def main():
print >>sys.stderr, "Transfer repetitions to multiple sequence \
alignment files. One geoup in one file. Waiting for alignment."
if len(sys.argv) != 2:
print >>sys.stderr,'Using python %s repfile' % sys.argv[0]
sys.exit(0)
#-------------------------------------
repDict = {}
readRep(sys.argv[1], repDict)
for locus, valueL in repDict.items():
midlen = 30
group = 0
for groupD in valueL:
group += 1
groupDKeyL = groupD.keys()
groupDKeyL.sort()
maxlen = 0
for seq in groupD.values():
lenseq = len(seq)
if lenseq > maxlen:
maxlen = lenseq
if maxlen <= midlen:
file = locus+'.'+str(group)+'.short'
else:
file = locus+'.'+str(group)+'.long'
fh = open(file, 'w')
for pos in groupDKeyL:
seq = groupD[pos]
#-------------------------------------------
posn = ':'.join((str(pos[0]), str(pos[1])))
print >>fh, '>%s.%s.%s\n%s' % \
(locus, str(group), posn, seq)
#--------END one group------------------------------
fh.close()
def main():
print >> sys.stderr, "Print the result to screen"
if len(sys.argv) != 3:
print >>sys.stderr, 'Using python %s cdsfile repfile' \
% sys.argv[0]
sys.exit(0)
#---------------------------------------------------------
repDict = {}
ctIO.readRep(sys.argv[2], repDict)
locusL = repDict.keys()
locusL.sort()
cdsDict = ctIO.readFasta(sys.argv[1], locusL)
for locus in locusL:
print '>%s' % locus
seq = cdsDict[locus]
tmpList = repDict[locus]
for posDict in tmpList:
posKeys = posDict.keys()
posKeys.sort()
repList = []
for posTuple in posKeys:
start = (posTuple[0] - 1) * 3
end = posTuple[1] * 3
if start >= end:
print >> sys.stderr, locus, posTuple
sys.exit(1)
#--------patch a bug---2011-08-25
#repList.append(seq[start:end]+':'+str(start+3))
repList.append(seq[start:end] + ':' + str(start + 1))
#--------------------------------------------------
print '#'.join(repList)
def main():
print >>sys.stderr, "Print the result to three files"
if len(sys.argv) != 3:
print >>sys.stderr, 'Using python %s seq rep' % sys.argv[0]
sys.exit(0)
#-------------------------------------------
codonList = codonSet()
cdsDict = readFasta(sys.argv[1])
#ct_rdict(cdsDict)
repDict = {}
readRep(sys.argv[2], repDict)
#ct_rdict(repDict)
codonRepDict, codonSeqDict = originalSta(repDict, cdsDict)
#ct_rdict(codonRepDict)
#print '*********************'
#ct_rdict(codonSeqDict)
#-------compare within protein with repeats----
#--get codons within repeat and divide codons within other
#seuquences, and bar graph the number of them, heatmap the
#ratio of each codons of one protein.
codonNumSeq = \
totalNumberProrep(codonRepDict, codonSeqDict, sys.argv[2])
singlRatioProRep(codonRepDict, codonSeqDict, sys.argv[2], codonList)
#--compare proteins have no repeat and proteins have repeats but
#delete repeats
repOrNot(codonNumSeq, codonRepDict, codonSeqDict, sys.argv[2],
codonList)
def main():
print >> sys.stderr, "position distribution, divide protein\
into three equal length segments, N-, mid-, C- terminal. Detect by\
midpoint of repetitions. If located in boundary, random choose"
print >> sys.stderr, "Print the result to screen"
if len(sys.argv) != 3:
print >> sys.stderr, 'Using python %s seq.for.c rep' % sys.argv[0]
sys.exit(0)
#-------------------------------------------------------------
repDict = {}
seqDict = {}
readSeq(sys.argv[1], seqDict)
readRep(sys.argv[2], repDict)
for key, valueL in repDict.items():
length = len(seqDict[key])
first = length / 3
second = first * 2
#print key, first, second, length
for valueD in valueL:
for keys in valueD.keys():
#print keys,
mid = sum(keys) / 2
if mid < first:
print -1
elif mid == first:
print -1 if randint(0, 1) else 0
elif mid < second:
print 0
elif mid == second:
print 0 if randint(0, 1) else 1
else:
print 1
def main():
print >> sys.stderr, "Print the result to three files"
if len(sys.argv) != 3:
print >> sys.stderr, 'Using python %s seq rep' % sys.argv[0]
sys.exit(0)
#-------------------------------------------
codonList = codonSet()
cdsDict = readFasta(sys.argv[1])
#ct_rdict(cdsDict)
repDict = {}
readRep(sys.argv[2], repDict)
#ct_rdict(repDict)
codonRepDict, codonSeqDict = originalSta(repDict, cdsDict)
#ct_rdict(codonRepDict)
#print '*********************'
#ct_rdict(codonSeqDict)
#-------compare within protein with repeats----
#--get codons within repeat and divide codons within other
#seuquences, and bar graph the number of them, heatmap the
#ratio of each codons of one protein.
