def test_iqtree_model_choice(self):
# Tip to tip dists should NOT be identical under different models.
# Default is MFP (auto select substitution model). We'll compare ouput
# of the GTR+G and HKY models.
# This test is comparing an ordered series of tip-to-tip distances.
# Take note, that for this comparison to work, all must have the same
# seed value set.
input_fp = self.get_data_path('aligned-dna-sequences-3.fasta')
input_sequences = AlignedDNAFASTAFormat(input_fp, mode='r')
# default GTR+G
with redirected_stdio(stderr=os.devnull):
gtrg = iqtree(input_sequences, seed=1723,
substitution_model='GTR+G')
gtrg_tree = skbio.TreeNode.read(
str(gtrg), convert_underscores=False)
gtrg_td = set(gtrg_tree.tip_tip_distances().to_series())
# set HKY
with redirected_stdio(stderr=os.devnull):
hky = iqtree(input_sequences, seed=1723,
substitution_model='HKY')
hky_tree = skbio.TreeNode.read(
str(hky), convert_underscores=False)
hky_td = set(hky_tree.tip_tip_distances().to_series())
# test pairs are not equivalent
self.assertNotEqual(gtrg_td, hky_td)
def test_iqtree_model_choice(self):
# Tip to tip dists should NOT be identical under different models.
# Default is MFP (auto select substitution model). We'll compare ouput
# of the GTR+G and HKY models.
# This test is comparing an ordered series of tip-to-tip distances.
# Take note, that for this comparison to work, all must have the same
# seed value set.
input_fp = self.get_data_path('aligned-dna-sequences-3.fasta')
input_sequences = AlignedDNAFASTAFormat(input_fp, mode='r')
# default GTR+G
with redirected_stdio(stderr=os.devnull):
gtrg = iqtree(input_sequences,
seed=1723,
substitution_model='GTR+G')
gtrg_tree = skbio.TreeNode.read(str(gtrg),
convert_underscores=False)
gtrg_td = set(gtrg_tree.tip_tip_distances().to_series())
# set HKY
with redirected_stdio(stderr=os.devnull):
hky = iqtree(input_sequences, seed=1723, substitution_model='HKY')
hky_tree = skbio.TreeNode.read(str(hky), convert_underscores=False)
hky_td = set(hky_tree.tip_tip_distances().to_series())
# test pairs are not equivalent
self.assertNotEqual(gtrg_td, hky_td)
def test_iqtree_safe_allnni(self):
# Same as `test_iqtree` but testing the `-safe` and `-allnni `flags
input_fp = self.get_data_path('aligned-dna-sequences-3.fasta')
input_sequences = AlignedDNAFASTAFormat(input_fp, mode='r')
with redirected_stdio(stderr=os.devnull):
obs = iqtree(input_sequences, safe='True', allnni='True')
obs_tree = skbio.TreeNode.read(str(obs))
tips = list(obs_tree.tips())
tip_names = [t.name for t in tips]
self.assertEqual(set(tip_names),
set(['GCA001510755', 'GCA001045515', 'GCA000454205',
'GCA000473545', 'GCA000196255', 'GCA000686145',
'GCA001950115', 'GCA001971985', 'GCA900007555']))
def test_iqtree_safe_allnni(self):
# Same as `test_iqtree` but testing the `-safe` and `-allnni `flags
input_fp = self.get_data_path('aligned-dna-sequences-3.fasta')
input_sequences = AlignedDNAFASTAFormat(input_fp, mode='r')
with redirected_stdio(stderr=os.devnull):
obs = iqtree(input_sequences, safe='True', allnni='True')
obs_tree = skbio.TreeNode.read(str(obs))
tips = list(obs_tree.tips())
tip_names = [t.name for t in tips]
self.assertEqual(set(tip_names),
set(['GCA001510755', 'GCA001045515', 'GCA000454205',
'GCA000473545', 'GCA000196255', 'GCA002142615',
'GCA000686145', 'GCA001950115', 'GCA001971985',
'GCA900007555']))
def test_iqtree(self):
# Test that output tree is made.
# Reads tree output and compares tip labels to expected labels.
input_fp = self.get_data_path('aligned-dna-sequences-3.fasta')
input_sequences = AlignedDNAFASTAFormat(input_fp, mode='r')
with redirected_stdio(stderr=os.devnull):
obs = iqtree(input_sequences)
obs_tree = skbio.TreeNode.read(str(obs))
# load the resulting tree and test that it has the right number of
# tips and the right tip ids
tips = list(obs_tree.tips())
tip_names = [t.name for t in tips]
self.assertEqual(set(tip_names),
set(['GCA001510755', 'GCA001045515', 'GCA000454205',
'GCA000473545', 'GCA000196255', 'GCA000686145',
'GCA001950115', 'GCA001971985', 'GCA900007555']))
def test_iqtree(self):
