def test_connected_components(self):
'''test connected_components'''
self.assertListEqual([['c1'], ['c2'], ['c3'], ['c4'], ['c5'], ['c6']], self.g.connected_components())
self.g.add_edge(edge.Edge('c1', 42, 1, 'c2', 1, 10))
self.assertListEqual([['c1', 'c2'], ['c3'], ['c4'], ['c5'], ['c6']], self.g.connected_components())
self.g.add_edge(edge.Edge('c3', 42, 1, 'c2', 1, 10))
self.assertListEqual([['c1', 'c2', 'c3'], ['c4'], ['c5'], ['c6']], self.g.connected_components())
def to_graph_edge(self, min_overlap_length=200, end_tolerance=50, min_identity=99):
if self.percent_identity < min_identity or min(self.hit_length_qry, self.hit_length_ref) < min_overlap_length:
return None
ref_at_ends = self._is_at_ends(tolerance=end_tolerance)
qry_at_ends = self._is_at_ends(use_qry=True, tolerance=end_tolerance)
bad_values = set([HIT_NO_ENDS, HIT_AT_BOTH_ENDS])
if ref_at_ends in bad_values or qry_at_ends in bad_values:
return None
good_values = set([HIT_AT_START, HIT_AT_END])
assert qry_at_ends in good_values
assert ref_at_ends in good_values
qry_fwd_strand = self.qry_start < self.qry_end
ref_fwd_strand = self.ref_start < self.ref_end
if ((qry_fwd_strand == ref_fwd_strand) == (qry_at_ends == ref_at_ends)):
return None
elif qry_fwd_strand:
if ref_fwd_strand:
if qry_at_ends == HIT_AT_END:
assert ref_at_ends == HIT_AT_START
qry_first = True
elif qry_at_ends == HIT_AT_START:
assert ref_at_ends == HIT_AT_END
qry_first = False
else:
raise Error('Error in mummer.to_graph_edge(). Cannot continue')
else:
if qry_at_ends == HIT_AT_END:
assert ref_at_ends == HIT_AT_END
qry_first = True
elif qry_at_ends == HIT_AT_START:
assert ref_at_ends == HIT_AT_START
qry_first = False
else:
raise Error('Error in mummer.to_graph_edge(). Cannot continue')
else:
if ref_fwd_strand:
if qry_at_ends == HIT_AT_END:
assert ref_at_ends == HIT_AT_END
qry_first = False
elif qry_at_ends == HIT_AT_START:
assert ref_at_ends == HIT_AT_START
qry_first = True
else:
raise Error('Error in mummer.to_graph_edge(). Cannot continue')
else:
if qry_at_ends == HIT_AT_END:
assert ref_at_ends == HIT_AT_START
qry_first = False
elif qry_at_ends == HIT_AT_START:
assert ref_at_ends == HIT_AT_END
qry_first = True
else:
raise Error('Error in mummer.to_graph_edge(). Cannot continue')
if qry_first:
return edge.Edge(self.qry_name, self.qry_start, self.qry_end, self.ref_name, self.ref_start, self.ref_end)
else:
return edge.Edge(self.ref_name, self.ref_start, self.ref_end, self.qry_name, self.qry_start, self.qry_end)
def test_open_end(self):
'''test open_end'''
e1 = edge.Edge('c1', 1, 42, 'c2', 50, 10)
e2 = edge.Edge('c1', 42, 1, 'c2', 1, 10)
self.assertEqual(e1.open_end('c1'), edge.LEFT)
self.assertEqual(e1.open_end('c2'), edge.LEFT)
self.assertEqual(e2.open_end('c1'), edge.RIGHT)
self.assertEqual(e2.open_end('c2'), edge.RIGHT)
def test_make_contig_forwards(self):
'''test make_contig_forwards'''
e = edge.Edge('c1', 1, 42, 'c2', 50, 10)
e._make_contig_forwards('c1')
