def test_get_score(self):
aln = AlignIO.read('TreeConstruction/msa.phy', 'phylip')
tree = Phylo.read('./TreeConstruction/upgma.tre', 'newick')
scorer = ParsimonyScorer()
score = scorer.get_score(tree, aln)
self.assertEqual(score, 2 + 1 + 2 + 2 + 1 + 1 + 1 + 3)
alphabet = ['A', 'T', 'C', 'G']
step_matrix = [[0], [2.5, 0], [2.5, 1, 0], [1, 2.5, 2.5, 0]]
matrix = _Matrix(alphabet, step_matrix)
scorer = ParsimonyScorer(matrix)
score = scorer.get_score(tree, aln)
self.assertEqual(score, 3.5 + 2.5 + 3.5 + 3.5 + 2.5 + 1 + 2.5 + 4.5)
alphabet = [
'A', 'C', 'D', 'E', 'F', 'G', 'H', 'I', 'K', 'L', 'M', 'N', 'P',
'Q', 'R', '1', '2', 'T', 'V', 'W', 'Y', '*', '-'
]
step_matrix = [
[0], [2, 0], [1, 2,
0],
[1, 2, 1, 0],
[2, 1, 2, 2, 0],
[1, 1, 1, 1, 2,
0], [2, 2, 1, 2, 2, 2,
0],
[2, 2, 2, 2, 1, 2,
2, 0], [2, 2, 2, 1, 2, 2, 2, 1,
0], [2, 2, 2, 2, 1, 2, 1, 1, 2,
0],
[2, 2, 2, 2, 2, 2, 2, 1, 1, 1,
0], [2, 2, 1, 2, 2, 2, 1, 1, 1, 2, 2,
0],
[1, 2, 2, 2, 2, 2, 1, 2, 2, 1, 2,
2, 0], [2, 2, 2, 1, 2, 2, 1, 2, 1, 1, 2, 2, 1,
0], [2, 1, 2, 2, 2, 1, 1, 1, 1, 1, 1, 2, 1, 1,
0], [1, 1, 2, 2, 1, 2, 2, 2, 2, 1, 2, 2, 1, 2, 2, 0],
[2, 1, 2, 2, 2, 1, 2, 1, 2, 2, 2, 1,
2, 2, 1, 2, 0],
[1, 2, 2, 2, 2, 2, 2, 1, 1, 2, 1, 1, 1, 2, 1, 1, 1, 0],
[1, 2, 1, 1, 1, 1, 2, 1, 2, 1, 1, 2, 2, 2, 2, 2, 2, 2, 0],
[2, 1, 2, 2, 2, 1, 2, 2, 2, 1, 2, 3, 2, 2, 1, 1, 2, 2, 2, 0],
[2, 1, 1, 2, 1, 2, 1, 2, 2, 2, 3, 1, 2, 2, 2, 1, 2, 2, 2, 2, 0],
[2, 1, 2, 1, 2, 1, 2, 2, 1, 1, 2, 2, 2, 1, 1, 1, 2, 2, 2, 1, 1, 0],
[
3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3,
3, 0
]
]
matrix = _Matrix(alphabet, step_matrix)
scorer = ParsimonyScorer(matrix)
score = scorer.get_score(tree, aln)
self.assertEqual(score, 3 + 1 + 3 + 3 + 2 + 1 + 2 + 5)
def test_get_neighbors(self):
tree = Phylo.read('./TreeConstruction/upgma.tre', 'newick')
alphabet = ['A', 'T', 'C', 'G']
step_matrix = [[0], [2.5, 0], [2.5, 1, 0], [1, 2.5, 2.5, 0]]
matrix = _Matrix(alphabet, step_matrix)
scorer = ParsimonyScorer(matrix)
searcher = NNITreeSearcher(scorer)
trees = searcher._get_neighbors(tree)
self.assertEqual(len(trees), 2 * (5 - 3))
Phylo.write(trees, './TreeConstruction/neighbor_trees.tre', 'newick')
def test_get_neighbors(self):
tree = Phylo.read("./TreeConstruction/upgma.tre", "newick")
alphabet = ["A", "T", "C", "G"]
step_matrix = [[0], [2.5, 0], [2.5, 1, 0], [1, 2.5, 2.5, 0]]
matrix = _Matrix(alphabet, step_matrix)
scorer = ParsimonyScorer(matrix)
searcher = NNITreeSearcher(scorer)
trees = searcher._get_neighbors(tree)
self.assertEqual(len(trees), 2 * (5 - 3))
