def uwda_unit_tests(neu_id, umls_api_key):
user = User(umls_api_key=umls_api_key)
neu_anat = gnomics.objects.anatomical_structure.AnatomicalStructure(
identifier=neu_id, identifier_type="NEU ID", source="UMLS")
print("Getting UWDA IDs from NEU ID (%s):" % neu_id)
for uwda in get_uwda_id(neu_anat, user=user):
print("- " + str(uwda))
def snomed_unit_tests(hpo_id, umls_api_key):
user = User(umls_api_key=umls_api_key)
hpo_phen = gnomics.objects.compound.Compound(
identifier=str(hpo_id),
identifier_type="HPO ID",
source="Human Phenotype Ontology")
print("Getting SNOMED-CT IDs from HPO ID (%s):" % hpo_id)
for sno in get_snomed_ct_id(hpo_phen, user=user):
print("- " + str(sno))
def get_loc_sh(anat, user=None, source="umls"):
loc_array = []
for ident in anat.identifiers:
if ident["identifier_type"].lower() in ["lch", "lcsh", "library of congress sh", "library of congress subject heading", "loc sh"] and ident["identifier"] not in loc_array:
loc_array.append(ident["identifier"])
if loc_array:
return loc_array
for iden in anat.identifiers:
if iden["identifier_type"].lower() in ["neu", "neu id", "neu identifier", "neuronames brain hierarchy id", "neuronames brain hierarchy identifier"]:
if source.lower() in ["umls", "all"]:
anat_array = []
umls_tgt = User.umls_tgt(user)
page_num = 0
base = "https://uts-ws.nlm.nih.gov/rest"
ext = "/crosswalk/current/source/NEU/" + iden["identifier"]
while True:
tick = User.umls_st(umls_tgt)
page_num += 1
query = {"ticket": tick, "pageNumber": page_num}
r = requests.get(base+ext, params=query)
r.encoding = 'utf-8'
items = json.loads(r.text)
json_data = items["result"]
for rep in json_data:
if rep["ui"] not in loc_array and rep["ui"] != "NONE":
# Library of Congress.
if rep["rootSource"] == "LCH":
loc_array.append(rep["ui"])
gnomics.objects.anatomical_structure.AnatomicalStructure.add_identifier(anat, identifier=rep["ui"], identifier_type="Library of Congress Subject Heading", language=None, source="UMLS Metathesaurus")
if not json_data:
break
return loc_array
def formula_unit_tests(chemspider_id, pubchem_cid, chemspider_security_token):
if chemspider_security_token is not None:
print("Creating user...")
user = User(chemspider_security_token=chemspider_security_token)
print("User created successfully.\n")
chemspider_com = gnomics.objects.compound.Compound(
identifier=str(chemspider_id),
identifier_type="ChemSpider ID",
source="ChemSpider")
print("\nGetting molecular formula from ChemSpider ID (%s):" %
chemspider_id)
start = timeit.timeit()
molec_array = get_molecular_formula(chemspider_com, user=user)
end = timeit.timeit()
print("\tTIME ELAPSED: %s seconds." % str(end - start))
print("\tRESULTS:")
for com in molec_array:
print("\t- %s" % str(com))
pubchem_com = gnomics.objects.compound.Compound(
identifier=str(pubchem_cid),
identifier_type="PubChem CID",
source="PubChem")
print("\nGetting molecular formula from PubChem CID (%s):" %
pubchem_cid)
start = timeit.timeit()
molec_array = get_molecular_formula(pubchem_com)
end = timeit.timeit()
print("\tTIME ELAPSED: %s seconds." % str(end - start))
print("\tRESULTS:")
for com in molec_array:
print("\t- %s" % str(com))
else:
print(
"No user provided. Cannot test ChemSpider conversion without ChemSpider security token.\n"
)
print("Continuing with PubChem CID conversion...\n")
pubchem_com = gnomics.objects.compound.Compound(
identifier=str(pubchem_cid),
identifier_type="PubChem CID",
source="PubChem")
print("\nGetting molecular formula from PubChem CID (%s):" %
pubchem_cid)
start = timeit.timeit()
molec_array = get_molecular_formula(pubchem_com)
end = timeit.timeit()
print("\tTIME ELAPSED: %s seconds." % str(end - start))
print("\tRESULTS:")
for com in molec_array:
print("\t- %s" % str(com))
def vernacular_name_unit_tests(eol_id, eol_api_key=None):
print("Creating user...")
user = User(eol_api_key=eol_api_key)
print("User created successfully.\n")
eol_tax = gnomics.objects.taxon.Taxon(identifier=str(eol_id),
identifier_type="EOL ID",
source="EOL")
print("Getting EOL object from EOL ID (%s):" % eol_id)
for iden in get_vernacular_names(eol_tax):
print("- %s" % iden)
def chemspider_unit_tests(inchi_id, chemspider_security_token):
user = User(chemspider_security_token=chemspider_security_token)
inchi_compound = gnomics.objects.compound.Compound(identifier = str(inchi_id), identifier_type = "InChi", source = "PubChem")
print("Getting ChemSpider ID from InChI (%s):" % inchi_id)
start = timeit.timeit()
cs_array = get_chemspider_id(inchi_compound, user = user)
end = timeit.timeit()
print("\tTIME ELAPSED: %s seconds." % str(end - start))
print("\tRESULTS:")
for com in cs_array:
print("\t- %s" % str(com))
def reference_pathway_unit_tests(pmid, openphacts_app_id, openphacts_app_key):
user = User(openphacts_app_id=openphacts_app_id,
openphacts_app_key=openphacts_app_key)
pm_ref = gnomics.objects.reference.Reference(identifier=pmid,
identifier_type="PubMed ID",
source="OpenPHACTS")
print("\nGetting pathway identifiers from PubMed ID (%s):" % pmid)
for path in get_pathways(pm_ref, user=user):
for iden in path.identifiers:
print("- %s (%s)" %
(str(iden["identifier"]), iden["identifier_type"]))
def drug_gene_unit_tests(drugbank_id, openphacts_app_id, openphacts_app_key):
user = User(openphacts_app_id = openphacts_app_id, openphacts_app_key = openphacts_app_key)
drugbank_drug = gnomics.objects.drug.Drug(identifier = drugbank_id, identifier_type = "DrugBank ID", source = "OpenPHACTS")
start = timeit.timeit()
all_genes = get_genes(drugbank_drug, user = user)
end = timeit.timeit()
print("TIME ELAPSED: %s seconds." % str(end - start))
for gene in all_genes:
for iden in gene.identifiers:
if iden["identifier_type"] == "HGNC Approved Symbol":
print("- %s (%s)" % (iden["identifier"], iden["identifier_type"]))
def basic_search_unit_tests(basic_query, umls_api_key, ncbo_api_key):
print("Beginning basic search for '%s'..." % basic_query)
basic_search_results = search(basic_query, source="ebi")
print(
"\nSearch returned %s result(s) with the following identifiers (EBI):"
% str(len(basic_search_results)))
for anat in basic_search_results:
for iden in anat.identifiers:
print("- %s: %s (%s)" %
(iden["identifier"], iden["name"], iden["identifier_type"]))
user = User(umls_api_key=umls_api_key)
start = timeit.timeit()
basic_search_results = search(basic_query, source="umls", user=user)
end = timeit.timeit()
print("TIME ELAPSED: %s seconds." % str(end - start))
print(
"\nSearch returned %s result(s) with the following identifiers (UMLS):"
% str(len(basic_search_results)))
for anat in basic_search_results:
for iden in anat.identifiers:
print("- %s: %s (%s)" %
(iden["identifier"], iden["name"], iden["identifier_type"]))
user = User(ncbo_api_key=ncbo_api_key)
start = timeit.timeit()
basic_search_results = search(basic_query, source="ncbo", user=user)
end = timeit.timeit()
print("TIME ELAPSED: %s seconds." % str(end - start))
print(
"\nSearch returned %s result(s) with the following identifiers (NCBO):"
% str(len(basic_search_results)))
for anat in basic_search_results:
for iden in anat.identifiers:
print("- %s: %s (%s)" %
(iden["identifier"], iden["name"], iden["identifier_type"]))
def mesh_unit_tests(meddra_id, umls_api_key, ncbo_api_key):
user = User(umls_api_key=umls_api_key, ncbo_api_key=ncbo_api_key)
meddra_ae = gnomics.objects.adverse_event.AdverseEvent(
identifier=meddra_id, identifier_type="MedDRA ID", source="UMLS")
print("Getting MeSH UIDs from MedDRA ID (%s):" % meddra_id)
start = timeit.timeit()
mesh_array = get_mesh_uid(meddra_ae, user=user)
end = timeit.timeit()
print("\tTIME ELAPSED: %s seconds." % str(end - start))
print("\tRESULTS:")
for mesh in mesh_array:
print("\t- %s" % str(mesh))
def icd10_unit_tests(kegg_disease_id,
omim_disease_id,
doid,
omim_api_key=None):
if omim_api_key is not None:
print("Creating user...")