self.assertEqual(e, edge.Edge('c1', 1, 42, 'c2', 50, 10))
e._make_contig_forwards('c2')
self.assertEqual(e, edge.Edge('c2', 10, 50, 'c1', 42, 1))
e._make_contig_forwards('c1')
self.assertEqual(e, edge.Edge('c1', 1, 42, 'c2', 50, 10))
def test_remove_redundant_nodes_from_simple_path(self):
'''test remove_redundant_nodes_from_simple_path'''
self.g.add_edge(edge.Edge('c1', 1, 100, 'c2', 1, 42))
self.g.add_edge(edge.Edge('c2', 100, 142, 'c3', 1, 42))
new_path = self.g.remove_redundant_nodes_from_simple_path(
['c1', 'c2', 'c3'])
self.assertListEqual(['c1', 'c2', 'c3'], new_path)
self.assertTrue('c2' in self.g.graph)
self.g = graph.Graph(self.asm)
self.g.add_edge(edge.Edge('c1', 51, 100, 'c2', 1, 50))
self.g.add_edge(edge.Edge('c2', 41, 80, 'c3', 1, 40))
new_path = self.g.remove_redundant_nodes_from_simple_path(
['c1', 'c2', 'c3'])
self.assertListEqual(['c1', 'c3'], new_path)
self.assertFalse('c2' in self.g.graph)
self.g = graph.Graph(self.asm)
self.g.add_edge(edge.Edge('c1', 51, 100, 'c2', 1, 50))
self.g.add_edge(edge.Edge('c2', 41, 80, 'c3', 1, 40))
self.g.add_edge(edge.Edge('c3', 100, 150, 'c4', 1, 50))
self.g.add_edge(edge.Edge('c4', 20, 70, 'c5', 1, 50))
self.g.add_edge(edge.Edge('c5', 40, 90, 'c6', 1, 50))
new_path = self.g.remove_redundant_nodes_from_simple_path(
['c1', 'c2', 'c3', 'c4', 'c5', 'c6'])
self.assertListEqual(['c1', 'c3', 'c5', 'c6'], new_path)
self.assertFalse('c2' in self.g.graph)
self.assertFalse('c4' in self.g.graph)
def test_simple_path_is_consistent(self):
'''test simple_path_is_consistent'''
self.g.add_edge(edge.Edge('c1', 1, 100, 'c2', 1, 42))
self.g.add_edge(edge.Edge('c2', 50, 100, 'c3', 1, 42))
self.assertTrue(self.g.simple_path_is_consistent(['c1', 'c2']))
self.g.add_edge(edge.Edge('c3', 10, 100, 'c4', 1, 1000))
self.assertTrue(self.g.simple_path_is_consistent(['c1', 'c2', 'c3']))
self.g = graph.Graph(self.asm)
self.g.add_edge(edge.Edge('c1', 1, 100, 'c2', 1, 42))
self.g.add_edge(edge.Edge('c2', 1000, 100, 'c3', 1, 42))
self.assertFalse(self.g.simple_path_is_consistent(['c1', 'c2', 'c3']))
def test_degree(self):
'''test degree'''
self.assertEqual(0, self.g._degree('c1'))
self.assertEqual(0, self.g._degree('c2'))
e1 = edge.Edge('c1', 1, 42, 'c2', 50, 10)
e2 = edge.Edge('c1', 4, 43, 'c2', 60, 10)
self.g.add_edge(e1)
self.assertEqual(1, self.g._degree('c1'))
self.assertEqual(1, self.g._degree('c2'))
self.g.add_edge(e2)
self.assertEqual(2, self.g._degree('c1'))
self.assertEqual(2, self.g._degree('c2'))
def test_add_and_get_edges(self):
'''test adding and getting edges'''
self.assertListEqual([], self.g._get_edges('not_in_graph', 'c1'))
self.assertListEqual([], self.g._get_edges('not_in_graph', 'c2'))
self.assertListEqual([], self.g._get_edges('c1', 'c2'))
self.assertListEqual([], self.g._get_edges('c2', 'c1'))
e1 = edge.Edge('c1', 1, 42, 'c2', 50, 10)
e2 = edge.Edge('c1', 4, 43, 'c2', 60, 10)
self.g.add_edge(e1)
self.assertListEqual([e1], self.g._get_edges('c1', 'c2'))