Phylo.write(trees, os.path.join(temp_dir, "neighbor_trees.tre"), "newick")
def create_tree_parsimony_impl(msa):
calculator = DistanceCalculator('identity')
constructor = DistanceTreeConstructor(distance_calculator=calculator, method='nj')
starting_tree = constructor.build_tree(msa)
scorer = ParsimonyScorer()
searcher = NNITreeSearcher(scorer)
constructor = ParsimonyTreeConstructor(searcher=searcher,starting_tree=starting_tree)
tree = constructor.build_tree(msa)
Phylo.write(tree, "../../data/created/tree" + str(random.randint(0,10000000)) + ".nex", "nexus")
Phylo.draw(tree,do_show=False)
plt.savefig("../../data/created/createdTree_parsimony.png")
return "../../data/created/createdTree_parsimony.png"
def test_build_tree(self):
aln = AlignIO.read('TreeConstruction/msa.phy', 'phylip')
tree1 = Phylo.read('./TreeConstruction/upgma.tre', 'newick')
tree2 = Phylo.read('./TreeConstruction/nj.tre', 'newick')
alphabet = ['A', 'T', 'C', 'G']
step_matrix = [[0], [2.5, 0], [2.5, 1, 0], [1, 2.5, 2.5, 0]]
matrix = _Matrix(alphabet, step_matrix)
scorer = ParsimonyScorer(matrix)
searcher = NNITreeSearcher(scorer)
constructor = ParsimonyTreeConstructor(searcher, tree1)
best_tree = constructor.build_tree(aln)
Phylo.write(best_tree, './TreeConstruction/pars1.tre', 'newick')
constructor.starting_tree = tree2
best_tree = constructor.build_tree(aln)
Phylo.write(best_tree, './TreeConstruction/pars2.tre', 'newick')
constructor.starting_tree = None
best_tree = constructor.build_tree(aln)
Phylo.write(best_tree, './TreeConstruction/pars3.tre', 'newick')
def test_build_tree(self):
aln = AlignIO.read("TreeConstruction/msa.phy", "phylip")
tree1 = Phylo.read("./TreeConstruction/upgma.tre", "newick")
tree2 = Phylo.read("./TreeConstruction/nj.tre", "newick")
alphabet = ["A", "T", "C", "G"]
step_matrix = [[0], [2.5, 0], [2.5, 1, 0], [1, 2.5, 2.5, 0]]
matrix = _Matrix(alphabet, step_matrix)
scorer = ParsimonyScorer(matrix)
searcher = NNITreeSearcher(scorer)
constructor = ParsimonyTreeConstructor(searcher, tree1)
best_tree = constructor.build_tree(aln)
Phylo.write(best_tree, os.path.join(temp_dir, "pars1.tre"), "newick")
constructor.starting_tree = tree2
best_tree = constructor.build_tree(aln)
Phylo.write(best_tree, os.path.join(temp_dir, "pars2.tre"), "newick")
constructor.starting_tree = None
best_tree = constructor.build_tree(aln)
Phylo.write(best_tree, os.path.join(temp_dir, "pars3.tre"), "newick")
def test_get_score(self):
aln = AlignIO.read('TreeConstruction/msa.phy', 'phylip')
tree = Phylo.read('./TreeConstruction/upgma.tre', 'newick')
