def ReadPercentTM(infile):#{{{
hdl = myfunc.ReadLineByBlock(infile)
if hdl.failure:
return {}
percentTMDict = {}
lines = hdl.readlines()
cntline = 0
while lines != None:
for line in lines:
cntline += 1
if not line or line[0] == "#":
continue
strs = line.split()
if len(strs) == 6:
try:
pfamid = strs[0]
numTM = int(strs[1])
numSeq = int(strs[3])
percentTMDict[pfamid] = [numTM, numSeq]
except (IndexError, ValueError):
msg = "Error in mapfile %s at line %d: \"%s\""
print >> sys.stderr, msg%(infile, cntline, line)
pass
lines = hdl.readlines()
hdl.close()
return percentTMDict
def MPA2MSA_old(infile, output_format, fpout): #{{{
hdl = myfunc.ReadLineByBlock(infile)
if hdl.failure:
return 1
lengthList = []
remainLineList = []
lines = hdl.readlines()
while lines != None:
lines = remainLineList + lines
numLine = len(lines)
numRD = numLine / 2
for i in xrange(numRD):
fpout.write("%s\n" % lines[2 * i])
strs = lines[2 * i + 1].split()
for ss in strs:
if ss.find("-") != -1:
strs1 = ss.split("-")
b = int(strs1[0])
e = int(strs1[1])
li = ["-"] * (e - b)
fpout.write("%s" % (''.join(li)))
else:
fpout.write("%s" % (ss))
fpout.write("\n")
if numRD * 2 < numLine:
remainLineList = [lines[numLine - 1]]
else:
remainLineList = []
lines = hdl.readlines()
hdl.close()
return 0
def ReadDupPairDict(infile):#{{{
hdl = myfunc.ReadLineByBlock(infile)
if hdl.failure:
return {}
dt = {}
lines = hdl.readlines()
while lines != None:
for line in lines:
strs = line.split()
if line == "" or line[0] == "#":
continue
if len(strs) >= 2:
if strs[1] == 'y': # it is a duplicated pair
ss = strs[0].split("-")
if len(ss) == 2:
key = (ss[0], ss[1])
dt[key] = {}
dt[key]['isDup'] = 'y'
li = []
strs1 = line.split('|')
for j in range(1, len(strs1)):
hit = ParseDupHit(strs1[j].strip()) # hit is a list of
# two segments
# from query
# and template
li.append(hit)
dt[key]['hit'] = li
lines = hdl.readlines()
hdl.close()
return (dt)
def MPA2MSA(infile, output_format, fpout): #{{{
hdl = myfunc.ReadLineByBlock(infile)
if hdl.failure:
return 1
lengthList = []
remainLineList = []
lines = hdl.readlines()
while lines != None:
lines = remainLineList + lines
numLine = len(lines)
numRD = numLine / 2
for i in xrange(numRD):
li = []
fpout.write("%s\n" % lines[2 * i])
strs = lines[2 * i + 1].split()
for ss in strs:
if ss[0].isdigit():
lgap = int(ss)
li.append("-" * lgap)
else:
li.append(ss)
fpout.write("%s\n" % ("".join(li)))
if numRD * 2 < numLine:
remainLineList = [lines[numLine - 1]]
else:
remainLineList = []
lines = hdl.readlines()
hdl.close()
return 0
def ReadPairInfo(infile): #{{{
hdl = myfunc.ReadLineByBlock(infile)
lst = []
if hdl.failure:
return []
lines = hdl.readlines()
while lines != None:
for line in lines:
if line != "" and line[0] != "#":
strs = line.split()
seqid1 = strs[0]
seqid2 = strs[1]
NtermState1 = strs[2]
NtermState2 = strs[3]
numTM1 = int(strs[4])
numTM2 = int(strs[5])
seqLen1 = int(strs[6])
seqLen2 = int(strs[7])
seqidt = float(strs[8])
lst.append([
seqid1, seqid2, NtermState1, NtermState2, numTM1, numTM2,
