from TAMO.MotifMetrics import Fasta
from gusPyCode.defs.JamesDefs import revComp
seedsFile = '/Users/biggus/Documents/James/Data/Tu_miRNA/miRNAs/testSeeds.fas'
kMersFile = '/Users/biggus/Documents/James/Data/Tu_miRNA/MDOSoutPut/CqAg_7mers_orthosForMDOS_500afterCoding.mdos.motifzSgte3.txt'
seeds = Fasta.file2dict(seedsFile)
kMers = map(lambda line: line.strip().split('\t'), open(kMersFile,'rU').readlines())
print 'seedsFile: %s\nkMersFile: %s\n' % (seedsFile,kMersFile)
for l in kMers:
for seed in seeds.keys():
if revComp(seeds[seed].upper()) == l[0]:
print '>%s\n%s\n' % (seed,'\t'.join(l))
print 'done'
from gusPyCode.defs.JamesDefs import revComp
#========================= User Defined Variables =========================
inFile = '/Users/biggus/Documents/James/Data/2KB/2kb_Sequence/2kb_Combo/2Kb_AllMosquitoes/MosqMotifs/MotifGroupPWMs/AllGroups/AllGroups_Aln.fwd.txt'
outFile = '/Users/biggus/Documents/James/Data/2KB/2kb_Sequence/2kb_Combo/2Kb_AllMosquitoes/MosqMotifs/MotifGroupPWMs/AllGroups/AllGroups_Aln.rvCmp.txt'
#==========================================================================
#--------- Script Specific Function Definitions ---------------------
#--------------------------------------------------------------------
inFile = map(lambda line : line.strip(), open(inFile, 'rU').readlines())
outData = []
for each in inFile:
outData.append(revComp(each)+"\n")
outFile = open(outFile, 'w')
outFile.writelines(outData)
print "Done."
from gusPyCode.defs.JamesDefs import revComp
from sets import Set
KmerCounts = {'AA':3,'TT':3,'GC':3,'CG':3,'CC':3,'TA':3,'AT':3}
allKmers = KmerCounts.keys()
#nrKmers = []
# make a set of sets that represent each revcomp pair Sets do not allow multiple identicle
# entries so you will end up with a single set for each rvcmp pair. Notice that for motifs
# like 'AT' the rvcmp IS 'AT' so there is only 'AT' in the set not set([AT,AT])''. But for
# most you should have set([fwd,rvcmp]) in rvCmpPairs
rvCmpPairSets = Set([])
for i in allKmers:
rc = Set([i,revComp(i)])
rvCmpPairSets.add(rc)
# now convert the sets back into lists and force them to become strings so we can use them for a dict key
rvCmpPairDict = {}
for i in rvCmpPairSets:
rvCmpPairDict[(str(list(i)))] = 0
# iterate through the original dict and ask if the original motif key is in the list that makes up the
# rvcmp pair key. This uses "eval" which will magicly convert the key into a list again since we created
# the string like this str([list]). We then add the value to whichever key in rvCmpPairDict that the key
# in KmerCounts matches.
for key in KmerCounts:
for pairKey in rvCmpPairDict:
if key in eval(pairKey):
rvCmpPairDict[pairKey] = rvCmpPairDict[pairKey] + KmerCounts[key] # adding kmercount to whatever value is in rvCmpPairDict[pairKey]
#--------------------------------------------------------------------
#========================= User Defined Variables =========================
inFile = '/Users/biggus/Documents/James/Data/2KB/2kb_Sequence/2kb_Combo/2kb_DmelMosquitoes/2KBup_CombinedDrosophilaAndCulexOrthologs.masked.fas'
outFile = '/Users/biggus/Documents/James/Data/2KB/2kb_Sequence/2kb_Combo/2kb_DmelMosquitoes/2KBup_CombinedDrosophilaAndCulexOrthologs.masked.rvCmp.fas'
#==========================================================================
inFile = map(lambda line : line.strip(), open(inFile, 'rU').readlines())
bp_10 = re.compile('^[ATGCN]{10,}')
for i in range(0,len(inFile)):
if bp_10.search(inFile[i]):
inFile[i] = "%snnn%s\n" % (inFile[i], revComp(inFile[i]))
else:
inFile[i] = inFile[i]+'\n'
outFile = open(outFile, 'w')
outFile.writelines(inFile)
print 'Done!'