codonNumSeq = \
totalNumberProrep(codonRepDict, codonSeqDict, sys.argv[2])
singlRatioProRep(codonRepDict, codonSeqDict, sys.argv[2], codonList)
#--compare proteins have no repeat and proteins have repeats but
#delete repeats
repOrNot(codonNumSeq, codonRepDict, codonSeqDict, sys.argv[2], codonList)
def main():
print >> sys.stderr, "Print the result to screen"
if len(sys.argv) != 2:
print >> sys.stderr, 'Using python %s repfile' % sys.argv[0]
sys.exit(0)
#------------------------------------------------------
repdict = {}
readRep(sys.argv[1], repdict)
for id, valueL in repdict.items():
i = 0
for seqDict in valueL:
filename = id + str(i) + '.fasta'
fh = open(filename, 'w')
seqDictK = seqDict.keys()
seqDictK.sort()
output = ''
for key in seqDictK:
output += ''.join(('>pos', str(key[0]), '-', str(key[1])\
, '\n', seqDict[key], '\n'))
#--------------------------------------------
print >> fh, output,
fh.close()
cmd = 't_coffee ' + filename
i += 1
os.system(cmd)
def main():
print >>sys.stderr, "Print the result to screen"
if len(sys.argv) != 2:
print >>sys.stderr, 'Using python %s repfile' % sys.argv[0]
sys.exit(0)
#------------------------------------------------------
repdict = {}
readRep(sys.argv[1], repdict)
for id, valueL in repdict.items():
i = 0
for seqDict in valueL:
filename = id + str(i) + '.fasta'
fh = open(filename, 'w')
seqDictK = seqDict.keys()
seqDictK.sort()
output = ''
for key in seqDictK:
output += ''.join(('>pos', str(key[0]), '-', str(key[1])\
, '\n', seqDict[key], '\n'))
#--------------------------------------------
print >>fh, output,
fh.close()
cmd = 't_coffee ' + filename
i += 1
os.system(cmd)
def main():
print >>sys.stderr, "position distribution, divide protein\
into three equal length segments, N-, mid-, C- terminal. Detect by\
midpoint of repetitions. If located in boundary, random choose"
print >>sys.stderr, "Print the result to screen"
if len(sys.argv) != 3:
print >>sys.stderr, 'Using python %s seq.for.c rep' % sys.argv[0]
sys.exit(0)
#-------------------------------------------------------------
repDict = {}
seqDict = {}
readSeq(sys.argv[1], seqDict)
readRep(sys.argv[2], repDict)
for key, valueL in repDict.items():
length = len(seqDict[key])
first = length / 3
second = first * 2
#print key, first, second, length
for valueD in valueL:
for keys in valueD.keys():
#print keys,
mid = sum(keys) / 2
if mid < first:
print -1
elif mid == first:
print -1 if randint(0,1) else 0
elif mid < second:
print 0
elif mid == second:
print 0 if randint(0,1) else 1
else:
print 1
def main():
print >>sys.stderr, "Using the average shannonIndex value \
of a group sequences to represent the last entropy."
print >>sys.stderr, "Print the result to screen"
if len(sys.argv) != 3:
print >>sys.stderr, 'Using python %s filename\
threshold(2)[threethe more the high complexity]' % sys.argv[0]
sys.exit(0)
#-----------------------------------
#this three dict have the same structure
repDict = {}
lcsDict = {} #save low complexity sequences
regularDict = {} #save regular sequences
readRep(sys.argv[1], repDict)
lcs = int(sys.argv[2])
for locus, valueL in repDict.items():
for itemD in valueL:
entropy = 0
i_valueS = set(itemD.values())
#i_keys = itemD.keys()
for item in i_valueS:
entropy += si(item)
entropy = entropy / len(i_valueS)
if entropy <= lcs:
saveDict(lcsDict, locus, itemD)
else:
saveDict(regularDict, locus, itemD)
#--------End one dict---------------
#-------------end all-----------------
prefile = sys.argv[1].split('/')[-1]
outputRep(lcsDict, prefile+'.LCSs')
outputRep(regularDict, prefile+'.HCSs')
def main():
print >> sys.stderr, "Transfer repetitions to multiple sequence \
alignment files. One geoup in one file. Waiting for alignment."
