def get_similar_nodes_in_common_parameters(node_ID, target_node_label, association_node_label):
"""
This function will get the parameters for get_similar_nodes_in_common based on target node, target label, and association label
:param node_ID: source node ID (name in KG)
:param target_label: the node types that you want returned
:param association_node_label: the association node (node in common between source and target) type
:return: dict, error_code, error_message (dict keys input_node_ID, input_node_label, association_node_label, input_association_relationship,
target_association_relationship, target_node_label)
"""
# Check if node exists
if not RU.node_exists_with_property(node_ID, 'id'):
error_message = "Sorry, the disease %s is not yet in our knowledge graph." % node_ID
error_code = "DiseaseNotFound"
return dict(), error_code, error_message
# Get label/kind of node the source is
input_node_label = RU.get_node_property(node_ID, "label")
input_node_ID = node_ID
# Get relationship between source and association label
rels = RU.get_relationship_types_between(input_node_ID, input_node_label, "", association_node_label, max_path_len=1)
# TODO: there could be multiple relationship types, for now, let's just pop one
if not rels:
error_code = "NoRelationship"
error_message = "Sorry, the %s %s is not connected to any %s." % (input_node_label, input_node_ID, association_node_label)
parent = RU.get_one_hop_target(input_node_label, input_node_ID, input_node_label, "subclass_of", direction="r")
if parent:
parent = parent.pop()
error_message += "\n Note that %s is a parent of %s, so you might try that instead." % (
RU.get_node_property(parent, 'name'), RU.get_node_property(input_node_ID, 'name'))
return dict(), error_code, error_message
input_association_relationship = rels.pop()
# Get relationship between target and association label
rels = RU.get_relationship_types_between("", target_node_label, "", association_node_label, max_path_len=1)
if not rels:
error_code = "NoRelationship"
error_message = "Sorry, no %s is not connected to any %s." % (target_node_label, association_node_label)
return dict(), error_code, error_message
target_association_relationship = rels.pop()
# TODO: kludgy fix for microRNA's having multiple relationship types, only one of which shows up frequently
if target_association_relationship == "gene_mutations_contribute_to":
target_association_relationship = "gene_associated_with_condition"
# populate the arguments
arguments = dict(input_node_ID=input_node_ID,
input_node_label=input_node_label,
association_node_label=association_node_label,
input_association_relationship=input_association_relationship,
target_association_relationship=target_association_relationship,
target_node_label=target_node_label)
return arguments, None, None
def old_answer(disease_ID, use_json=False, threshold=0.2):
# This is about 5 times slower than the current answer, but is a bit clearer in how it's coded
# Initialize the response class
response = FormatOutput.FormatResponse(4)
# Check if node exists
if not RU.node_exists_with_property(disease_ID, 'name'):
error_message = "Sorry, the disease %s is not yet in our knowledge graph." % disease_ID
error_code = "DiseaseNotFound"
if not use_json:
print(error_message)
return 1
else:
response.add_error_message(error_code, error_message)
response.print()
return 1
# Get label/kind of node the source is
disease_label = RU.get_node_property(disease_ID, "label")
if disease_label != "disease" and disease_label != "disease":
error_message = "Sorry, the input has label %s and needs to be one of: disease, disease." \
" Please try a different term" % disease_label
error_code = "NotADisease"
if not use_json:
print(error_message)
return 1
else:
response.add_error_message(error_code, error_message)
response.print()
return 1
# get the description
disease_description = RU.get_node_property(disease_ID, 'description')
# get the phenotypes associated to the disease
disease_phenotypes = RU.get_one_hop_target(disease_label, disease_ID,
"phenotypic_feature",
"has_phenotype")
# Look more steps beyond if we didn't get any physically_interacts_with
if disease_phenotypes == []:
for max_path_len in range(2, 5):
disease_phenotypes = RU.get_node_names_of_type_connected_to_target(
disease_label,
disease_ID,
"phenotypic_feature",
max_path_len=max_path_len,
direction="u")
if disease_phenotypes:
break
# print("Total of %d phenotypes" % len(disease_phenotypes))
# Make sure you actually picked up at least one phenotype
if not disease_phenotypes:
error_message = "No phenotypes found for this disease."