scorer = ParsimonyScorer()
score = scorer.get_score(tree, aln)
self.assertEqual(score, 2 + 1 + 2 + 2 + 1 + 1 + 1 + 3)
alphabet = ['A', 'T', 'C', 'G']
step_matrix = [[0],
[2.5, 0],
[2.5, 1, 0],
[1, 2.5, 2.5, 0]]
matrix = _Matrix(alphabet, step_matrix)
scorer = ParsimonyScorer(matrix)
score = scorer.get_score(tree, aln)
self.assertEqual(score, 3.5 + 2.5 + 3.5 + 3.5 + 2.5 + 1 + 2.5 + 4.5)
alphabet = ['A', 'C', 'D', 'E', 'F', 'G', 'H', 'I', 'K', 'L', 'M', 'N',
'P', 'Q', 'R', '1', '2', 'T', 'V', 'W', 'Y', '*', '-']
step_matrix = [[0],
[2, 0],
[1, 2, 0],
[1, 2, 1, 0],
[2, 1, 2, 2, 0],
[1, 1, 1, 1, 2, 0],
[2, 2, 1, 2, 2, 2, 0],
[2, 2, 2, 2, 1, 2, 2, 0],
[2, 2, 2, 1, 2, 2, 2, 1, 0],
[2, 2, 2, 2, 1, 2, 1, 1, 2, 0],
[2, 2, 2, 2, 2, 2, 2, 1, 1, 1, 0],
[2, 2, 1, 2, 2, 2, 1, 1, 1, 2, 2, 0],
[1, 2, 2, 2, 2, 2, 1, 2, 2, 1, 2, 2, 0],
[2, 2, 2, 1, 2, 2, 1, 2, 1, 1, 2, 2, 1, 0],
[2, 1, 2, 2, 2, 1, 1, 1, 1, 1, 1, 2, 1, 1, 0],
[1, 1, 2, 2, 1, 2, 2, 2, 2, 1, 2, 2, 1, 2, 2, 0],
[2, 1, 2, 2, 2, 1, 2, 1, 2, 2, 2, 1, 2, 2, 1, 2, 0],
[1, 2, 2, 2, 2, 2, 2, 1, 1, 2, 1, 1, 1, 2, 1, 1, 1, 0],
[1, 2, 1, 1, 1, 1, 2, 1, 2, 1, 1, 2, 2, 2, 2, 2, 2, 2, 0],
[2, 1, 2, 2, 2, 1, 2, 2, 2, 1, 2, 3, 2, 2, 1, 1, 2, 2, 2, 0],
[2, 1, 1, 2, 1, 2, 1, 2, 2, 2, 3, 1, 2, 2, 2, 1, 2, 2, 2, 2, 0],
[2, 1, 2, 1, 2, 1, 2, 2, 1, 1, 2, 2, 2, 1, 1, 1, 2, 2, 2, 1, 1, 0],
[3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 0]]
matrix = _Matrix(alphabet, step_matrix)
scorer = ParsimonyScorer(matrix)
score = scorer.get_score(tree, aln)
self.assertEqual(score, 3 + 1 + 3 + 3 + 2 + 1 + 2 + 5)
def plot_phylo_tree_pars(align: MultipleSeqAlignment, accession_numbers: dict):
"""
Plots a phylogenetic tree
:param align: MultipleSeqAlignment with the alignment result to be plotted
:param accession_numbers: dict of accession numbers and their translation to human-understandable names
:return: figure-handle of the plotted phylogenetic tree
"""
scorer = ParsimonyScorer()
searcher = NNITreeSearcher(scorer)
constructor = ParsimonyTreeConstructor(searcher)
tree = constructor.build_tree(align)
print(Phylo.draw_ascii(tree))
# plot the tree
fig, ax = plt.subplots(1, 1)
# remove the names for the non-terminals for better visual appeal
for non_terminal in tree.get_nonterminals():
non_terminal.name = ''
# draw the resulting tree
Phylo.draw(tree, show_confidence=False, axes=ax, do_show=False)
ax.set_xlim(right=0.8)
return fig
def build_parsimony_tree(alignment):
scorer = ParsimonyScorer()
searcher = NNITreeSearcher(scorer)
constructor = ParsimonyTreeConstructor(searcher)