user = User(omim_api_key=omim_api_key)
print("User created successfully.\n")
omim_disease = gnomics.objects.disease.Disease(
identifier=str(omim_disease_id),
identifier_type="MIM Number",
source="OMIM")
print("Getting ICD-10-CM IDs from MIM Number (%s):" % omim_disease_id)
for icd in get_icd10(omim_disease, user=user):
print("- " + str(icd))
kegg_disease = gnomics.objects.disease.Disease(
identifier=str(kegg_disease_id),
identifier_type="KEGG Disease ID",
source="KEGG")
print("\nGetting ICD-10-CM IDs from KEGG Disease ID (%s):" %
kegg_disease_id)
for icd10 in get_icd10(kegg_disease):
print("- " + str(icd10))
doid_dis = gnomics.objects.disease.Disease(identifier=str(doid),
identifier_type="DOID",
source="Disease Ontology")
print("\nGetting ICD-10-CM IDs from DOID (%s):" % doid)
for icd10 in get_icd10(doid_dis):
print("- " + str(icd10))
else:
kegg_disease = gnomics.objects.disease.Disease(
identifier=str(kegg_disease_id),
identifier_type="KEGG Disease ID",
source="KEGG")
print("\nGetting ICD-10-CM IDs from KEGG Disease ID (%s):" %
kegg_disease_id)
for icd10 in get_icd10(kegg_disease):
print("- " + str(icd10))
doid_dis = gnomics.objects.disease.Disease(identifier=str(doid),
identifier_type="DOID",
source="Disease Ontology")
print("\nGetting ICD-10-CM IDs from DOID (%s):" % doid)
for icd10 in get_icd10(doid_dis):
print("- " + str(icd10))
def tissue_protein_unit_tests(caloha_id, openphacts_app_id,
openphacts_app_key):
user = User(openphacts_app_id=openphacts_app_id,
openphacts_app_key=openphacts_app_key)
caloha_tiss = gnomics.objects.tissue.Tissue(identifier=caloha_id,
identifier_type="CALOHA ID",
source="OpenPHACTS")
print("\nGetting protein identifiers from CALOHA identifier (%s):" %
caloha_id)
for prot in get_proteins(caloha_tiss, user=user):
for iden in prot.identifiers:
print("- %s (%s)" %
(str(iden["identifier"]), iden["identifier_type"]))
def psy_unit_tests(neu_id, uwda_id, umls_api_key):
user = User(umls_api_key=umls_api_key)
neu_anat = gnomics.objects.anatomical_structure.AnatomicalStructure(
identifier=neu_id, identifier_type="NEU ID", source="UMLS")
print("Getting PSY ID from NEU ID (%s):" % neu_id)
for psy in get_psy(neu_anat, user=user):
print("- " + str(psy))
uwda_anat = gnomics.objects.anatomical_structure.AnatomicalStructure(
identifier=uwda_id, identifier_type="UWDA ID", source="UMLS")
print("\nGetting PSY ID from UWDA ID (%s):" % uwda_id)
for psy in get_psy(uwda_anat, user=user):
print("- " + str(psy))
def basic_search_unit_tests(basic_query, umls_api_key):
user = User(umls_api_key=umls_api_key)
print("Beginning basic searches for '%s'..." % basic_query)
start = timeit.timeit()
basic_search_results = search(basic_query, user, search_type="exact")
end = timeit.timeit()
print("TIME ELAPSED: %s seconds." % str(end - start))
print(
"\nSearch returned %s exact result(s) with the following procedure identifiers:"
% str(len(basic_search_results)))
for proc in basic_search_results:
for iden in proc.identifiers:
print("- %s (%s)" % (iden["identifier"], iden["identifier_type"]))
def snomed_unit_tests(neu_id, uwda_id, umls_api_key):
user = User(umls_api_key=umls_api_key)
neu_anat = gnomics.objects.anatomical_structure.AnatomicalStructure(
identifier=neu_id, identifier_type="NEU ID", source="UMLS")
print("Getting SNOMED identifiers from NEU ID (%s):" % neu_id)
for snomed in get_snomed(neu_anat, user=user):
print("- " + str(snomed))
uwda_anat = gnomics.objects.anatomical_structure.AnatomicalStructure(
identifier=uwda_id, identifier_type="UWDA ID", source="UMLS")
print("\nGetting SNOMED identifiers from UWDA ID (%s):" % uwda_id)
for snomed in get_snomed(uwda_anat, user=user):
print("- " + str(snomed))
def cid_unit_tests(chemspider_id, kegg_compound_id, wikidata_accession, chemspider_security_token=None):
if chemspider_security_token is not None:
print("\nCreating user...")
user = User(chemspider_security_token = chemspider_security_token)
print("User created successfully.\n")
chemspider_com = gnomics.objects.compound.Compound(identifier = str(chemspider_id), identifier_type = "ChemSpider ID", source = "ChemSpider")
print("Getting PubChem CID from ChemSpider ID (%s):" % chemspider_id)
start = timeit.timeit()
cid_array = get_pubchem_cids(chemspider_com, user = user)
end = timeit.timeit()
print("\tTIME ELAPSED: %s seconds." % str(end - start))
print("\tRESULTS:")
for com in cid_array:
print("\t- %s" % str(com))
kegg_com = gnomics.objects.compound.Compound(identifier = str(kegg_compound_id), identifier_type = "KEGG Compound ID", source = "KEGG")
print("\nGetting PubChem CID from KEGG Compound ID (%s):" % kegg_compound_id)
start = timeit.timeit()
cid_array = get_pubchem_cids(kegg_com, user = user)
end = timeit.timeit()
print("\tTIME ELAPSED: %s seconds." % str(end - start))
print("\tRESULTS:")
for com in cid_array:
print("\t- %s" % str(com))
wikidata_com = gnomics.objects.compound.Compound(identifier = str(wikidata_accession), identifier_type = "Wikidata Accession", source = "Wikidata")
print("\nGetting PubChem CID from Wikidata Accession (%s):" % wikidata_accession)
start = timeit.timeit()
cid_array = get_pubchem_cids(wikidata_com)
end = timeit.timeit()
print("\tTIME ELAPSED: %s seconds." % str(end - start))
print("\tRESULTS:")
for com in cid_array:
print("\t- %s" % str(com))
else:
print("No user provided. Cannot test ChemSpider conversion without ChemSpider security token.\n")
print("Continuing with KEGG Compound conversion...\n")
kegg_com = gnomics.objects.compound.Compound(identifier = str(kegg_compound_id), identifier_type = "KEGG Compound ID", source = "KEGG")
print("Getting PubChem CID from KEGG Compund ID (%s):" % kegg_compound_id)
start = timeit.timeit()
cid_array = get_pubchem_cids(kegg_com)
end = timeit.timeit()
print("\tTIME ELAPSED: %s seconds." % str(end - start))
print("\tRESULTS:")
for com in cid_array:
print("\t- %s" % str(com))
def basic_search_unit_tests(basic_query, email):
user = User(email=email)
print("Beginning basic searches for '%s'..." % basic_query)
start = timeit.timeit()
basic_search_results = search(basic_query, source="all", user=user)
end = timeit.timeit()
print("TIME ELAPSED: %s seconds." % str(end - start))
print(
"\nEntrez search returned %s result(s) with the following identifiers:"
% str(len(basic_search_results)))
for ent in basic_search_results:
for iden in ent.identifiers:
print("- %s: %s (%s) [%s]" %
(iden["identifier"], iden["name"], iden["identifier_type"],
iden["taxon"]))
def rcd_unit_tests(neu_id, uwda_id, umls_api_key):
user = User(umls_api_key=umls_api_key)
neu_anat = gnomics.objects.anatomical_structure.AnatomicalStructure(
identifier=neu_id, identifier_type="NEU ID", source="UMLS")
print("Getting read codes from NEU ID (%s):" % neu_id)
for rcd in get_read_codes(neu_anat, user=user):
print("- " + str(rcd))
uwda_anat = gnomics.objects.anatomical_structure.AnatomicalStructure(
identifier=uwda_id, identifier_type="UWDA ID", source="UMLS")
print("\nGetting read codes from UWDA ID (%s):" % uwda_id)
for rcd in get_read_codes(uwda_anat, user=user):
print("- " + str(rcd))
def conceptwiki_unit_tests(conceptwiki_id, chemspider_id, chembl_id,
schembl_id, openphacts_app_id, openphacts_app_key):
user = User(openphacts_app_id=openphacts_app_id,
openphacts_app_key=openphacts_app_key)
conceptwiki_com = gnomics.objects.compound.Compound(
identifier=conceptwiki_id,
identifier_type="ConceptWiki ID",
source="OpenPHACTS")
chemspider_com = gnomics.objects.compound.Compound(
identifier=chemspider_id,
identifier_type="ChemSpider ID",
source="OpenPHACTS")
print("Getting ConceptWiki IDs from ChemSpider ID (%s):" % chemspider_id)
start = timeit.timeit()
conceptwiki_array = get_conceptwiki_id(chemspider_com, user=user)
end = timeit.timeit()
print("\tTIME ELAPSED: %s seconds." % str(end - start))
print("\tRESULTS:")
for com in conceptwiki_array:
print("\t- %s" % str(com))
