j) pair
# pi = qii + sum( qij/2 )_{i!=j}
pi = {}
for i in xrange(0, len(AAlist)):
A = AAlist[i]
sum_qij = 0
for j in xrange(i+1, len(AAlist)): # i should not = j
B = AAlist[j]
sum_qij += sm[A+B]/2
pi[A] = sm[A+A] + sum_qij
print repr(pi)
print ''
# The desired denominator is the expected frequency for each pair
eij = {}
for i in xrange(0, len(AAlist)):
A = AAlist[i]
for j in xrange(i+1, len(AAlist)):
B = AAlist[j]
eij[A+B] = 2 * pi[A] * pi[B]
eij[A+A] = pi[A] * pi[A]
print len(eij)
print repr(eij)
print ''
# Log odds ratio sij = round(2*log2(qij/eij))
sij = {}
for i in xrange(0, len(AAlist)):
A = AAlist[i]
for j in xrange(i, len(AAlist)):
B = AAlist[j]
if eij[A+B] == 0.0 or sm[A+B]==0.0:
sij[A+B] = 0
else:
sij[A+B] = int(round(2*math.log((sm[A+B]/eij[A+B]),2)))
# sij[A+B] = sm[A+B]/eij[A+B]
print repr(sij)
print len(sij)
print ''
saveBlosum(EBlist, sij, outfile)
def main():
pdbname = '1t3r.pdb'
p = protein(pdbname)
#p.writeCA(p.pdb+'.ca')
p.printPDB()
p.writeChainATips('AAtips.def', p.pdb+'.tip')
