def run_method(method, tree, m = 300, kappa = 2, mutation_rate=0.05, threshold = None, verbose = False):
start_time = time.time()
observations, taxa_meta = generation.simulate_sequences(m, tree_model=tree, seq_model=generation.HKY(kappa = kappa), mutation_rate=mutation_rate, alphabet="DNA")
runtime = time.time() - start_time
print("Simulation took %s seconds" % runtime)
if method == "RaXML":
raxml_HKY = reconstruct_tree.RAxML()
start_time = time.time()
tree_rec = raxml_HKY(observations, taxa_meta, raxml_args="-T 2 --HKY85 -c 1")
if method == "SNJ":
snj = reconstruct_tree.SpectralNeighborJoining(reconstruct_tree.HKY_similarity_matrix)
start_time = time.time()
tree_rec = snj(observations, taxa_meta)
if method == "NJ":
nj = reconstruct_tree.NeighborJoining(reconstruct_tree.HKY_similarity_matrix)
start_time = time.time()
tree_rec = nj(observations, taxa_meta)
if method == "STR+NJ":
spectral_method = reconstruct_tree.STDR(reconstruct_tree.NeighborJoining, reconstruct_tree.HKY_similarity_matrix)
start_time = time.time()
tree_rec = spectral_method.deep_spectral_tree_reconstruction(observations, reconstruct_tree.HKY_similarity_matrix,
taxa_metadata = taxa_meta,
threshhold = threshold, min_split = 5, verbose = verbose)
if method == "STR+SNJ":
spectral_method = reconstruct_tree.STDR(reconstruct_tree.SpectralNeighborJoining, reconstruct_tree.HKY_similarity_matrix)
start_time = time.time()
tree_rec = spectral_method.deep_spectral_tree_reconstruction(observations, reconstruct_tree.HKY_similarity_matrix,
taxa_metadata = taxa_meta,
threshhold = threshold, min_split = 5, verbose = verbose)
if method == "STR+RaXML":
spectral_method = reconstruct_tree.STDR(reconstruct_tree.RAxML, reconstruct_tree.HKY_similarity_matrix)
start_time = time.time()
tree_rec = spectral_method.deep_spectral_tree_reconstruction(observations, reconstruct_tree.HKY_similarity_matrix,
taxa_metadata = taxa_meta,
threshhold = threshold,
raxml_args = "-T 2 --HKY85 -c 1", min_split = 5, verbose = verbose)
runtime = time.time() - start_time
RF,F1 = reconstruct_tree.compare_trees(tree_rec, tree)
print(method)
if threshold is not None: print(threshold)
print("--- %s seconds ---" % runtime)
print("RF = ",RF)
print("F1% = ",F1)
return([method, str(threshold), runtime, RF, F1])
def run_method(method, tree, seqs, threshold=None):
ch_list = list()
taxons = [x.label for x in tree.taxon_namespace]
for t in taxons:
ch_list.append([x.symbol for x in seqs[t]])
ch_arr = np.array(ch_list)
ch_arr[ch_arr == "U"] = "T"
ch_dendro = dendropy.DnaCharacterMatrix()
ch_dendro.taxon_namespace = tree.taxon_namespace
for t, taxon in enumerate(taxons):
ch_dendro.new_sequence(tree.taxon_namespace[t], ch_arr[t, :].tolist())
if method == "RaXML":
raxml_HKY = reconstruct_tree.RAxML()
start_time = time.time()
tree_rec = raxml_HKY(ch_dendro, raxml_args="-T 2 --HKY85 -c 1")
if method == "SNJ":
snj = reconstruct_tree.SpectralNeighborJoining(
reconstruct_tree.HKY_similarity_matrix_missing_data)
start_time = time.time()
tree_rec = snj(ch_arr, tree.taxon_namespace)
if method == "NJ":
nj = reconstruct_tree.NeighborJoining(
reconstruct_tree.HKY_similarity_matrix_missing_data)
start_time = time.time()
tree_rec = nj(ch_arr, tree.taxon_namespace)
if method == "STR + NJ":
spectral_method = reconstruct_tree.SpectralTreeReconstruction(
reconstruct_tree.NeighborJoining,
reconstruct_tree.HKY_similarity_matrix_missing_data)
start_time = time.time()
tree_rec = spectral_method.deep_spectral_tree_reonstruction(
ch_arr,
reconstruct_tree.HKY_similarity_matrix_missing_data,
taxon_namespace=tree.taxon_namespace,
threshhold=threshold,
min_split=5)
if method == "STR + SNJ":
spectral_method = reconstruct_tree.SpectralTreeReconstruction(
reconstruct_tree.SpectralNeighborJoining,
reconstruct_tree.HKY_similarity_matrix_missing_data)
start_time = time.time()
tree_rec = spectral_method.deep_spectral_tree_reonstruction(
ch_arr,
