def test_synth_induced(self):
tre = OT.synth_induced_tree(ott_ids=synth_spp).tree
leaves = [
leaf.taxon.label for leaf in OT.synth_induced_tree(
ott_ids=synth_spp).tree.leaf_nodes()
]
assert leaves.sort() == expected_tips.sort()
assert isinstance(tre, dendropy.datamodel.treemodel.Tree)
def get_ott_ids_for_group(group_ott_id, write_file = 'children_ott_ids.txt', synth_only = False):
"""Returns all descendent ottids of a taxon"""
sys.stdout.write('Gathering ott ids from group with ott id {}.\n'.format(group_ott_id))
#debug(group_ott_id)
subtree = OT.taxon_subtree(ott_id = group_ott_id, label_format='name_and_id')
if synth_only == True:
nodes = [taxon.label.split()[-1] for taxon in subtree.tree.taxon_namespace]
resp = OT.synth_node_info(node_ids = nodes)
if 'unknown' in resp.response_dict:
synth_ids = set(nodes).difference(set(resp.response_dict['unknown']))
ott_ids = [nodeid.strip('ott') for nodeid in synth_ids]
else:
ott_ids =[taxon.label.split()[-1].strip('ott') for taxon in subtree.tree.taxon_namespace]
return ott_ids
def get_ott_ids_for_rank(rank, taxonomy_file, synth_only = True):
"""Returns all the ott_ids for a given rank.
Args
rank: (must be in ['species', 'genus', 'family', 'order', 'class'])
taxonomy_file: path to taxonomy.tsv
If synth_only == True, will return only ids included in synth.
(Does not assess if taxa actaully appear as monophyletic in synth, e.g. if taxa are broken.)
"""
assert rank in ['species', 'genus', 'family', 'order', 'class']
assert os.path.exists(taxonomy_file)
taxon_dir = os.path.dirname(taxonomy_file)
output_path = "{}/{}.tsv".format(taxon_dir, rank)
#if not os.path.exists(output_path):
os.system("""cat {tf} | awk '$7 == "{r}"' > {op}""".format(tf=taxonomy_file, r=rank, op=output_path))
# clean taxonomy file
# os.system('grep -a "' + rank + '" ' + taxonomy_file + ' | egrep -v "Incertae" | egrep -v "no rank" | egrep -v "major_rank_conflict" | egrep -v "uncultured" | egrep -v "barren" | egrep -v "extinct" | egrep -v "incertae" | egrep -v "unplaced" | egrep -v "hidden" | egrep -v "inconsistent" | egrep -v "synonym" | egrep -v "in ' + rank + '" | egrep -v "species" | egrep -v "genus" | egrep -v "super' + rank + '" | egrep -v "sub' + rank + '" > {}'.format(output_path))
# extract ott ids from taxonomy reduced file
with open(output_path, "r") as inp:
ott_ids = []
for lin in inp:
lii = lin.split('\t')
ott_ids.append(lii[0])
if synth_only == True:
nodes = ['ott' + idn for idn in ott_ids]
resp = OT.synth_node_info(node_ids = nodes)
if 'unknown' in resp.response_dict:
synth_ids = set(nodes).difference(set(resp.response_dict['unknown']))
ott_ids = [nodeid.strip('ott') for nodeid in synth_ids]
return ott_ids
def test_get_tree(self):
res = OT.get_tree(study_id=study_id,
tree_id=tree_id,
label_format='ot:otttaxonname',
tree_format='nexus')
nex = res.response_dict['content'].decode("utf-8")
assert nex.startswith("#NEXUS")
def test_relabel(self): ## JUST PUT A LIST OF IDS TO SIMPLIFY
jetz = OT.get_tree(study_id='ot_809',
tree_id='tree1',
tree_format="newick",
label_format="ot:ottId")
jetz_tree = Tree.get(string=jetz.response_dict['content'].decode(),
schema='newick',
suppress_internal_node_taxa=True,