seqLen1, seqLen2, seqidt
])
lines = hdl.readlines()
hdl.close()
return lst
def ReadPfamScan2(infile):#{{{
# a quick solution, to same a little memory
evalue_threshold = g_params['evalue_threshold']
seqIDPfamScanDict = {}
hdl = myfunc.ReadLineByBlock(infile)
if hdl.failure:
return {}
lines = hdl.readlines()
while lines != None:
for line in lines:
if line != "" and line[0] != "#":
strs = line.split()
if len(strs) >= 15:
seqid = strs[0]
alnBeg = int (strs[1])
alnEnd = int (strs[2])
pfamid = strs[5].split('.')[0]
# tmpdict['pfamname'] = strs[6]
evalue = float(strs[12])
clanid = strs[14]
tup_info = (alnBeg, alnEnd, pfamid, clanid)
if evalue <= evalue_threshold:
if seqid in seqIDPfamScanDict:
seqIDPfamScanDict[seqid].append(tup_info)
else:
seqIDPfamScanDict[seqid] = []
seqIDPfamScanDict[seqid].append(tup_info)
lines = hdl.readlines()
if hdl:
hdl.close()
return seqIDPfamScanDict
def Filter_seqid2fam_map(infile, keyIDSet, contentIDSet, isKeyIDSet,
isContentIDSet, fpout):
hdl = myfunc.ReadLineByBlock(infile)
if hdl.failure:
return 1
lines = hdl.readlines()
while lines != None:
for line in lines:
if line:
strs = line.split()
try:
key = strs[0]
num = int(strs[1])
idlist = strs[2:]
tmp_idlist = []
if (not isKeyIDSet) or (key in keyIDSet):
for idd in idlist:
if (not isContentIDSet) or (idd in contentIDSet):
tmp_idlist.append(idd)
if len(tmp_idlist) > 0:
fpout.write("%s %d"%(key, len(tmp_idlist)))
for idd in tmp_idlist:
fpout.write(" %s"%(idd))
fpout.write("\n")
except (IndexError):
msg = "Error in infile %s with line \"%s\""
print >> sys.stderr, msg%(infile, line)
return 1
lines = hdl.readlines()
hdl.close()
return 0
def ReadDGScore(infile):#{{{
hdl = myfunc.ReadLineByBlock(infile)
if hdl.failure:
msg = "Failed to read file %s in function %s"
print(msg%(infile, sys._getframe().f_code.co_name), file=sys.stderr)
return {}
dgScoreDict = {}
lines = hdl.readlines()
while lines != None:
for line in lines:
if line and line[0] != "#":
strs = line.split()
numStr = len(strs)
if numStr >= 2:
try:
seqid = strs[0]
if numStr == 2:
dgscore = float(strs[1])
elif numStr == 3:
dgscore = float(strs[2])
if not seqid in dgScoreDict:
dgScoreDict[seqid] = []
dgScoreDict[seqid].append(dgscore)
except (ValueError, TypeError):
pass
lines = hdl.readlines()
hdl.close()
return dgScoreDict
def ReadPSIPREDSS2(infile):
hdl = myfunc.ReadLineByBlock(infile)
if hdl.failure:
return (None, None, None)
aaSeqList = []
ssSeqList = []
arrayList = []
for i in range(3):
arrayList.append(array('h'))
lines = hdl.readlines()
while lines != None:
for line in lines:
strs = line.split()
if len(strs) == 6 and strs[0].isdigit():
aaSeqList.append(strs[1])
ssSeqList.append(strs[2])
for i in range(3):
try:
value = int(float(strs[i + 3]) * 1000)
arrayList[i].append(value)
except (ValueError, IndexError):
msg = "Bad record \"%s\" in file %s"
print >> sys.stderr, msg % (line, infile)
return (None, None, None)
lines = hdl.readlines()
hdl.close()
aaSeq = "".join(aaSeqList)
ssSeq = "".join(ssSeqList)
