def setUp(self):
# library(ape)
# tree = read.nexus("data/pythonidae.mle.nex")
# pdm = cophenetic.phylo(tree)
# write.csv(format(pdm,digits=22), "pythonidae.mle.weighted.pdm.csv")
with open(pathmap.other_source_path("pythonidae.mle.weighted.pdm.csv")) as src:
self.reference_pdm_weighted_table = container.DataTable.from_csv(src, default_data_type=float, delimiter=",")
with open(pathmap.other_source_path("pythonidae.mle.unweighted.pdm.csv")) as src:
self.reference_pdm_unweighted_table = container.DataTable.from_csv(src, default_data_type=float, delimiter=",")
self.tree = dendropy.Tree.get(path=pathmap.tree_source_path(
"pythonidae.mle.nex"),
schema="nexus",
preserve_underscores=True)
self.pdm = self.tree.phylogenetic_distance_matrix()
def test_distances(self):
## get distances from ape
# library(ape)
# tr = read.nexus("pythonidae.mle.nex")
# tr$node.label <- (Ntip(tr)+1):(nrow(tr$edge)+1)
# tr$tip.label <- (1:Ntip(tr))
# write.tree(tr)
# d = dist.nodes(tr)
# write.csv(d, "file.csv")
test_runs = [
("hiv1.newick", True, "hiv1.node-to-node-dists.csv"),
("pythonidae.mle.numbered-nodes.newick", True, "pythonidae.mle.node-to-node-dists.csv"),
("hiv1.newick", False, "hiv1.unweighted.node-to-node-dists.csv"),
("pythonidae.mle.numbered-nodes.newick", False, "pythonidae.mle.unweighted.node-to-node-dists.csv"),
]
for tree_filename, is_weighted, distances_filename in test_runs:
tree = dendropy.Tree.get_from_path(
src=pathmap.tree_source_path(tree_filename), schema="newick", suppress_leaf_node_taxa=True
)
ndm = tree.node_distance_matrix()
reference_table = container.DataTable.from_csv(
src=open(pathmap.other_source_path(distances_filename)), default_data_type=float, delimiter=","
)
for nd1 in tree.postorder_node_iter():
for nd2 in tree.postorder_node_iter():
d = ndm.distance(nd1, nd2, is_weighted_edge_distances=is_weighted)
e = reference_table[nd1.label, nd2.label]
self.assertAlmostEqual(d, e)
def test_upgma_average_from_distance_matrices(self):
# library(phangorn)
# d = read.csv("wpupgmaex.csv", header=T, row.names=1)
# upgma(d)
test_runs = [
("wpupgmaex.csv", "((e:11,(a:8.5,b:8.5):2.5):5.5,(c:14,d:14):2.5);"),
(
"pythonidae.mle.weighted.pdm.csv",
"(Candoia_aspera:0.3358679339,(Loxocemus_bicolor:0.239139024,(Xenopeltis_unicolor:0.2306593655,((Python_regius:0.1021235458,(Python_curtus:0.0883212354,(Python_sebae:0.0482829776,Python_molurus:0.0482829776):0.0400382578):0.01380231042):0.04278465647,((Python_timoriensis:0.06537053625,Python_reticulatus:0.06537053625):0.06029549731,(((Liasis_albertisii:0.0590368856,Bothrochilus_boa:0.0590368856):0.03300696511,(Morelia_boeleni:0.08681248898,((Antaresia_melanocephalus:0.03530849105,Antaresia_ramsayi:0.03530849105):0.04351804164,((Liasis_fuscus:0.0168409813,Liasis_mackloti:0.0168409813):0.04845559302,(Apodora_papuana:0.05507916735,Liasis_olivaceus:0.05507916735):0.01021740697):0.01352995836):0.007985956296):0.005231361731):0.005812651357,(((Morelia_tracyae:0.0359450459,(Morelia_amethistina:0.02553168923,(Morelia_clastolepis:0.0084128718,(Morelia_kinghorni:0.0080990783,Morelia_nauta:0.0080990783):0.0003137935):0.01711881743):0.01041335667):0.02235606786,(Morelia_oenpelliensis:0.05722136872,(Morelia