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) < 4:
print >> sys.stderr, 'Using python %s pep prospero \
outputfile [overlap percentage]' % sys.argv[0]
sys.exit(0)
#---ori--------------------------------------------
pat = re.compile(">.+?from (\d+) to (\d+).+?from (\d+) to (\d+) ")
seqDict = readFasta(sys.argv[1])
repDict = {}
for line in open(sys.argv[2]):
if line.startswith('using sequence1'):
locus = line.strip().split()[-1]
seq = seqDict[locus]
repDict[locus] = []
elif line[0] == '>':
match = pat.match(line)
tmpDict = {}
pos1 = int(match.group(1))
pos2 = int(match.group(2))
pos3 = int(match.group(3))
pos4 = int(match.group(4))
if len(sys.argv) == 5:
if (pos2-pos3+1.0)/(pos4-pos1+1.0) > \
float(sys.argv[4]):
continue
tmpDict[(pos1, pos2)] = seq[pos1 - 1:pos2]
tmpDict[(pos3, pos4)] = seq[pos3 - 1:pos4]
repDict[locus].append(tmpDict)
#------------------------------------------------
outputRep(repDict, sys.argv[3])
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) < 4:
print >>sys.stderr, 'Using python %s pep prospero \
outputfile [overlap percentage]' % sys.argv[0]
sys.exit(0)
#---ori--------------------------------------------
pat = re.compile(">.+?from (\d+) to (\d+).+?from (\d+) to (\d+) ")
seqDict = readFasta(sys.argv[1])
repDict = {}
for line in open(sys.argv[2]):
if line.startswith('using sequence1'):
locus = line.strip().split()[-1]
seq = seqDict[locus]
repDict[locus] = []
elif line[0] == '>':
match = pat.match(line)
tmpDict = {}
pos1 = int(match.group(1))
pos2 = int(match.group(2))
pos3 = int(match.group(3))
pos4 = int(match.group(4))
if len(sys.argv) == 5:
if (pos2-pos3+1.0)/(pos4-pos1+1.0) > \
float(sys.argv[4]):
continue
tmpDict[(pos1, pos2)] = seq[pos1-1:pos2]
tmpDict[(pos3, pos4)] = seq[pos3-1:pos4]
repDict[locus].append(tmpDict)
#------------------------------------------------
outputRep(repDict, sys.argv[3])
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, "Print the result to screen"
if len(sys.argv) != 2:
print >>sys.stderr, 'Using python %s filename' % sys.argv[0]
sys.exit(0)
#------------------------------------------------
repDict = readFasta(sys.argv[1])
#----------------------------------
tmpSet = set()
for key, value in repDict.items():
if value not in tmpSet:
tmpSet.add(value)
print '>%s\n%s' % (key, value)
def main():
print >>sys.stderr, "Print the result to files"
print >>sys.stderr, "Split a multiple sequence fasta file to\
multiple files with one sequence each"
if len(sys.argv) != 2:
print >>sys.stderr, 'Using python %s filename' % sys.argv[0]
sys.exit(0)
#---------------
seqDict = readFasta(sys.argv[1])
for key, value in seqDict.items():
fh = open(key, 'w')
print >>fh, '>%s\n%s' % (key, value)
fh.close()
def main():
if len(sys.argv) != 2:
print >> sys.stderr, "Print the result to screen"
print >> sys.stderr, 'Using python %s filename' % sys.argv[0]
sys.exit(0)
#------------------------------------------------
repDict = readFasta(sys.argv[1])
#----------------------------------
tmpSet = set()
for key, value in repDict.items():
if value not in tmpSet:
tmpSet.add(value)
print '>%s\n%s' % (key, value)
def main():
print >> sys.stderr, "Print the result to files"
print >> sys.stderr, "Split a multiple sequence fasta file to\
multiple files with one sequence each"
if len(sys.argv) != 2:
print >> sys.stderr, 'Using python %s filename' % sys.argv[0]
sys.exit(0)
#---------------
seqDict = readFasta(sys.argv[1])
for key, value in seqDict.items():
fh = open(key, 'w')
print >> fh, '>%s\n%s' % (key, value)
fh.close()
def main():
print >>sys.stderr, "Print the result to screen"
if len(sys.argv) != 4:
print >>sys.stderr, 'Using python %s filename subjS atseq' % sys.argv[0]
sys.exit(0)
#---------------------------------------------------
subjSDict = readSubjS(sys.argv[2])
atDict = readFasta(sys.argv[3])
at = 1
for line in open(sys.argv[1]):
if line[0] == '=':
group = line[1:].split()[1]
at = 1 #label the following locus is Arabidopsis
elif line[0] == '>':
if at:
locus = (line[1:].rsplit('.', 1))[0]
seq = atDict[locus]
at = 0
else:
locus = line[1:-1]
seq = subjSDict[locus]
#--------------------------------
else:
