def test_load_from_server(self):
# Not valid use_data_from
with self.assertRaises(TypeError):
ham.Ham(use_data_from='xxx')
# Valid use_data_from but missing query_database
with self.assertRaises(TypeError):
ham.Ham(use_data_from='oma')
def test_wrong_type_hog_file(self):
with self.assertRaises(TypeError):
ham.Ham(self.nwk_str, self.orthoxml_path, type_hog_file='xs')
with self.assertRaises(TypeError):
ham.Ham(self.nwk_str, self.orthoxml_path, type_hog_file='')
with self.assertRaises(TypeError):
ham.Ham(self.nwk_str, self.orthoxml_path, type_hog_file=None)
def test_wrong_newick_str(self):
with self.assertRaises(ete3.parser.newick.NewickError):
ham.Ham(self.nwk_str_empty,
self.orthoxml_path,
type_hog_file='orthoxml')
with self.assertRaises(ete3.parser.newick.NewickError):
ham.Ham(self.nwk_str_wrong,
self.orthoxml_path,
type_hog_file='orthoxml')
def test_orthoxml_as_string(self):
self.ham_analysis = ham.Ham(tree_file=self.nwk_str,
hog_file=self.orthoxml_string,
type_hog_file='orthoxml',
orthoXML_as_string=True)
with self.assertRaises(IOError):
self.ham_analysis = ham.Ham(tree_file=self.nwk_str,
hog_file=self.orthoxml_string,
type_hog_file='orthoxml')
def test_phyloxml_tag(self):
with self.assertRaises(TypeError):
ham.Ham(self.phyloxml_file,
self.orthoxml_path,
type_hog_file='orthoxml',
tree_format='phyloxml',
phyloxml_leaf_name_tag='None')
ham.Ham(self.phyloxml_file,
self.orthoxml_path,
type_hog_file='orthoxml',
tree_format='phyloxml',
phyloxml_leaf_name_tag='clade_name')
def setUp(self):
nwk_path = os.path.join(os.path.dirname(__file__),
'./data/simpleEx.nwk')
tree_str = utils.get_newick_string(nwk_path, type="nwk")
orthoxml_path = os.path.join(os.path.dirname(__file__),
'./data/simpleEx.orthoxml')
self.ham_analysis = ham.Ham(tree_file=tree_str,
hog_file=orthoxml_path,
type_hog_file='orthoxml',
use_internal_name=True)
self.human = self.ham_analysis.get_extant_genome_by_name(
name="HUMAN")
self.frog = self.ham_analysis.get_extant_genome_by_name(
name="XENTR")
self.mouse = self.ham_analysis.get_extant_genome_by_name(
name="MOUSE")
self.rat = self.ham_analysis.get_extant_genome_by_name(
name="RATNO")
self.chimp = self.ham_analysis.get_extant_genome_by_name(
name="PANTR")
self.vertebrates = self.ham_analysis.get_ancestral_genome_by_mrca_of_genome_set(
{self.human, self.frog})
self.rodents = self.ham_analysis.get_ancestral_genome_by_mrca_of_genome_set(
{self.mouse, self.rat})
self.primates = self.ham_analysis.get_ancestral_genome_by_mrca_of_genome_set(
{self.human, self.chimp})
self.euarchontoglires = self.ham_analysis.get_ancestral_genome_by_mrca_of_genome_set(
{self.human, self.mouse})
def test_non_luca_root_hog_works_from_omabrowser(self):
analysis = ham.Ham(query_database='P53_RAT', use_data_from='oma')
fn = os.path.join(self.tmpdir, 'tree_profile.html')
analysis.create_tree_profile(outfile=fn)
with open(fn, 'rt') as fh:
html = fh.read()
self.assertIn('treeData', html)
def setUp(self):
nwk_path = os.path.join(os.path.dirname(__file__), './data/simpleEx.nwk')
tree_str = utils.get_newick_string(nwk_path, type="nwk")
orthoxml_path = os.path.join(os.path.dirname(__file__), './data/simpleEx.orthoxml')
self.ham_analysis = ham.Ham(tree_file=tree_str, hog_file=orthoxml_path, type_hog_file='orthoxml',
use_internal_name=True)
def setUp(self):
self.phyloxml_path = os.path.join(
os.path.dirname(__file__), "data",
"p53_augmented_speciestree.phyloxml")
self.orthoxml_path = os.path.join(os.path.dirname(__file__), "data",
"p53_augmented.orthoxml")
self.ham_analysis = ham.Ham(tree_file=self.phyloxml_path,
tree_format="phyloxml",
hog_file=self.orthoxml_path,
type_hog_file="orthoxml",
use_internal_name=True)
def test_parser_accepts_multiple_consequative_dups(self):
ham_analysis = ham.Ham(tree_file=self.nwk_str,
hog_file=self.orthoxml_path,
type_hog_file='orthoxml',
use_internal_name=True)
hogs = ham_analysis.get_list_top_level_hogs()
self.assertEqual(1, len(hogs))
hog = hogs[0]
self.assertEqual(5, len(hog.children))
self.assertFalse(hog.children[0].arose_by_duplication)
dup_events = {g.arose_by_duplication for g in hog.children[1:]}
self.assertEqual(1, len(dup_events))
def test_treeProfile_on_full_setup(self):
logging.basicConfig(
level=logging.INFO,
format="%(asctime)s %(name)-12s %(levelname)-8s %(message)s")
nwk_path = os.path.join(os.path.dirname(__file__),
'./data/simpleEx.nwk')
tree_str = utils.get_newick_string(nwk_path, type="nwk")
orthoxml_path = os.path.join(os.path.dirname(__file__),
'./data/simpleEx.orthoxml')
ham_analysis = ham.Ham(tree_file=tree_str,
hog_file=orthoxml_path,
type_hog_file='orthoxml')
def setUp(self):
nwk_path = os.path.join(os.path.dirname(__file__),
'./data/parser/tree.newick')
nwk_str = utils.get_newick_string(nwk_path, type="nwk")
orthoxml_path = os.path.join(
os.path.dirname(__file__),
'./data/parser/conflict_duplication_children.orthoxml')
self.ham_analysis = ham.Ham(tree_file=nwk_str,
hog_file=orthoxml_path,
type_hog_file='orthoxml',
use_internal_name=True)
def setUp(self):
nwk_path = os.path.join(os.path.dirname(__file__),
'./data/simpleEx.nwk')
nwk_str = utils.get_newick_string(nwk_path, type="nwk")
nwk_path_no_name = os.path.join(os.path.dirname(__file__),
'./data/simpleEx.nwk')
nwk_str_no_name = utils.get_newick_string(nwk_path_no_name, type="nwk")
orthoxml_path = os.path.join(os.path.dirname(__file__),
'./data/simpleEx.orthoxml')
# using newick with name on both internal nodes and leaves
self.h = ham.Ham(nwk_str, orthoxml_path)
# using newick with name only at leaves
self.hn = ham.Ham(nwk_str_no_name, orthoxml_path)
# using newick with name on both internal nodes and leaves and filter for HOG2
self.filter_genome = {"HUMAN", "MOUSE", "CANFA", "PANTR"}
self.filter_genes = {'2', '32', '22', '12'}
self.filter_genes_ext = {'HUMAN2', 'MOUSE2', 'CANFA2', 'PANTR2'}
self.filter_hogs = {'2'}
self.no_filter_genome = {"XENTR", "RATNO"}
self.no_filter_genes = {
'1', '11', '21', '31', '41', '51', '3', '13', '23', '33', '53',
'34', '14'
}
self.no_filter_genes_ext = {
'HUMAN1', 'PANTR1', 'CANFA1', 'MOUSE1', 'RATNO1', 'XENTR1',
'HUMAN3', 'PANTR3', 'CANFA3', 'MOUSE3', 'XENTR3', 'MOUSE4',
'PANTR4'
}
self.no_filter_hogs = {'1', '3'}
f = ham.ParserFilter()
f.add_hogs_via_hogId([2])
self.hf = ham.Ham(nwk_str, orthoxml_path, filter_object=f)
def setUp(self):
nwk_path = os.path.join(os.path.dirname(__file__),
'./data/simpleEx.nwk')
nwk_str = utils.get_newick_string(nwk_path, type="nwk")
orthoxml_path = os.path.join(os.path.dirname(__file__),
'./data/simpleEx.orthoxml')
self.ham_analysis = ham.Ham(tree_file=nwk_str,
hog_file=orthoxml_path,
type_hog_file='orthoxml',
use_internal_name=True)
self.hogs = self.ham_analysis.get_dict_top_level_hogs()
self.genes = self.ham_analysis.get_dict_extant_genes()
def test_load_taxonomy_from_nwk_file_and_all_hogs_from_orthoxml_file_no_filter(
self):
# load the logger
logging.basicConfig(
level=logging.INFO,
