Edit on GitHub
  • John Snow Labs
  • Aug 07, 2026

Mapping Gene Entities in Text with Their Corresponding HGNC Codes

  • en
  • chunk_mapper
  • licensed
  • clinical
  • hgnc
  • gene

Description

This model maps gene mentions extracted from clinical or biomedical text to their corresponding HUGO Gene Nomenclature Committee (HGNC) identifiers, using current approved gene symbols and official names. Trained on the HGNC monthly release dated 2026-08-04.

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")

word_embeddings = WordEmbeddingsModel.pretrained("embeddings_clinical","en","clinical/models")\
    .setInputCols(["sentence","token"])\
    .setOutputCol("word_embeddings")

ner_hgnc = MedicalNerModel.pretrained("ner_human_phenotype_gene_clinical","en","clinical/models")\
    .setInputCols(["sentence","token","word_embeddings"])\
    .setOutputCol("ner")

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

hgnc_mapper = ChunkMapperModel.pretrained("hgnc_mapper_2026","en","clinical/models")\
    .setInputCols(["ner_chunk"])\
    .setOutputCol("mappings")\
    .setRels(["hgnc_id"])\
    .setLowerCase(True)

pipeline = Pipeline(stages=[\
    document_assembler, sentence_detector, tokenizer, word_embeddings,\
    ner_hgnc, ner_converter, hgnc_mapper\
])

data = spark.createDataFrame([["Genetic testing confirmed a pathogenic BRCA1 variant, and the report also flagged elevated risk associated with the EGFR and KRAS genes."]]).toDF("text")
result = pipeline.fit(data).transform(data)

document_assembler = nlp.DocumentAssembler()\
    .setInputCol("text")\
    .setOutputCol("document")

sentence_detector = nlp.SentenceDetector()\
    .setInputCols(["document"])\
    .setOutputCol("sentence")

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

word_embeddings = nlp.WordEmbeddingsModel.pretrained("embeddings_clinical","en","clinical/models")\
    .setInputCols(["sentence","token"])\
    .setOutputCol("word_embeddings")

ner_hgnc = medical.NerModel.pretrained("ner_human_phenotype_gene_clinical","en","clinical/models")\
    .setInputCols(["sentence","token","word_embeddings"])\
    .setOutputCol("ner")

ner_converter = medical.NerConverterInternal()\
    .setInputCols(["sentence","token","ner"])\
    .setOutputCol("ner_chunk")\
    .setWhiteList(["GENE"])

hgnc_mapper = medical.ChunkMapperModel.pretrained("hgnc_mapper_2026","en","clinical/models")\
    .setInputCols(["ner_chunk"])\
    .setOutputCol("mappings")\
    .setRels(["hgnc_id"])\
    .setLowerCase(True)

pipeline = nlp.Pipeline(stages=[\
    document_assembler, sentence_detector, tokenizer, word_embeddings,\
    ner_hgnc, ner_converter, hgnc_mapper\
])

data = spark.createDataFrame([["Genetic testing confirmed a pathogenic BRCA1 variant, and the report also flagged elevated risk associated with the EGFR and KRAS genes."]]).toDF("text")
result = pipeline.fit(data).transform(data)


val documentAssembler = new DocumentAssembler()
    .setInputCol("text")
    .setOutputCol("document")

val sentenceDetector = new SentenceDetector()
    .setInputCols(Array("document"))
    .setOutputCol("sentence")

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

val wordEmbeddings = WordEmbeddingsModel
    .pretrained("embeddings_clinical", "en", "clinical/models")
    .setInputCols(Array("sentence", "token"))
    .setOutputCol("word_embeddings")

val nerHgnc = MedicalNerModel
    .pretrained("ner_human_phenotype_gene_clinical", "en", "clinical/models")
    .setInputCols(Array("sentence", "token", "word_embeddings"))
    .setOutputCol("ner")

val nerConverter = new NerConverterInternal()
    .setInputCols(Array("sentence", "token", "ner"))
    .setOutputCol("ner_chunk")
    .setWhiteList(Array("GENE"))

val hgncMapper = ChunkMapperModel
    .pretrained("hgnc_mapper_2026", "en", "clinical/models")
    .setInputCols("ner_chunk")
    .setOutputCol("mappings")
    .setRels(Array("hgnc_id"))
    .setLowerCase(true)

val pipeline = new Pipeline().setStages(Array(
    documentAssembler, sentenceDetector, tokenizer, wordEmbeddings,
    nerHgnc, nerConverter, hgncMapper
))

val data = Seq("Genetic testing confirmed a pathogenic BRCA1 variant, and the report also flagged elevated risk associated with the EGFR and KRAS genes.").toDF("text")
val result = pipeline.fit(data).transform(data)

Results

| chunk   | HGNC Code   | all_k_resolutions   |
|:--------|:------------|:--------------------|
| BRCA1   | HGNC:1100   | HGNC:1100:::        |
| EGFR    | HGNC:3236   | HGNC:3236:::        |
| KRAS    | HGNC:6407   | HGNC:6407:::        |

Model Information

Model Name: hgnc_mapper_2026
Compatibility: Healthcare NLP 6.4.1+
License: Licensed
Edition: Official
Input Labels: [ner_chunk]
Output Labels: [mappings]
Language: en
Size: 1.6 MB