scispacy_entity_ruler.py

import spacy

# load a spacy model that detects DNA, RNA and PROTEINS from
# biomedical documents

model = spacy.load(
    "en_ner_jnlpba_md",
    disable=["tok2vec", "tagger", "parser", "attribute_ruler", "lemmatizer"],
)

# build a list of patterns and inject them into the entity ruler. 
# these patterns contain entities that are not initially captured 
# by the model. 
# knowledge bases or ontologies could be used to construct the patterns

patterns = build_patterns_from_knowledge_base()

print(patterns[:3])
# [{'label': 'PROTEIN', 'pattern': 'tetraspanin-5'},
#  {'label': 'PROTEIN', 'pattern': 'estradiol 17-beta-dehydrogenase akr1b15'},
#  {'label': 'PROTEIN', 'pattern': 'moz, ybf2/sas3, sas2 and tip60 protein 4'}]

# define an entity ruler
entity_ruler = model.add_pipe("entity_ruler", after="ner")

# add the patterns to the entity ruler
entity_ruler.add_patterns(patterns)