if len(sys.argv) != 2:
print >> sys.stderr, 'Using python %s repfile' % sys.argv[0]
sys.exit(0)
#-------------------------------------
repDict = {}
readRep(sys.argv[1], repDict)
for locus, valueL in repDict.items():
midlen = 30
group = 0
for groupD in valueL:
group += 1
groupDKeyL = groupD.keys()
groupDKeyL.sort()
maxlen = 0
for seq in groupD.values():
lenseq = len(seq)
if lenseq > maxlen:
maxlen = lenseq
if maxlen <= midlen:
file = locus + '.' + str(group) + '.short'
else:
file = locus + '.' + str(group) + '.long'
fh = open(file, 'w')
for pos in groupDKeyL:
seq = groupD[pos]
#-------------------------------------------
posn = ':'.join((str(pos[0]), str(pos[1])))
print >>fh, '>%s.%s.%s\n%s' % \
(locus, str(group), posn, seq)
#--------END one group------------------------------
fh.close()
def main():
print >>sys.stderr, "Print the result to screen"
if len(sys.argv) != 3:
print >>sys.stderr, 'Using python %s cdsfile repfile' \
% sys.argv[0]
sys.exit(0)
#---------------------------------------------------------
repDict = {}
ctIO.readRep(sys.argv[2], repDict)
locusL = repDict.keys()
locusL.sort()
cdsDict = ctIO.readFasta(sys.argv[1], locusL)
for locus in locusL:
print '>%s' % locus
seq = cdsDict[locus]
tmpList = repDict[locus]
for posDict in tmpList:
posKeys = posDict.keys()
posKeys.sort()
repList = []
for posTuple in posKeys:
start = (posTuple[0] - 1) * 3
end = posTuple[1] * 3
if start >= end:
print >>sys.stderr, locus, posTuple
sys.exit(1)
#--------patch a bug---2011-08-25
#repList.append(seq[start:end]+':'+str(start+3))
repList.append(seq[start:end]+':'+str(start+1))
#--------------------------------------------------
print '#'.join(repList)
def main():
print >>sys.stderr, "Print the result to screen"
if len(sys.argv) != 2:
print >>sys.stderr, 'Using python %s filename' % sys.argv[0]
sys.exit(0)
#------------------------------
repDict = {}
readRep(sys.argv[1], repDict)
outputRep(repDict, sys.argv[1]+'ctIO.test')
def main():
print >>sys.stderr, 'used to transfer merged repetition file \
to fasta, the output is STDOUT.'
if len(sys.argv) != 2:
print 'Using python %s filename' % sys.argv[0]
sys.exit(0)
repDict = {}
readRep(sys.argv[1], repDict)
transfer(repDict)
def main():
print >> sys.stderr, "Print the result to screen"
if len(sys.argv) != 2:
print >> sys.stderr, 'Using python %s filename' % sys.argv[0]
sys.exit(0)
#------------------------------
repDict = {}
readRep(sys.argv[1], repDict)
outputRep(repDict, sys.argv[1] + 'ctIO.test')
def main():
print >> sys.stderr, 'used to transfer merged repetition file \
to fasta, the output is STDOUT.'
if len(sys.argv) != 2:
print 'Using python %s filename' % sys.argv[0]
sys.exit(0)
repDict = {}
readRep(sys.argv[1], repDict)
transfer(repDict)
def main():
print >>sys.stderr, "Split a multiple sequence fasta file to\
multiple files aligned together using t_coffee"
print >>sys.stderr, 'used to transfer merged repetition file \
to fasta, the output is STDOUT.'
if len(sys.argv) != 2:
print 'Using python %s filename' % sys.argv[0]
sys.exit(0)
repDict = {}
readRep(sys.argv[1], repDict)
transfer(repDict)
def main():
print >>sys.stderr, "Using the average shannonIndex value \
of a group sequences to represent the last entropy."
print >>sys.stderr, "Print the result to screen"
if len(sys.argv) != 2:
print >>sys.stderr, 'Using python %s filename' % sys.argv[0]
sys.exit(0)
#-----------------------------------
repDict = {}
readRep(sys.argv[1], repDict)
for valueL in repDict.values():
for itemD in valueL:
entropy = 0
i_valueS = set(itemD.values())
for item in i_valueS:
entropy += si(item)
entropy = entropy / len(i_valueS)
print "%.2f" % entropy
def main():
print >> sys.stderr, "Using the average shannonIndex value \
of a group sequences to represent the last entropy."
