opts.trim[0] = int(opts.trim[0])
if opts.trim[1] == 'None':
opts.trim[1] = None
else:
opts.trim[1] = int(opts.trim[1])
optionsObj = {'kmerSize':opts.ksize,'kmerRange':opts.krange} # need to change the use of this to be how mortals think of numbers
posArgs = [opts.fasta,opts.regs]
outFile = opts.out
tWrap = TamoWrap(optionsObj,posArgs)
shorties = 0
if opts.trim:
for i in tWrap.allSeqs.probes:
oLen = len(tWrap.allSeqs.probes[i])
tWrap.allSeqs.probes[i] = tWrap.allSeqs.probes[i][opts.trim[0]:opts.trim[1]]
nLen = len(tWrap.allSeqs.probes[i])
#print 'old:%s, new:%s' % (oLen,nLen)
if not nLen < oLen:
shorties+=1
if shorties/float(len(tWrap.allSeqs.probes)) > 0.25:
warn("""WARNING: more than 1/4 of the total sequences were shorter or equal to the length of the requested substring.""")
tWrap.linkedSeqs_seqs = tWrap.allSeqs.seqs_from_ids(tWrap.linkedSeqs_ids)
tWrap.go()
# TamoWrap -> def __init__(self, optionsObj, posArgs):
# get list of file paths
dirPath = '/Users/biggus/Documents/James/Data/ReClustering/kmedsPear33Clus50x_2/Clus2_247genes.6EucClus/'
files = glob.glob('%s*.genes.txt' % (dirPath))
for genesFile in files:
optionsObj = {'kmerSize':7,'kmerRange':'6,9'} # need to change the use of this to be how mortals think of numbers
posArgs = ['/Users/biggus/Documents/James/Data/2KB/2kb_Sequence/2kb_Anopheles/2KBupTSS_goodAffyAGAPsFastasOUT.masked.nr.fas',
genesFile]
outFile = genesFile.replace('.txt','.6-9mers.txt')
tWrap = TamoWrap(optionsObj,posArgs)
tWrap.go()
#for l in tWrap.toFile:
#print l.strip()
print 'num of keepers = %s' % (len(tWrap.output))
outFile = open(outFile, 'w')
outFile.writelines(tWrap.toFile)
outFile.close()
del(outFile)
print 'Done.'
