def isIndexRevComp(indexfile,indexes,n=500000):
"""Determine if the indexes are reverse complemented or not
:param indexfile: filename of the Fastq index file
:param indexes: list or tuple of index strings
:param n: integer number of reads to sample
"""
print("HERE")
ifile = Fastq(indexfile)
ilength=len(indexes[0])
print(ilength)
indexreads = collections.defaultdict(int)
for i in range(n):
indexreads[ifile.next().sequence[:ilength]]+=1
counts = {'normal':0,
'revcomp':0}
for k,v in list(indexreads.items()):
print(k,v)
for i in indexes:
if(pylev.levenshtein(k,i)<=1):
counts['normal']+=v
continue
if(pylev.levenshtein(k,revcomp(i))<=1):
counts['revcomp']+=v
if(counts['revcomp']>counts['normal']):
print('using revcomp')
else:
print('NOT revcomp')
return(counts['revcomp']>counts['normal'])
def isIndexRevComp(indexfile, indexes, n=500000):
"""Determine if the indexes are reverse complemented or not
:param indexfile: filename of the Fastq index file
:param indexes: list or tuple of index strings
:param n: integer number of reads to sample
"""
print("HERE")
ifile = Fastq(indexfile)
ilength = len(indexes[0])
print(ilength)
indexreads = collections.defaultdict(int)
for i in range(n):
indexreads[ifile.next().sequence[:ilength]] += 1
counts = {'normal': 0, 'revcomp': 0}
for k, v in list(indexreads.items()):
print(k, v)
for i in indexes:
if (pylev.levenshtein(k, i) <= 1):
counts['normal'] += v
continue
if (pylev.levenshtein(k, revcomp(i)) <= 1):
counts['revcomp'] += v
if (counts['revcomp'] > counts['normal']):
print('using revcomp')
else:
print('NOT revcomp')
return (counts['revcomp'] > counts['normal'])
