def test_fitch_descendants_missing_data(self):
"""fitch_descendants should work with missing data"""
#tree and envs for testing missing values
t_str = '(((a:1,b:2):4,(c:3,d:1):2):1,(e:2,f:1):3);'
env_str = """a A
b B
c D
d C
e C
f D"""
t = DndParser(t_str, UniFracTreeNode)
node_index, nodes = index_tree(t)
env_counts = count_envs(env_str.split('\n'))
count_array, unique_envs, env_to_index, node_to_index = \
index_envs(env_counts, node_index)
branch_lengths = get_branch_lengths(node_index)
#test just the AB pair
ab_counts = count_array[:, 0:2]
bindings = bind_to_array(nodes, ab_counts)
changes = fitch_descendants(bindings, counter=FitchCounter)
self.assertEqual(changes, 1)
orig_result = ab_counts.copy()
#check that the original Fitch counter gives the expected
#incorrect parsimony result
changes = fitch_descendants(bindings, counter=FitchCounterDense)
self.assertEqual(changes, 5)
new_result = ab_counts.copy()
#check that the two versions fill the array with the same values
self.assertEqual(orig_result, new_result)
def test_fitch_descendants_missing_data(self):
"""fitch_descendants should work with missing data"""
#tree and envs for testing missing values
t_str = '(((a:1,b:2):4,(c:3,d:1):2):1,(e:2,f:1):3);'
env_str = """a A
b B
c D
d C
e C
f D"""
t = DndParser(t_str, UniFracTreeNode)
node_index, nodes = index_tree(t)
env_counts = count_envs(env_str.split('\n'))
count_array, unique_envs, env_to_index, node_to_index = \
index_envs(env_counts, node_index)
branch_lengths = get_branch_lengths(node_index)
#test just the AB pair
ab_counts = count_array[:, 0:2]
bindings = bind_to_array(nodes, ab_counts)
changes = fitch_descendants(bindings, counter=FitchCounter)
self.assertEqual(changes, 1)
orig_result = ab_counts.copy()
#check that the original Fitch counter gives the expected
#incorrect parsimony result
changes = fitch_descendants(bindings, counter=FitchCounterDense)
self.assertEqual(changes, 5)
new_result = ab_counts.copy()
#check that the two versions fill the array with the same values
self.assertEqual(orig_result, new_result)
def setUp(self):
"""Define a couple of standard trees"""
self.t1 = DndParser("(((a,b),c),(d,e))", UniFracTreeNode)
self.t2 = DndParser("(((a,b),(c,d)),(e,f))", UniFracTreeNode)
self.t3 = DndParser("(((a,b,c),(d)),(e,f))", UniFracTreeNode)
self.t4 = DndParser("((c)b,((f,g,h)e,i)d)", UniFracTreeNode)
self.t4.Name = "a"
self.t_str = "((a:1,b:2):4,(c:3,(d:1,e:1):2):3)"
self.t = DndParser(self.t_str, UniFracTreeNode)
self.env_str = """
a A 1
a C 2
b A 1
b B 1
c B 1
d B 3
e C 1"""
self.env_counts = count_envs(self.env_str.splitlines())
self.node_index, self.nodes = index_tree(self.t)
self.count_array, self.unique_envs, self.env_to_index, self.node_to_index = index_envs(
self.env_counts, self.node_index
)
self.branch_lengths = get_branch_lengths(self.node_index)
self.old_t_str = "((org1:0.11,org2:0.22,(org3:0.12,org4:0.23)g:0.33)b:0.2,(org5:0.44,org6:0.55)c:0.3,org7:0.4)"
self.old_t = DndParser(self.old_t_str, UniFracTreeNode)
