def setUp(self):
self.namespace1 = dendropy.TaxonNamespace(
["dog", "cat", "snake", "fish", "tree"])
self.taxa1 = spectraltree.TaxaMetadata(self.namespace1,
["fish", "snake", "cat", "dog"],
"DNA")
self.dog = self.namespace1.get_taxon("dog")
self.snake = self.namespace1.get_taxon("snake")
self.array1 = np.array([
[3, 1, 1, 0, 0],
[3, 2, 1, 0, 0],
[3, 2, 4, 0, 0],
[2, 2, 0, 0, 0],
])
self.tax2seq = {
"fish": self.array1[0, :],
"snake": self.array1[1, :],
"cat": self.array1[2, :],
"dog": self.array1[3, :],
}
d = {
"fish": "TCCAA",
"snake": "TGCAA",
"cat": "TG-AA",
"dog": "GGAAA",
}
self.dna_charmatrix = dendropy.DnaCharacterMatrix.from_dict(
d, taxon_namespace=self.namespace1)
self.tree = spectraltree.lopsided_tree(4, self.taxa1)
self.dm = self.tree.phylogenetic_distance_matrix()
def part12_cat(num_taxa_s_cat, Ns_cat):
##### Part 1: NJ vs SNJ
print("Starting Part 12")
snj = spectraltree.SpectralNeighborJoining(spectraltree.JC_similarity_matrix)
nj = spectraltree.NeighborJoining(spectraltree.JC_similarity_matrix)
methods = [snj, nj]
## Part 1.2: different Taxa
cat_trees = [spectraltree.lopsided_tree(num_taxa) for num_taxa in num_taxa_s_cat]
res_cat12 = compare_methods.experiment(tree_list = cat_trees, sequence_model = sequence_model, Ns = Ns_cat, methods = methods,
mutation_rates=mutation_rates, reps_per_tree=5, verbose=True)
return res_cat12
def part11_cat(num_taxa, Ns_cat):
##### Part 1: NJ vs SNJ
print("Starting Part 11")
snj = spectraltree.SpectralNeighborJoining(spectraltree.JC_similarity_matrix)
nj = spectraltree.NeighborJoining(spectraltree.JC_similarity_matrix)
methods = [snj, nj]
## Part 1.1: different N
#alphabet = "Binary"
cat_tree = spectraltree.lopsided_tree(num_taxa)
res_cat11 = compare_methods.experiment(tree_list = [cat_tree], sequence_model =sequence_model, Ns = Ns_cat,
methods = methods, mutation_rates=mutation_rates, reps_per_tree=5, verbose=True,
savepath = '20200821_res12_cat_SNJPAPER',folder = './experiments/snj_paper_experiments/results/')
return res_cat11
def part22_cat(num_taxa_s_cat, Ns_cat):
## Part 2.2: different Taxa
print("Starting Part 22 for caterpillar trees")
snj = spectraltree.SpectralNeighborJoining(spectraltree.JC_similarity_matrix)
nj = spectraltree.NeighborJoining(spectraltree.JC_similarity_matrix)
rg = spectraltree.RG(spectraltree.JC_distance_matrix)
clrg = spectraltree.CLRG()
methods = [snj, nj,rg]
alphabet = "Binary"
cat_trees = [spectraltree.lopsided_tree(num_taxa) for num_taxa in num_taxa_s_cat]
res_cat22 = compare_methods.experiment(tree_list = cat_trees, sequence_model = sequence_model, Ns = Ns_cat, methods = methods, mutation_rates=mutation_rates, reps_per_tree=5, alphabet=alphabet , verbose=True)
return res_cat22
def part21_cat(num_taxa_cat, Ns_cat):
##### Part 2: NJ vs SNJ vs RG vs CLRG
print("Starting Part 21 for caterpillar tree")
snj = spectraltree.SpectralNeighborJoining(spectraltree.JC_similarity_matrix)
nj = spectraltree.NeighborJoining(spectraltree.JC_similarity_matrix)
rg = spectraltree.RG(spectraltree.JC_distance_matrix)
#clrg = spectraltree.CLRG()
methods = [snj, nj,rg]
alphabet = "DNA"
## Part 2.1: different N
cat_tree = spectraltree.lopsided_tree(num_taxa_cat)