self.g.add_edge(e2)
self.assertListEqual([e1, e2], self.g._get_edges('c1', 'c2'))
with self.assertRaises(graph.Error):
self.g.add_edge(edge.Edge('c7', 1, 10, 'c8', 42, 84))
def test_node_to_coords(self):
'''test _node_to_coords'''
self.g.add_edge(edge.Edge('c1', 199, 0, 'c2', 1319, 1119))
nodes = ['c1', 'c2']
self.assertListEqual(['c1', intervals.Interval(200, 659), True], self.g._node_to_coords(nodes, 0))
self.assertListEqual(['c2', intervals.Interval(0, 1319), True], self.g._node_to_coords(nodes, 1))
self.g = graph.Graph(self.asm)
self.g.add_edge(edge.Edge('c2', 1119, 1319, 'c1', 0, 199))
nodes = ['c1', 'c2']
self.assertListEqual(['c1', intervals.Interval(200, 659), True], self.g._node_to_coords(nodes, 0))
self.assertListEqual(['c2', intervals.Interval(0, 1319), True], self.g._node_to_coords(nodes, 1))
self.g = graph.Graph(self.asm)
self.g.add_edge(edge.Edge('c1', 551, 650, 'c2', 1, 100))
self.g.add_edge(edge.Edge('c2', 1201, 1300, 'c3', 11, 110))
nodes = ['c1', 'c2', 'c3']
self.assertListEqual(['c1', intervals.Interval(0, 550), False], self.g._node_to_coords(nodes, 0))
self.assertListEqual(['c2', intervals.Interval(1, 1200), False], self.g._node_to_coords(nodes, 1))
self.assertListEqual(['c3', intervals.Interval(11, 2159), False], self.g._node_to_coords(nodes, 2))
self.g = graph.Graph(self.asm)
self.g.add_edge(edge.Edge('c1', 551, 650, 'c2', 1, 100))
self.g.add_edge(edge.Edge('c3', 110, 11, 'c2', 1300, 1201))
self.g.add_edge(edge.Edge('c3', 2051, 2150, 'c4', 6, 115))
nodes = ['c1', 'c2', 'c3', 'c4']
self.assertListEqual(['c1', intervals.Interval(0, 550), False], self.g._node_to_coords(nodes, 0))
self.assertListEqual(['c2', intervals.Interval(1, 1200), False], self.g._node_to_coords(nodes, 1))
self.assertListEqual(['c3', intervals.Interval(11, 2050), False], self.g._node_to_coords(nodes, 2))
self.assertListEqual(['c4', intervals.Interval(6, 1259), False], self.g._node_to_coords(nodes, 3))
def test_make_contig_first(self):
'''test make_contig_first'''
e = edge.Edge('c1', 1, 42, 'c2', 50, 10)
e_original = copy.copy(e)
e.make_contig_first('c1')
self.assertEqual(e, e_original)
e.make_contig_first('c2')
self.assertEqual(e, e_original)
e.make_contig_first('c1')
self.assertEqual(e, e_original)
def test_merged_coords_from_simple_nonredundant_path(self):
'''test merged_coords_from_simple_nonredundant_path'''
self.g.add_edge(edge.Edge('c1', 199, 0, 'c2', 1319, 1119))
nodes = ['c1', 'c2']
coords = self.g.merged_coords_from_simple_nonredundant_path(nodes)
expected = [
['c1', intervals.Interval(200, 659), True],
['c2', intervals.Interval(0, 1319), True],
]
self.assertListEqual(expected, coords)
self.g = graph.Graph(self.asm)
self.g.add_edge(edge.Edge('c1', 610, 652, 'c2', 1, 42))
self.g.add_edge(edge.Edge('c2', 1250, 1310, 'c3', 5, 65))
nodes = ['c1', 'c2', 'c3']
coords = self.g.merged_coords_from_simple_nonredundant_path(nodes)
expected = [['c1', intervals.Interval(0, 609), False],