chembl_com = gnomics.objects.compound.Compound(identifier=chembl_id,
identifier_type="ChEMBL ID",
source="OpenPHACTS")
print("\nGetting ConceptWiki IDs from ChEMBL ID (%s):" % chembl_id)
start = timeit.timeit()
conceptwiki_array = get_conceptwiki_id(chembl_com, user=user)
end = timeit.timeit()
print("\tTIME ELAPSED: %s seconds." % str(end - start))
print("\tRESULTS:")
for com in conceptwiki_array:
print("\t- %s" % str(com))
schembl_com = gnomics.objects.compound.Compound(
identifier=schembl_id,
identifier_type="SCHEMBL ID",
source="OpenPHACTS")
print("\nGetting ConceptWiki IDs from SCHEMBL ID (%s):" % schembl_id)
start = timeit.timeit()
conceptwiki_array = get_conceptwiki_id(schembl_com, user=user)
end = timeit.timeit()
print("\tTIME ELAPSED: %s seconds." % str(end - start))
print("\tRESULTS:")
for com in conceptwiki_array:
print("\t- %s" % str(com))
def drug_adverse_event_unit_tests(rxcui, fda_api_key):
user = User(fda_api_key=fda_api_key)
rx_com = gnomics.objects.compound.Compound(identifier=str(rxcui),
identifier_type="RxCUI",
source="RxNorm")
print("Getting adverse events from RxCUI (%s):" % rxcui)
start = timeit.timeit()
all_aes = get_adverse_events(rx_com,
user=user,
exact=False,
counts=True,
details=False)
end = timeit.timeit()
print("TIME ELAPSED: %s seconds." % str(end - start))
for ae_name, ae_count in all_aes.items():
print("- %s: %s" % (ae_name, str(ae_count)))
def aids_unit_tests(pubchem_aid, bioassay_id, openphacts_app_id,
openphacts_app_key):
assay = gnomics.objects.assay.Assay(identifier=pubchem_aid,
identifier_type="PubChem AID",
language=None,
source="PubChem")
print(get_pubchem_assay(assay))
user = User(openphacts_app_id=openphacts_app_id,
openphacts_app_key=openphacts_app_key)
bio_assay = gnomics.objects.assay.Assay(identifier=bioassay_id,
identifier_type="OIDD Bioassay ID",
source="OIDD")
print("\nGetting PubChem AIDs from OIDD Bioassay ID (%s):" % bioassay_id)
for iden in get_aids(bio_assay, user=user):
print("- %s" % iden)
def basic_search_unit_tests(basic_query, ncbo_api_key):
user = User(ncbo_api_key=ncbo_api_key)
print("Beginning basic search for '%s'..." % basic_query)
start = timeit.timeit()
basic_search_results = search(basic_query, source="all", user=user)
end = timeit.timeit()
print("TIME ELAPSED: %s seconds." % str(end - start))
print("\nSearch returned %s result(s) with the following identifiers:" %
str(len(basic_search_results)))
for ae in basic_search_results:
for iden in ae.identifiers:
print("- %s (%s) [%s]" %
(iden["identifier"], iden["name"], iden["identifier_type"]))
def drug_compound_unit_tests(drugbank_id, openphacts_app_id,
openphacts_app_key):
user = User(openphacts_app_id=openphacts_app_id,
openphacts_app_key=openphacts_app_key)
drugbank_drug = gnomics.objects.drug.Drug(identifier=drugbank_id,
identifier_type="DrugBank ID",
source="OpenPHACTS")
start = timeit.timeit()
all_coms = get_compounds(drugbank_drug, user=user)
end = timeit.timeit()
print("TIME ELAPSED: %s seconds." % str(end - start))
print("\nGetting compound identifiers from DrugBank ID (%s):" %
drugbank_id)
for com in all_coms:
for iden in com.identifiers:
print("- %s (%s)" %
(str(iden["identifier"]), iden["identifier_type"]))
def adverse_event_phenotype_unit_tests(meddra_term, umls_api_key,
ncbo_api_key):
user = User(umls_api_key=umls_api_key, ncbo_api_key=ncbo_api_key)
print("\nGetting HPO IDs from MedDRA Term (%s):" % meddra_term)
meddra_ae = gnomics.objects.adverse_event.AdverseEvent(
identifier=meddra_term,
identifier_type="MedDRA Term",
source="UMLS",
language="en")
start = timeit.timeit()
phenotypes = get_phenotypes(meddra_ae, user=user)
end = timeit.timeit()
print("TIME ELAPSED: %s seconds." % str(end - start))
for phen in phenotypes:
for iden in phen.identifiers:
print("- %s (%s)" %
(str(iden["identifier"]), iden["identifier_type"]))
def uberon_unit_tests(caloha_id, bto_id, openphacts_app_id, openphacts_app_key,
ncbo_api_key):
user = User(openphacts_app_id=openphacts_app_id,
openphacts_app_key=openphacts_app_key,
ncbo_api_key=ncbo_api_key)
caloha_tiss = gnomics.objects.tissue.Tissue(identifier=caloha_id,
identifier_type="CALOHA ID",
source="OpenPHACTS")
print("Getting UBERON IDs from CALOHA ID (%s):" % caloha_id)
for uberon in get_uberon_id(caloha_tiss, user=user):
print("- %s" % uberon)
bto_tiss = gnomics.objects.tissue.Tissue(identifier=bto_id,
identifier_type="BTO ID",
source="OpenPHACTS")
print("\nGetting UBERON IDs from BTO ID (%s):" % bto_id)
for uberon in get_uberon_id(bto_tiss, user=user):
print("- %s" % uberon)
def doid_unit_tests(omim_disease_id, doid, omim_api_key=None):
if omim_api_key is not None:
print("Creating user...")
user = User(omim_api_key=omim_api_key)
print("User created successfully.\n")
omim_disease = gnomics.objects.disease.Disease(
identifier=str(omim_disease_id),
identifier_type="MIM Number",
source="OMIM")
print("Getting Disease Ontology IDs from MIM Number (%s):" %
omim_disease_id)
for sno in get_doid(omim_disease, user=user):
print("- " + str(sno))
doid_dis = gnomics.objects.disease.Disease(identifier=str(doid),
identifier_type="DOID",
source="Disease Ontology")
print("\nGetting DO terms from Disease Ontology ID (%s):" % doid)
for term in get_do_terms(doid_dis):
print("- " + str(term))
def disease_patent_unit_tests(mesh_uid, openphacts_app_id, openphacts_app_key):
user = User(openphacts_app_id=openphacts_app_id,
openphacts_app_key=openphacts_app_key)
mesh_disease = gnomics.objects.disease.Disease(identifier=mesh_uid,
identifier_type="MeSH UID",
source="OpenPHACTS")
print("\nGetting patent identifiers from MeSH UID (%s):" % mesh_uid)
for pat in get_patents(mesh_disease, user=user):
print(pat)
start = timeit.timeit()
all_pats = get_patents(mesh_disease, user=user, count_only=True)
end = timeit.timeit()
print("TIME ELAPSED: %s seconds." % str(end - start))
print("\nGetting number of patent identifiers from MeSH UID (%s):" %
mesh_uid)
for pat in all_pats:
print("- %s" % str(pat))
def reference_person_unit_tests(pmid, doi, orcid_client_id,
orcid_client_secret, elsevier_api_key):
user = User(elsevier_api_key=elsevier_api_key)
pubmed_ref = gnomics.objects.reference.Reference(identifier=pmid,
identifier_type="PMID",
language=None,
source="PubMed")
print("Getting authors from PMID (%s):" % pmid)
for auth in get_authors(pubmed_ref, user=user):
for iden in auth.identifiers:
print("- %s (%s)" %
(str(iden["identifier"]), iden["identifier_type"]))
doi_ref = gnomics.objects.reference.Reference(identifier=doi,
identifier_type="DOI",
language=None,
source="Nature")
print("\nGetting authors from DOI (%s):" % doi)
for auth in get_authors(doi_ref, user=user):
for iden in auth.identifiers:
print("- %s (%s)" %
(str(iden["identifier"]), iden["identifier_type"]))
def fma_unit_tests(neu_id, uwda_id, wikidata_accession, umls_api_key):
user = User(umls_api_key=umls_api_key)
neu_anat = gnomics.objects.anatomical_structure.AnatomicalStructure(
identifier=neu_id, identifier_type="NEU ID", source="UMLS")
print("Getting FMA ID from NEU ID (%s):" % neu_id)
for fma in get_fma_id(neu_anat, user=user):
print("- " + str(fma))
uwda_anat = gnomics.objects.anatomical_structure.AnatomicalStructure(
identifier=uwda_id, identifier_type="UWDA ID", source="UMLS")
print("\nGetting FMA ID from UWDA ID (%s):" % uwda_id)
for fma in get_fma_id(uwda_anat, user=user):
print("- " + str(fma))
wikidata_anat = gnomics.objects.anatomical_structure.AnatomicalStructure(
identifier=wikidata_accession,
identifier_type="Wikidata Accession",
language=None,
source="Wikidata")
print("\nGetting FMA ID from Wikidata Accession (%s):" %
wikidata_accession)
for fma in get_fma_id(wikidata_anat):
print("- %s" % fma)
def umls_crosswalk(user,
from_source,
to_source,
source_id,
other="id",
verbose=False):
found_array = []
if user is None:
print(
"A valid user object with a valid UMLS API key is required for this function."