self.old_env_str = """
org1 env1 1
org1 env2 1
org2 env2 1
org3 env2 1
org4 env3 1
org5 env1 1
org6 env1 1
org7 env3 1
"""
self.old_env_counts = count_envs(self.old_env_str.splitlines())
self.old_node_index, self.old_nodes = index_tree(self.old_t)
self.old_count_array, self.old_unique_envs, self.old_env_to_index, self.old_node_to_index = index_envs(
self.old_env_counts, self.old_node_index
)
self.old_branch_lengths = get_branch_lengths(self.old_node_index)
def setUp(self):
"""Define a couple of standard trees"""
self.t1 = DndParser('(((a,b),c),(d,e))', UniFracTreeNode)
self.t2 = DndParser('(((a,b),(c,d)),(e,f))', UniFracTreeNode)
self.t3 = DndParser('(((a,b,c),(d)),(e,f))', UniFracTreeNode)
self.t4 = DndParser('((c)b,((f,g,h)e,i)d)', UniFracTreeNode)
self.t4.Name = 'a'
self.t_str = '((a:1,b:2):4,(c:3,(d:1,e:1):2):3)'
self.t = DndParser(self.t_str, UniFracTreeNode)
self.env_str = """
a A 1
a C 2
b A 1
b B 1
c B 1
d B 3
e C 1"""
self.env_counts = count_envs(self.env_str.splitlines())
self.node_index, self.nodes = index_tree(self.t)
self.count_array, self.unique_envs, self.env_to_index, \
self.node_to_index = index_envs(self.env_counts, self.node_index)
self.branch_lengths = get_branch_lengths(self.node_index)
self.old_t_str = '((org1:0.11,org2:0.22,(org3:0.12,org4:0.23)g:0.33)b:0.2,(org5:0.44,org6:0.55)c:0.3,org7:0.4)'
self.old_t = DndParser(self.old_t_str, UniFracTreeNode)
self.old_env_str = """
org1 env1 1
org1 env2 1
org2 env2 1
org3 env2 1
org4 env3 1
org5 env1 1
org6 env1 1
org7 env3 1
"""
self.old_env_counts = count_envs(self.old_env_str.splitlines())
self.old_node_index, self.old_nodes = index_tree(self.old_t)
self.old_count_array, self.old_unique_envs, self.old_env_to_index, \
self.old_node_to_index = index_envs(self.old_env_counts, self.old_node_index)
self.old_branch_lengths = get_branch_lengths(self.old_node_index)
def test_PD_generic_whole_tree(self):
"""PD_generic_whole_tree should correctly compute PD for test tree."""
self.t1 = DndParser('((a:1,b:2):4,(c:3,(d:1,e:1):2):3)', \
UniFracTreeNode)
self.env_str = """
a A 1
a C 2
b A 1
b B 1
c B 1
d B 3
e C 1"""
env_counts = count_envs(self.env_str.splitlines())
self.assertEqual(PD_generic_whole_tree(self.t1,self.env_counts), \
(['A','B','C'], array([7.,15.,11.])))
def test_count_envs(self):
"""count_envs should return correct counts from lines"""
envs = """
a A 3 some other junk
a B
a C 1
b A 2
skip
c B
d
b A 99
"""
result = count_envs(envs.splitlines())
self.assertEqual(result, {"a": {"A": 3, "B": 1, "C": 1}, "b": {"A": 99}, "c": {"B": 1}})
def test_PD_generic_whole_tree(self):
"""PD_generic_whole_tree should correctly compute PD for test tree."""
self.t1 = DndParser('((a:1,b:2):4,(c:3,(d:1,e:1):2):3)', \
UniFracTreeNode)
self.env_str = """
a A 1
a C 2
b A 1
b B 1
c B 1
d B 3
e C 1"""
env_counts = count_envs(self.env_str.splitlines())
self.assertEqual(PD_generic_whole_tree(self.t1,self.env_counts), \
(['A','B','C'], array([7.,15.,11.])))