error_code = "NoPhenotypesFound"
if not use_json:
print(error_message)
return 1
else:
response.add_error_message(error_code, error_message)
response.print()
return 1
disease_phenotypes_set = set(disease_phenotypes)
# get all the other disease that connect and get the phenotypes in common
other_disease_IDs_to_intersection_counts = dict()
for target_label in ["disease", "disease"]:
# direct connection
# print("direct")
node_label_list = ["phenotypic_feature"]
relationship_label_list = ["has_phenotype", "has_phenotype"]
node_of_interest_position = 0
names2counts, names2nodes = RU.count_nodes_of_type_on_path_of_type_to_label(
disease_ID, disease_label, target_label, node_label_list,
relationship_label_list, node_of_interest_position)
for ID in names2counts.keys():
if names2counts[ID] / float(
len(disease_phenotypes_set)
) >= threshold: # if it's below this threshold, no way the Jaccard index will be large enough
other_disease_IDs_to_intersection_counts[ID] = names2counts[ID]
if not other_disease_IDs_to_intersection_counts:
error_code = "NoDiseasesFound"
error_message = "No diseases were found with similarity crossing the threshold of %f." % threshold
parent = RU.get_one_hop_target(disease_label, disease_ID,
disease_label, "subclass_of").pop()
if parent:
error_message += "\n Note that %s is a parent disease to %s, so you might try that instead." % (
RU.get_node_property(parent,
'description'), disease_description)
if not use_json:
print(error_message)
return 1
else:
response.add_error_message(error_code, error_message)
response.print()
return 1
# print("Total number of other diseases %d" % len(list(other_disease_IDs_to_intersection_counts.keys())))
# Now for each of the diseases in here, compute the actual Jaccard index
disease_jaccard_tuples = []
# i = 0
for other_disease_ID in other_disease_IDs_to_intersection_counts.keys():
# print(i)
# i += 1
# print(other_disease_ID)
# get the phenotypes associated to the disease
if other_disease_ID.split(":")[0] == "DOID":
other_disease_label = "disease"
if other_disease_ID.split(":")[0] == "OMIM":
other_disease_label = "disease"
other_disease_phenotypes = RU.get_one_hop_target(
other_disease_label, other_disease_ID, "phenotypic_feature",
"has_phenotype")
# Look more steps beyond if we didn't get any physically_interacts_with
if other_disease_phenotypes == []:
for max_path_len in range(2, 5):
other_disease_phenotypes = RU.get_node_names_of_type_connected_to_target(
other_disease_label,
other_disease_ID,
"phenotypic_feature",
max_path_len=max_path_len,
direction="u")
if other_disease_phenotypes:
break
# compute the Jaccard index
if not other_disease_phenotypes:
jaccard = 0
else:
other_disease_phenotypes_set = set(other_disease_phenotypes)
jaccard = other_disease_IDs_to_intersection_counts[
other_disease_ID] / float(
len(
list(
disease_phenotypes_set.union(
other_disease_phenotypes_set))))
# print("jaccard %f" % jaccard)
if jaccard > threshold:
disease_jaccard_tuples.append((other_disease_ID, jaccard))