)
return found_array
elif user.umls_api_key is None:
print(
"A valid UMLS API key associated with the user object is required for this function."
)
return found_array
umls_tgt = User.umls_tgt(user)
page_num = 0
base = "https://uts-ws.nlm.nih.gov/rest"
ext = "/crosswalk/current/source/" + from_source.upper() + "/" + source_id
verbose = True
while True:
tick = User.umls_st(umls_tgt)
page_num += 1
query = {"ticket": tick, "pageNumber": page_num}
try:
r = requests.get(
base + ext,
params=query,
headers={
"Content-Type":
"application/json",
"User-Agent":
"Mozilla/5.0 (Windows NT 6.0; WOW64; rv:24.0) Gecko/20100101 Firefox/24.0"
})
r.encoding = 'utf-8'
try:
items = json.loads(r.text)
json_data = items["result"]
empty = False
for rep in json_data:
if other == "id":
if rep["ui"] not in found_array and rep["ui"] != "NONE":
if rep["rootSource"] == to_source.upper():
found_array.append(rep["ui"])
elif other == "name":
if (rep["name"] not in found_array and rep["name"] !=
"NONE") and (rep["ui"] not in found_array
and rep["ui"] != "NONE"):
if rep["rootSource"] == to_source.upper():
found_array.append((rep["ui"], rep["name"]))
else:
print(
"This value for 'other' is not currently supported."
)
if "results" in json_data:
if json_data["results"][0]["ui"] == "NONE":
empty = True
break
if not json_data:
break
elif empty:
break
except ValueError as e:
if verbose:
print(
"A value error occurred while attempting to load resulting JSON."
)
print("ERROR: %s" % str(e))
break
except:
if verbose:
print("Some other unknown error occurred.")
break
else:
continue
except ConnectionError as e:
if verbose:
print("A connection error occurred while attempting request.")
print("ERROR: %s" % str(e))
break
except requests.exceptions.ConnectionError as e:
if verbose:
print("A connection error occurred while attempting request.")
print("ERROR: %s" % str(e))
break
except HTTPException as e:
if verbose:
print(
"An HTTP exception error occurred while attempting request."
)
print("ERROR: %s" % str(e))
break
except ProtocolError as e:
if verbose:
print("A protocol error occurred while attempting request.")
print("ERROR: %s" % str(e))
break
except urllib3.exceptions.ProtocolError as e:
if verbose:
print("A protocol error occurred while attempting request.")
print("ERROR: %s" % str(e))
break
except SysCallError as e:
if verbose:
print("A system call error occurred while attempting request.")
print("ERROR: %s" % str(e))
break
except OpenSSL.SSL.SysCallError as e:
if verbose:
print("A system call error occurred while attempting request.")
print("ERROR: %s" % str(e))
break
except ssl.SSLError as e:
if verbose:
print("A system call error occurred while attempting request.")
print("ERROR: %s" % str(e))
break
except SSLError as e:
if verbose:
print("A SSL error occurred while attempting request.")
print("ERROR: %s" % str(e))
break
except requests.exceptions.SSLError as e:
if verbose:
print("A SSL error occurred while attempting request.")
print("ERROR: %s" % str(e))
break
except BadStatusLine as e:
if verbose:
print(
"A bad status line error occurred while attempting request."
)
print("ERROR: %s" % str(e))
break
except httplib.BadStatusLine as e:
if verbose:
print(
"A bad status line error occurred while attempting request."
)
print("ERROR: %s" % str(e))
break
except http.client.BadStatusLine as e:
if verbose:
print("A protocol error occurred while attempting request.")
print("ERROR: %s" % str(e))
break
except MaxRetryError as e:
if verbose:
print("A max retry error occurred while attempting request.")
print("ERROR: %s" % str(e))
break
except urllib3.exceptions.MaxRetryError as e:
if verbose:
print("A max retry error occurred while attempting request.")
print("ERROR: %s" % str(e))
break
except:
print("Some other HTTP/URL error encountered.")
break
else:
break
return found_array
def get_snomed_ct_id(phen, user = None):
if user is not None:
umls_tgt = User.umls_tgt(user)
phen_array = []
for ident in phen.identifiers:
if ident["identifier_type"].lower() in ["sct id", "sct identifier", "sctid", "snomed ct", "snomed ct concept id", "snomed id", "snomed identifier", "snomed-ct", "snomed-ct concept id", "snomed-ct id", "snomed-ct identifier"]:
phen_array.append(ident["identifier"])
if phen_array:
return phen_array
ids_completed = []
for ident in phen.identifiers:
if (ident["identifier_type"].lower() in ["hp code", "hp id", "hp identifier", "hpo code", "hpo id", "hpo identifier", "human phenotype ontology code", "human phenotype ontology id", "human phenotype ontology identifier", "hp", "hpo", "human phenotype ontology"]) and user is not None:
stringy = ident["identifier"]
page_num = 0
base = "https://uts-ws.nlm.nih.gov/rest"
ext = "/crosswalk/current/source/HPO/" + ident["identifier"] + "?targetSource=SNOMEDCT_US"
while True:
tick = User.umls_st(umls_tgt)
page_num += 1
query = {"ticket": tick, "pageNumber": page_num}
r = requests.get(base+ext, params=query)
r.encoding = 'utf-8'
items = json.loads(r.text)
json_data = items["result"]
for er in json_data:
if er["ui"] not in phen_array and er["ui"] != "NONE":
snomedct = er["ui"]
phen_array.append(snomedct)
if not json_data:
break
elif (ident["identifier_type"].lower() in ["hp code", "hp id", "hp identifier", "hpo code", "hpo id", "hpo identifier", "human phenotype ontology code", "human phenotype ontology id", "human phenotype ontology identifier", "hp", "hpo", "human phenotype ontology"]) and user is None:
if ident["identifier"] not in ids_completed:
ids_completed.append(ident["identifier"])
hpo_id = ident["identifier"]
if ":" in hpo_id:
hpo_id = hpo_id.replace(":", "_")
url = "https://www.ebi.ac.uk/ols/api/ontologies"
ext = "/hp/terms/http%253A%252F%252Fpurl.obolibrary.org%252Fobo%252F" + hpo_id
r = requests.get(url+ext, headers={"Content-Type": "application/json"})
if not r.ok:
print("Something went wrong.")