format="%(asctime)s %(name)-12s %(levelname)-8s %(message)s")
# Clement select a nwk file as a taxonomy reference
nwk_path = os.path.join(os.path.dirname(__file__),
'./data/simpleEx.nwk')
# And extract the newick tree as a string
tree_str = utils.get_newick_string(nwk_path, type="nwk")
# then clement select his favorite orthoXML file
orthoxml_path = os.path.join(os.path.dirname(__file__),
'./data/simpleEx.orthoxml')
# Clement create the Ham object that will be the kernel of all analysis
ham_analysis = ham.Ham(tree_file=tree_str,
hog_file=orthoxml_path,
use_internal_name=True,
type_hog_file='orthoxml')
# And verifying if all tree elements are created
self.assertEqual(
ham_analysis.taxonomy.tree_str,
"(XENTR,(((HUMAN,PANTR)Primates,(MOUSE,RATNO)Rodents)Euarchontoglires,"
"CANFA)Mammalia)Vertebrata;")
# After he get all the top level hogs
self.assertEqual(len(ham_analysis.top_level_hogs), 3)
self.assertEqual(len(ham_analysis.extant_gene_map), 19)
# Clement is curious to look at the species present within this taxonomy
extant_genomes = ham_analysis.get_list_extant_genomes()
# then look if its 6 species are present
extant_genomes_name = set(ext_genome.name
for ext_genome in extant_genomes)
self.assertEqual(
extant_genomes_name,
{'RATNO', 'HUMAN', 'CANFA', 'PANTR', 'XENTR', 'MOUSE'})
self.assertEqual(len(ham_analysis.taxonomy.leaves), 6)
self.assertEqual(len(ham_analysis.taxonomy.internal_nodes), 5)
def test_lineage_comparative_analysis(self):
# Clement initialise the pyham analyzer objet as it's explained in the documentation
logging.basicConfig(
level=logging.WARNING,
format="%(asctime)s %(name)-12s %(levelname)-8s %(message)s")
nwk_path = os.path.join(os.path.dirname(__file__),
'./data/simpleEx.nwk')
tree_str = utils.get_newick_string(nwk_path, type="nwk")
orthoxml_path = os.path.join(os.path.dirname(__file__),
'./data/simpleEx.orthoxml')
ham_analysis = ham.Ham(tree_file=tree_str,
hog_file=orthoxml_path,
type_hog_file='orthoxml',
use_internal_name=True)
# Then clement is interest to investigate on what happened between the ancestral genomes of vertebrates
# and the extent genomes of the mouse.
# First he select the related genomes objectt via their name or mrca.
mouse = ham_analysis.get_extant_genome_by_name(name="MOUSE")
frog = ham_analysis.get_extant_genome_by_name(name="XENTR")
vertebrates = ham_analysis.get_ancestral_genome_by_mrca_of_genome_set(
{mouse, frog})
# Then, he compare the two genomes of interest
vertical_map_mouse_vs_vert = ham_analysis.compare_genomes_vertically(
mouse, vertebrates)
# Now he is interest by the HOG that have stay single copy between these two levels
self.assertDictEqual({'<HOG(1)>': 'Gene(31)'},
_str_dict_one_value(
vertical_map_mouse_vs_vert.get_retained()))
# ... and at the duplicated genes
self.assertDictEqual({'<HOG(3)>': {'Gene(34)', 'Gene(33)'}},
_str_dict_array_value(
vertical_map_mouse_vs_vert.get_duplicated()))
# Clement is curious and want to look if there is gene that have been lost
self.assertSetEqual(set(),
_str_array(vertical_map_mouse_vs_vert.get_lost()))
def test_load_taxonomy_from_nwk_file_and_from_orthoxml_file_with_filter_hog2(
self):
# load the logger
logging.basicConfig(
level=logging.INFO,
format="%(asctime)s %(name)-12s %(levelname)-8s %(message)s")
# Clement select a nwk file as a taxonomy reference
nwk_path = os.path.join(os.path.dirname(__file__),
'./data/simpleEx.nwk')
# And extract the newick tree as a string
tree_str = utils.get_newick_string(nwk_path, type="nwk")