# Format the results.
# Maybe nothing passed the threshold
if not disease_jaccard_tuples:
error_code = "NoDiseasesFound"
error_message = "No diseases were found with similarity crossing the threshold of %f." % threshold
parent = RU.get_one_hop_target(disease_label, disease_ID,
disease_label, "subclass_of")
if parent:
error_message += "\n Note that %s is a parent disease to %s, so you might try that instead." % (
RU.get_node_property(parent,
'description'), disease_description)
if not use_json:
print(error_message)
return 1
else:
response.add_error_message(error_code, error_message)
return 1
# Otherwise there are results to return, first sort them largest to smallest
disease_jaccard_tuples_sorted = [(x, y) for x, y in sorted(
disease_jaccard_tuples, key=lambda pair: pair[1], reverse=True)]
if not use_json:
to_print = "The diseases similar to %s are: \n" % disease_description
for other_disease_ID, jaccard in disease_jaccard_tuples_sorted:
to_print += "%s\t%s\tJaccard %f\n" % (
other_disease_ID,
RU.get_node_property(other_disease_ID, 'description'), jaccard)
print(to_print)
else:
for other_disease_ID, jaccard in disease_jaccard_tuples_sorted:
to_print = "%s is similar to the disease %s with similarity value %f" % (
disease_description,
RU.get_node_property(other_disease_ID, 'decription'), jaccard)
g = RU.get_node_as_graph(other_disease_ID)
response.add_subgraph(g.nodes(data=True), g.edges(data=True),
to_print, jaccard)
response.print()
def answer(self, disease_ID, use_json=False, threshold=0.2):
"""
Answer the question: what other diseases have similarity >= jaccard=0.2 with the given disease_ID
(in terms of phenotype overlap)
:param disease_ID: KG disease name (eg. DOID:8398)
:param use_json: use the standardized output format
:param threshold: only include diseases with Jaccard index above this
:return: None (print to stdout), unless there's an error, then return 1
"""
# Initialize the response class
response = FormatOutput.FormatResponse(4)
# Check if node exists
if not RU.node_exists_with_property(disease_ID, 'name'):
error_message = "Sorry, the disease %s is not yet in our knowledge graph." % disease_ID
error_code = "DiseaseNotFound"
if not use_json:
print(error_message)
return 1
else:
response.add_error_message(error_code, error_message)
response.print()
return 1
# Get label/kind of node the source is
disease_label = RU.get_node_property(disease_ID, "label")
if disease_label != "disease" and disease_label != "disease":
error_message = "Sorry, the input has label %s and needs to be one of: disease, disease." \
" Please try a different term" % disease_label
error_code = "NotADisease"
if not use_json:
print(error_message)
return 1
else:
response.add_error_message(error_code, error_message)
response.print()
return 1
# get the description
disease_description = RU.get_node_property(disease_ID, 'description')
# get the phenotypes associated to the disease
disease_phenotypes = RU.get_one_hop_target(disease_label, disease_ID,
"phenotypic_feature",
"has_phenotype")
# Look more steps beyond if we didn't get any physically_interacts_with
if disease_phenotypes == []:
for max_path_len in range(2, 5):
disease_phenotypes = RU.get_node_names_of_type_connected_to_target(
disease_label,
disease_ID,
"phenotypic_feature",
max_path_len=max_path_len,
direction="u")
if disease_phenotypes:
break
# Make sure you actually picked up at least one phenotype
if not disease_phenotypes:
error_message = "No phenotypes found for this disease."
error_code = "NoPhenotypesFound"
if not use_json:
print(error_message)
return 1
else:
response.add_error_message(error_code, error_message)
response.print()
return 1
disease_phenotypes_set = set(disease_phenotypes)
# get all the other disease that connect and get the phenotypes in common
# direct connection
node_label_list = ["phenotypic_feature"]
relationship_label_list = ["has_phenotype", "has_phenotype"]
node_of_interest_position = 0
other_disease_IDs_to_intersection_counts = dict()
for target_label in ["disease", "disease"]:
names2counts, names2nodes = RU.count_nodes_of_type_on_path_of_type_to_label(
disease_ID, disease_label, target_label, node_label_list,
relationship_label_list, node_of_interest_position)
for ID in names2counts.keys():
if names2counts[ID] / float(
len(disease_phenotypes_set)
) >= threshold: # if it's below this threshold, no way the Jaccard index will be large enough
other_disease_IDs_to_intersection_counts[
ID] = names2counts[ID]
# check if any other diseases passed the threshold
if not other_disease_IDs_to_intersection_counts:
error_code = "NoDiseasesFound"
error_message = "No diseases were found with similarity crossing the threshold of %f." % threshold
parent = RU.get_one_hop_target(disease_label,
disease_ID,
disease_label,
"subclass_of",