print >> sys.stderr, "Print the result to screen"
if len(sys.argv) != 2:
print >> sys.stderr, 'Using python %s filename' % sys.argv[0]
sys.exit(0)
#-----------------------------------
repDict = {}
readRep(sys.argv[1], repDict)
for valueL in repDict.values():
for itemD in valueL:
entropy = 0
i_valueS = set(itemD.values())
for item in i_valueS:
entropy += si(item)
entropy = entropy / len(i_valueS)
print "%.2f" % entropy
def main():
print >> sys.stderr, "To detect the conservation among orthologs,\
use repetitions as the query and its related orthologs as db(after \
makeblastdb). "
if len(sys.argv) != 3:
print >> sys.stderr, 'Using python %s repfile dbpath/' % sys.argv[0]
sys.exit(0)
#-------------------------------------
file = sys.argv[1]
if file.find('LCSs') != -1:
label = '.LCSs'
elif file.find('HCSs') != -1:
label = '.HCSs'
#patched at 20110922. Before not give the inital value to [label].
#So it will give an error when dealing with non 'LCSs' and 'HCSs'
#files.
else:
label = ''
noOrtho = 0
path = sys.argv[2]
repDict = {}
readRep(sys.argv[1], repDict)
for locus, valueL in repDict.items():
tmppath = path + locus
#print tmppath
if not os.path.exists(tmppath):
noOrtho += 1
continue
#-------------------------------
midlen = 30
short = locus + label + '.short'
long = locus + label + '.long'
fhshort = open(short, 'w')
fhlong = open(long, 'w')
group = 0
for groupD in valueL:
group += 1
tmpDict = {}
groupDKeyL = groupD.keys()
groupDKeyL.sort()
for pos in groupDKeyL:
seq = groupD[pos]
if seq not in tmpDict:
tmpDict[seq] = [str(pos[0])]
else:
tmpDict[seq].append(str(pos[0]))
#-------------------------------------------
tmpDictKeyL = tmpDict.keys()
tmpDictKeyL.sort()
for seq in tmpDictKeyL:
lenseq = len(seq)
pos = ':'.join(tmpDict[seq])
if lenseq <= midlen:
print >>fhshort, '>%s.%s.%s\n%s' % \
(locus, str(group), pos, seq)
else:
print >>fhlong, '>%s.%s.%s\n%s' % \
(locus, str(group), pos, seq)
#--------END one group------------------------------
fhshort.close()
fhlong.close()
cmdshort = ' '.join(('psiblast -query', short, '-db', tmppath, \
'-out', short+'.out', '-num_iterations 5','-evalue 20000',\
'-matrix PAM30', '-comp_based_stats 0', '-word_size 2'))
cmdlong = ' '.join(('psiblast -query', long, '-db', tmppath, \
'-out', long+'.out', '-num_iterations 5'))
os.system(cmdshort)
os.system(cmdlong)
cmdshort = ' '.join(('psiblast -query', short, '-db', tmppath, \
'-out', short+'.table', '-num_iterations 5','-evalue 20000',\
'-matrix PAM30', '-comp_based_stats 0', '-word_size 2',
'-outfmt 7'))
cmdlong = ' '.join(('psiblast -query', long, '-db', tmppath, \
'-out', long+'.table', '-num_iterations 5', '-outfmt 7'))
#print cmd
#break
os.system(cmdshort)
os.system(cmdlong)
#------------END one locus
print noOrtho
def main():
print >> sys.stderr, "Print the result to screen"
if len(sys.argv) != 3:
print >>sys.stderr, 'Using python %s repname interpro'\
% sys.argv[0]
sys.exit(0)
#---------------------------------------------
aDict = readInterpro(sys.argv[2])
repDict = {}
'''
repDict =
{
AT1G62760:
[
{(25, 31): 'SSLSPSS', (51,57): 'SSLSPSS'},
{(52, 60): 'SLSPSSPPP',},
]
}
'''
readRep(sys.argv[1], repDict)
if 0:
print aDict
print repDict
'''
Some symbol:
!: new
------ domain
--- rep
@: overlap
------ domain
------- rep
^: rep in domain
----------- domain
------- rep
$: domain in rep
------- domain
------------- rep
'''
for locus, valueL in repDict.items():
if locus in aDict:
hasDomain = 1
domainPosL = aDict[locus]
else:
hasDomain = 0
for dictrep in valueL:
for posset in dictrep.keys():
begin = posset[0]
end = posset[1]
if 0:
print "begin is %d, end is %d" % (begin, end)
if hasDomain:
nooverlap = 1
for domainset in domainPosL:
ds = domainset[0]
de = domainset[1]
if 0:
print "ds is %d, de is %d" % (ds, de)
if (begin > ds and begin < de and end > de)\
or (begin < ds and end > ds and end < de):
dictrep[posset] += ':' + str(begin) + '@'
nooverlap = 0
if 0: print '@'
break
elif (begin > ds and end <= de) or\
(begin == ds and end < de):
dictrep[posset] += ':' + str(begin) + '^'
nooverlap = 0
if 0: print '^'
break
elif (begin <= ds and end >= de):
dictrep[posset] += ':' + str(begin) + '$'
nooverlap = 0
if 0: print '$'
break
#--------end tracing each position------------------
if nooverlap:
dictrep[posset] += ':' + str(begin) + '!'
