def compute_jaccard(self,
input_genes: List[dict],
lower_bound: float = 0.7) -> List[dict]:
similarities = []
for index, igene in enumerate(input_genes):
for subject_curie in self.associations.subject_label_map.keys():
input_gene = GenericSimilarity.trim_mgi_prefix(
input_gene=igene['sim_input_curie'],
subject_curie=subject_curie)
if input_gene is not subject_curie:
score = jaccard_similarity(self.associations, input_gene,
subject_curie)
if float(score) > float(lower_bound):
subject_label = self.associations.label(subject_curie)
similarities.append({
'input_id':
input_gene,
'input_symbol':
igene['input_symbol'],
'hit_symbol':
subject_label,
'hit_id':
subject_curie,
'score':
score,
})
return similarities
def compute_jaccard(self, input_curies:List[str], lower_bound:float=0.7, upper_bound:float=1.0) -> List[dict]:
similarities = []
for input_curie in input_curies:
for subject_curie in self.associations.subject_label_map.keys():
score = jaccard_similarity(self.associations, input_curie, subject_curie)
if score > lower_bound and score < upper_bound:
similarities.append({
'input_curie': input_curie,
'sim_hit_name': self.associations.label(subject_curie),
'sim_hit_curie': subject_curie,
'sim_score': score,
})
return similarities