['c2', intervals.Interval(1, 1249), False],
['c3', intervals.Interval(5, 2159), False]]
self.assertListEqual(expected, coords)
def test_to_graph_edge(self):
'''Test to_graph_edge'''
hits = [
'\t'.join(['781', '981', '10', '210', '200', '200', '98', '1000', '1000', '1', '1', 'ref', 'qry']), # %id too low
'\t'.join(['781', '980', '10', '210', '199', '200', '98', '1000', '1000', '1', '1', 'ref', 'qry']), # hit too short
'\t'.join(['781', '981', '10', '209', '200', '199', '98', '1000', '1000', '1', '1', 'ref', 'qry']), # hit too short
'\t'.join(['1', '200', '1', '200', '200', '200', '100.00', '1000', '1000', '1', '1', 'ref', 'qry']), # bad orientation
'\t'.join(['200', '1', '200', '1', '200', '200', '100.00', '1000', '1000', '1', '1', 'ref', 'qry']), # bad orientation
'\t'.join(['800', '1000', '800', '1000', '200', '200', '100.00', '1000', '1000', '1', '1', 'ref', 'qry']), # bad orientation
'\t'.join(['1000', '800', '1000', '800', '200', '200', '100.00', '1000', '1000', '1', '1', 'ref', 'qry']), # bad orientation
'\t'.join(['300', '500', '300', '500', '200', '200', '100.00', '1000', '1000', '1', '1', 'ref', 'qry']), # not at ends
'\t'.join(['1', '1000', '1', '1000', '1000', '1000', '100.00', '1000', '1000', '1', '1', 'ref', 'qry']), # whole contigs hit
'\t'.join(['1', '500', '1', '1000', '500', '500', '100.00', '500', '1000', '1', '1', 'ref1', 'qry1']), # contained contig
'\t'.join(['1', '200', '791', '991', '200', '200', '100.00', '1000', '1000', '1', '1', 'ref2', 'qry2']),
'\t'.join(['781', '981', '10', '210', '200', '200', '100.00', '1000', '1000', '1', '1', 'ref3', 'qry3']),
'\t'.join(['991', '791', '781', '981', '200', '200', '100.00', '1000', '1000', '1', '1', 'ref4', 'qry4']),
'\t'.join(['210', '10', '15', '215', '200', '200', '100.00', '1000', '1000', '1', '1', 'ref5', 'qry5']),
'\t'.join(['781', '981', '991', '791', '200', '200', '100.00', '1000', '1000', '1', '1', 'ref6', 'qry6']),
'\t'.join(['10', '210', '215', '5', '200', '200', '100.00', '1000', '1000', '1', '1', 'ref7', 'qry7']),
'\t'.join(['210', '10', '980', '780', '200', '200', '100.00', '1000', '1000', '1', '1', 'ref8', 'qry8']),
'\t'.join(['995', '795', '215', '15', '200', '200', '100.00', '1000', '1000', '1', '1', 'ref9', 'qry9']),
]
expected = [
None,
None,
None,
None,
None,
None,
None,
None,
None,
None,
edge.Edge('qry2', 790, 990, 'ref2', 0, 199),
edge.Edge('ref3', 780, 980, 'qry3', 9, 209),
edge.Edge('qry4', 780, 980, 'ref4', 990, 790),
edge.Edge('ref5', 209, 9, 'qry5', 14, 214),
edge.Edge('ref6', 780, 980, 'qry6', 990, 790),
edge.Edge('qry7', 214, 4, 'ref7', 9, 209),
edge.Edge('ref8', 209, 9, 'qry8', 979, 779),
edge.Edge('qry9', 214, 14, 'ref9', 994, 794),
]
assert len(expected) == len(hits)
for i in range(len(hits)):
m = mummer.NucmerHit(hits[i])
self.assertEqual(m.to_graph_edge(), expected[i])
def test_find_simple_path(self):
'''test find_simple_path'''
self.assertListEqual([], self.g.find_simple_path(['c1']))
