def test_hsp_overlap_size(self):
overlap_size = hmm_detection.hsp_overlap_size
first = FakeHSPHit("A", "A", 50, 60, 0., None)
second = FakeHSPHit("B", "B", 70, 100, 0., None)
# no overlap
assert overlap_size(first, second) == 0
first.hit_end = 70
# still no overlap, end isn't inclusive
assert overlap_size(first, second) == 0
# a mix of second starting inside first
for i in range(1, 30):
first.hit_end += 1
assert overlap_size(first, second) == i
# second wholly contained
first.hit_end = 110
assert overlap_size(first, second) == 30
# first inside second
first.hit_start = 75
assert overlap_size(first, second) == 25
# first inside second, but direction reversed
first.hit_end = 50
with self.assertRaises(AssertionError):
overlap_size(first, second)
def test_filter(self):
# fake HSPs all in one CDS with overlap > 20 and query_ids from the same equivalence group
# not overlapping by > 20
first = FakeHSPHit("AMP-binding", "A", 50, 90, 0.1, None)
second = FakeHSPHit("A-OX", "A", 70, 100, 0.5, None)
new, by_id = hmm_detection.filter_results([first, second], {"A": [first, second]},
self.filter_file, self.signature_names)
assert new == [first, second]
assert by_id == {"A": [first, second]}
# overlapping, in same group
first.hit_end = 91
assert hmm_detection.hsp_overlap_size(first, second) == 21
new, by_id = hmm_detection.filter_results([first, second], {"A": [first, second]},
self.filter_file, self.signature_names)
assert new == [second]
assert by_id == {"A": [second]}
# overlapping, not in same group
second.query_id = "none"
new, by_id = hmm_detection.filter_results([first, second], {"A": [first, second]},
self.filter_file, self.signature_names)
assert new == [first, second]
assert by_id == {"A": [first, second]}
# not in the same CDS, but int he same group
second.hit_id = "B"
second.query_id = "A-OX"
new, by_id = hmm_detection.filter_results([first, second], {"A": [first], "B": [second]},
self.filter_file, self.signature_names)
assert new == [first, second]
assert by_id == {"A": [first], "B": [second]}