reconstruct_tree.HKY_similarity_matrix_missing_data,
taxon_namespace=tree.taxon_namespace,
threshhold=threshold,
min_split=5)
if method == "STR + RaXML":
spectral_method = reconstruct_tree.SpectralTreeReconstruction(
reconstruct_tree.RAxML,
reconstruct_tree.HKY_similarity_matrix_missing_data)
start_time = time.time()
tree_rec = spectral_method.deep_spectral_tree_reonstruction(
ch_arr,
reconstruct_tree.HKY_similarity_matrix_missing_data,
taxon_namespace=tree.taxon_namespace,
threshhold=threshold,
raxml_args="-T 2 --HKY85 -c 1",
min_split=5)
runtime = time.time() - start_time
RF, F1 = reconstruct_tree.compare_trees(tree_rec, tree)
print(method)
if threshold is not None: print(threshold)
print("--- %s seconds ---" % runtime)
print("RF = ", RF)
print("F1% = ", F1)
return ([method, str(threshold), runtime, RF, F1])
def run_method(method, tree, threshold=None):
data_HKY = simulate_discrete_chars(1000,
tree,
Hky85(kappa=2),
mutation_rate=0.1)
ch_list = list()
for t in data_HKY.taxon_namespace:
ch_list.append([x.symbol for x in data_HKY[t]])
ch_arr = np.array(ch_list)
if method == "RaXML":
raxml_HKY = reconstruct_tree.RAxML()
start_time = time.time()
tree_rec = raxml_HKY(data_HKY, raxml_args="-T 2 --HKY85 -c 1")
if method == "SNJ":
snj = reconstruct_tree.SpectralNeighborJoining(
reconstruct_tree.HKY_similarity_matrix)
start_time = time.time()
tree_rec = snj(ch_arr, tree.taxon_namespace)
if method == "NJ":
nj = reconstruct_tree.NeighborJoining(
reconstruct_tree.HKY_similarity_matrix)
start_time = time.time()
tree_rec = nj(ch_arr, tree.taxon_namespace)
if method == "STR + NJ":
spectral_method = reconstruct_tree.SpectralTreeReconstruction(
reconstruct_tree.NeighborJoining,
reconstruct_tree.HKY_similarity_matrix)
start_time = time.time()
tree_rec = spectral_method.deep_spectral_tree_reonstruction(
ch_arr,
reconstruct_tree.HKY_similarity_matrix,
taxon_namespace=tree.taxon_namespace,
threshhold=threshold,
min_split=5)
if method == "STR + SNJ":
spectral_method = reconstruct_tree.SpectralTreeReconstruction(
reconstruct_tree.SpectralNeighborJoining,
reconstruct_tree.HKY_similarity_matrix)
start_time = time.time()
tree_rec = spectral_method.deep_spectral_tree_reonstruction(
ch_arr,
reconstruct_tree.HKY_similarity_matrix,
taxon_namespace=tree.taxon_namespace,
threshhold=threshold,
min_split=5)
if method == "STR + RaXML":
spectral_method = reconstruct_tree.SpectralTreeReconstruction(
reconstruct_tree.RAxML, reconstruct_tree.HKY_similarity_matrix)
start_time = time.time()
tree_rec = spectral_method.deep_spectral_tree_reonstruction(
ch_arr,
reconstruct_tree.HKY_similarity_matrix,
taxon_namespace=tree.taxon_namespace,
threshhold=threshold,
raxml_args="-T 2 --HKY85 -c 1",
min_split=5)
runtime = time.time() - start_time
RF, F1 = reconstruct_tree.compare_trees(tree_rec, tree)
print(method)
if threshold is not None: print(threshold)
print("--- %s seconds ---" % runtime)
print("RF = ", RF)
print("F1% = ", F1)
return ([method, str(threshold), runtime, RF, F1])
import generation
from dendropy.interop import raxml
from dendropy.model.discrete import simulate_discrete_chars, Jc69
from dendropy.calculate.treecompare import symmetric_difference
import pandas as pd
import numpy as np
#num_taxa = [128,256,512,1024,2048,4096]
num_taxa = np.arange(200, 2000, 200)
n_itr = 10
#num_taxa = [8,16,32]
N = 1000
jc = generation.Jukes_Cantor()
mutation_rate = jc.p2t(0.95)
nj = reconstruct_tree.NeighborJoining(reconstruct_tree.JC_similarity_matrix)
raxml = reconstruct_tree.RAxML()
#tree_list = [utils.balanced_binary(m) for m in num_taxa]
df = pd.DataFrame(columns=['method', 'runtime', 'RF', 'm'])
for m in num_taxa:
for n_itr in range(n_itr):
reference_tree = utils.unrooted_pure_kingman_tree(m)
observations, taxa_meta = generation.simulate_sequences(
N,
tree_model=reference_tree,
seq_model=jc,
mutation_rate=mutation_rate,
alphabet="DNA")
# NJ
time_s = time.time()