# Test that output tree is made.
# Reads tree output and compares tip labels to expected labels.
input_fp = self.get_data_path('aligned-dna-sequences-3.fasta')
input_sequences = AlignedDNAFASTAFormat(input_fp, mode='r')
with redirected_stdio(stderr=os.devnull):
obs = iqtree(input_sequences)
obs_tree = skbio.TreeNode.read(str(obs))
# load the resulting tree and test that it has the right number of
# tips and the right tip ids
tips = list(obs_tree.tips())
tip_names = [t.name for t in tips]
self.assertEqual(set(tip_names),
set(['GCA001510755', 'GCA001045515', 'GCA000454205',
'GCA000473545', 'GCA000196255', 'GCA002142615',
'GCA000686145', 'GCA001950115', 'GCA001971985',
'GCA900007555']))
def test_iqtree_n_cores_auto(self):
# Test that an output tree is made when invoking automatic threads.
input_fp = self.get_data_path('aligned-dna-sequences-3.fasta')
input_sequences = AlignedDNAFASTAFormat(input_fp, mode='r')
with redirected_stdio(stderr=os.devnull):
obs = iqtree(input_sequences, n_cores='auto')
obs_tree = skbio.TreeNode.read(str(obs), convert_underscores=False)
# load the resulting tree and test that it has the right number of
# tips and the right tip ids
tips = list(obs_tree.tips())
tip_names = [t.name for t in tips]
self.assertEqual(set(tip_names),
set(['GCA001510755', 'GCA001045515', 'GCA000454205',
'GCA000473545', 'GCA000196255', 'GCA000686145',
'GCA001950115', 'GCA001971985', 'GCA900007555']))
def test_iqtree_underscore_ids(self):
# Test that output tree is made with underscores in tip IDs.
# Some programs and python wrappers may strip underscores.
# Reads tree output and compares tip labels to expected labels.
input_fp = self.get_data_path('aligned-dna-sequences-4.fasta')
input_sequences = AlignedDNAFASTAFormat(input_fp, mode='r')
with redirected_stdio(stderr=os.devnull):
obs = iqtree(input_sequences)
obs_tree = skbio.TreeNode.read(str(obs), convert_underscores=False)
# load the resulting tree and test that it has the right number of
# tips and the right tip ids
tips = list(obs_tree.tips())
tip_names = [t.name for t in tips]
self.assertEqual(set(tip_names),
set(['GCA_001510755_1', 'GCA_001045515_1',
'GCA_000454205_1', 'GCA_000473545_1',
'GCA_000196255_1', 'GCA_002142615_1',
'GCA_000686145_1', 'GCA_001950115_1',
'GCA_001971985_1', 'GCA_900007555_1']))
def test_iqtree_underscore_ids(self):
# Test that output tree is made with underscores in tip IDs.
# Some programs and python wrappers may strip underscores.
# Reads tree output and compares tip labels to expected labels.
input_fp = self.get_data_path('aligned-dna-sequences-4.fasta')
input_sequences = AlignedDNAFASTAFormat(input_fp, mode='r')
with redirected_stdio(stderr=os.devnull):
obs = iqtree(input_sequences)
obs_tree = skbio.TreeNode.read(str(obs), convert_underscores=False)
# load the resulting tree and test that it has the right number of
# tips and the right tip ids
tips = list(obs_tree.tips())
tip_names = [t.name for t in tips]
self.assertEqual(set(tip_names),
set(['GCA_001510755_1', 'GCA_001045515_1',
'GCA_000454205_1', 'GCA_000473545_1',
'GCA_000196255_1', 'GCA_002142615_1',
'GCA_000686145_1', 'GCA_001950115_1',
'GCA_001971985_1', 'GCA_900007555_1']))
def test_iqtree_with_seed(self):
# Test tip-to-tip dists are identical to manually run IQ-TREE output.
# This test is comparing an ordered series of tip-to-tip distances
# to a tree output from a manual run of the default command:
# iqtree -seed 1723 -m HKY -s aligned-dna-sequences-3.fasta
# -nt 1 -pre q2iqtree
# NOTE: I cleanly rounded the tip-to-tip dists (i.e. `%.4f`) as
# IQ-TREE may return slightly different rounding errors on different
# systems.
input_fp = self.get_data_path('aligned-dna-sequences-3.fasta')
input_sequences = AlignedDNAFASTAFormat(input_fp, mode='r')
with redirected_stdio(stderr=os.devnull):
obs = iqtree(input_sequences, seed=1723, substitution_model='HKY')
obs_tree = skbio.TreeNode.read(str(obs), convert_underscores=False)
obs_tl = list(obs_tree.tip_tip_distances().to_series())
obs_series = set(['%.4f' % e for e in obs_tl])
exp_tree = skbio.TreeNode.read(self.get_data_path('test4.tre'))
exp_tl = list(exp_tree.tip_tip_distances().to_series())
exp_series = set(['%.4f' % e for e in exp_tl])
self.assertEqual(obs_series, exp_series)
def test_iqtree_with_seed(self):
# Test tip-to-tip dists are identical to manually run IQ-TREE output.
# This test is comparing an ordered series of tip-to-tip distances
# to a tree output from a manual run of the default command:
# iqtree -seed 1723 -m HKY -s aligned-dna-sequences-3.fasta
# -nt 1 -pre q2iqtree
# NOTE: I cleanly rounded the tip-to-tip dists (i.e. `%.4f`) as
# IQ-TREE may return slightly different rounding errors on different
# systems.
input_fp = self.get_data_path('aligned-dna-sequences-3.fasta')
input_sequences = AlignedDNAFASTAFormat(input_fp, mode='r')
with redirected_stdio(stderr=os.devnull):
obs = iqtree(input_sequences, seed=1723,
substitution_model='HKY')
obs_tree = skbio.TreeNode.read(str(obs), convert_underscores=False)
obs_tl = list(obs_tree.tip_tip_distances().to_series())
obs_series = set(['%.4f' % e for e in obs_tl])
exp_tree = skbio.TreeNode.read(self.get_data_path('test4.tre'))
exp_tl = list(exp_tree.tip_tip_distances().to_series())
exp_series = set(['%.4f' % e for e in exp_tl])
self.assertEqual(obs_series, exp_series)