def test_shared_branch_length_to_root(self):
"""Should return the correct shared branch length by env to root"""
t_str = "(((a:1,b:2):3,c:4),(d:5,e:6,f:7):8);"
envs = """
a A 1
b A 1
c A 1
d A 1
e A 1
f B 1
"""
env_counts = count_envs(envs.splitlines())
t = DndParser(t_str, UniFracTreeNode)
exp = {'A':29.0,'B':15.0}
obs = shared_branch_length_to_root(t, env_counts)
self.assertEqual(obs, exp)
def test_count_envs(self):
"""count_envs should return correct counts from lines"""
envs = """
a A 3 some other junk
a B
a C 1
b A 2
skip
c B
d
b A 99
"""
result = count_envs(envs.splitlines())
self.assertEqual(result, \
{'a':{'A':3,'B':1,'C':1},'b':{'A':99},'c':{'B':1}})
def test_sum_env_dict(self):
"""sum_env_dict should return correct counts from env_dict"""
envs = """
a A 3 some other junk
a B
a C 1
b A 2
skip
c B
d
b A 99
"""
result = count_envs(envs.splitlines())
sum_ = sum_env_dict(result)
self.assertEqual(sum_, 105)
def test_count_envs(self):
"""count_envs should return correct counts from lines"""
envs = """
a A 3 some other junk
a B
a C 1
b A 2
skip
c B
d
b A 99
"""
result = count_envs(envs.splitlines())
self.assertEqual(result, \
{'a':{'A':3,'B':1,'C':1},'b':{'A':99},'c':{'B':1}})
def test_sum_env_dict(self):
"""sum_env_dict should return correct counts from env_dict"""
envs = """
a A 3 some other junk
a B
a C 1
b A 2
skip
c B
d
b A 99
"""
result = count_envs(envs.splitlines())
sum_ = sum_env_dict(result)
self.assertEqual(sum_, 105)
def test_shared_branch_length_to_root(self):
"""Should return the correct shared branch length by env to root"""
t_str = "(((a:1,b:2):3,c:4),(d:5,e:6,f:7):8);"
envs = """
a A 1
b A 1
c A 1
d A 1
e A 1
f B 1
"""
env_counts = count_envs(envs.splitlines())
t = DndParser(t_str, UniFracTreeNode)
exp = {'A': 29.0, 'B': 15.0}
obs = shared_branch_length_to_root(t, env_counts)
self.assertEqual(obs, exp)
def test_PD_whole_tree(self):
"""PD_whole_tree should correctly compute PD for test tree.
environment M contains only tips not in tree, tip j is in no envs
"""
t1 = DndParser('((a:1,b:2):4,((c:3, j:17),(d:1,e:1):2):3)', \
UniFracTreeNode)
env_str = """
a A 1
a C 2
b A 1
b B 1
c B 1
d B 3
e C 1
m M 88"""
env_counts = count_envs(env_str.splitlines())
self.assertEqual(PD_whole_tree(t1,env_counts), \
(['A','B','C'], array([7.,15.,11.])))
def test_PD_whole_tree(self):
"""PD_whole_tree should correctly compute PD for test tree.
environment M contains only tips not in tree, tip j is in no envs
"""
t1 = DndParser('((a:1,b:2):4,((c:3, j:17),(d:1,e:1):2):3)', \
UniFracTreeNode)
env_str = """
a A 1
a C 2
b A 1
b B 1
c B 1
d B 3
e C 1
m M 88"""
env_counts = count_envs(env_str.splitlines())
self.assertEqual(PD_whole_tree(t1,env_counts), \
(['A','B','C'], array([7.,15.,11.])))
def test_unifrac_explicit(self):
"""unifrac should correctly compute correct values.
environment M contains only tips not in tree, tip j is in no envs
values were calculated by hand
"""
t1 = DndParser('((a:1,b:2):4,((c:3, j:17),(d:1,e:1):2):3)', \
UniFracTreeNode) # note c,j is len 0 node
# /-------- /-a
# ---------| \-b
# | /-------- /-c
# \--------| \-j
# \-------- /-d
# \-e
env_str = """
a A 1
a C 2
b A 1
b B 1
c B 1
d B 3
e C 1
m M 88"""
env_counts = count_envs(env_str.splitlines())
self.assertFloatEqual(fast_unifrac(t1,env_counts)['distance_matrix'], \
(array(
[[0,10/16, 8/13],
[10/16,0,8/17],
[8/13,8/17,0]]),['A','B','C']))
# changing tree topology relative to c,j tips shouldn't change
# anything
t2 = DndParser('((a:1,b:2):4,((c:2, j:16):1,(d:1,e:1):2):3)', \
UniFracTreeNode)
self.assertFloatEqual(fast_unifrac(t2,env_counts)['distance_matrix'], \
(array(
[[0,10/16, 8/13],
[10/16,0,8/17],
[8/13,8/17,0]]),['A','B','C']))
def test_unifrac_explicit(self):
"""unifrac should correctly compute correct values.