res_cat21 = compare_methods.experiment(tree_list = [cat_tree], sequence_model = sequence_model, Ns = Ns_cat, methods = methods, mutation_rates=mutation_rates, reps_per_tree=5, alphabet=alphabet, verbose=True)
return res_cat21
def part31_cat(num_taxa_cat, Ns_cat):
##### Part 3: NJ vs SNJ vs RG vs CLRG vs Forrest vs Tree_SVD
print("Starting Part 31")
snj = spectraltree.SpectralNeighborJoining(spectraltree.JC_similarity_matrix)
nj = spectraltree.NeighborJoining(spectraltree.JC_similarity_matrix)
#rg = spectraltree.RG(spectraltree.JC_distance_matrix)
#clrg = spectraltree.CLRG()
forrest = spectraltree.Forrest()
tree_svd = spectraltree.TreeSVD()
#methods = [snj, nj,rg,clrg, forrest,tree_svd]
methods = [snj, nj, forrest,tree_svd]
alphabet = "Binary"
## Part 3.1: different N
cat_tree = spectraltree.lopsided_tree(num_taxa_cat)
res_cat31 = compare_methods.experiment(tree_list = [cat_tree], sequence_model = sequence_model2, Ns = Ns_cat, methods = methods, mutation_rates=mutation_rates2, reps_per_tree=5, alphabet=alphabet, verbose=True)
return res_cat31
def test_angle_least_square(self):
# copied from test_deep_spectral_tree_reonstruction
N = 1000
jc = spectraltree.Jukes_Cantor()
mutation_rate = jc.p2t(0.95)
num_itr = 2 #0
#reference_tree = spectraltree.balanced_binary(num_taxa)
lopsided_reference_tree = spectraltree.lopsided_tree(128)
# reference_tree = spectraltree.unrooted_birth_death_tree(num_taxa, birth_rate=1)
# for x in reference_tree.preorder_edge_iter():
# x.length = 1
merging_method_list = ['least_square', 'angle']
RF = {'least_square': [], 'angle': []}
F1 = {'least_square': [], 'angle': []}
for merge_method in merging_method_list:
for i in range(num_itr):
observations, taxa_meta = spectraltree.simulate_sequences(
seq_len=N,
tree_model=lopsided_reference_tree,
seq_model=jc,
mutation_rate=mutation_rate,
rng=np.random.default_rng(789))
spectral_method = spectraltree.STDR(
spectraltree.NeighborJoining,
spectraltree.JC_similarity_matrix)
tree_rec = spectral_method.deep_spectral_tree_reconstruction(
observations,
spectraltree.JC_similarity_matrix,
taxa_metadata=taxa_meta,
threshhold=16,
merge_method=merge_method)
RF_i, F1_i = spectraltree.compare_trees(
tree_rec, lopsided_reference_tree)
RF[merge_method].append(RF_i)
F1[merge_method].append(F1_i)
self.assertEqual(np.mean(RF['angle']), 0)
self.assertEqual(np.mean(RF['least_square']), 0)
import metricNearness
N = 100
num_taxa = 60
#################################
## Tree generation
#################################
print("Creating tree")
jc = spectraltree.Jukes_Cantor()
hky = spectraltree.HKY(kappa=2)
mutation_rate = [jc.p2t(0.95)]
# mutation_rate = [0.1]
#reference_tree = spectraltree.unrooted_birth_death_tree(num_taxa, birth_rate=0.5)
reference_tree = spectraltree.lopsided_tree(num_taxa)
# reference_tree = spectraltree.balanced_binary(num_taxa)
# for x in reference_tree.preorder_edge_iter():
# x.length = 0.5
print("Genration observations by JC and HKY")
observationsJC, metaJC = spectraltree.simulate_sequences(
N,
tree_model=reference_tree,
seq_model=jc,
mutation_rate=mutation_rate,
alphabet="DNA")
#################################
## SNJ - Jukes_Cantor
#################################
def setUp(self):
self.reference_tree = spectraltree.lopsided_tree(32)