def count_words_tree(sequences,
l,
searchLocation,
strand='+-',
overlap=False,
error=0,
spacing=(1, 1)):
"""Count each word of length l in sequences
l -- oligonucleotide length
searchLocation -- location tuple example (-200,-1)
strand -- + or +-
overlap -- allow auto-overlapping
return N, H
"""
location = find_location(sequences)
#H = {} #hash table key=oligonucleotide value=list of occurrence position
N = {} #scanned base count per position fo each word size
N[l] = [0] * (searchLocation[1] - searchLocation[0] + 1)
scannedPositions = 0
scannedWords = 0
info = cli.Info(len(sequences), 1, 1)
#
# construct SuffixTree
#
st = ST.SuffixTree(maxDepth=l,
overlapping=overlap,
maxIUPAC=error,
NExtension=spacing,
storePosition=True)
for s in sequences:
info('Counting words in [%+05d:%+05d]' %
(searchLocation[0], searchLocation[1]))
a, b = max(searchLocation[0],
s.location[0]), min(searchLocation[1],
s.location[1] - l + 1)
dna = s.get_dna((a, b + l + 1))
st.add_dna(dna, shift=a)
for I in range(a, b + 1):
i = I - s.location[0]
w = dna[i:i + l]
if w.find('N') >= 0:
continue
N[l][I - searchLocation[0]] += 1
#@DEBUG
#ST.display(st.root, maxDepth=6, full=1)
#
# Count
#
#@DEBUG
#keys = st.extract(minLength=l, maxLength=l).keys()
#keys.sort()
#print '\n'.join(keys)
C = st.extract(minLength=l, maxLength=l)
if strand == '+-':
H = ST.get_positions_two_strands(C, overlap)
else:
H = ST.get_positions(C)
return dict(N=N,
H=H,
scannedPositions=scannedPositions,
scannedWords=scannedWords)