return (aaSeq, ssSeq, arrayList)
def GetFullSeq(infile, hdl_seqdb, fpout):#{{{
hdl = myfunc.ReadLineByBlock(infile)
if hdl.failure:
return (1, 0, 0)
cntRetrieved = 0
idList = []
lines = hdl.readlines()
while lines != None:
idList += GetDatabaseIDList(lines)
lines = hdl.readlines()
hdl.close()
idList = myfunc.uniquelist(idList)
numID = len(idList)
for seqid in idList:
record = hdl_seqdb.GetRecord(seqid)
if record:
fpout.write(record)
cntRetrieved += 1
else:
msg = "Failed to retrieve record for ID %s"
print >> sys.stderr, msg%(seqid)
return (0, numID, cntRetrieved)
def ReadPairAlnTableInfo(infile):#{{{
hdl = myfunc.ReadLineByBlock(infile)
if hdl.failure:
msg = "Failed to read file %s in function %s"
print(msg%(infile, sys._getframe().f_code.co_name), file=sys.stderr)
return {}
pairalnStat = {}
lines = hdl.readlines()
while lines != None:
for line in lines:
if line != "" and line[0] != "#":
strs = line.split()
if len(strs) == 13:
try:
id1 = strs[0]
id2 = strs[1]
seqidt = float(strs[2])
alignLen = float(strs[4])
seqlen1 = int(strs[5])
seqlen2 = int(strs[6])
seqidt1 = float(strs[11])
seqidt2 = float(strs[12])
pairid = id1+'-'+id2
pairalnStat[pairid] = {}
tmpdict = pairalnStat[pairid]
tmpdict['seqidt'] = seqidt
tmpdict['seqidt1'] = seqidt1
tmpdict['seqidt2'] = seqidt1
tmpdict['seqLength1'] = seqlen1
tmpdict['seqLength2'] = seqlen2
except (IndexError, ValueError, TypeError, KeyError):
pass
lines = hdl.readlines()
hdl.close()
return pairalnStat
def ReadPfamDefFile(infile):#{{{
hdl = myfunc.ReadLineByBlock(infile)
if hdl.failure:
return ({}, {})
dtClan = {}
dtPfam = {}
lines = hdl.readlines()
while lines != None:
for line in lines:
strs = line.split("\t")
try:
pfamid = strs[0]
pfamDefShort = strs[3]
dtPfam[pfamid] = pfamDefShort
clanid = strs[1]
clanDefShort = strs[2]
if clanid != r"\N":
dtClan[clanid] = clanDefShort
else:
dtClan[pfamid] = pfamDefShort
except IndexError:
pass
lines = hdl.readlines()
hdl.close()
return (dtPfam, dtClan)
def CountUniquePairInvertedInfo(infile, pfamidDefDict, fpout):
idset1 = set([])
idset2 = set([])
numTMSet = set([])
numInvPair = 0
numAllPair = 0
ratio = 0.0
hdl = myfunc.ReadLineByBlock(infile)
if hdl.failure:
return 1
lines = hdl.readlines()
while lines != None:
for line in lines:
if line.find("General") == 0:
strs = line.split()
numInvPair = int(strs[1])
numAllPair = int(strs[2])
ratio = float(strs[3])
if line.find("Pair") == 0:
strs = line.split()
id1 = strs[1]
id2 = strs[2]
NtermState1 = strs[3]
NtermState2 = strs[4]
numTM = int(strs[5])
numTMSet.add(numTM)
if NtermState1 == 'i':
idset1.add(id1)
idset2.add(id2)
else:
idset1.add(id2)
idset2.add(id1)
lines = hdl.readlines()
hdl.close()
pfamid = os.path.basename(infile).split(".")[0]
try:
pfamdef = pfamidDefDict[pfamid]
except KeyError:
pfamdef = "N/A"
if len(idset1) > 0 or len(idset2) > 0:
fpout.write("%-8s %20s %4d %4d %2d %8s %5d %5d %6.3f\n"%(
pfamid,
pfamdef,
len(idset1),
len(idset2),
len(numTMSet),
str(list(numTMSet)),
numInvPair,
numAllPair,
ratio
))
def IDMap2SeqID(infile, fpout):