_bredli:0.02582922315,Morelia_spilota:0.02582922315):0.03139214558):0.001079745035):0.03700402529,((Morelia_carinata:0.06795956147,(Morelia_viridisN:0.04255445115,Morelia_viridisS:0.04255445115):0.02540511032):0.01460551598,(Antaresia_maculosa:0.07026059995,(Antaresia_perthensis:0.06383429933,(Antaresia_stimsoni:0.01919038275,Antaresia_childreni:0.01919038275):0.04464391658):0.006426300625):0.0123044775):0.01274006159):0.002551363025):0.02780953149):0.01924216872):0.08575116319):0.008479658536):0.09672890989);",
),
(
"laurasiatherian.distances.ml.csv",
"(Platypus:0.115554082,((Opposum:0.04554785647,(Bandicoot:0.03760589713,(Wallaroo:0.02994721074,Possum:0.02994721074):0.00765868639):0.007941959338):0.05561264108,(Elephant:0.09767314505,(Tenrec:0.09197201988,(Hedghog:0.08893681608,((Cebus:0.07429923126,(Baboon:0.06398456889,Human:0.06398456889):0.01031466238):0.01347573751,((Mouse:0.04952979734,Vole:0.04952979734):0.03752885067,(Gymnure:0.08423117145,((GuineaPig:0.0740040685,CaneRat:0.0740040685):0.009033085883,(Armadillo:0.0815558576,((Squirrel:0.0719024199,Dormouse:0.0719024199):0.006011912967,(Loris:0.07535539083,((Rabbit:0.06082665549,Pika:0.06082665549):0.01312116941,(LongTBat:0.07253285264,(Aardvark:0.07207716472,(FruitBat:0.06375844723,((((FurSeal:0.03311262951,(HarbSeal:0.004907721762,GraySeal:0.004907721762):0.02820490774):0.01108478546,(Cat:0.04153849221,Dog:0.04153849221):0.002658922751):0.01112227127,((Mole:0.04702531576,Shrew:0.04702531576):0.006612877503,((Rbat:0.0483680062,(FlyingFox:0.01426606479,RyFlyFox:0.01426606479):0.03410194142):0.002903547772,(Pig:0.04899261297,((Horse:0.009073986173,Donkey:0.009073986173):0.02905609806,(WhiteRhino:0.02269245743,IndianRhin:0.02269245743):0.0154376268):0.01086252874):0.002278941003):0.002366639287):0.001681492971):0.004794138467,(Alpaca:0.05736084145,(Hippo:0.05532140845,((Cow:0.02807794212,Sheep:0.02807794212):0.02602799145,(SpermWhale:0.03397215079,(FinWhale:0.01328705847,BlueWhale:0.01328705847):0.02068509233):0.02013378278):0.001215474875):0.002039433007):0.002752983249):0.003644622527):0.008318717494):0.0004556879157):0.001414972262):0.001407565924):0.00255894204):0.003641524737):0.001481296783):0.001194017065):0.002827476566):0.0007163207591):0.001161847302):0.003035203803):0.005701125173):0.0034873525):0.01439358448);",
),
## note:following fails, probably due to different arbitrary resolutions of equal distances
# ("pythonidae.mle.unweighted.pdm.csv", "((((Morelia_carinata:1.5,(Morelia_viridisN:1,Morelia_viridisS:1):0.5):1.458333333,((Antaresia_stimsoni:1,Antaresia_childreni:1):0.75,(Antaresia_maculosa:1.5,Antaresia_perthensis:1.5):0.25):1.208333333):1.416666667,((Morelia_bredli:1,Morelia_spilota:1):2.166666667,((Morelia_clastolepis:1.5,(Morelia_kinghorni:1,Morelia_nauta:1):0.5):0.8333333333,(Morelia_oenpelliensis:1.75,(Morelia_tracyae:1.5,Morelia_amethistina:1.5):0.25):0.5833333333):0.8333333333):1.208333333):0.6861111111,(((Morelia_boeleni:2,(Liasis_albertisii:1,Bothrochilus_boa:1):1):0.8333333333,((Antaresia_melanocephalus:1,Antaresia_ramsayi:1):1.5,((Apodora_papuana:1,Liasis_olivaceus:1):1,(Liasis_fuscus:1,Liasis_mackloti:1):1):0.5):0.3333333333):1.888888889,(((Python_sebae:1,Python_molurus:1):0.75,(Python_regius:1.5,Python_curtus:1.5):0.25):1.275,((Python_timoriensis:1,Python_reticulatus:1):1.833333333,(Loxocemus_bicolor:1.5,(Xenopeltis_unicolor:1,Candoia_aspera:1):0.5):1.333333333):0.1916666667):1.697222222):0.3388888889);"),
]
