Detect Genes and Human Phenotypes (biobert)

Description

This model can be used to detect normalized mentions of genes (gene) and human phenotypes (hp) in medical text.

Predicted Entities

HP, GENE

Live Demo Open in Colab Copy S3 URI

How to use

document_assembler = DocumentAssembler()\
    .setInputCol("text")\
    .setOutputCol("document")
         
sentence_detector = SentenceDetector()\
    .setInputCols(["document"])\
    .setOutputCol("sentence")

tokenizer = Tokenizer()\
    .setInputCols(["sentence"])\
    .setOutputCol("token")

embeddings_clinical = BertEmbeddings.pretrained("biobert_pubmed_base_cased")\
    .setInputCols(["sentence", "token"])\
    .setOutputCol("embeddings")

clinical_ner = MedicalNerModel.pretrained("ner_human_phenotype_gene_biobert", "en", "clinical/models")\
    .setInputCols(["sentence", "token", "embeddings"])\
    .setOutputCol("ner")

ner_converter = NerConverter()\
 	  .setInputCols(["sentence", "token", "ner"])\
 	  .setOutputCol("ner_chunk")

nlpPipeline = Pipeline(stages=[document_assembler, sentence_detector, tokenizer, embeddings_clinical, clinical_ner, ner_converter])

model = nlpPipeline.fit(spark.createDataFrame([[""]]).toDF("text"))

results = model.transform(spark.createDataFrame([["EXAMPLE_TEXT"]]).toDF("text"))
val document_assembler = new DocumentAssembler()
    .setInputCol("text")
    .setOutputCol("document")
         
val sentence_detector = new SentenceDetector()
    .setInputCols("document")
    .setOutputCol("sentence")

val tokenizer = new Tokenizer()
    .setInputCols("sentence")
    .setOutputCol("token")

val embeddings_clinical = BertEmbeddings.pretrained("biobert_pubmed_base_cased")
    .setInputCols(Array("sentence", "token"))
    .setOutputCol("embeddings")

val ner = MedicalNerModel.pretrained("ner_human_phenotype_gene_biobert", "en", "clinical/models")
    .setInputCols(Array("sentence", "token", "embeddings"))
    .setOutputCol("ner")

val ner_converter = new NerConverter()
 	.setInputCols(Array("sentence", "token", "ner"))
 	.setOutputCol("ner_chunk")

val pipeline = new Pipeline().setStages(Array(document_assembler, sentence_detector, tokenizer, embeddings_clinical, ner, ner_converter))

val result = pipeline.fit(data).transform(data)
import nlu
nlu.load("en.med_ner.human_phenotype.gene_biobert").predict("""Put your text here.""")

Model Information

Model Name: ner_human_phenotype_gene_biobert
Compatibility: Healthcare NLP 3.0.0+
License: Licensed
Edition: Official
Input Labels: [sentence, token, embeddings]
Output Labels: [ner]
Language: en

Benchmarking

entity     tp    fp    fn  total precision recall     f1
HP 1761.0 198.0 342.0 2103.0    0.8989 0.8374 0.8671
GENE 1600.0 290.0 361.0 1961.0    0.8466 0.8159  0.831
macro    -     -     -      -        -      -    0.8490
micro    -     -     -      -        -      -    0.8496