if 0: print '!'
#----------if no domain-------------
else:
dictrep[posset] += ':' + str(begin) + '!'
if 0: print '!!'
#--------------------------------
#-----end of trace one group domain------------------
#---------end of trace onelocusus-------------------------------
#-------------end of all-------
output(repDict)
def main():
print >>sys.stderr, "Print the result to screen"
if len(sys.argv) != 3:
print >>sys.stderr, 'Using python %s repname interpro'\
% sys.argv[0]
sys.exit(0)
#---------------------------------------------
aDict = readInterpro(sys.argv[2])
repDict = {}
'''
repDict =
{
AT1G62760:
[
{(25, 31): 'SSLSPSS', (51,57): 'SSLSPSS'},
{(52, 60): 'SLSPSSPPP',},
]
}
'''
readRep(sys.argv[1], repDict)
if 0:
print aDict
print repDict
'''
Some symbol:
!: new
------ domain
--- rep
@: overlap
------ domain
------- rep
^: rep in domain
----------- domain
------- rep
$: domain in rep
------- domain
------------- rep
'''
for locus, valueL in repDict.items():
if locus in aDict:
hasDomain = 1
domainPosL = aDict[locus]
else:
hasDomain = 0
for dictrep in valueL:
for posset in dictrep.keys():
begin = posset[0]
end = posset[1]
if 0:
print "begin is %d, end is %d" % (begin, end)
if hasDomain:
nooverlap = 1
for domainset in domainPosL:
ds = domainset[0]
de = domainset[1]
if 0:
print "ds is %d, de is %d" % (ds, de)
if (begin > ds and begin < de and end > de)\
or (begin < ds and end > ds and end < de):
dictrep[posset] += ':'+str(begin)+'@'
nooverlap = 0
if 0: print '@'
break
elif (begin > ds and end <= de) or\
(begin == ds and end < de):
dictrep[posset] += ':'+str(begin)+'^'
nooverlap = 0
if 0: print '^'
break
elif (begin <= ds and end >= de):
dictrep[posset] += ':'+str(begin)+'$'
nooverlap = 0
if 0: print '$'
break
#--------end tracing each position------------------
if nooverlap:
dictrep[posset] += ':'+str(begin)+'!'
if 0 : print '!'
#----------if no domain-------------
else:
dictrep[posset] += ':'+str(begin)+'!'
if 0 : print '!!'