for data_filename, expected_tree_str in test_runs:
with open(pathmap.other_source_path(data_filename)) as src:
pdm = dendropy.PhylogeneticDistanceMatrix.from_csv(
src,
is_first_row_column_names=True,
is_first_column_row_names=True,
is_allow_new_taxa=True,
delimiter=",",
)
obs_tree = pdm.upgma_tree()
expected_tree = dendropy.Tree.get(
data=expected_tree_str,
schema="newick",
# rooting="force-unrooted",
taxon_namespace=pdm.taxon_namespace,
preserve_underscores=True,
)
self.check_tree(obs_tree=obs_tree, expected_tree=expected_tree)
def test1(self):
with open(pathmap.other_source_path("multispecies_coalescent_test_data.json")) as src:
test_regimes = json.load(src)
for test_regime in test_regimes:
species_tree = dendropy.Tree.get(
data=test_regime["species_tree"],
schema="newick",
rooting="force-rooted",
)
species_tree.taxon_namespace.is_mutable = False
msc = multispeciescoalescent.MultispeciesCoalescent(species_tree=species_tree)
coalescent_species_lineage_label_map = test_regime["coalescent_species_lineage_label_map"]
coalescent_species_lineage_map_fn = lambda x: species_tree.taxon_namespace.require_taxon(coalescent_species_lineage_label_map[x.label])
coalescent_taxa = dendropy.TaxonNamespace(sorted(coalescent_species_lineage_label_map.keys()))
coalescent_taxa.is_mutable = False
for sub_regime in test_regime["coalescent_trees"]:
coalescent_tree = dendropy.Tree.get(
data=sub_regime["coalescent_tree"],
schema="newick",
rooting="force-rooted",
taxon_namespace=coalescent_taxa,
)
obs_ln_likelihood = msc.score_coalescent_tree(
coalescent_tree=coalescent_tree,
coalescent_species_lineage_map_fn=coalescent_species_lineage_map_fn,
)
exp_ln_likelihood = sub_regime["log_likelihood"]
self.assertAlmostEqual(obs_ln_likelihood, exp_ln_likelihood, 2)
def test1(self):
with open(
pathmap.other_source_path(
"multispecies_coalescent_test_data.json")) as src:
test_regimes = json.load(src)
for test_regime in test_regimes:
species_tree = dendropy.Tree.get(
data=test_regime["species_tree"],
schema="newick",
rooting="force-rooted",
)
species_tree.taxon_namespace.is_mutable = False
msc = multispeciescoalescent.MultispeciesCoalescent(
species_tree=species_tree)
coalescent_species_lineage_label_map = test_regime[
"coalescent_species_lineage_label_map"]
coalescent_species_lineage_map_fn = lambda x: species_tree.taxon_namespace.require_taxon(
coalescent_species_lineage_label_map[x.label])
coalescent_taxa = dendropy.TaxonNamespace(
sorted(coalescent_species_lineage_label_map.keys()))
coalescent_taxa.is_mutable = False
for sub_regime in test_regime["coalescent_trees"]:
coalescent_tree = dendropy.Tree.get(
data=sub_regime["coalescent_tree"],
schema="newick",
rooting="force-rooted",
taxon_namespace=coalescent_taxa,
)
obs_ln_likelihood = msc.score_coalescent_tree(
coalescent_tree=coalescent_tree,
coalescent_species_lineage_map_fn=
coalescent_species_lineage_map_fn,
)