hdl = myfunc.ReadLineByBlock(infile)
if hdl.failure:
return 1
lines = hdl.readlines()
while lines != None:
for line in lines:
if not line or line[0] == "#":
continue
strs = line.split()
if len(strs) > 2:
for ss in strs[2:]:
print >> fpout, ss
lines = hdl.readlines()
hdl.close()
def ReadSeqPathMapDict(infile):#{{{
hdl = myfunc.ReadLineByBlock(infile)
if hdl.failure:
return {}
dt = {}
lines = hdl.readlines()
while lines != None:
for line in lines:
if not line or line[0] == "#":
continue
strs = line.split()
if len(strs) == 2:
dt[strs[0]] = strs[1]
lines = hdl.readlines()
return dt
def ReadGOTerm(infile): #{{{
hdl = myfunc.ReadLineByBlock(infile)
dt = {}
if hdl.failure:
return 1
lines = hdl.readlines()
while lines != None:
for line in lines:
if line != "" and line[0] != "#":
strs = line.split("\t")
if len(strs) >= 2:
goid = strs[0].strip()
dt[goid] = strs[1].strip()
lines = hdl.readlines()
hdl.close()
return dt
def ReadGOInfo(infile): #{{{
hdl = myfunc.ReadLineByBlock(infile)
GOinfoList = []
if hdl.failure:
return 1
lines = hdl.readlines()
while lines != None:
for line in lines:
if line != "" and line[0] != "#":
goinfo = ScanfGOInfo(line)
if goinfo != {}:
GOinfoList.append(goinfo)
lines = hdl.readlines()
hdl.close()
return GOinfoList
def ReadSignalPFile(infile): #{{{
hdl = myfunc.ReadLineByBlock(infile)
dt = {}
if hdl.failure:
return 1
lines = hdl.readlines()
while lines != None:
for line in lines:
if line == "" or line[0] == "#":
continue
#seqid = myfunc.GetFirstWord(line)
seqid = myfunc.GetSeqIDFromAnnotation(line)
dt[seqid] = line
lines = hdl.readlines()
hdl.close()
return dt
def ReadGOAnc(infile):
hdl = myfunc.ReadLineByBlock(infile)
goAncDict = {}
if hdl.failure:
return 1
lines = hdl.readlines()
while lines != None:
for line in lines:
if line != "" and line[0] != "#":
strs = line.split(";")
goid = strs[0].strip()
goAncDict[goid] = line
lines = hdl.readlines()
hdl.close()
return goAncDict
def ReadDupPairList(infile):#{{{
hdl = myfunc.ReadLineByBlock(infile)
if hdl.failure:
return []
li = []
lines = hdl.readlines()
while lines != None:
for line in lines:
strs = line.split()
if len(strs) >= 2:
if strs[1] == 'y':
ss = strs[0].split("-")
if len(ss) == 2:
li.append((ss[0], ss[1]))
lines = hdl.readlines()
hdl.close()
return (li)
def ReadSeqLengthDict(infile):#{{{
hdl = myfunc.ReadLineByBlock(infile)
if hdl.failure:
return {}
dt = {}
lines = hdl.readlines()
while lines != None:
for line in lines:
if not line or line[0] == "#":
continue
strs = line.split()
if len(strs) == 2:
seqid = strs[0]
length = int(strs[1])
dt[seqid] = length
lines = hdl.readlines()
hdl.close()
return dt
def ReadIDWithAnnoInfo(infile):#{{{
hdl = myfunc.ReadLineByBlock(infile)
if hdl.failure:
return {}
dt = {}
lines = hdl.readlines()
while lines != None:
for line in lines:
if not line or line[0] == "#":
continue
strs = line.split("\t")
if len(strs) == 2:
seqid = strs[0]
anno = strs[1].strip()
dt[seqid] = anno
lines = hdl.readlines()
hdl.close()
return dt
def SelectLineByID(infile, idListSet, fpout):#{{{