#--------------------------------
#-----end of trace one group domain------------------
#---------end of trace onelocusus-------------------------------
#-------------end of all-------
output(repDict)
def main():
(options, args) = cmdpara(sys.argv)
print >> sys.stderr, "*******Print the result to screen.*******"
# -------------------macro-------------------------------------
isRep = 0
isLoc = 0
# -------------------------------------------------------------
if options.seqfile != None:
seqdict = {}
ctIO.readseq(options.seqfile, seqdict)
if options.seqrepfile != None:
seqdict = {}
repdict = {}
ctIO.readseqrep(options.seqrepfile, seqdict, repdict)
isRep = 1
if options.repfile != None:
repdict = {}
ctIO.readRep(options.repfile, repdict)
isRep = 1
if options.locusfile != None:
locusList = [line.strip() for line in open(options.locusfile)]
isLoc = 1
if not isLoc:
locusList = repdict.keys() if isRep else seqdict.keys()
if isRep or isLoc:
annodict = {}
ctIO.readAnno(options.anno, annodict, 1, locusList)
interproDict = {}
ctIO.readInterpro(options.interpro, interproDict, locusList)
# print locusList
# print repdict.keys()
# print repdict
# print isRep
# sys.exit(1)
# ----------------------------------------------------------------
latexHead()
latexExplain()
# ---------------------------------------------------------------
for id in locusList:
if id not in seqdict:
print >> sys.stderr, "Unknown locus %s" % id
else:
hasInterpro = 0
seq = list(seqdict[id])
# -------------get newDict--------------------------------
newDict = {}
if id in interproDict:
hasInterpro = 1
domainDespList = []
domainPosL = interproDict[id].keys()
getnewDictDomain(interproDict[id], domainDespList, newDict)
# ------------------------------------------------
if isRep:
repDespList = []
repdictSonL = repdict[id]
num = len(repdictSonL)
if not hasInterpro:
domainPosL = []
getnewDictRep(repdictSonL, domainPosL, repDespList, newDict)
getnewDictRepDesp(id, num, repDespList)
# ----------------get newDict---------------------------
modifySeq(seq, newDict)
# ---------------------------------------------------------
print "".join((r"\section{", id, "}"))
annos = annodict[id].replace("_", r"\_")
annos = annos.replace("%", r"\%")
annos = annos.replace("~", r"\~")
annos = annos.replace("&", r"\&")
annos = r"\tair{" + id[:-2] + "} " + annos
print r"\anno{", annos, "}"
print r"""
\noindent\begin{minipage}{\textwidth}
\noindent\rule{\textwidth}{2pt}
\DNA!"""
# --without annotation
seq = "".join(seq)
print seq
print r"""!
\end{minipage}
"""
# ------------------------------------------------
print
print "." * 100
print
# ---------------Rep------------------------------
if isRep:
for repSeq in repDespList:
print repSeq
print
# -------------Domain desp----------------------
if hasInterpro:
print "." * 100
print
for domainDesp in domainDespList:
print domainDesp
print
print r"\clearpage"
print
# ----------------End of else ---one locus-------------
# ----------------END of for ---all locus------------------
latexTail()
def main():
(options, args) = cmdpara(sys.argv)
if options.sort:
print 'sort'
sys.exit(1)
else:
print 'no sort'
sys.exit(1)
print >> sys.stderr, "*******Print the result to screen.*******"
#-------------------macro-------------------------------------
isRep = 0
isLoc = 0
#-------------------------------------------------------------
if options.seqfile != None:
seqdict = {}
ctIO.readseq(options.seqfile, seqdict)
if options.seqrepfile != None:
seqdict = {}
repdict = {}
ctIO.readseqrep(options.seqrepfile, seqdict, repdict)
isRep = 1
if options.repfile != None:
repdict = {}
ctIO.readRep(options.repfile, repdict)
isRep = 1
if options.locusfile != None:
locusList = [line.strip() for line in open(options.locusfile)]
isLoc = 1
if not isLoc:
locusList = repdict.keys() if isRep else seqdict.keys()
locusList.sort()
if isRep or isLoc:
annodict = {}
ctIO.readAnno(options.anno, annodict, 1, locusList)
interproDict = {}
ctIO.readInterpro(options.interpro, interproDict, locusList)
#print locusList
#print repdict.keys()
#print repdict
#print isRep
#sys.exit(1)
#----------------------------------------------------------------
latexHead()
latexExplain()
#---------------------------------------------------------------
for id in locusList:
if id not in seqdict:
print >> sys.stderr, "Unknown locus %s" % id
else:
hasInterpro = 0
seq = list(seqdict[id])
#-------------get newDict--------------------------------
newDict = {}
if id in interproDict:
hasInterpro = 1
domainDespList = []
domainPosL = interproDict[id].keys()
getnewDictDomain(interproDict[id], domainDespList, newDict)
#------------------------------------------------
if isRep:
repDespList = []
repdictSonL = repdict[id]
num = len(repdictSonL)
if not hasInterpro:
domainPosL = []
getnewDictRep(repdictSonL, domainPosL, repDespList, newDict)
getnewDictRepDesp(id, num, repDespList)
#----------------get newDict---------------------------
modifySeq(seq, newDict)
#---------------------------------------------------------
shortAnno = ''
annos = annodict[id].replace('_', r'\_')
annos = annos.replace('%', r'\%')
annos = annos.replace('~', r'\~')
annos = annos.replace('&', r'\&')
firstBr = annos.find('[')
if firstBr != -1:
shortAnno = annos[:firstBr]
print ''.join((r'\section{', id, ' ', shortAnno, '}'))
annos = r'\tair{' + id[:-2] + '} ' + annos
print r'\anno{', annos, '}'
print r'''
\noindent\begin{minipage}{\textwidth}
\noindent\rule{\textwidth}{2pt}
\DNA!'''
