def get_dataset_from_treebase(study_id,
phylesystem_loc='api'):
ATT_list = []
nexson = get_nexson(study_id, phylesystem_loc)
treebase_url = nexson['nexml'][u'^ot:dataDeposit'][u'@href']
if 'treebase' not in nexson['nexml'][u'^ot:dataDeposit'][u'@href']:
sys.stderr("No treebase record associated with study ")
sys.exit()
else:
tb_id = treebase_url.split(':S')[1]
dna = DataSet.get(url="https://treebase.org/treebase-web/search/downloadAStudy.html?id={}&format=nexml".format(tb_id),
schema="nexml")
return(dna)
def get_dataset_from_treebase(study_id, phylesystem_loc="api"):
"""Function is used to get the aln from treebase, for a tree that OpenTree has the mapped tree.
"""
try:
nexson = get_nexson(study_id, phylesystem_loc)
except HTTPError as err:
sys.stderr.write(err)
sys.stderr.write(
"couldn't find study id {} in phylesystem location {}\n".format(
study_id, phylesystem_loc))
treebase_url = nexson['nexml'][u'^ot:dataDeposit'][u'@href']
if 'treebase' not in nexson['nexml'][u'^ot:dataDeposit'][u'@href']:
sys.stderr.write("No treebase record associated with study ")
sys.exit(-2)
else:
tb_id = treebase_url.split(':S')[1]
url = "https://treebase.org/treebase-web/search/downloadAStudy.html?id={}&format=nexml".format(
tb_id)
if _DEBUG:
sys.stderr.write(url + "\n")
dna = DataSet.get(url=url, schema="nexml")
return dna
def parse_nexus(nexus_loc):
""" Parses nexus file into a dictionary for template engine
Parameters
----------
nexus_loc: str
location of nexus file
Returns
-------
dict
dictionary containing tree in newick format, and a list of taxa containing their sequences, dates, and labels.
"""
return_dict = {"taxa": {}}
print("Parsing nexus file... ", end="")
nexus = DataSet.get(path=nexus_loc, schema="nexus")
return_dict["tree"] = nexus.tree_lists[0].as_string("newick")
count = 0
max_date = 2020.1
for k, v in nexus.char_matrices[0].items():
count += 1
date = parse_date(k.label)
if date > max_date:
max_date = date
taxa_dict = {"id": k.label, "date": date, "sequence": str(v)}
return_dict["taxa"][k.label] = taxa_dict
print("Done. {} taxa loaded".format(count))
return_dict["site_count"] = nexus.char_matrices[0].max_sequence_size
return_dict["taxon_count"] = len(return_dict["taxa"])
return_dict["cutoff"] = max_date - 2019.75
return_dict["grid_points"] = round(return_dict["cutoff"] * 52)
return return_dict