hdl = myfunc.ReadLineByBlock(infile)
if hdl.failure:
return 1
method_getid = g_params['method_getid']
sel_field_list = g_params['sel_field_list']
if method_getid == 3:
if len(sel_field_list) == 0:
sel_field = 0
elif len(sel_field_list) == 1:
sel_field = sel_field_list[0]
lines = hdl.readlines()
while lines != None:
for line in lines:
if not line or line[0] == "#":
fpout.write("%s\n"%line)
else:
try:
if method_getid == 0:
idd = line.split(None, 1)[0]
elif method_getid == 1:
idd = (line.split(None, 1)[0]).partition(";")[0]
elif method_getid == 2:
idd = myfunc.GetSeqIDFromAnnotation(line)
elif method_getid == 3:
if len(sel_field_list) < 2:
idd = line.split()[sel_field-1]
else:
strs = line.split()
tmpli = []
for ff in sel_field_list:
tmpli.append(strs[ff-1])
idd = tuple(tmpli)
else:
print method_getid
except (IndexError):
print >> sys.stderr, ("Bad line \"%s\"\n"%line)
if idd in idListSet:
fpout.write("%s\n"%line)
lines = hdl.readlines()
hdl.close()
return 0
def ReadMapFile(infile):#{{{
mapDict = {}
hdl = myfunc.ReadLineByBlock(infile)
if hdl.failure:
return mapDict
lines = hdl.readlines()
while lines != None:
for line in lines:
if not line or line[0] == "#":
continue
strs = line.split("\t")
try:
mapDict[strs[0]] = strs[1]
except IndexError:
pass
lines = hdl.readlines()
hdl.close()
return mapDict
def ReadRLTYInfo(infile):#{{{
hdl = myfunc.ReadLineByBlock(infile)
if hdl.failure:
msg = "Failed to read file %s in function %s"
print(msg%(infile, sys._getframe().f_code.co_name), file=sys.stderr)
return {}
rltyDict = {}
lines = hdl.readlines()
while lines != None:
for line in lines:
strs = line.split()
if len(strs) == 2:
try:
seqid = strs[0]
rlty = float(strs[1])
rltyDict[seqid] = rlty
except (ValueError, TypeError, KeyError):
pass
lines = hdl.readlines()
hdl.close()
return rltyDict
def ReadPairInfo(infile): #{{{
"""
Format of the pairlistfile
#seqid1 seqid2 seqidt famid pfamdef numSeqCls1 numSeqCls2 numSeq nTM1 nTM2 isSP isPDB
Output:
pairInfoDict {pfamid: {'':, ''}}
"""
hdl = myfunc.ReadLineByBlock(infile)
if hdl.failure:
return {}
lines = hdl.readlines()
dt = {}
while lines != None:
for line in lines:
if not line or line[0] == "#":
continue
strs = line.split()
if len(strs) >= 12:
pfamid = strs[3]
if not pfamid in dt:
dt[pfamid] = {}
dt[pfamid]['pfamdef'] = strs[4]
dt[pfamid]['numSeqCls1'] = int(strs[5])
dt[pfamid]['numSeqCls2'] = int(strs[6])
dt[pfamid]['numseq'] = int(strs[7])
dt[pfamid]['nTM_Group1'] = int(strs[8])
dt[pfamid]['nTM_Group2'] = int(strs[9])
dt[pfamid]['pairlist'] = []
seqid1 = strs[0]
seqid2 = strs[1]
seqidt = float(strs[2])
isSP = int(strs[10])
isPDB = int(strs[11])
dt[pfamid]['pairlist'].append(
(seqid1, seqid2, seqidt, isSP, isPDB))
lines = hdl.readlines()
hdl.close()
return dt
def ReadSignalPDict(infile):#{{{
# format of signalp file
# SeqID location Y
hdl = myfunc.ReadLineByBlock(infile)
if hdl.failure:
return {}
signalpDict = {}
lines = hdl.readlines()
while lines != None:
for line in lines:
if not line or line[0] == "#":