exp_ln_likelihood = sub_regime["log_likelihood"]
self.assertAlmostEqual(obs_ln_likelihood, exp_ln_likelihood, 2)
def setUp(self):
self.tree = dendropy.Tree.get_from_path(
src=pathmap.tree_source_path("community.tree.newick"), schema="newick", rooting="force-rooted"
)
self.pdm = dendropy.PhylogeneticDistanceMatrix.from_tree(self.tree)
assemblage_data_filepath = pathmap.other_source_path("community.data.tsv")
with open(assemblage_data_filepath) as src:
self.data_table = container.DataTable.from_csv(src, default_data_type=int, delimiter="\t")
self.assemblage_membership_definitions = self.pdm.assemblage_membership_definitions_from_csv(
assemblage_data_filepath, delimiter="\t"
)
self.assemblage_memberships = self.assemblage_membership_definitions.values()
def test_njtree_from_distance_matrices(self):
# library(ape)
# ---
# z = matrix( c(0,5,9,9,8, 5,0,10,10,9, 9,10,0,8,7, 9,10,8,0,3, 8,9,7,3,0), byrow=T, nrow=5)
# rownames(z) <- c("a", "b", "c", "d", "e")
# colnames(z) <- c("a", "b", "c", "d", "e")
# t = nj(z)
# write.tree(t)
# ---
# p1 = read.csv("pythonidae.mle.unweighted.pdm.csv", header=T, row.names=1)
# m1 = as.matrix(p1)
# nj(m1)
# t = nj(m1)
# write.tree(t)
test_runs = [
("wpnjex.csv", "(e:1,d:2,((a:2,b:3):3,c:4):2);"),
("saitou_and_nei_1987_table1.csv", "(h:6,g:2,((((a:5,b:2):2,c:1):1,d:3):2,(e:1,f:4):2):1);"),
(
"pythonidae.mle.unweighted.pdm.csv",
"(Morelia_spilota:1,Morelia_bredli:1,((((((Morelia_kinghorni:1,Morelia_nauta:1):1,Morelia_clastolepis:1):1,Morelia_amethistina:1):1,Morelia_tracyae:1):1,Morelia_oenpelliensis:1):1,(((((Liasis_albertisii:1,Bothrochilus_boa:1):1,((Antaresia_melanocephalus:1,Antaresia_ramsayi:1):1,((Liasis_fuscus:1,Liasis_mackloti:1):1,(Apodora_papuana:1,Liasis_olivaceus:1):1):1):1):1,Morelia_boeleni:1):1,((Python_timoriensis:1,Python_reticulatus:1):1,((((Python_sebae:1,Python_molurus:1):1,Python_curtus:1):1,Python_regius:1):1,((Xenopeltis_unicolor:1,Candoia_aspera:1):1,Loxocemus_bicolor:1):1):1):1):1,((((Antaresia_stimsoni:1,Antaresia_childreni:1):1,Antaresia_perthensis:1):1,Antaresia_maculosa:1):1,((Morelia_viridisN:1,Morelia_viridisS:1):1,Morelia_carinata:1):1):1):1):1);",
),
(
"pythonidae.mle.weighted.pdm.csv",
"((Liasis_albertisii:0.0542142498,Bothrochilus_boa:0.0638595214):0.038444,(((Apodora_papuana:0.0670782319,Liasis_olivaceus:0.0430801028):0.010168,(Liasis_fuscus:0.0194903208,Liasis_mackloti:0.0141916418):0.048505):0.013422,(Antaresia_melanocephalus:0.0380695554,Antaresia_ramsayi:0.0325474267):0.043626):0.007734,(((((((Antaresia_stimsoni:0.0152390165,Antaresia_childreni:0.023141749):0.032397,Antaresia_perthensis:0.0760812159):0.012848,Antaresia_maculosa:0.0679212061):0.011617,((Morelia_viridisN:0.0377499268,Morelia_viridisS:0.0473589755):0.027329,Morelia_carinata:0.0660356718):0.013482):0.015469,((((((Morelia_kinghorni:0.0075825724,Morelia_nauta:0.0086155842):0.004182,Morelia_clastolepis:0.0045446653):0.018597,Morelia_amethistina:0.0227641045):0.007181,Morelia_tracyae:0.0377936102):0.024796,Morelia_oenpelliensis:0.0579745143):0.004283,(Morelia_bredli:0.0274921037,Morelia_spilota:0.0241663426):0.026356):0.031732):0.006602,(((((Python_sebae:0.0629755585,Python_molurus:0.0335903967):0.02165,Python_curtus:0.1067094932):0.016163,Python_regius:0.1058922755):0.032743,((Xenopeltis_unicolor:0.1983677797,Candoia_aspera:0.4092923305):0.048508,Loxocemus_bicolor:0.2627888765):0.060789):0.030952,(Python_timoriensis:0.074479767,Python_reticulatus:0.0562613055):0.06004):0.027099):0.002859,Morelia_boeleni:0.0843874314):0.002713);",