environment M contains only tips not in tree, tip j is in no envs
values were calculated by hand
"""
t1 = DndParser('((a:1,b:2):4,((c:3, j:17),(d:1,e:1):2):3)', \
UniFracTreeNode) # note c,j is len 0 node
# /-------- /-a
# ---------| \-b
# | /-------- /-c
# \--------| \-j
# \-------- /-d
# \-e
env_str = """
a A 1
a C 2
b A 1
b B 1
c B 1
d B 3
e C 1
m M 88"""
env_counts = count_envs(env_str.splitlines())
self.assertFloatEqual(fast_unifrac(t1,env_counts)['distance_matrix'], \
(array(
[[0,10/16, 8/13],
[10/16,0,8/17],
[8/13,8/17,0]]),['A','B','C']))
# changing tree topology relative to c,j tips shouldn't change
# anything
t2 = DndParser('((a:1,b:2):4,((c:2, j:16):1,(d:1,e:1):2):3)', \
UniFracTreeNode)
self.assertFloatEqual(fast_unifrac(t2,env_counts)['distance_matrix'], \
(array(
[[0,10/16, 8/13],
[10/16,0,8/17],
[8/13,8/17,0]]),['A','B','C']))
def test_shared_branch_length(self):
"""Should return the correct shared branch length by env"""
t_str = "(((a:1,b:2):3,c:4),(d:5,e:6,f:7):8);"
envs = """
a A 1
b A 1
c A 1
d A 1
e A 1
f B 1
"""
env_counts = count_envs(envs.splitlines())
t = DndParser(t_str, UniFracTreeNode)
exp = {('A', ): 21.0, ('B', ): 7.0}
obs = shared_branch_length(t, env_counts, 1)
self.assertEqual(obs, exp)
exp = {('A', 'B'): 8.0}
obs = shared_branch_length(t, env_counts, 2)
self.assertEqual(obs, exp)
self.assertRaises(ValueError, shared_branch_length, t, env_counts, 3)
def test_shared_branch_length(self):
"""Should return the correct shared branch length by env"""
t_str = "(((a:1,b:2):3,c:4),(d:5,e:6,f:7):8);"
envs = """
a A 1
b A 1
c A 1
d A 1
e A 1
f B 1
"""
env_counts = count_envs(envs.splitlines())
t = DndParser(t_str, UniFracTreeNode)
exp = {('A',):21.0,('B',):7.0}
obs = shared_branch_length(t, env_counts, 1)
self.assertEqual(obs, exp)
exp = {('A','B'):8.0}
obs = shared_branch_length(t, env_counts, 2)
self.assertEqual(obs, exp)
self.assertRaises(ValueError, shared_branch_length, t, env_counts, 3)
def setUp(self):
"""Define some standard trees."""
self.t_str = '((a:1,b:2):4,(c:3,(d:1,e:1):2):3)'
self.t = DndParser(self.t_str, UniFracTreeNode)
self.env_str = """
a A 1
a C 2
b A 1
b B 1
c B 1
d B 3
e C 1"""
self.env_counts = count_envs(self.env_str.splitlines())
self.missing_env_str = """
a A 1
a C 2
e C 1"""
self.missing_env_counts = count_envs(self.missing_env_str.splitlines())
self.extra_tip_str = """
q A 1
w C 2
e A 1
r B 1
t B 1
y B 3
u C 1"""
self.extra_tip_counts = count_envs(self.extra_tip_str.splitlines())
self.wrong_tip_str = """
q A 1
w C 2
r B 1
t B 1
y B 3
u C 1"""
self.wrong_tip_counts = count_envs(self.wrong_tip_str.splitlines())
self.t2_str = '(((a:1,b:1):1,c:5):2,d:4)'
self.t2 = DndParser(self.t2_str, UniFracTreeNode)
self.env2_str = """
a B 1
b A 1
c A 2
c C 2
d B 1
d C 1"""
self.env2_counts = count_envs(self.env2_str.splitlines())