self.g.add_edge(edge.Edge('c1', 1, 100, 'c2', 1, 42))
self.assertListEqual(['c1', 'c2'], self.g.find_simple_path(['c1', 'c2']))
self.g.add_edge(edge.Edge('c2', 50, 100, 'c3', 1, 42))
self.assertListEqual(['c1', 'c2', 'c3'], self.g.find_simple_path(['c1', 'c2', 'c3']))
self.g.add_edge(edge.Edge('c2', 50, 100, 'c3', 1, 42))
self.assertListEqual([], self.g.find_simple_path(['c1', 'c2', 'c3']))
self.g.add_edge(edge.Edge('c1', 1, 100, 'c2', 1, 42))
self.assertListEqual([], self.g.find_simple_path(['c1', 'c2']))
self.g = graph.Graph(self.asm)
self.g.add_edge(edge.Edge('c1', 1, 100, 'c2', 1, 42))
self.g.add_edge(edge.Edge('c2', 50, 100, 'c3', 1, 42))
self.g.add_edge(edge.Edge('c3', 10, 100, 'c4', 1, 1000))
self.assertListEqual(['c1', 'c2', 'c3', 'c4'], self.g.find_simple_path(['c1', 'c2', 'c3', 'c4']))
self.g.add_edge(edge.Edge('c3', 10, 100, 'c5', 1, 1000))
self.assertListEqual([], self.g.find_simple_path(['c1', 'c2', 'c3']))
def test_remove_middle_node(self):
'''test remove_middle_node'''
self.g.add_edge(edge.Edge('c1', 1, 100, 'c2', 1, 42))
self.g.add_edge(edge.Edge('c2', 100, 142, 'c3', 1, 42))
self.assertFalse(self.g._remove_middle_node('c1', 'c2', 'c3'))
self.g = graph.Graph(self.asm)
self.g.add_edge(edge.Edge('c1', 51, 100, 'c2', 1, 50))
self.g.add_edge(edge.Edge('c2', 41, 80, 'c3', 1, 40))
self.assertTrue(self.g._remove_middle_node('c1', 'c2', 'c3'))
self.assertTrue('c2' not in self.g.graph)
self.assertEqual(1, len(self.g.graph['c1']['c3']['edges']))
self.assertEqual(1, len(self.g.graph['c3']['c1']['edges']))
self.assertEqual(self.g.graph['c1']['c3']['edges'][0], edge.Edge('c1', 91, 100, 'c3', 1, 10))
self.assertEqual(self.g.graph['c3']['c1']['edges'][0], edge.Edge('c1', 91, 100, 'c3', 1, 10))
def test_edges_are_consistent(self):
'''test edges_are_consistent'''
self.g.add_edge(edge.Edge('c1', 1, 100, 'c2', 1, 42))
self.g.add_edge(edge.Edge('c2', 50, 100, 'c3', 1, 42))
self.assertTrue(self.g._edges_are_consistent('c1', 'c2', 'c3'))
self.g.add_edge(edge.Edge('c1', 1, 100, 'c3', 1, 42))
self.assertFalse(self.g._edges_are_consistent('c1', 'c2', 'c3'))
self.g = graph.Graph(self.asm)
self.g.add_edge(edge.Edge('c1', 1, 100, 'c2', 1, 42))
self.g.add_edge(edge.Edge('c1', 1, 100, 'c2', 1, 42))
self.g.add_edge(edge.Edge('c2', 50, 100, 'c3', 1, 42))
self.assertFalse(self.g._edges_are_consistent('c1', 'c2', 'c3'))
self.g = graph.Graph(self.asm)
self.g.add_edge(edge.Edge('c1', 1, 100, 'c2', 1, 42))
self.g.add_edge(edge.Edge('c2', 50, 100, 'c3', 1, 42))
self.g.add_edge(edge.Edge('c2', 50, 100, 'c3', 1, 42))
self.assertFalse(self.g._edges_are_consistent('c1', 'c2', 'c3'))
self.g = graph.Graph(self.asm)
self.g.add_edge(edge.Edge('c1', 1, 100, 'c2', 1, 42))
self.g.add_edge(edge.Edge('c2', 100, 50, 'c3', 1, 42))
self.assertFalse(self.g._edges_are_consistent('c1', 'c2', 'c3'))
self.g = graph.Graph(self.asm)
self.g.add_edge(edge.Edge('c1', 1, 100, 'c2', 42, 1))
self.g.add_edge(edge.Edge('c2', 50, 100, 'c3', 1, 42))