else:
decoded = r.json()
for xref in decoded["annotation"]["database_cross_reference"]:
if "SNOMEDCT_US:" in xref:
snomed_id = xref.split("SNOMEDCT_US:")[1]
phen_array.append(snomed_id)
gnomics.objects.phenotype.Phenotype.add_identifier(phen, identifier = snomed_id, identifier_type = "SNOMED-CT ID", source = "OLS")
return phen_array
def get_aod(anat, user=None, source="umls"):
aod_array = []
for iden in gnomics.objects.auxiliary_files.identifier.filter_identifiers(anat.identifiers, ["alcohol and other drug", "alcohol and other drug id", "alcohol and other drug identifier", "aod", "aod id", "aod identifier"]):
if iden["identifier"] not in aod_array:
aod_array.append(iden["identifier"])
if aod_array:
return aod_array
ids_completed = []
for iden in gnomics.objects.auxiliary_files.identifier.filter_identifiers(anat.identifiers, ["neu id", "neu identifier", "neuronames brain hierarchy id", "neuronames brain hierarchy identifier", "neu"]):
if iden["identifier"] not in ids_completed and user is not None:
ids_completed.append(iden["identifier"])
if source.lower() in ["umls", "all"]:
umls_tgt = User.umls_tgt(user)
page_num = 0
base = "https://uts-ws.nlm.nih.gov/rest"
ext = "/crosswalk/current/source/NEU/" + str(iden["identifier"])
while True:
tick = User.umls_st(umls_tgt)
page_num += 1
query = {"ticket": tick, "pageNumber": page_num}
r = requests.get(base+ext, params=query)
r.encoding = 'utf-8'
items = json.loads(r.text)
json_data = items["result"]
for rep in json_data:
if rep["ui"] != "NONE":
# AOD ID.
if rep["rootSource"] == "AOD" and rep["ui"] not in aod_array:
aod_array.append(rep["ui"])
gnomics.objects.anatomical_structure.AnatomicalStructure.add_identifier(anat, identifier=rep["ui"], identifier_type="AOD ID", language=None, source="UMLS Metathesaurus")
if not json_data:
break
for iden in gnomics.objects.auxiliary_files.identifier.filter_identifiers(anat.identifiers, ["uwda", "uwda id", "uwda identifier"]):
if iden["identifier"] not in ids_completed and user is not None:
ids_completed.append(iden["identifier"])
if source.lower() in ["umls", "all"]:
umls_tgt = User.umls_tgt(user)
page_num = 0
base = "https://uts-ws.nlm.nih.gov/rest"
ext = "/crosswalk/current/source/UWDA/" + str(iden["identifier"])
while True:
tick = User.umls_st(umls_tgt)
page_num += 1
query = {"ticket": tick, "pageNumber": page_num}
r = requests.get(base+ext, params=query)
r.encoding = 'utf-8'
items = json.loads(r.text)
json_data = items["result"]
for rep in json_data:
if rep["ui"] != "NONE":
# AOD ID.
if rep["rootSource"] == "AOD" and rep["ui"] not in aod_array:
aod_array.append(rep["ui"])
gnomics.objects.anatomical_structure.AnatomicalStructure.add_identifier(anat, identifier=rep["ui"], identifier_type="AOD ID", language=None, source="UMLS Metathesaurus")
if not json_data:
break
return aod_array
def get_mesh_uid(phen, user=None):
mesh_array = []
for ident in phen.identifiers:
if ident["identifier_type"].lower() in ["mesh", "mesh uid", "mesh unique id", "mesh unique identifier", "msh", "msh uid", "msh unique id", "msh unique identifier"]:
if ident["identifier"] not in mesh_array:
mesh_array.append(ident["identifier"])
if mesh_array:
return mesh_array
meddra_array = []
ids_completed = []
for ident in phen.identifiers:
if ident["identifier_type"].lower() in ["mdr", "mdr code", "mdr id", "mdr identifier", "meddra", "meddra code", "meddra id", "meddra identifier"]:
if user is not None:
if ident["identifier"] not in meddra_array:
umls_tgt = User.umls_tgt(user)
page_num = 0
base = "https://uts-ws.nlm.nih.gov/rest"
ext = "/crosswalk/current/source/MDR/" + str(ident["identifier"]) + "?targetSource=MSH"
while True:
tick = User.umls_st(umls_tgt)
page_num += 1
query = {"string": ident["identifier"], "ticket": tick, "pageNumber": page_num}
r = requests.get(base+ext, params=query)
r.encoding = 'utf-8'
try:
items = json.loads(r.text)
json_data = items["result"]
empty = False
for rep in json_data:
if rep["ui"] not in mesh_array and rep["ui"] != "NONE":
gnomics.objects.phenotype.Phenotype.add_identifier(phen, identifier = rep["ui"], identifier_type = "MeSH ID", source = "UMLS")
mesh_array.append(rep["ui"])
if "ui" not in rep and not rep["result"]:
empty = True
break
if not json_data:
break
if empty:
break
except:
break
break
meddra_array.append(ident["identifier"])
elif ident["identifier_type"].lower() in ["hp code", "hp id", "hp identifier", "hpo code", "hpo id", "hpo identifier", "human phenotype ontology code", "human phenotype ontology id", "human phenotype ontology identifier", "hp", "hpo", "human phenotype ontology"]:
if ident["identifier"] not in ids_completed:
ids_completed.append(ident["identifier"])
hpo_id = ident["identifier"]
if ":" in hpo_id:
hpo_id = hpo_id.replace(":", "_")
url = "https://www.ebi.ac.uk/ols/api/ontologies"
ext = "/hp/terms/http%253A%252F%252Fpurl.obolibrary.org%252Fobo%252F" + hpo_id
r = requests.get(url+ext, headers={"Content-Type": "application/json"})
if not r.ok:
print("Something went wrong.")
else:
decoded = r.json()
for xref in decoded["annotation"]["database_cross_reference"]:
if "MSH:" in xref:
mesh_uid = xref.split("MSH:")[1]
mesh_array.append(mesh_uid)
gnomics.objects.phenotype.Phenotype.add_identifier(phen, identifier = mesh_uid, identifier_type = "MeSH UID", source = "OLS")
return mesh_array
def get_psy(anat, user=None, source="umls"):
anat_array = []
for iden in anat.identifiers:
if iden["identifier_type"].lower() in ["neu id", "neu identifier", "neu"]:
if source.lower() in ["umls", "all"]:
umls_tgt = User.umls_tgt(user)
page_num = 0
base = "https://uts-ws.nlm.nih.gov/rest"
ext = "/crosswalk/current/source/NEU/" + iden["identifier"]
while True:
tick = User.umls_st(umls_tgt)
page_num += 1
query = {"ticket": tick, "pageNumber": page_num}
r = requests.get(base+ext, params=query)
r.encoding = 'utf-8'
items = json.loads(r.text)
json_data = items["result"]
for rep in json_data:
if rep["ui"] not in anat_array and rep["ui"] != "NONE":
# PSY ID.
if rep["rootSource"] == "PSY":
anat_array.append(rep["ui"])
gnomics.objects.anatomical_structure.AnatomicalStructure.add_identifier(anat, identifier=rep["ui"], identifier_type="PSY ID", language=None, source="UMLS Metathesaurus", name=rep["name"])
if not json_data:
break
elif iden["identifier_type"].lower() in ["uwda id", "uwda identifier", "uwda"]:
if source.lower() in ["umls", "all"]:
umls_tgt = User.umls_tgt(user)
page_num = 0
base = "https://uts-ws.nlm.nih.gov/rest"
ext = "/crosswalk/current/source/UWDA/" + iden["identifier"]
while True:
tick = User.umls_st(umls_tgt)
page_num += 1
query = {"ticket": tick, "pageNumber": page_num}
r = requests.get(base+ext, params=query)
r.encoding = 'utf-8'
items = json.loads(r.text)
json_data = items["result"]
for rep in json_data:
if rep["ui"] not in anat_array and rep["ui"] != "NONE":
# PSY ID.
if rep["rootSource"] == "PSY":
anat_array.append(rep["ui"])
gnomics.objects.anatomical_structure.AnatomicalStructure.add_identifier(anat, identifier=rep["ui"], identifier_type="PSY ID", language=None, source="UMLS Metathesaurus", name=rep["name"])
if not json_data:
break
elif iden["identifier_type"].lower() in ["rcd id", "rcd identifier", "rcd"]:
if source.lower() in ["umls", "all"]:
umls_tgt = User.umls_tgt(user)
page_num = 0
base = "https://uts-ws.nlm.nih.gov/rest"
ext = "/crosswalk/current/source/RCD/" + iden["identifier"]
while True:
tick = User.umls_st(umls_tgt)
page_num += 1
query = {"ticket": tick, "pageNumber": page_num}
r = requests.get(base+ext, params=query)
r.encoding = 'utf-8'
items = json.loads(r.text)
json_data = items["result"]
for rep in json_data:
if rep["ui"] not in anat_array and rep["ui"] != "NONE":
# PSY ID.
if rep["rootSource"] == "PSY":
anat_array.append(rep["ui"])
gnomics.objects.anatomical_structure.AnatomicalStructure.add_identifier(anat, identifier=rep["ui"], identifier_type="PSY ID", language=None, source="UMLS Metathesaurus", name=rep["name"])
if not json_data:
break
elif iden["identifier_type"].lower() in ["aod id", "aod identifier", "aod"]:
if source.lower() in ["umls", "all"]:
umls_tgt = User.umls_tgt(user)
page_num = 0
base = "https://uts-ws.nlm.nih.gov/rest"
ext = "/crosswalk/current/source/AOD/" + iden["identifier"]
while True:
tick = User.umls_st(umls_tgt)
page_num += 1
query = {"ticket": tick, "pageNumber": page_num}
r = requests.get(base+ext, params=query)
r.encoding = 'utf-8'
items = json.loads(r.text)
json_data = items["result"]
for rep in json_data:
if rep["ui"] not in anat_array and rep["ui"] != "NONE":