# Clement will now setup the filter object
f = ham.ParserFilter()
f.add_hogs_via_hogId([2])
# Clement check that the filter contained all information
self.assertEqual(set(f.HOGId_filter), {'2'})
self.assertEqual(set(f.GeneExtId_filter), set())
self.assertEqual(set(f.GeneIntId_filter), set())
# then clement select his favorite orthoXML file
orthoxml_path = os.path.join(os.path.dirname(__file__),
'./data/simpleEx.orthoxml')
# Clement create the Ham object that will be the kernel of all analysis
ham_analysis = ham.Ham(tree_str,
orthoxml_path,
filter_object=f,
use_internal_name=True)
self.assertEqual(f, ham_analysis.filter_obj)
# Clement check that what the filter understood was good
self.assertSetEqual(set(ham_analysis.filter_obj.geneUniqueId),
{'2', '32', '22', '12'})
self.assertSetEqual(set(ham_analysis.filter_obj.hogsId), {'2'})
# Clement check that the parsed informatio is correct
self.assertEqual(len(ham_analysis.top_level_hogs), 1)
self.assertEqual(len(ham_analysis.extant_gene_map), 4)
def setUp(self):
nwk_path = os.path.join(os.path.dirname(__file__),
'./data/simpleEx.nwk')
tree_str = utils.get_newick_string(nwk_path, type="nwk")
orthoxml_path = os.path.join(os.path.dirname(__file__),
'./data/simpleEx.orthoxml')
self.ham_analysis = ham.Ham(tree_file=tree_str,
hog_file=orthoxml_path,
type_hog_file='orthoxml')
self.hogs = self.ham_analysis.get_dict_top_level_hogs()
self.genes = self.ham_analysis.get_dict_extant_genes()
self.human = self.ham_analysis.get_extant_genome_by_name(name="HUMAN")
self.frog = self.ham_analysis.get_extant_genome_by_name(name="XENTR")
self.mouse = self.ham_analysis.get_extant_genome_by_name(name="MOUSE")
self.rat = self.ham_analysis.get_extant_genome_by_name(name="RATNO")
self.chimp = self.ham_analysis.get_extant_genome_by_name(name="PANTR")
self.vertebrates = self.ham_analysis.get_ancestral_genome_by_mrca_of_genome_set(
{self.human, self.frog})
def setUp(self):
nwk_path = os.path.join(os.path.dirname(__file__), './data/Conflict1/tree.nwk')
tree_str = utils.get_newick_string(nwk_path, type="nwk")
orthoxml_path = os.path.join(os.path.dirname(__file__), './data/Conflict1/hog.orthoxml')
self.ham_analysis = ham.Ham(tree_file=tree_str, hog_file=orthoxml_path, type_hog_file='orthoxml', use_internal_name=True)
self.hog = self.ham_analysis.get_list_top_level_hogs()[0]
def setUp(self):
nwk_path = os.path.join(os.path.dirname(__file__), './data/simpleEx.nwk')
nwk_str = utils.get_newick_string(nwk_path, type="nwk")
orthoxml_path = os.path.join(os.path.dirname(__file__), './data/simpleEx.orthoxml')
self.h = ham.Ham(nwk_str, orthoxml_path, use_internal_name=True)
def test_wrong_filter(self):
with self.assertRaises(TypeError):
ham.Ham(self.nwk_str, self.orthoxml_path, filter_object="x")
def setUp(self):
nwk_path = os.path.join(os.path.dirname(__file__),
'./data/simpleEx.nwk')
tree_str = utils.get_newick_string(nwk_path, type="nwk")
orthoxml_path = os.path.join(os.path.dirname(__file__),
'./data/simpleEx.orthoxml')
self.ham_analysis = ham.Ham(tree_file=tree_str,
hog_file=orthoxml_path,
type_hog_file='orthoxml',
use_internal_name=True)
self.ham_analysis_no_name = ham.Ham(tree_file=tree_str,
hog_file=orthoxml_path,
type_hog_file='orthoxml',
use_internal_name=False)
# gene, retained, duplicated, gain, lost
self.exp_full = {
"Mammalia": [3, 2, 0, 1, 0],
"Euarchontoglires": [4, 2, 2, 0, 0],
"Primates": [4, 4, 0, 0, 0],