direction="r")
if parent:
parent = parent.pop()
error_message += "\n Note that %s is a parent disease to %s, so you might try that instead." % (
RU.get_node_property(parent,
'description'), disease_description)
if not use_json:
print(error_message)
return 1
else:
response.add_error_message(error_code, error_message)
response.print()
return 1
# Now for each of the diseases connecting to source, count number of phenotypes
node_label_list = ["phenotypic_feature"]
relationship_label_list = ["has_phenotype", "has_phenotype"]
node_of_interest_position = 0
other_doid_counts = RU.count_nodes_of_type_for_nodes_that_connect_to_label(
disease_ID, disease_label, "disease", node_label_list,
relationship_label_list, node_of_interest_position)
other_omim_counts = RU.count_nodes_of_type_for_nodes_that_connect_to_label(
disease_ID, disease_label, "disease", node_label_list,
relationship_label_list, node_of_interest_position)
# union the two
other_disease_counts = dict()
for key in other_doid_counts.keys():
other_disease_counts[key] = other_doid_counts[key]
for key in other_omim_counts.keys():
other_disease_counts[key] = other_omim_counts[key]
# then compute the jaccard index
disease_jaccard_tuples = []
for other_disease_ID in other_disease_counts.keys():
jaccard = 0
if other_disease_ID in other_disease_IDs_to_intersection_counts:
union_card = len(disease_phenotypes) + other_disease_counts[other_disease_ID] - \
other_disease_IDs_to_intersection_counts[other_disease_ID]
jaccard = other_disease_IDs_to_intersection_counts[
other_disease_ID] / float(union_card)
if jaccard > threshold:
disease_jaccard_tuples.append((other_disease_ID, jaccard))
# Format the results.
# Maybe nothing passed the threshold
if not disease_jaccard_tuples:
error_code = "NoDiseasesFound"
error_message = "No diseases were found with similarity crossing the threshold of %f." % threshold
parent = RU.get_one_hop_target(disease_label,
disease_ID,
disease_label,
"subclass_of",
direction="r")
if parent:
parent = parent.pop()
error_message += "\n Note that %s is a parent disease to %s, so you might try that instead." % (
RU.get_node_property(parent,
'description'), disease_description)
if not use_json:
print(error_message)
return 1
else:
response.add_error_message(error_code, error_message)
return 1
# Otherwise there are results to return, first sort them largest to smallest
disease_jaccard_tuples_sorted = [(x, y) for x, y in sorted(
disease_jaccard_tuples, key=lambda pair: pair[1], reverse=True)]
if not use_json:
to_print = "The diseases with phenotypes similar to %s are: \n" % disease_description
for other_disease_ID, jaccard in disease_jaccard_tuples_sorted:
to_print += "%s\t%s\tJaccard %f\n" % (
other_disease_ID,
RU.get_node_property(other_disease_ID,
'description'), jaccard)
print(to_print)
else:
for other_disease_ID, jaccard in disease_jaccard_tuples_sorted:
to_print = "%s is phenotypically similar to the disease %s with similarity value %f" % (
disease_description,
RU.get_node_property(other_disease_ID,
'description'), jaccard)
g = RU.get_node_as_graph(other_disease_ID)
response.add_subgraph(g.nodes(data=True), g.edges(data=True),
to_print, jaccard)
response.print()
def answer(tissue_id,
input_protein_list,
use_json=False,
num_show=20,
rev=True):
# Initialize the response class
response = FormatOutput.FormatResponse(6)
# Make sure everything exists in the graph
if not RU.node_exists_with_property(tissue_id, "id"):
tissue_id = RU.get_node_property(tissue_id,
"id",
node_label="anatomical_entity")
for i in range(len(input_protein_list)):
id = input_protein_list[i]
if not RU.node_exists_with_property(id, "id"):
input_protein_list[i] = RU.get_node_property(
id, "id", node_label="protein")
# Initialize the QueryLilGim class
q = QueryLilGIM.QueryLilGIM()
# get the description
tissue_description = RU.get_node_property(
tissue_id, 'name', node_label="anatomical_entity")
# Get the correlated proteins
try:
correlated_proteins_dict = q.query_neighbor_genes_for_gene_set_in_a_given_anatomy(
tissue_id, tuple(input_protein_list))
#correlated_proteins_dict = {'UniProtKB:Q99618': 0.4276333333333333, 'UniProtKB:Q92698': 0.464, 'UniProtKB:P56282': 0.5810000000000001, 'UniProtKB:P49454': 0.4441, 'UniProtKB:P49642': 0.5188333333333334, 'UniProtKB:Q9BZD4': 0.5042666666666668, 'UniProtKB:P38398': 0.4464, 'UniProtKB:Q9BXL8': 0.5009, 'UniProtKB:P42166': 0.4263000000000001, 'UniProtKB:Q96CS2': 0.5844333333333332, 'UniProtKB:Q9BQP7': 0.4903333333333333, 'UniProtKB:O95997': 0.4743333333333333, 'UniProtKB:Q9H4K1': 0.4709, 'UniProtKB:Q9H967': 0.5646666666666667, 'UniProtKB:Q12834': 0.4478, 'UniProtKB:Q71F23': 0.4361, 'UniProtKB:Q9UQ84': 0.4800666666666666, 'UniProtKB:Q9NSP4': 0.4347}
except:
error_message = "Lil'GIM is experiencing a problem."