),
]
for data_filename, expected_tree_str in test_runs:
with open(pathmap.other_source_path(data_filename)) as src:
pdm = dendropy.PhylogeneticDistanceMatrix.from_csv(
src,
is_first_row_column_names=True,
is_first_column_row_names=True,
is_allow_new_taxa=True,
delimiter=",",
)
obs_tree = pdm.nj_tree()
# print(obs_tree.as_string("newick"))
# print(obs_tree.as_ascii_plot(plot_metric="length"))
expected_tree = dendropy.Tree.get(
data=expected_tree_str,
schema="newick",
rooting="force-unrooted",
taxon_namespace=pdm.taxon_namespace,
preserve_underscores=True,
)
self.check_tree(obs_tree=obs_tree, expected_tree=expected_tree)
def test_nonabundance_edgeweighted_unnormalized_ses_mntd(self):
# suppressMessages(library(picante))
# dists = as.matrix(read.csv("data/dist.csv",header=T,row.names=1))
# comm = as.matrix(read.csv("data/community.data.tsv",sep="\t",header=T,row.names=1))
# results.mntd = ses.mntd(comm, dists, null.model="taxa.labels",abundance.weighted=F,runs=100000)
# write.csv(format(results.mntd, digits=22), quote=F, "community.data.weighted.unnormalized.ses.mntd.csv")
# results.mntd = ses.mntd(comm, dists, null.model="taxa.labels",abundance.weighted=F,runs=100000)
# write.csv(format(results.mntd,digits=22), quote=F, "community.data.weighted.unnormalized.ses.mntd.csv")
with open(pathmap.other_source_path("community.data.weighted.unnormalized.ses.mntd.csv")) as src:
expected_results_data_table = container.DataTable.from_csv(src, default_data_type=float, delimiter=",")
# for row_name in expected_results_data_table.row_name_iter():
# for column_name in expected_results_data_table.column_name_iter():
# v = expected_results_data_table[row_name, column_name]
# print("{}, {}: {} ({})".format(row_name, column_name, v, type(v)))
obs_results = self.pdm.standardized_effect_size_mean_nearest_taxon_distance(
assemblage_memberships=self.assemblage_memberships,
num_randomization_replicates=100,
is_weighted_edge_distances=True,
is_normalize_by_tree_size=False,
)
self.assertEqual(len(obs_results), expected_results_data_table.num_rows())
for obs_result, expected_result_row_name in zip(obs_results, expected_results_data_table.row_name_iter()):
self.assertTrue(
self._low_precision_equality(
obs_result.obs, expected_results_data_table[expected_result_row_name, "mntd.obs"]
)
)
self.assertTrue(
self._low_precision_equality(
obs_result.null_model_mean, expected_results_data_table[expected_result_row_name, "mntd.rand.mean"]
)
)
self.assertTrue(
self._low_precision_equality(
obs_result.null_model_sd, expected_results_data_table[expected_result_row_name, "mntd.rand.sd"]
)
)
self.assertTrue(
self._low_precision_equality(
obs_result.z, expected_results_data_table[expected_result_row_name, "mntd.obs.z"]
)
)
self.assertTrue(
self._low_precision_equality(
obs_result.p, expected_results_data_table[expected_result_row_name, "mntd.obs.p"]
)
)