"Rodents": [4, 4, 0, 0, 0],
"Vertebrata": [2, None, None, None, None]
}
self.exp_full_nn = {
"HUMAN/PANTR/MOUSE/RATNO/CANFA": [3, 2, 0, 1, 0],
"HUMAN/PANTR/MOUSE/RATNO": [4, 2, 2, 0, 0],
"HUMAN/PANTR": [4, 4, 0, 0, 0],
"MOUSE/RATNO": [4, 4, 0, 0, 0],
"XENTR/HUMAN/PANTR/MOUSE/RATNO/CANFA": [2, None, None, None, None],
"HUMAN": [4, 3, 0, 1, 1],
"PANTR": [4, 4, 0, 0, 0],
"MOUSE": [4, 4, 0, 0, 0],
"RATNO": [2, 1, 0, 1, 3],
"CANFA": [3, 3, 0, 0, 0],
"XENTR": [2, 2, 0, 0, 0]
}
# gene, retained, duplicated, lost
self.expected_level_1 = {
"Mammalia": [1, 1, 0, 0],
"Euarchontoglires": [1, 1, 0, 0],
"Primates": [1, 1, 0, 0],
"Rodents": [1, 1, 0, 0],
"Vertebrata": [1, None, None, None],
"HUMAN": [1, 1, 0, 0],
"PANTR": [1, 1, 0, 0],
"MOUSE": [1, 1, 0, 0],
"RATNO": [1, 1, 0, 0],
"CANFA": [1, 1, 0, 0],
"XENTR": [1, 1, 0, 0]
}
self.expected_level_2 = {
"Mammalia": [1, None, None, None],
"Euarchontoglires": [1, 1, 0, 0],
"Primates": [1, 1, 0, 0],
"Rodents": [1, 1, 0, 0],
"HUMAN": [1, 1, 0, 0],
"PANTR": [1, 1, 0, 0],
"MOUSE": [1, 1, 0, 0],
"RATNO": [0, 0, 0, 1],
"CANFA": [1, 1, 0, 0]
}
self.expected_level_3 = {
"Mammalia": [1, 1, 0, 0],
"Euarchontoglires": [2, 0, 2, 0],
"Primates": [2, 2, 0, 0],
"Rodents": [2, 2, 0, 0],
"Vertebrata": [1, None, None, None],
"HUMAN": [1, 1, 0, 1],
"PANTR": [2, 2, 0, 0],
"MOUSE": [2, 2, 0, 0],
"RATNO": [0, 0, 0, 2],
"CANFA": [1, 1, 0, 0],
"XENTR": [1, 1, 0, 0]
}
def setUp(self):
nwk_path = os.path.join(os.path.dirname(__file__),
'./data/simpleEx.nwk')
nwk_str = utils.get_newick_string(nwk_path, type="nwk")
nwk_path_no_name = os.path.join(os.path.dirname(__file__),
'./data/simpleEx.nwk')
nwk_str_no_name = utils.get_newick_string(nwk_path_no_name, type="nwk")
phyloxml_file = os.path.join(os.path.dirname(__file__),
'./data/simpleEx.phyloxml')
orthoxml_path = os.path.join(os.path.dirname(__file__),
'./data/simpleEx.orthoxml')
with open(orthoxml_path, 'r') as orthoxml_file:
data = orthoxml_file.read()
self.orthoxml_string = data
# using newick with name on both internal nodes and leaves
self.h = ham.Ham(nwk_str, orthoxml_path, use_internal_name=True)
# using newick with name only at leaves
self.hn = ham.Ham(nwk_str_no_name, orthoxml_path)
# using phyloxml file with name
self.hpx = ham.Ham(
phyloxml_file,
orthoxml_path,
use_internal_name=True,
tree_format='phyloxml',
phyloxml_internal_name_tag='taxonomy_scientific_name',
phyloxml_leaf_name_tag='taxonomy_code')
# using newick with name on both internal nodes and leaves and filter for HOG2
self.filter_genome = {"HUMAN", "MOUSE", "CANFA", "PANTR"}
self.filter_genes = {'2', '32', '22', '12'}
self.filter_genes_ext = {'HUMAN2', 'MOUSE2', 'CANFA2', 'PANTR2'}
self.filter_hogs = {'2'}
self.no_filter_genome = {"XENTR", "RATNO"}
self.no_filter_genes = {
'1', '11', '21', '31', '41', '51', '3', '13', '23', '33', '53',
'34', '14'
}
self.no_filter_genes_ext = {
'HUMAN1', 'PANTR1', 'CANFA1', 'MOUSE1', 'RATNO1', 'XENTR1',
'HUMAN3', 'PANTR3', 'CANFA3', 'MOUSE3', 'XENTR3', 'MOUSE4',
'PANTR4'
}
self.no_filter_hogs = {'1', '3'}
f = ham.ParserFilter()
f.add_hogs_via_hogId([2])
self.hf = ham.Ham(nwk_str,
orthoxml_path,
filter_object=f,
use_internal_name=True)
# test that filter work with string
self.hstring = ham.Ham(nwk_str,
self.orthoxml_string,
use_internal_name=True,
orthoXML_as_string=True)
# test that filter work with string
self.hfstring = ham.Ham(nwk_str,
self.orthoxml_string,
filter_object=f,
use_internal_name=True,
orthoXML_as_string=True)