return constructor.build_tree(alignment)
def test_get_score(self):
aln = AlignIO.read("TreeConstruction/msa.phy", "phylip")
tree = Phylo.read("./TreeConstruction/upgma.tre", "newick")
scorer = ParsimonyScorer()
score = scorer.get_score(tree, aln)
self.assertEqual(score, 2 + 1 + 2 + 2 + 1 + 1 + 1 + 3)
alphabet = ["A", "T", "C", "G"]
step_matrix = [[0], [2.5, 0], [2.5, 1, 0], [1, 2.5, 2.5, 0]]
matrix = _Matrix(alphabet, step_matrix)
scorer = ParsimonyScorer(matrix)
score = scorer.get_score(tree, aln)
self.assertEqual(score, 3.5 + 2.5 + 3.5 + 3.5 + 2.5 + 1 + 2.5 + 4.5)
alphabet = [
"A",
"C",
"D",
"E",
"F",
"G",
"H",
"I",
"K",
"L",
"M",
"N",
"P",
"Q",
"R",
"1",
"2",
"T",
"V",
"W",
"Y",
"*",
"-",
]
step_matrix = [
[0],
[2, 0],
[1, 2, 0],
[1, 2, 1, 0],
[2, 1, 2, 2, 0],
[1, 1, 1, 1, 2, 0],
[2, 2, 1, 2, 2, 2, 0],
[2, 2, 2, 2, 1, 2, 2, 0],
[2, 2, 2, 1, 2, 2, 2, 1, 0],
[2, 2, 2, 2, 1, 2, 1, 1, 2, 0],
[2, 2, 2, 2, 2, 2, 2, 1, 1, 1, 0],
[2, 2, 1, 2, 2, 2, 1, 1, 1, 2, 2, 0],
[1, 2, 2, 2, 2, 2, 1, 2, 2, 1, 2, 2, 0],
[2, 2, 2, 1, 2, 2, 1, 2, 1, 1, 2, 2, 1, 0],
[2, 1, 2, 2, 2, 1, 1, 1, 1, 1, 1, 2, 1, 1, 0],
[1, 1, 2, 2, 1, 2, 2, 2, 2, 1, 2, 2, 1, 2, 2, 0],
[2, 1, 2, 2, 2, 1, 2, 1, 2, 2, 2, 1, 2, 2, 1, 2, 0],
[1, 2, 2, 2, 2, 2, 2, 1, 1, 2, 1, 1, 1, 2, 1, 1, 1, 0],
[1, 2, 1, 1, 1, 1, 2, 1, 2, 1, 1, 2, 2, 2, 2, 2, 2, 2, 0],
[2, 1, 2, 2, 2, 1, 2, 2, 2, 1, 2, 3, 2, 2, 1, 1, 2, 2, 2, 0],
[2, 1, 1, 2, 1, 2, 1, 2, 2, 2, 3, 1, 2, 2, 2, 1, 2, 2, 2, 2, 0],
[2, 1, 2, 1, 2, 1, 2, 2, 1, 1, 2, 2, 2, 1, 1, 1, 2, 2, 2, 1, 1, 0],
[
3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3,
3, 0
],
]
matrix = _Matrix(alphabet, step_matrix)
scorer = ParsimonyScorer(matrix)
score = scorer.get_score(tree, aln)
self.assertEqual(score, 3 + 1 + 3 + 3 + 2 + 1 + 2 + 5)
#
stdout, stderr = cline()
# print(stdout, stderr)
# print(cline)
aln = AlignIO.read('outAlign.aln', 'clustal')
# print(aln)
calculator = DistanceCalculator('identity')
dm = calculator.get_distance(aln)
print(dm)
constructor = DistanceTreeConstructor(calculator, 'nj')
tree = constructor.build_tree(aln)
print(tree)
scorer = ParsimonyScorer()
searcher = NNITreeSearcher(scorer)
constructor = ParsimonyTreeConstructor(searcher, tree)
pars_tree = constructor.build_tree(aln)
egfr_phy = pars_tree.as_phyloxml()
print(pars_tree)
print(egfr_phy)
print(list(pars_tree.find_elements('Inner3')))
for clade in egfr_phy.get_terminals():
key = clade.name
accession = PhyloXML.Accession(key, 'NCBI')
mol_seq = PhyloXML.MolSeq(lookup[key], is_aligned=True)
sequence = PhyloXML.Sequence(type='aa',