continue
strs = line.split()
if len(strs) >= 2:
try:
signalpDict[strs[0]] = int(strs[1])
except (ValueError):
pass
lines = hdl.readlines()
hdl.close()
return signalpDict
def FilterUniprotIDMap(infile, fpout):
hdl = myfunc.ReadLineByBlock(infile)
if not hdl:
return 1
lines = hdl.readlines()
while lines != None:
for line in lines:
isIgnore = False
strs = line.split("\t")
try:
if strs[2].find(strs[0]) != -1:
uniprotid = GetUniprotIDFromLongName(strs[2])
if uniprotid != "":
if uniprotid == strs[0]:
isIgnore = True
else:
print >> sys.stderr, "Error\t", line
else:
print >> sys.stderr, "Null\t", line
if not isIgnore:
print >> fpout, line
except IndexError:
print >> sys.stderr, "IndexError\t", line
lines = hdl.readlines()
def main(g_params): #{{{
argv = sys.argv
numArgv = len(argv)
if numArgv < 2:
PrintHelp()
return 1
outfile = ""
infile = ""
gramPositiveFile = ""
gramNegativeFile = ""
eukFile = ""
i = 1
isNonOptionArg = False
while i < numArgv:
if isNonOptionArg == True:
infile = argv[i]
isNonOptionArg = False
i += 1
elif argv[i] == "--":
isNonOptionArg = True
i += 1
elif argv[i][0] == "-":
if argv[i] in ["-h", "--help"]:
PrintHelp()
return 1
elif argv[i] in ["-o", "--o", "-outfile"]:
(outfile, i) = myfunc.my_getopt_str(argv, i)
elif argv[i] in ["-gram+", "--gram+"]:
(gramPositiveFile, i) = myfunc.my_getopt_str(argv, i)
elif argv[i] in ["-gram-", "--gram-"]:
(gramNegativeFile, i) = myfunc.my_getopt_str(argv, i)
elif argv[i] in ["-euk", "--euk"]:
(eukFile, i) = myfunc.my_getopt_str(argv, i)
elif argv[i] in ["-q", "--q"]:
g_params['isQuiet'] = True
i += 1
elif argv[i] in ["-debug", "--debug"]:
g_params['isDEBUG'] = True
i += 1
else:
print >> sys.stderr, "Error! Wrong argument:", argv[i]
return 1
else:
infile = argv[i]
i += 1
if myfunc.checkfile(infile, "taxidwithtaxoFile") != 0:
return 1
if myfunc.checkfile(gramPositiveFile, "gramPositiveFile") != 0:
return 1
if myfunc.checkfile(gramNegativeFile, "gramNegativeFile") != 0:
return 1
if myfunc.checkfile(eukFile, "eukFile") != 0:
return 1
gramPositiveDict = ReadSignalPFile(gramPositiveFile)
gramNegativeDict = ReadSignalPFile(gramNegativeFile)
eukDict = ReadSignalPFile(eukFile)
fpout = myfunc.myopen(outfile, sys.stdout, "w", False)
hdl = myfunc.ReadLineByBlock(infile)
if hdl.failure:
return 1
lines = hdl.readlines()
while lines != None:
for line in lines:
strs = line.split("\t")
if len(strs) == 3:
seqid = strs[0].strip()
taxo = strs[2].strip()
info = ""
try:
if taxo == "Gram+" or taxo == "gram+":
info = gramPositiveDict[seqid]
elif taxo == "Gram-" or taxo == "gram-":
info = gramNegativeDict[seqid]
elif taxo == "Euk" or taxo == "euk":
info = eukDict[seqid]
if g_params['isDEBUG']:
print >> sys.stderr, "%s: %s" % (seqid, taxo)
except KeyError:
info = ""
if info != "":
fpout.write("%s\n" % info)
lines = hdl.readlines()
hdl.close()
myfunc.myclose(fpout)
def RunHHSearchPairwise(tableinfoFile, #{{{
hhprofilepathList, hhprofilepathMapDictList,
hhsearchpathList, hhsearchpathMapDictList,
topoDict, outpath, dupfile):