#--without annotation
seq = ''.join(seq)
print seq
print r'''!
\end{minipage}
'''
#------------------------------------------------
print
print '.' * 100
print
#---------------Rep------------------------------
if isRep:
for repSeq in repDespList:
print repSeq
print
#-------------Domain desp----------------------
if hasInterpro:
print '.' * 100
print
for domainDesp in domainDespList:
print domainDesp
print
print r'\clearpage'
print
#----------------End of else ---one locus-------------
#----------------END of for ---all locus------------------
latexTail()
def main():
print >>sys.stderr, "To detect the conservation among orthologs,\
use repetitions as the query and its related orthologs as db(after \
makeblastdb). "
if len(sys.argv) != 3:
print >>sys.stderr,'Using python %s repfile dbpath/' % sys.argv[0]
sys.exit(0)
#-------------------------------------
file = sys.argv[1]
if file.find('LCSs') != -1:
label = '.LCSs'
elif file.find('HCSs') != -1:
label = '.HCSs'
#patched at 20110922. Before not give the inital value to [label].
#So it will give an error when dealing with non 'LCSs' and 'HCSs'
#files.
else:
label = ''
noOrtho = 0
path = sys.argv[2]
repDict = {}
readRep(sys.argv[1], repDict)
for locus, valueL in repDict.items():
tmppath = path + locus
#print tmppath
if not os.path.exists(tmppath):
noOrtho += 1
continue
#-------------------------------
midlen = 30
short = locus+label+'.short'
long = locus +label+'.long'
fhshort = open(short, 'w')
fhlong = open(long, 'w')
group = 0
for groupD in valueL:
group += 1
tmpDict = {}
groupDKeyL = groupD.keys()
groupDKeyL.sort()
for pos in groupDKeyL:
seq = groupD[pos]
if seq not in tmpDict:
tmpDict[seq] = [str(pos[0])]
else:
tmpDict[seq].append(str(pos[0]))
#-------------------------------------------
tmpDictKeyL = tmpDict.keys()
tmpDictKeyL.sort()
for seq in tmpDictKeyL:
lenseq = len(seq)
pos = ':'.join(tmpDict[seq])
if lenseq <= midlen:
print >>fhshort, '>%s.%s.%s\n%s' % \
(locus, str(group), pos, seq)
else:
print >>fhlong, '>%s.%s.%s\n%s' % \
(locus, str(group), pos, seq)
#--------END one group------------------------------
fhshort.close()
fhlong.close()
cmdshort = ' '.join(('psiblast -query', short, '-db', tmppath, \
'-out', short+'.out', '-num_iterations 5','-evalue 20000',\
'-matrix PAM30', '-comp_based_stats 0', '-word_size 2'))
cmdlong = ' '.join(('psiblast -query', long, '-db', tmppath, \
'-out', long+'.out', '-num_iterations 5'))
os.system(cmdshort)
os.system(cmdlong)
cmdshort = ' '.join(('psiblast -query', short, '-db', tmppath, \
'-out', short+'.table', '-num_iterations 5','-evalue 20000',\
'-matrix PAM30', '-comp_based_stats 0', '-word_size 2',
'-outfmt 7'))
cmdlong = ' '.join(('psiblast -query', long, '-db', tmppath, \
'-out', long+'.table', '-num_iterations 5', '-outfmt 7'))
#print cmd
#break
os.system(cmdshort)
os.system(cmdlong)
#------------END one locus
print noOrtho
def main():
print >>sys.stderr, "Paste the mother sequene and related\
repetition together"
print >>sys.stderr, "Print the result to screen"
if len(sys.argv) < 3:
print >>sys.stderr, 'Using python %s forc repResult \
[anno] [locus] ' % sys.argv[0]
sys.exit(0)
tair = \
"http://www.arabidopsis.org/servlets/TairObject?name=&type=locus"
seqDict = {}
readseq(sys.argv[1], seqDict)
#--------------------------------------------
isAnno = 0
if len(sys.argv) > 3:
if sys.argv[3]:
isAnno = 1
annoDict = {}
readAnnoNew(sys.argv[3], annoDict)
#--------------------------------------------
isLoc = 0
if len(sys.argv) > 4:
if sys.argv[4]:
isLoc = 1
locL = [locus.strip() for locus in open(sys.argv[4])]
#--------------------------------------------
repDict = {}
'''
repDict =
{
AT1G62760:
[
{(25, 31): 'SSLSPSS', (51,57): 'SSLSPSS'},
{(52, 60): 'SLSPSSPPP',},
]
}
'''
readRep(sys.argv[2], repDict)
#-------------------------------------------