error_code = "LilGIMerror"
response.add_error_message(error_code, error_message)
response.print()
return 1
# as a list of tuples
correlated_proteins_tupes = []
for k, v in correlated_proteins_dict.items():
correlated_proteins_tupes.append((k, v))
# sort by freq
correlated_proteins_tupes_sorted = sorted(correlated_proteins_tupes,
key=lambda x: x[1],
reverse=rev)
correlated_proteins_tupes_sorted = correlated_proteins_tupes_sorted[
0:num_show]
correlated_proteins_tupes = correlated_proteins_tupes_sorted
# return the results
if not use_json:
try:
protein_descriptions = RU.get_node_property(
input_protein_list[0],
"name",
node_label="protein",
name_type="id")
except:
protein_descriptions = input_protein_list[0]
for id in input_protein_list[1:-1]:
protein_descriptions += ", "
try:
protein_descriptions += RU.get_node_property(
id, "name", node_label="protein", name_type="id")
except:
protein_descriptions += id
if len(input_protein_list) > 1:
try:
protein_descriptions += ", and %s" % RU.get_node_property(
input_protein_list[-1],
"name",
node_label="protein",
name_type="id")
except:
protein_descriptions += ", and %s" % input_protein_list[-1]
if rev:
to_print = "In the tissue: %s, the proteins that correlate most with %s" % (
tissue_description, protein_descriptions)
else:
to_print = "In the tissue: %s, the proteins that correlate least with %s" % (
tissue_description, protein_descriptions)
to_print += " according to Lil'GIM, are:\n"
for id, val in correlated_proteins_tupes_sorted:
try:
to_print += "protein: %s\t correlation %f\n" % (
RU.get_node_property(
id, "name", node_label="protein",
name_type="id"), val)
except:
to_print += "protein: %s\t correlation %f\n" % (id, val)
print(to_print)
else:
# otherwise, you want a JSON output
protein_descriptions = []
is_in_KG_list = []
for protein, corr in correlated_proteins_tupes:
try:
description = RU.get_node_property(protein,
"name",
node_label="protein",
name_type="id")
protein_descriptions.append(description)
is_in_KG_list.append(True)
except:
protein_description = protein
protein_descriptions.append(protein_description)
is_in_KG_list.append(False)
# just get the ones that are actually in the KG. TODO: do something with the ones that are not in the KG
correlated_proteins_tupes_in_KG = []
for i in range(len(correlated_proteins_tupes)):
if is_in_KG_list[i]:
correlated_proteins_tupes_in_KG.append(
correlated_proteins_tupes[i])
# Return the results
full_g = RU.get_graph_from_nodes(
[id for id, val in correlated_proteins_tupes_in_KG],
node_property_label="id")
id2node = dict()
for nx_id, node in full_g.nodes(data=True):
id2node[node['properties']['id']] = node
for id, corr in correlated_proteins_tupes_in_KG:
to_print = "In the tissue: %s, the protein %s has correlation %f with the given list of proteins." % (
tissue_description,
RU.get_node_property(
id, "name", node_label="protein",
name_type="id"), corr)
response.add_subgraph([(id, id2node[id])], [], to_print, corr)
response.print()