self.assertFalse(self.g._edges_are_consistent('c1', 'c2', 'c3'))
def test_reverse(self):
'''test reverse'''
e = edge.Edge('c1', 1, 42, 'c2', 50, 10)
e.reverse()
self.assertEqual(e, edge.Edge('c2', 10, 50, 'c1', 42, 1))
def test_merge_into(self):
'''test merge_into'''
e1 = edge.Edge('c1', 71, 100, 'c2', 1, 30)
e2 = edge.Edge('c2', 41, 80, 'c3', 1, 40)
e2_original = copy.copy(e2)
self.assertFalse(e1.merge_into(e2, 'c2'))
self.assertEqual(e2, e2_original)
e1 = edge.Edge('c1', 51, 100, 'c2', 1, 50)
e2 = edge.Edge('c2', 41, 80, 'c3', 1, 40)
e2_original = copy.copy(e2)
self.assertTrue(e1.merge_into(e2, 'c2'))
self.assertEqual(e2, e2_original)
self.assertEqual(e1, edge.Edge('c1', 91, 100, 'c3', 1, 10))
e2 = edge.Edge('c1', 51, 100, 'c2', 1, 50)
e1 = edge.Edge('c2', 41, 80, 'c3', 1, 40)
e2_original = copy.copy(e2)
self.assertTrue(e1.merge_into(e2, 'c2'))
self.assertEqual(e2, e2_original)
self.assertEqual(e1, edge.Edge('c1', 91, 100, 'c3', 1, 10))
e1 = edge.Edge('c1', 51, 1, 'c2', 2, 52)
e2 = edge.Edge('c2', 41, 80, 'c3', 1, 40)
e2_original = copy.copy(e2)
self.assertTrue(e1.merge_into(e2, 'c2'))
self.assertEqual(e2, e2_original)
self.assertEqual(e1, edge.Edge('c1', 12, 1, 'c3', 1, 12))
e2 = edge.Edge('c1', 51, 1, 'c2', 2, 52)
e1 = edge.Edge('c2', 41, 80, 'c3', 1, 40)
e2_original = copy.copy(e2)
self.assertTrue(e1.merge_into(e2, 'c2'))
self.assertEqual(e2, e2_original)
self.assertEqual(e1, edge.Edge('c1', 12, 1, 'c3', 1, 12))
def test_change_hit_coords_with_intersection(self):
'''test test_change_hit_coords_with_intersection'''
e = edge.Edge('c1', 1, 42, 'c2', 10, 50)
e._change_hit_coords_with_intersection('c1', intervals.Interval(20, 30))
self.assertEqual(e, edge.Edge('c1', 20, 30, 'c2', 29, 38))
e = edge.Edge('c1', 1, 42, 'c2', 10, 50)
e._change_hit_coords_with_intersection('c2', intervals.Interval(20, 30))
self.assertEqual(e, edge.Edge('c1', 11, 22, 'c2', 20, 30))
e = edge.Edge('c1', 1, 42, 'c2', 50, 10)
e._change_hit_coords_with_intersection('c1', intervals.Interval(20, 30))
self.assertEqual(e, edge.Edge('c1', 20, 30, 'c2', 31, 22))
e = edge.Edge('c1', 1, 42, 'c2', 50, 10)
e._change_hit_coords_with_intersection('c2', intervals.Interval(20, 30))
self.assertEqual(e, edge.Edge('c1', 21, 32, 'c2', 30, 20))
e = edge.Edge('c1', 42, 1, 'c2', 10, 50)
e._change_hit_coords_with_intersection('c1', intervals.Interval(20, 30))
self.assertEqual(e, edge.Edge('c1', 30, 20, 'c2', 22, 31))
e = edge.Edge('c1', 42, 1, 'c2', 10, 50)
e._change_hit_coords_with_intersection('c2', intervals.Interval(20, 30))
self.assertEqual(e, edge.Edge('c1', 32, 21, 'c2', 20, 30))
e = edge.Edge('c1', 42, 1, 'c2', 50, 10)
e._change_hit_coords_with_intersection('c1', intervals.Interval(20, 30))
self.assertEqual(e, edge.Edge('c1', 30, 20, 'c2', 38, 29))
e = edge.Edge('c1', 42, 1, 'c2', 50, 10)
e._change_hit_coords_with_intersection('c2', intervals.Interval(20, 30))
self.assertEqual(e, edge.Edge('c1', 22, 11, 'c2', 30, 20))