self.trees = [self.t, self.t2]
self.envs = [self.env_counts, self.env2_counts]
self.mc_1 = array([.5, .4, .3, .2, .1, .6, .7, .8, .9, 1.0])
# from old EnvsNode tests
self.old_t_str = '((org1:0.11,org2:0.22,(org3:0.12,org4:0.23)g:0.33)b:0.2,(org5:0.44,org6:0.55)c:0.3,org7:0.4)'
self.old_t = DndParser(self.old_t_str, UniFracTreeNode)
self.old_env_str = """
org1 env1 1
org1 env2 1
org2 env2 1
org3 env2 1
org4 env3 1
org5 env1 1
org6 env1 1
org7 env3 1
"""
self.old_env_counts = count_envs(self.old_env_str.splitlines())
self.old_node_index, self.old_nodes = index_tree(self.old_t)
self.old_count_array, self.old_unique_envs, self.old_env_to_index, \
self.old_node_to_index = index_envs(self.old_env_counts, self.old_node_index)
self.old_branch_lengths = get_branch_lengths(self.old_node_index)
def test_unifrac_make_subtree(self):
"""unifrac result should not depend on make_subtree
environment M contains only tips not in tree, tip j, k is in no envs
one clade is missing entirely
values were calculated by hand
we also test that we still have a valid tree at the end
"""
t1 = DndParser('((a:1,b:2):4,((c:3, (j:1,k:2)mt:17),(d:1,e:1):2):3)',\
UniFracTreeNode) # note c,j is len 0 node
# /-------- /-a
# ---------| \-b
# | /-------- /-c
# \--------| \mt------ /-j
# | \-k
# \-------- /-d
# \-e
#
env_str = """
a A 1
a C 2
b A 1
b B 1
c B 1
d B 3
e C 1
m M 88"""
env_counts = count_envs(env_str.splitlines())
self.assertFloatEqual(fast_unifrac(t1,env_counts,make_subtree=False)['distance_matrix'], \
(array(
[[0,10/16, 8/13],
[10/16,0,8/17],
[8/13,8/17,0]]),['A','B','C']))
self.assertFloatEqual(fast_unifrac(t1,env_counts,make_subtree=True)['distance_matrix'], \
(array(
[[0,10/16, 8/13],
[10/16,0,8/17],
[8/13,8/17,0]]),['A','B','C']))
# changing tree topology relative to c,j tips shouldn't change anything
t2 = DndParser('((a:1,b:2):4,((c:2, (j:1,k:2)mt:17):1,(d:1,e:1):2):3)', \
UniFracTreeNode)
self.assertFloatEqual(fast_unifrac(t2,env_counts,make_subtree=False)['distance_matrix'], \
(array(
[[0,10/16, 8/13],
[10/16,0,8/17],
[8/13,8/17,0]]),['A','B','C']))
self.assertFloatEqual(fast_unifrac(t2,env_counts,make_subtree=True)['distance_matrix'], \
(array(
[[0,10/16, 8/13],
[10/16,0,8/17],
[8/13,8/17,0]]),['A','B','C']))
# ensure we haven't meaningfully changed the tree
# by passing it to unifrac
t3 = DndParser('((a:1,b:2):4,((c:3, (j:1,k:2)mt:17),(d:1,e:1):2):3)',\
UniFracTreeNode) # note c,j is len 0 node
t1_tips = [tip.Name for tip in t1.tips()]
t1_tips.sort()
t3_tips = [tip.Name for tip in t3.tips()]
t3_tips.sort()
self.assertEqual(t1_tips, t3_tips)
tipj3 = t3.getNodeMatchingName('j')
tipb3 = t3.getNodeMatchingName('b')
tipj1 = t1.getNodeMatchingName('j')
tipb1 = t1.getNodeMatchingName('b')
self.assertFloatEqual(tipj1.distance(tipb1), tipj3.distance(tipb3))
def setUp(self):
"""Define some standard trees."""