repDictKeyL = repDict.keys()
repDictKeyL.sort()
for locus in repDictKeyL:
if isLoc and (locus not in locL) and \
(locus[:-2] not in locL):
continue
#------------------------------------
print '>', locus
locusSub = "name=" + locus[:-2]
print tair.replace("name=", locusSub)
if isAnno and locus in annoDict:
print annoDict[locus].replace('\\\\', '\n')
#if locus in seqDict:
# print seqDict[locus]
seq = seqDict[locus] #this substitute the last one for we
#know it has this key, if not, wrong
locusRepL = repDict[locus]
repoutput = []
for repitemDIct in locusRepL:
grep = ''
posKey = repitemDIct.keys()
posKey.sort()
for pos in posKey:
rep = repitemDIct[pos]
grep += ':'.join([rep, str(pos[0]), str(pos[1])])
reps = '*'+rep+'*'
seq = seq.replace(rep, reps)
repoutput.append(grep)
print seq
print '\n'.join(repoutput)
def main():
(options, args) = cmdpara(sys.argv)
if options.sort:
print 'sort'
sys.exit(1)
else:
print 'no sort'
sys.exit(1)
print >>sys.stderr, "*******Print the result to screen.*******"
#-------------------macro-------------------------------------
isRep = 0
isLoc = 0
#-------------------------------------------------------------
if options.seqfile != None:
seqdict = {}
ctIO.readseq(options.seqfile, seqdict)
if options.seqrepfile != None:
seqdict = {}
repdict = {}
ctIO.readseqrep(options.seqrepfile, seqdict, repdict)
isRep = 1
if options.repfile != None:
repdict = {}
ctIO.readRep(options.repfile, repdict)
isRep = 1
if options.locusfile != None:
locusList = [line.strip() for line in open(options.locusfile)]
isLoc = 1
if not isLoc:
locusList = repdict.keys() if isRep else seqdict.keys()
locusList.sort()
if isRep or isLoc:
annodict = {}
ctIO.readAnno(options.anno, annodict, 1, locusList)
interproDict = {}
ctIO.readInterpro(options.interpro, interproDict, locusList)
#print locusList
#print repdict.keys()
#print repdict
#print isRep
#sys.exit(1)
#----------------------------------------------------------------
latexHead()
latexExplain()
#---------------------------------------------------------------
for id in locusList:
if id not in seqdict:
print >>sys.stderr, "Unknown locus %s" % id
else:
hasInterpro = 0
seq = list(seqdict[id])
#-------------get newDict--------------------------------
newDict = {}
if id in interproDict:
hasInterpro = 1
domainDespList = []
domainPosL = interproDict[id].keys()
getnewDictDomain(interproDict[id], domainDespList,
newDict)
#------------------------------------------------
if isRep:
repDespList = []
repdictSonL = repdict[id]
num = len(repdictSonL)
if not hasInterpro:
domainPosL = []
getnewDictRep(repdictSonL, domainPosL, repDespList, newDict)
getnewDictRepDesp(id, num, repDespList)
#----------------get newDict---------------------------
modifySeq(seq, newDict)
#---------------------------------------------------------
shortAnno = ''
annos = annodict[id].replace('_', r'\_')
annos = annos.replace('%', r'\%')
annos = annos.replace('~', r'\~')
annos = annos.replace('&', r'\&')
firstBr = annos.find('[')
if firstBr != -1:
shortAnno = annos[:firstBr]
print ''.join((r'\section{', id, ' ', shortAnno, '}' ))
annos = r'\tair{' + id[:-2] + '} ' + annos
print r'\anno{', annos, '}'
print r'''
\noindent\begin{minipage}{\textwidth}
\noindent\rule{\textwidth}{2pt}
\DNA!'''
#--without annotation
seq = ''.join(seq)
print seq
print r'''!
\end{minipage}
'''
#------------------------------------------------
print
print '.' * 100
print
#---------------Rep------------------------------
if isRep:
for repSeq in repDespList:
print repSeq
print
#-------------Domain desp----------------------
if hasInterpro:
print '.' * 100
print
for domainDesp in domainDespList:
print domainDesp
print
print r'\clearpage'
print
#----------------End of else ---one locus-------------
#----------------END of for ---all locus------------------
latexTail()
