def findAllMotifs_SameLine(motifList, seqName, dictOfFastas, resultList):
for motif in motifList:
# convert from IUPAC to regEx and search in forward direction
fwd_RegExMotif = re.compile(JamesDefs.iupac2regex(motif), re.IGNORECASE)
# initiate result string for forward matches with name of AGAP and fwd IUPAC motif string
MatchesStr = seqName+'\t'+motif
# initiate location list to hold then sort locations
matchLocations = []
# sequentially append each hit's coords to the end of locationList
for fwdMatcheObj in fwd_RegExMotif.finditer(dictOfFastas[seqName].seq.tostring()):
## must add 1 to the start pos due to computer numbers.............*
matchLocations.append(fwdMatcheObj.start()+1)
# commented this because i am combining fwd and rev hits onto one line for memory's sake down the pipe
### add trailing newline for printing to file later
##fwd_MatchesStr = fwd_MatchesStr+'\n'
### send fwd results to resultList
##resultList.append(fwd_MatchesStr)
# convert from IUPAC to regEx and search in reverse direction
rev_RegExMotif = re.compile(JamesDefs.iupac2regex(JamesDefs.revComp(motif)), re.IGNORECASE)
### initiate result string for forward matches with name of AGAP and fwd IUPAC motif string
##rev_MatchesStr = seqName+'\t'+motif+'_rc\t'
# sequentially append each hit's coords to the end of rev_MatchesStr
for revMatcheObj in rev_RegExMotif.finditer(dictOfFastas[seqName].seq.tostring()):
## must add 1 to the start pos due to computer numbers.............*
matchLocations.append(revMatcheObj.start()+1)
# sort locations by start
matchLocations.sort()
# format matchStr
for loc in matchLocations:
MatchesStr = "%s\t%i" % (MatchesStr, loc)
# add trailing newline for printing to file later
MatchesStr = MatchesStr+'\n'
# send fwd results to resultList
resultList.append(MatchesStr)
def countModuleInAll(module, seqDict):
import re
##motifList = moduleStrs.split('\t')
# Calculate revComp for each motif, convert them into perl-like regular expressions, compile those RegExStrings into
# python regEx objs and modify data structure to be list of lists with each
# 2ary list = [regExObj_Fwd, regExObj_Rev]
i = 0
for IUPACmotif in module:
# convert data struct and calc revComp
module[i] = [IUPACmotif, [IUPACmotif, JamesDefs.revComp(IUPACmotif)]]
c = 0
for each in module[i][1]:
module[i][1][c] = JamesDefs.iupac2regex(module[i][1][c])
c += 1
module[i][1] = makeFwdAndRevCompRegExObj(module[i][1])
i += 1
# Loop over list and count module in fwd and revComp oris for presence absense
# Sum total hits in totalHits
totalHits = 0
for record in seqDict:
# initiate modulePresent attrib to 0
seqDict[record].modulePresent = 0
hit = findModuleInLength(module, seqDict[record], 500)
totalHits += hit
return totalHits
def makeFwdAndRevCompRegExObj(motif):
import re
motifPair = [motif, JamesDefs.revComp(motif)]
# convert iupac string to regEx string
for i in range(len(motifPair)):
motifPair[i] = JamesDefs.iupac2regex(motifPair[i])
motif = '(%s|%s)' % (motifPair[0], motifPair[1])
fwdRevComp_regExObj = re.compile(motif, re.IGNORECASE)
return fwdRevComp_regExObj
def findAllMotifs(motifList, seqName, dictOfFastas, resultList):
for motif in motifList:
# convert from IUPAC to regEx and search in forward direction
fwd_RegExMotif = re.compile(JamesDefs.iupac2regex(motif), re.IGNORECASE)
# initiate result string for forward matches with name of AGAP and fwd IUPAC motif string
fwd_MatchesStr = seqName+'\t'+motif+'\t'
# sequentially append each hit's coords to the end of fwd_MatchesStr
for fwdMatcheObj in fwd_RegExMotif.finditer(dictOfFastas[seqName].seq.tostring()):
## must add 1 to the start pos due to computer numbers.............*
fwd_MatchesStr = fwd_MatchesStr+'%s\t' % (str(fwdMatcheObj.start()+1))
# add trailing newline for printing to file later
fwd_MatchesStr = fwd_MatchesStr+'\n'
# send fwd results to resultList
resultList.append(fwd_MatchesStr)
# convert from IUPAC to regEx and search in reverse direction
rev_RegExMotif = re.compile(JamesDefs.iupac2regex(JamesDefs.revComp(motif)), re.IGNORECASE)
# initiate result string for forward matches with name of AGAP and fwd IUPAC motif string
rev_MatchesStr = seqName+'\t'+motif+'_rc\t'
# sequentially append each hit's coords to the end of rev_MatchesStr
for revMatcheObj in rev_RegExMotif.finditer(dictOfFastas[seqName].seq.tostring()):
## must add 1 to the start pos due to computer numbers.............*
rev_MatchesStr = rev_MatchesStr+'%s\t' % (str(revMatcheObj.start()+1))
# add trailing newline for printing to file later
rev_MatchesStr = rev_MatchesStr+'\n'
# send fwd results to resultList
resultList.append(rev_MatchesStr)
def convertMotifList(motifList):
i = 0
while i < len(motifList):
motifList[i] = [motifList[i], JamesDefs.iupac2regex(motifList[i])]
i += 1
