README.md

---
tags:
  - flair
  - entity-mention-linker
---

## biosyn-sapbert-ncbi-disease

Biomedical Entity Mention Linking for diseases:

- Model: [dmis-lab/biosyn-sapbert-ncbi-disease](https://huggingface.co/dmis-lab/biosyn-sapbert-ncbi-disease)
- Dictionary: [CTD Diseases](https://ctdbase.org/voc.go?type=disease) (See License)

### Demo: How to use in Flair

Requires:

- **[Flair](https://github.com/flairNLP/flair/)>=0.14.0** (`pip install flair` or `pip install git+https://github.com/flairNLP/flair.git`)
  
```python
from flair.data import Sentence
from flair.models import Classifier, EntityMentionLinker
from flair.tokenization import SciSpacyTokenizer

sentence = Sentence(
    "The mutation in the ABCD1 gene causes X-linked adrenoleukodystrophy, "
    "a neurodegenerative disease, which is exacerbated by exposure to high "
    "levels of mercury in dolphin populations.",
    use_tokenizer=SciSpacyTokenizer()
)

# load hunflair to detect the entity mentions we want to link.
tagger = Classifier.load("hunflair-disease")
tagger.predict(sentence)

# load the linker and dictionary
linker = EntityMentionLinker.load("hunflair/biosyn-sapbert-ncbi-disease")
dictionary = linker.dictionary

# find then candidates for the mentions
linker.predict(sentence)

# print the results for each entity mention:
for span in sentence.get_spans(tagger.label_type):
    print(f"Span: {span.text}")
    for candidate_label in span.get_labels(linker.label_type):
        candidate = dictionary[candidate_label.value]
        print(f"Candidate: {candidate.concept_name}")
```

As an alternative to downloading the already precomputed model (much storage). You can also build the model
and compute the embeddings for the dataset using:

```python
linker = EntityMentionLinker.build("dmis-lab/biosyn-biobert-ncbi-disease", dictionary_name_or_path="ctd-diseases", hybrid_search=True)
```

This will reduce the download requirements, at the cost of computation.