def motif_count(sequences, start_at=4, stop_at=8):
"""Return a dict of motif counts for all motifs, lengths 4 through 7.
The output dict is nested like so:
motifs = {
4: {
'GGAG': 5,
}
}
sequences -- A list of sequences
"""
motifs = dict()
for motif_length in range(start_at, stop_at):
motifs[motif_length] = dict()
for sequence in sequences:
for motif in possible_motifs_by_length(motif_length):
if motif not in motifs[motif_length]:
motifs[motif_length][motif] = 0
if sequence.find(motif) != -1:
motifs[motif_length][motif] += overlap_count(
sequence, motif)
return motifs
def test_count_with_overlap(self):
count = cStrings.overlap_count("GGAGGAGG", "GGAGG")
self.assertEqual(count, 2)