suppress_leaf_node_taxa=True)
tips = [tip.label for tip in jetz_tree.leaf_node_iter()]
ott_ids = set()
for tip in tips:
try:
ott_ids.add(int(tip))
except:
pass
ret = taxonomy_helpers.labelled_induced_synth(ott_ids=list(ott_ids),
label_format='name')
tips = [
tip.taxon.label for tip in ret['labelled_tree'].leaf_node_iter()
if tip.taxon
]
assert len(tips) == 6624
ret = taxonomy_helpers.labelled_induced_synth(
ott_ids=list(ott_ids), label_format='name_and_id')
nodes = [
node.taxon.label for node in ret['labelled_tree'] if node.taxon
]
assert 'MRCA of taxa in Amazona auropalliata_ott1118 Amazona oratrix_ott1119' in nodes, nodes
def test_get_tree_object(self):
res = OT.get_tree(study_id=study_id,
tree_id=tree_id,
label_format='ot:ottid',
tree_format='object')
tree_dict = res.response_dict['data']
assert isinstance(tree_dict, dict)
def test_find_trees(self):
phylesystem_studies_resp = OT.find_trees(bg_tax,
search_property='ot:ottId')
matches = [
study['ot:studyId'] for study in
phylesystem_studies_resp.response_dict['matched_studies']
]
assert 'ot_409' in matches
def test_find_chrono(self):
output = OT.find_trees(search_property="ot:branchLengthMode",
value="ot:time")
chronograms = set()
for study in output.response_dict["matched_studies"]:
study_id = study['ot:studyId']
for tree in study['matched_trees']:
tree_id = tree['ot:treeId']
chronograms.add('{}@{}'.format(study_id, tree_id))
assert 'ot_1000@tree1' in chronograms
def test_taxon_flag(self):
corr_url = 'https://github.com/OpenTreeOfLife/reference-taxonomy/wiki/Taxon-flags#flags-leading-to-taxa-being-unavailable-for-tnrs'
util.get_suppressed_taxon_flag_expl_url()
assert util.get_suppressed_taxon_flag_expl_url() == corr_url, util.get_suppressed_taxon_flag_expl_url()
assert util.ott_str_as_int('23') == 23
corr_ott_link = 'https://tree.opentreeoflife.org/taxonomy/browse?id=123'
assert util._create_link_from_node_info_conf_key_value_pair('ott', 123) == corr_ott_link
corr_study_link = 'https://tree.opentreeoflife.org/curator/study/view/ot_1979?tab=trees&tree=tree1&node=node5'
assert util._create_link_from_node_info_conf_key_value_pair('ot_1979@tree1', 'node5') == corr_study_link
blob = OT.synth_node_info(node_id='mrcaott354607ott374748').response_dict
util.write_node_info_links_to_input_trees(blob)
blob = OT.synth_node_info(node_id='mrcaott177ott29310').response_dict
util.write_node_info_links_to_input_trees(blob)
def _gather_broken_taxa_info(broken_response, label_format):
"""Gathers information about broken taxa in a synth tree call
Args:
broken_response: induced_subtree_response['broken']
label format: one of ['name', 'id', 'name_and_id']
Returns: (relabel, relabel_ott_ids, broken_dict)
where
relabel: {nodeid : [label_broken_tax1, label_broken_tax2]
relabel_ott_ids: {nodeid : [ottid_broken_tax1, ottid_broken_tax2]
broken_dict: {ottid_broken_tax1: {'url: url_to_taxonomy,
'MRCA_location_in_synth': nodeid1,
'broken_taxa_mapping_to_same_node': ottid_broken_tax2,
and all the other responses from OT.taxon_info, e.g.
'name': ott taxon name,
}
}
"""
broken_dict = {}
relabel = {}
relabel_ott_ids = {}
for taxon in broken_response:
remap = broken_response[taxon] # Where on the tree is that taxon now?