# PSY ID.
if rep["rootSource"] == "PSY":
anat_array.append(rep["ui"])
gnomics.objects.anatomical_structure.AnatomicalStructure.add_identifier(anat, identifier=rep["ui"], identifier_type="PSY ID", language=None, source="UMLS Metathesaurus", name=rep["name"])
if not json_data:
break
return anat_array
def get_meddra_id(phen, user=None):
meddra_array = []
for ident in phen.identifiers:
if ident["identifier_type"].lower() in ["mdr", "mdr code", "mdr id", "mdr identifier", "meddra", "meddra code", "meddra id", "meddra identifier"]:
if ident["identifier"] not in meddra_array:
hpo_id_array.append(ident["identifier"])
ids_completed = []
for ident in phen.identifiers:
if ident["identifier_type"].lower() in ["meddra term", "meddra label", "mdr label", "mdr term"]:
if user is not None:
umls_tgt = User.umls_tgt(user)
page_num = 0
base = "https://uts-ws.nlm.nih.gov/rest"
ext = "/search/current?sabs=MDR&searchType=exact&returnIdType=code"
while True:
tick = User.umls_st(umls_tgt)
page_num += 1
query = {"string": ident["identifier"], "ticket": tick, "pageNumber": page_num}
r = requests.get(base+ext, params=query)
r.encoding = 'utf-8'
try:
items = json.loads(r.text)
json_data = items["result"]
empty = False
for rep in json_data["results"]:
if rep["ui"] not in meddra_array and rep["ui"] != "NONE":
gnomics.objects.phenotype.Phenotype.add_identifier(phen, identifier = rep["ui"], identifier_type = "MedDRA ID", source = "UMLS")
meddra_array.append(rep["ui"])
if json_data["results"][0]["ui"] == "NONE":
empty = True
break
if not json_data:
break
if empty:
break
except:
break
elif ident["identifier_type"].lower() in ["hp code", "hp id", "hp identifier", "hpo code", "hpo id", "hpo identifier", "human phenotype ontology code", "human phenotype ontology id", "human phenotype ontology identifier", "hp", "hpo", "human phenotype ontology"]:
if ident["identifier"] not in ids_completed:
ids_completed.append(ident["identifier"])
hpo_id = ident["identifier"]
if ":" in hpo_id:
hpo_id = hpo_id.replace(":", "_")
url = "https://www.ebi.ac.uk/ols/api/ontologies"
ext = "/hp/terms/http%253A%252F%252Fpurl.obolibrary.org%252Fobo%252F" + hpo_id
r = requests.get(url+ext, headers={"Content-Type": "application/json"})
if not r.ok:
print("Something went wrong.")
else:
decoded = r.json()
if meddra_array:
return meddra_array
for ident in phen.identifiers:
print("NOT FUNCTIONAL")
return ""
def get_hpo_id(phen, user=None):
hpo_id_array = []
for ident in phen.identifiers:
if ident["identifier_type"].lower() in ["hp code", "hp id", "hp identifier", "hpo code", "hpo id", "hpo identifier", "human phenotype ontology code", "human phenotype ontology id", "human phenotype ontology identifier", "hp", "hpo", "human phenotype ontology"]:
if ident["identifier"] not in hpo_id_array:
hpo_id_array.append(ident["identifier"])
if hpo_id_array:
return hpo_id_array
mesh_is_here = False
mesh_array = []
for ident in phen.identifiers:
if ident["identifier_type"].lower() in ["mesh", "mesh uid", "mesh unique id", "mesh unique identifier", "msh", "msh uid", "msh unique id", "msh unique identifier"]:
mesh_is_here = True
if ident["identifier"] not in mesh_array:
page_num = 0
base = "https://uts-ws.nlm.nih.gov/rest"
ext = "/crosswalk/current/source/MSH/" + ident["identifier"] + "?targetSource=HPO"
umls_tgt = User.umls_tgt(user)
while True:
tick = User.umls_st(umls_tgt)
page_num += 1
query = {"ticket": tick, "pageNumber": page_num}
r = requests.get(base+ext, params=query)
r.encoding = 'utf-8'
try:
items = json.loads(r.text)
json_data = items["result"]
for er in json_data:
if er["ui"] not in hpo_id_array and er["ui"] != "NONE":
hpo_id = er["ui"]
gnomics.objects.phenotype.Phenotype.add_identifier(phen, identifier = hpo_id, identifier_type = "HPO ID", source = "UMLS", taxon = "H**o sapiens")
hpo_id_array.append(hpo_id)
if not json_data:
break
except:
break
break
if hpo_id_array:
return hpo_id_array
if mesh_is_here:
return []
for ident in phen.identifiers:
if ident["identifier_type"].lower() in ["mdr", "mdr code", "mdr id", "mdr identifier", "meddra", "meddra code", "meddra id", "meddra identifier"]:
mesh_uid = gnomics.objects.phenotype.Phenotype.mesh_uid(phen, user)
if mesh_uid:
return get_hpo_id(phen, user)
else:
return []
for ident in phen.identifiers:
if ident["identifier_type"].lower() in ["meddra term", "meddra label", "mdr label", "mdr term"]:
gnomics.objects.phenotype.Phenotype.meddra_id(phen, user)
return get_hpo_id(phen, user)
def get_meddra_obj(adverse_event, user=None, source="umls"):
obj_array = []
for ae_obj in adverse_event.adverse_event_objects:
if 'object_type' in com_obj:
if ae_obj['object_type'].lower() in ['mdr', 'mdr code', 'mdr id', 'mdr identifier', 'meddra', 'meddra code', 'meddra id', 'meddra identifier', 'meddra label', 'meddra object', 'meddra term']:
return ae_obj['object']
if obj_array:
return obj_array
ids_completed = []
if user is not None:
for meddra_term in get_meddra_term(adverse_event):
if source.lower() in ["umls", "all"] and meddra_term not in ids_completed and user.umls_api_key is not None:
umls_tgt = User.umls_tgt(user)
page_num = 0
base = "https://uts-ws.nlm.nih.gov/rest"
ext = "/search/current?sabs=MDR&searchType=exact&returnIdType=code"
id_array = []
while True:
tick = User.umls_st(umls_tgt)
page_num += 1
query = {"string": str(meddra_term), "ticket": tick, "pageNumber": page_num}
r = requests.get(base+ext, params=query)
r.encoding = 'utf-8'
if not r.ok:
break
else:
items = json.loads(r.text)
json_data = items["result"]
if json_data["results"][0]["ui"] == "NONE":
break
else:
id_array.append(json_data)
if id_array:
gnomics.objects.adverse_event.AdverseEvent.add_object(adverse_event, obj = id_array, object_type = "MedDRA Object")
obj_array.append(id_array)
if source.lower() != "all":
ids_completed.append(meddra_term)
if source.lower() in ["ncbo", "all"] and meddra_term not in ids_completed and user.ncbo_api_key is not None:
base = "http://data.bioontology.org/search"
ext = "?q=" + str(meddra_term) + "&ontologies=MEDDRA&require_exact_match=true&roots_only=true/?apikey=" + user.ncbo_api_key
r = requests.get(base+ext, headers={"Content-Type": "application/json", "Authorization": "apikey token="+ user.ncbo_api_key})
if not r.ok:
continue
else:
decoded = json.loads(r.text)
id_array = []
for result in decoded["collection"]:
id_array.append(result)
if id_array:
gnomics.objects.adverse_event.AdverseEvent.add_object(adverse_event, obj = id_array, object_type = "MedDRA Object")
obj_array.append(id_array)
if source.lower() != "all":
ids_completed.append(meddra_term)
return obj_array
else:
print("MedDRA object cannot be obtained without valid user object (with valid UMLS API key or NCBO API key).")