fpoutDup = None
if dupfile != "":
fpoutDup = myfunc.myopen(dupfile, sys.stdout, "w", False)
hdl = myfunc.ReadLineByBlock(tableinfoFile)
if hdl.failure:
return 1
cnt = 0
lines = hdl.readlines()
while lines != None:
for line in lines:
if not line or line[0] == "#":
continue
strs = line.split()
try:
seqid1 = strs[0]
seqid2 = strs[1]
except (IndexError, ValueError):
print >> sys.stderr, "Bad record line \"%s\""%(line)
continue
try:
topo1 = topoDict[seqid1]
except KeyError:
topo1 = ""
try:
topo2 = topoDict[seqid2]
except KeyError:
topo2 = ""
seqlen1 = len(topo1)
seqlen2 = len(topo2)
pairlist = [(seqid1, seqlen1), (seqid2, seqlen2)]
pairlist = sorted(pairlist, key=lambda x:x[1], reverse=False) # short - long
hhrfile = "%s%s%s_%s.hhr"%(outpath, os.sep, seqid1, seqid2)
if g_params['isUsePreBuildHHSearchResult']:
keystr = "%s_%s"%(seqid1, seqid2)
tmp_hhrfile = GetProfileFileName(hhsearchpathList,
hhsearchpathMapDictList, keystr, ".hhr")
if os.path.exists(tmp_hhrfile):
hhrfile = tmp_hhrfile
else:
print >> sys.stderr, "hhrfile %s does not exist in"\
" the prebuilt path"%(hhrfile)
# update seqid1 and seqid2 (shorter - longer)
seqid1 = pairlist[0][0] # shorter sequence
seqid2 = pairlist[1][0] # longer sequence
try:
topo1 = topoDict[seqid1]
except KeyError:
topo1 = ""
try:
topo2 = topoDict[seqid2]
except KeyError:
topo2 = ""
seqlen1 = len(topo1)
seqlen2 = len(topo2)
numTM1 = len(myfunc.GetTMPosition(topo1))
numTM2 = len(myfunc.GetTMPosition(topo2))
if not os.path.exists(hhrfile) or g_params['isForceOverWrite']:
a3mfile = GetProfileFileName(hhprofilepathList, #query
hhprofilepathMapDictList, pairlist[0][0], ".a3m")
hhmfile = GetProfileFileName(hhprofilepathList, #template
hhprofilepathMapDictList, pairlist[1][0], ".hhm")
if a3mfile == "" or not os.path.exists(a3mfile):
print >> sys.stderr, "a3mfile not found for %s. Ignore." %(pairlist[0][0])
elif hhmfile == "" or not os.path.exists(hhmfile):
print >> sys.stderr, "hhmfile not found for %s. Ignore." %(pairlist[1][0])
else:
tmp_hhrfile = "%s.tmp"%(hhrfile)
cmd = "hhsearch -i %s -d %s -o %s -v 0 -nocons -nopred -nodssp" % (
a3mfile, hhmfile, tmp_hhrfile)
os.system(cmd)
if os.path.exists(tmp_hhrfile):
os.system("/bin/mv -f %s %s"%(tmp_hhrfile, hhrfile))
print hhrfile, "output"
if fpoutDup and os.path.exists(hhrfile):
ss_isdup = ""
hitinfo = {}
# if IsDuplicatedByHHSearch(hhrfile, seqid1, seqid2, cnt):
# ss_isdup = 'y'
# else:
# ss_isdup = 'n'
hitinfo = CheckDuplication(hhrfile, seqid1, seqid2, topoDict, cnt)
if hitinfo != {}:
fpoutDup.write("%s-%s %s %4d %4d %4d %4d" %(
seqid1, seqid2, hitinfo['isDup'],
len(topo1), len(topo2), numTM1, numTM2))
if 'hit' in hitinfo:
for j in xrange(len(hitinfo['hit'])):
hit = hitinfo['hit'][j]
ss_hit = "%d-%d(nTM=%d) %d-%d(nTM=%d)"%(
hit['posQuery'][0], hit['posQuery'][1], hit['numTM1'],
hit['posTemplate'][0], hit['posTemplate'][1], hit['numTM2'])
fpoutDup.write(" | %35s"%(ss_hit))
fpoutDup.write("\n")
cnt += 1
lines = hdl.readlines()
hdl.close()
myfunc.myclose(fpoutDup)
return 0