ott_id = taxon.strip('ott')
tax_inf = OT.taxon_info(ott_id=ott_id).response_dict
tax_inf['tax_url'] = "https://tree.opentreeoflife.org/taxonomy/browse?id={}".format(ott_id)
tax_inf['synth_url'] = "https://tree.opentreeoflife.org/opentree/argus/ottol@{}".format(ott_id)
tax_inf['MRCA_location_in_synth'] = remap
taxon_name = tax_inf.get('name', taxon)
if label_format == 'name':
taxon_label = "{}".format(taxon_name)
elif label_format == 'name_and_id':
taxon_label = "{}_{}".format(taxon_name, taxon)
else:
taxon_label = taxon
if remap not in relabel:
relabel[remap] = [] #Sometimes multiple taxa map to the same node or id
relabel_ott_ids[remap] = []
relabel[remap].append("{}".format(taxon_label))
relabel_ott_ids[remap].append(ott_id)
tax_inf['broken_taxa_mapping_to_same_node'] = relabel[remap]
broken_dict[ott_id] = tax_inf
return relabel, relabel_ott_ids, broken_dict
def _gather_unknown_taxa_info(unknown_ids):
"""Gathers taxon info for unknwon ids
Args:
unknown_ids: a list of unknown ott ids
Returns a dictionary containing:
unknown_dict: a dictionary with ott_ids as keys
value: dictionary containnig
full response of a taxon_info call
+ 'url': the link to the taxon in taxonomy browser
"""
unknown_dict = {}
for unk in unknown_ids:
uid = unk.strip('ott') #URL for taxonomy needs integer
tax_inf = OT.taxon_info(ott_id=uid).response_dict
tax_inf['url'] = "https://tree.opentreeoflife.org/taxonomy/browse?id={}".format(uid)
unknown_dict[unk] = tax_inf
return unknown_dict
def test_get_citations(self):
cites = OT.get_citations(studies=['ot_1000@tree1', 'ot_1984'])
def test_success_mixed_ids(self):
OT.synth_induced_tree(node_ids=['ott770315'], ott_ids=[417950])
def test_success_ott_ids(self):
OT.synth_induced_tree(ott_ids=[417950, 770315])
def test_taxon_mrca(self):
res = OT.taxon_mrca(ott_ids=[bos, h**o]).response_dict
assert res['mrca']['name'] == 'Boreoeutheria'
def test_taxon_subtree(self):
res = OT.taxon_subtree(ott_id=bos)
nwk = res.response_dict['newick']
assert isinstance(nwk, str)
curl = res.curl_call
tax = res.taxon
def test_properties(self):
properties = OT.studies_properties().response_dict
assert 'ot:curatorName', 'ot:curatorName' in properties[
'study_properties']
assert 'ot:ottid', 'ot:curatorName' in properties['tree_properties']
def test_get_otus(self):
res = OT.get_otus(study_id=study_id)
otu_dict = res.response_dict['otus1']['otuById']
assert len(otu_dict) == 45
def test_conflict(self):
res = OT.conflict_info(study_id=study_id,
tree_id=tree_id,
compare_to='synth')
assert 'node5' in res.response_dict
def test_matchdict(self):
matches, failed = OT.get_matchdict_from_taxlist(
['H**o', 'Bos', 'Meep'])
assert matches['Bos'] == 'ott{}'.format(bos)
assert 'Meep' in failed
def test_find_studies(self):
res = OT.find_studies("Ilex", "ot:focalCladeOTTTaxonName")
assert "ot_1984" in [
match['ot:studyId']
for match in res.response_dict["matched_studies"]
]
def test_subproblems_fail(self):
with self.assertRaises(OTWebServicesError):
## Bos is not in the synth tree
sol = OT.get_subproblem_solution('opentree12.3', bos)
sol_trees = OT.get_subproblem_trees('opentree12.3', bos)
rev_sol = OT.get_reversed_subproblem_solution('opentree12.3', bos)
def test_taxon_info(self):
res = OT.taxon_info(ott_id=bos).response_dict
assert 'Taurus' in res['synonyms']
def test_subproblems(self):
sol = OT.get_subproblem_solution('opentree12.3', h**o)
sol_trees = OT.get_subproblem_trees('opentree12.3', h**o)
rev_sol = OT.get_reversed_subproblem_solution('opentree12.3', h**o)
def test_int_ott_ids(self):
with self.assertRaises(ValueError):
OT.synth_induced_tree(ott_ids=["hi"])
def test_about(self):
ret = OT.about()
assert 'taxonomy_about', 'synth_tree_about' in ret
def test_success_node_ids(self):
OT.synth_induced_tree(node_ids=['ott417950', 'ott770315'])
def test_get_tree_newick(self):
res = OT.get_tree(study_id=study_id,
tree_id=tree_id,
tree_format='newick')
nwk = res.response_dict['content'].decode("utf-8")
assert isinstance(nwk, str)
def test_demands_id_arg(self):
with self.assertRaises(ValueError):
OT.synth_induced_tree()
def test_get_tree_bad_format(self):
with self.assertRaises(ValueError):
res = OT.get_tree(study_id=study_id,
tree_id=tree_id,
tree_format='newrk')