def get_hpo_term(phen, user=None):
hpo_term_array = []
for ident in phen.identifiers:
if ident["identifier_type"].lower() in ["hp label", "hp term", "hpo label", "hpo term", "human phenotype ontology label", "human phenotype ontology term"]:
if ident["identifier"] not in hpo_id_array:
hpo_id_array.append(ident["identifier"])
if hpo_term_array:
return hpo_term_array
for ident in phen.identifiers:
if ident["identifier_type"].lower() in ["hp code", "hp id", "hp identifier", "hpo code", "hpo id", "hpo identifier", "human phenotype ontology code", "human phenotype ontology id", "human phenotype ontology identifier", "hp", "hpo", "human phenotype ontology"]:
if user:
page_num = 0
base = "https://uts-ws.nlm.nih.gov/rest"
ext = "/content/current/source/HPO/" + ident["identifier"]
umls_tgt = User.umls_tgt(user)
while True:
tick = User.umls_st(umls_tgt)
page_num += 1
query = {"ticket": tick, "pageNumber": page_num}
r = requests.get(base+ext, params=query)
r.encoding = 'utf-8'
try:
items = json.loads(r.text)
json_data = items["result"]
if "name" in json_data:
if json_data["name"] not in hpo_term_array:
hpo_term = json_data["name"]
gnomics.objects.phenotype.Phenotype.add_identifier(phen, identifier = hpo_term, identifier_type = "HPO Term", source = "UMLS", taxon = "H**o sapiens")
hpo_term_array.append(hpo_term)
else:
break
except:
break
break
else:
proc_id = ident["identifier"]
if ":" in proc_id:
proc_id = proc_id.replace(":", "_")
url = "https://www.ebi.ac.uk/ols/api/ontologies"
ext = "/hp/terms/http%253A%252F%252Fpurl.obolibrary.org%252Fobo%252F" + proc_id
r = requests.get(url+ext, headers={"Content-Type": "application/json"})
if not r.ok:
print("Something went wrong.")
else:
new_decoded = r.json()
if new_decoded["label"] not in hpo_term_array:
gnomics.objects.phenotype.Phenotype.add_identifier(phen, identifier = new_decoded["label"], identifier_type = "HPO Term", source = "OLS", taxon = "H**o sapiens")
hpo_term_array.append(new_decoded["label"])
return hpo_term_array
def get_fma_id(anat, user=None, source="umls"):
fma_array = []
for ident in anat.identifiers:
if ident["identifier_type"].lower() in ["fma", "fma id", "fma identifier", "fmaid", "foundational model of anatomy", "foundational model of anatomy id", "foundational model of anatomy identifier"] and ident["identifier"] not in fma_array:
fma_array.append(ident["identifier"])
if fma_array:
return fma_array
for iden in anat.identifiers:
if iden["identifier_type"].lower() in ["neu", "neu id", "neu identifier", "neuronames brain hierarchy id", "neuronames brain hierarchy identifier"]:
if source.lower() in ["umls", "all"] and user is not None:
umls_tgt = User.umls_tgt(user)
page_num = 0
base = "https://uts-ws.nlm.nih.gov/rest"
ext = "/crosswalk/current/source/NEU/" + iden["identifier"]
while True:
tick = User.umls_st(umls_tgt)
page_num += 1
query = {"ticket": tick, "pageNumber": page_num}
r = requests.get(base+ext, params=query)
r.encoding = 'utf-8'
items = json.loads(r.text)
json_data = items["result"]
for rep in json_data:
if rep["ui"] not in anat_array and rep["ui"] != "NONE":
# FMA ID.
if rep["rootSource"] == "FMA":
fma_array.append(rep["ui"])
gnomics.objects.anatomical_structure.AnatomicalStructure.add_identifier(anat, identifier=rep["ui"], identifier_type="FMA ID", language=None, source="UMLS Metathesaurus", name=rep["name"])
if not json_data:
break
elif iden["identifier_type"].lower() in ["uwda", "uwda id", "uwda identifier"]:
if source.lower() in ["umls", "all"] and user is not None:
umls_tgt = User.umls_tgt(user)
page_num = 0
base = "https://uts-ws.nlm.nih.gov/rest"
ext = "/crosswalk/current/source/UWDA/" + iden["identifier"]
while True:
tick = User.umls_st(umls_tgt)
page_num += 1
query = {"ticket": tick, "pageNumber": page_num}
r = requests.get(base+ext, params=query)
r.encoding = 'utf-8'
items = json.loads(r.text)
json_data = items["result"]
for rep in json_data:
if rep["ui"] not in anat_array and rep["ui"] != "NONE":
# FMA ID.
if rep["rootSource"] == "FMA":
fma_array.append(rep["ui"])
gnomics.objects.anatomical_structure.AnatomicalStructure.add_identifier(anat, identifier=rep["ui"], identifier_type="FMA ID", language=None, source="UMLS Metathesaurus", name=rep["name"])
if not json_data:
break
if iden["identifier_type"].lower() in ["wikidata", "wikidata accession", "wikidata id", "wikidata identifier"]:
for stuff in gnomics.objects.anatomical_structure.AnatomicalStructure.wikidata(anat):
for prop_id, prop_dict in stuff["claims"].items():
base = "https://www.wikidata.org/w/api.php"
ext = "?action=wbgetentities&ids=" + prop_id + "&format=json"
r = requests.get(base+ext, headers={"Content-Type": "application/json"})
if not r.ok:
r.raise_for_status()
sys.exit()
decoded = json.loads(r.text)
en_prop_name = decoded["entities"][prop_id]["labels"]["en"]["value"]
if en_prop_name.lower() == "foundational model of anatomy id":
for x in prop_dict:
if x["mainsnak"]["datavalue"]["value"] not in fma_array:
gnomics.objects.anatomical_structure.AnatomicalStructure.add_identifier(anat, identifier = x["mainsnak"]["datavalue"]["value"], identifier_type = "Foundational Model of Anatomy ID", language = None, source = "Wikidata")
fma_array.append(x["mainsnak"]["datavalue"]["value"])
elif (ident["identifier_type"].lower() in ["wikipedia", "wikipedia accession", "wikipedia article"]) and ident["language"].lower() == "en":
for stuff in gnomics.objects.anatomical_structure.AnatomicalStructure.wikidata(anat):
for prop_id, prop_dict in stuff["claims"].items():
base = "https://www.wikidata.org/w/api.php"
ext = "?action=wbgetentities&ids=" + prop_id + "&format=json"
r = requests.get(base+ext, headers={"Content-Type": "application/json"})
if not r.ok:
r.raise_for_status()
sys.exit()
decoded = json.loads(r.text)
en_prop_name = decoded["entities"][prop_id]["labels"]["en"]["value"]
if en_prop_name.lower() == "foundational model of anatomy id":
for x in prop_dict:
if x["mainsnak"]["datavalue"]["value"] not in fma_array:
gnomics.objects.anatomical_structure.AnatomicalStructure.add_identifier(anat, identifier = x["mainsnak"]["datavalue"]["value"], identifier_type = "Foundational Model of Anatomy ID", language = None, source = "Wikidata")
fma_array.append(x["mainsnak"]["datavalue"]["value"])
elif ident["identifier_type"].lower() in ["uberon", "uberon id", "uberon identifier"]:
gnomics.objects.anatomical_structure.AnatomicalStructure.wikipedia_accession(anat, language = "en")
anat_array = []
for stuff in gnomics.objects.anatomical_structure.AnatomicalStructure.wikidata(anat):
for prop_id, prop_dict in stuff["claims"].items():
base = "https://www.wikidata.org/w/api.php"
ext = "?action=wbgetentities&ids=" + prop_id + "&format=json"
r = requests.get(base+ext, headers={"Content-Type": "application/json"})
if not r.ok:
r.raise_for_status()
sys.exit()
decoded = json.loads(r.text)
en_prop_name = decoded["entities"][prop_id]["labels"]["en"]["value"]
if en_prop_name.lower() == "foundational model of anatomy id":
for x in prop_dict:
if x["mainsnak"]["datavalue"]["value"] not in fma_array:
gnomics.objects.anatomical_structure.AnatomicalStructure.add_identifier(anat, identifier = x["mainsnak"]["datavalue"]["value"], identifier_type = "Foundational Model of Anatomy ID", language = None, source = "Wikidata")
fma_array.append(x["mainsnak"]["datavalue"]["value"])
return fma_array
def get_aod(anat, user=None, source="umls"):
aod_array = []
for iden in gnomics.objects.auxiliary_files.identifier.filter_identifiers(
anat.identifiers, [
"alcohol and other drug", "alcohol and other drug id",
"alcohol and other drug identifier", "aod", "aod id",
"aod identifier"
]):
if iden["identifier"] not in aod_array:
aod_array.append(iden["identifier"])
if aod_array:
return aod_array
ids_completed = []
for iden in gnomics.objects.auxiliary_files.identifier.filter_identifiers(
anat.identifiers, [
"neu id", "neu identifier", "neuronames brain hierarchy id",
"neuronames brain hierarchy identifier", "neu"
]):
if iden["identifier"] not in ids_completed and user is not None:
ids_completed.append(iden["identifier"])
if source.lower() in ["umls", "all"]:
umls_tgt = User.umls_tgt(user)
page_num = 0
base = "https://uts-ws.nlm.nih.gov/rest"
ext = "/crosswalk/current/source/NEU/" + str(
iden["identifier"])
while True:
tick = User.umls_st(umls_tgt)
page_num += 1
query = {"ticket": tick, "pageNumber": page_num}
r = requests.get(base + ext, params=query)
r.encoding = 'utf-8'
items = json.loads(r.text)
json_data = items["result"]
for rep in json_data:
if rep["ui"] != "NONE":