self.t_str = '((a:1,b:2):4,(c:3,(d:1,e:1):2):3)'
self.t = DndParser(self.t_str, UniFracTreeNode)
self.env_str = """
a A 1
a C 2
b A 1
b B 1
c B 1
d B 3
e C 1"""
self.env_counts = count_envs(self.env_str.splitlines())
self.missing_env_str = """
a A 1
a C 2
e C 1"""
self.missing_env_counts = count_envs(self.missing_env_str.splitlines())
self.extra_tip_str = """
q A 1
w C 2
e A 1
r B 1
t B 1
y B 3
u C 1"""
self.extra_tip_counts = count_envs(self.extra_tip_str.splitlines())
self.wrong_tip_str = """
q A 1
w C 2
r B 1
t B 1
y B 3
u C 1"""
self.wrong_tip_counts = count_envs(self.wrong_tip_str.splitlines())
self.t2_str = '(((a:1,b:1):1,c:5):2,d:4)'
self.t2 = DndParser(self.t2_str, UniFracTreeNode)
self.env2_str = """
a B 1
b A 1
c A 2
c C 2
d B 1
d C 1"""
self.env2_counts = count_envs(self.env2_str.splitlines())
self.trees = [self.t, self.t2]
self.envs = [self.env_counts, self.env2_counts]
self.mc_1 = array([.5, .4, .3, .2, .1, .6, .7, .8, .9, 1.0])
# from old EnvsNode tests
self.old_t_str = '((org1:0.11,org2:0.22,(org3:0.12,org4:0.23)g:0.33)b:0.2,(org5:0.44,org6:0.55)c:0.3,org7:0.4)'
self.old_t = DndParser(self.old_t_str, UniFracTreeNode)
self.old_env_str = """
org1 env1 1
org1 env2 1
org2 env2 1
org3 env2 1
org4 env3 1
org5 env1 1
org6 env1 1
org7 env3 1
"""
self.old_env_counts = count_envs(self.old_env_str.splitlines())
self.old_node_index, self.old_nodes = index_tree(self.old_t)
self.old_count_array, self.old_unique_envs, self.old_env_to_index, \
self.old_node_to_index = index_envs(self.old_env_counts, self.old_node_index)
self.old_branch_lengths = get_branch_lengths(self.old_node_index)
def test_unifrac_make_subtree(self):
"""unifrac result should not depend on make_subtree
environment M contains only tips not in tree, tip j, k is in no envs
one clade is missing entirely
values were calculated by hand
we also test that we still have a valid tree at the end
"""
t1 = DndParser('((a:1,b:2):4,((c:3, (j:1,k:2)mt:17),(d:1,e:1):2):3)',\
UniFracTreeNode) # note c,j is len 0 node
# /-------- /-a
# ---------| \-b
# | /-------- /-c
# \--------| \mt------ /-j
# | \-k
# \-------- /-d
# \-e
#
env_str = """
a A 1
a C 2
b A 1
b B 1
c B 1
d B 3
e C 1
m M 88"""
env_counts = count_envs(env_str.splitlines())
self.assertFloatEqual(fast_unifrac(t1,env_counts,make_subtree=False)['distance_matrix'], \
(array(
[[0,10/16, 8/13],
[10/16,0,8/17],
[8/13,8/17,0]]),['A','B','C']))
self.assertFloatEqual(fast_unifrac(t1,env_counts,make_subtree=True)['distance_matrix'], \
(array(
[[0,10/16, 8/13],
[10/16,0,8/17],
[8/13,8/17,0]]),['A','B','C']))
# changing tree topology relative to c,j tips shouldn't change anything
t2 = DndParser('((a:1,b:2):4,((c:2, (j:1,k:2)mt:17):1,(d:1,e:1):2):3)', \
UniFracTreeNode)
self.assertFloatEqual(fast_unifrac(t2,env_counts,make_subtree=False)['distance_matrix'], \
(array(
[[0,10/16, 8/13],
[10/16,0,8/17],
[8/13,8/17,0]]),['A','B','C']))
self.assertFloatEqual(fast_unifrac(t2,env_counts,make_subtree=True)['distance_matrix'], \
(array(
[[0,10/16, 8/13],
[10/16,0,8/17],
[8/13,8/17,0]]),['A','B','C']))
# ensure we haven't meaningfully changed the tree
# by passing it to unifrac
t3 = DndParser('((a:1,b:2):4,((c:3, (j:1,k:2)mt:17),(d:1,e:1):2):3)',\
UniFracTreeNode) # note c,j is len 0 node
t1_tips = [tip.Name for tip in t1.tips()]
t1_tips.sort()
t3_tips = [tip.Name for tip in t3.tips()]
t3_tips.sort()
self.assertEqual(t1_tips, t3_tips)
tipj3 = t3.getNodeMatchingName('j')
tipb3 = t3.getNodeMatchingName('b')
tipj1 = t1.getNodeMatchingName('j')
tipb1 = t1.getNodeMatchingName('b')
self.assertFloatEqual(tipj1.distance(tipb1), tipj3.distance(tipb3))