# AOD ID.
if rep["rootSource"] == "AOD" and rep[
"ui"] not in aod_array:
aod_array.append(rep["ui"])
gnomics.objects.anatomical_structure.AnatomicalStructure.add_identifier(
anat,
identifier=rep["ui"],
identifier_type="AOD ID",
language=None,
source="UMLS Metathesaurus")
if not json_data:
break
for iden in gnomics.objects.auxiliary_files.identifier.filter_identifiers(
anat.identifiers, ["uwda", "uwda id", "uwda identifier"]):
if iden["identifier"] not in ids_completed and user is not None:
ids_completed.append(iden["identifier"])
if source.lower() in ["umls", "all"]:
umls_tgt = User.umls_tgt(user)
page_num = 0
base = "https://uts-ws.nlm.nih.gov/rest"
ext = "/crosswalk/current/source/UWDA/" + str(
iden["identifier"])
while True:
tick = User.umls_st(umls_tgt)
page_num += 1
query = {"ticket": tick, "pageNumber": page_num}
r = requests.get(base + ext, params=query)
r.encoding = 'utf-8'
items = json.loads(r.text)
json_data = items["result"]
for rep in json_data:
if rep["ui"] != "NONE":
# AOD ID.
if rep["rootSource"] == "AOD" and rep[
"ui"] not in aod_array:
aod_array.append(rep["ui"])
gnomics.objects.anatomical_structure.AnatomicalStructure.add_identifier(
anat,
identifier=rep["ui"],
identifier_type="AOD ID",
language=None,
source="UMLS Metathesaurus")
if not json_data:
break
return aod_array
def umls_crosswalk(user, from_source, to_source, source_id, other="id", verbose=False):
found_array = []
if user is None:
print("A valid user object with a valid UMLS API key is required for this function.")
return found_array
elif user.umls_api_key is None:
print("A valid UMLS API key associated with the user object is required for this function.")
return found_array
umls_tgt = User.umls_tgt(user)
page_num = 0
base = "https://uts-ws.nlm.nih.gov/rest"
ext = "/crosswalk/current/source/" + from_source.upper() + "/" + source_id
verbose = True
while True:
tick = User.umls_st(umls_tgt)
page_num += 1
query = {"ticket": tick, "pageNumber": page_num}
try:
r = requests.get(base+ext, params=query, headers = {"Content-Type": "application/json", "User-Agent": "Mozilla/5.0 (Windows NT 6.0; WOW64; rv:24.0) Gecko/20100101 Firefox/24.0"})
r.encoding = 'utf-8'
try:
items = json.loads(r.text)
json_data = items["result"]
empty = False
for rep in json_data:
if other == "id":
if rep["ui"] not in found_array and rep["ui"] != "NONE":
if rep["rootSource"] == to_source.upper():
found_array.append(rep["ui"])
elif other == "name":
if (rep["name"] not in found_array and rep["name"] != "NONE") and (rep["ui"] not in found_array and rep["ui"] != "NONE"):
if rep["rootSource"] == to_source.upper():
found_array.append((rep["ui"], rep["name"]))
else:
print("This value for 'other' is not currently supported.")
if "results" in json_data:
if json_data["results"][0]["ui"] == "NONE":
empty = True
break
if not json_data:
break
elif empty:
break
except ValueError as e:
if verbose:
print("A value error occurred while attempting to load resulting JSON.")
print("ERROR: %s" % str(e))
break
except:
if verbose:
print("Some other unknown error occurred.")
break
else:
continue
except ConnectionError as e:
if verbose:
print("A connection error occurred while attempting request.")
print("ERROR: %s" % str(e))
break
except requests.exceptions.ConnectionError as e:
if verbose:
print("A connection error occurred while attempting request.")
print("ERROR: %s" % str(e))
break
except HTTPException as e:
if verbose:
print("An HTTP exception error occurred while attempting request.")
print("ERROR: %s" % str(e))
break
except ProtocolError as e:
if verbose:
print("A protocol error occurred while attempting request.")
print("ERROR: %s" % str(e))
break
except urllib3.exceptions.ProtocolError as e:
if verbose:
print("A protocol error occurred while attempting request.")
print("ERROR: %s" % str(e))
break
except SysCallError as e:
if verbose:
print("A system call error occurred while attempting request.")
print("ERROR: %s" % str(e))
break
except OpenSSL.SSL.SysCallError as e:
if verbose:
print("A system call error occurred while attempting request.")
print("ERROR: %s" % str(e))
break
except ssl.SSLError as e:
if verbose:
print("A system call error occurred while attempting request.")
print("ERROR: %s" % str(e))
break
except SSLError as e:
if verbose:
print("A SSL error occurred while attempting request.")
print("ERROR: %s" % str(e))
break
except requests.exceptions.SSLError as e:
if verbose:
print("A SSL error occurred while attempting request.")
print("ERROR: %s" % str(e))
break
except BadStatusLine as e:
if verbose:
print("A bad status line error occurred while attempting request.")
print("ERROR: %s" % str(e))
break
except httplib.BadStatusLine as e:
if verbose:
print("A bad status line error occurred while attempting request.")
print("ERROR: %s" % str(e))
break
except http.client.BadStatusLine as e:
if verbose:
print("A protocol error occurred while attempting request.")
print("ERROR: %s" % str(e))
break
except MaxRetryError as e:
if verbose:
print("A max retry error occurred while attempting request.")
print("ERROR: %s" % str(e))
break
except urllib3.exceptions.MaxRetryError as e:
if verbose:
print("A max retry error occurred while attempting request.")
print("ERROR: %s" % str(e))
break
except:
print("Some other HTTP/URL error encountered.")
break
else:
break
return found_array
def get_phenotypes(adverse_event, user=None):
phen_array = []
ids_completed = []
for iden in gnomics.objects.auxiliary_files.identifier.filter_identifiers(adverse_event.identifiers, ["meddra term", "mdr label", "mdr name", "mdr term", "meddra label", "meddra name"]):
if iden["identifier"] not in ids_completed and user is not None:
ids_completed.append(iden["identifier"])
if user.ncbo_api_key is not None:
# Map MedDRA term to MedDRA ID.
meddra_id_array = gnomics.objects.adverse_event.AdverseEvent.meddra_id(adverse_event, user)
hpo_id_array = []
for iden in meddra_id_array:
base = "http://data.bioontology.org/ontologies/"
ext = "MEDDRA/classes/http%3A%2F%2Fpurl.bioontology.org%2Fontology%2FMEDDRA%2F" + str(iden) + "/mappings/?apikey=" + user.ncbo_api_key
r = requests.get(base+ext, headers={"Content-Type": "application/json"})
if not r.ok:
continue
else:
decoded = json.loads(r.text)
for result in decoded:
for subresult in result["classes"]:
if "http://purl.obolibrary.org/obo/HP_" in subresult["@id"]:
hpo_id = subresult["@id"].split("/obo/")[1]
if hpo_id not in hpo_id_array:
hpo_id_array.append(hpo_id)
temp_phen = gnomics.objects.phenotype.Phenotype(identifier = hpo_id, identifier_type = "HPO ID", source = "NCBO BioPortal", taxon = "H**o sapiens")
phen_array.append(temp_phen)
if not hpo_id_array:
mesh_uid_array = []
mesh_uids = gnomics.objects.adverse_event.AdverseEvent.mesh_uid(adverse_event, user)
mesh_uid_array.extend(mesh_uids)
for iden in mesh_uid_array:
umls_tgt = User.umls_tgt(user)
page_num = 0
base = "https://uts-ws.nlm.nih.gov/rest"
ext = "/crosswalk/current/source/MSH/" + iden + "?targetSource=HPO"
try:
tick = User.umls_st(umls_tgt)
page_num += 1
query = {"ticket": tick, "pageNumber": page_num}
r = requests.get(base+ext, params=query)
r.encoding = 'utf-8'
if not r.ok:
print("No mapping from MeSH to HPO found.")
else:
items = json.loads(r.text)
json_data = items["result"]
for er in json_data:
if er["ui"] not in hpo_id_array and er["ui"] != "NONE":
hpo_id = er["ui"]
hpo_id_array.append(hpo_id)
temp_phen = gnomics.objects.phenotype.Phenotype(identifier = hpo_id, identifier_type = "HPO ID", source = "UMLS", taxon = "H**o sapiens")
phen_array.append(temp_phen)
if not json_data:
continue
except:
continue
else:
print("A valid NCBO API key is necessary to access the NCBO Bioontology API. Please provide a valid user object with such a key.")
else:
print("A valid user object with an NCBO API key is necessary to access the NCBO Bioontology API. Please provide such an object.")
return phen_array
