Description
This model maps gene symbols and official names to HUGO Gene Nomenclature Committee (HGNC) identifiers using sbiobert_base_cased_mli_onnx embeddings. Trained on the HGNC monthly release dated 2026-08-04.
Live Demo Open in Colab Copy S3 URI
How to use
documentAssembler = DocumentAssembler()\
.setInputCol("text")\
.setOutputCol("document")
sentenceDetector = 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_model = 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"])
chunk2doc = Chunk2Doc()\
.setInputCols("ner_chunk")\
.setOutputCol("ner_chunk_doc")
embedder = BertSentenceEmbeddings.pretrained("sbiobert_base_cased_mli_onnx", "en", "clinical/models")\
.setInputCols(["ner_chunk_doc"])\
.setOutputCol("sbert_embeddings")\
.setCaseSensitive(False)
resolver = SentenceEntityResolverModel.pretrained("sbiobertresolve_hgnc_2026","en","clinical/models")\
.setInputCols(["sbert_embeddings"])\
.setOutputCol("resolution")\
.setDistanceFunction("EUCLIDEAN")
pipeline = Pipeline(stages=[\
documentAssembler, sentenceDetector, tokenizer, word_embeddings,\
ner_model, ner_converter, chunk2doc, embedder, resolver\
])
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)
documentAssembler = nlp.DocumentAssembler()\
.setInputCol("text")\
.setOutputCol("document")
sentenceDetector = 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_model = 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"])
chunk2doc = nlp.Chunk2Doc()\
.setInputCols("ner_chunk")\
.setOutputCol("ner_chunk_doc")
embedder = nlp.BertSentenceEmbeddings.pretrained("sbiobert_base_cased_mli_onnx", "en", "clinical/models")\
.setInputCols(["ner_chunk_doc"])\
.setOutputCol("sbert_embeddings")\
.setCaseSensitive(False)
resolver = medical.SentenceEntityResolverModel.pretrained("sbiobertresolve_hgnc_2026","en","clinical/models")\
.setInputCols(["sbert_embeddings"])\
.setOutputCol("resolution")\
.setDistanceFunction("EUCLIDEAN")
pipeline = nlp.Pipeline(stages=[\
documentAssembler, sentenceDetector, tokenizer, word_embeddings,\
ner_model, ner_converter, chunk2doc, embedder, resolver\
])
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 word_embeddings = WordEmbeddingsModel
.pretrained("embeddings_clinical", "en", "clinical/models")
.setInputCols(Array("sentence", "token"))
.setOutputCol("word_embeddings")
val ner_model = MedicalNerModel
.pretrained("ner_human_phenotype_gene_clinical", "en", "clinical/models")
.setInputCols(Array("sentence", "token", "word_embeddings"))
.setOutputCol("ner")
val ner_converter = new NerConverterInternal()
.setInputCols(Array("sentence", "token", "ner"))
.setOutputCol("ner_chunk")
.setWhiteList(Array("GENE"))
val chunk2doc = new Chunk2Doc()
.setInputCols("ner_chunk")
.setOutputCol("ner_chunk_doc")
val embedder = BertSentenceEmbeddings
.pretrained("sbiobert_base_cased_mli_onnx", "en", "clinical/models")
.setInputCols(Array("ner_chunk_doc"))
.setOutputCol("sbert_embeddings")
.setCaseSensitive(false)
val resolver = SentenceEntityResolverModel
.pretrained("sbiobertresolve_hgnc_2026", "en", "clinical/models")
.setInputCols(Array("sbert_embeddings"))
.setOutputCol("resolution")
.setDistanceFunction("EUCLIDEAN")
val pipeline = new Pipeline().setStages(Array(
documentAssembler, sentenceDetector, tokenizer, word_embeddings,
ner_model, ner_converter, chunk2doc, embedder, resolver
))
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 res = pipeline.fit(data).transform(data)
Results
| ner_chunk | entity | HGNC Code | Resolution | all_k_results | all_k_cosine_distances | all_k_resolutions | all_k_aux_labels |
|:------------|:---------|:------------|:----------------------------------------|:------------------------------------------------------------------------------------|:------------------------------------------------------------------------------------|:------------------------------------------------------------------------------------|:------------------------------------------------------------------------------------|
| BRCA1 | GENE | HGNC:1100 | BRCA1 [BRCA1 DNA repair associated] | HGNC:1100:::HGNC:18994:::HGNC:23057:::HGNC:28153:::HGNC:24170:::HGNC:11551:::HGN... | 0.0000:::0.0269:::0.0295:::0.0320:::0.0324:::0.0329:::0.0327:::0.0339:::0.0366::... | BRCA1 [BRCA1 DNA repair associated]:::BRSK1 [BR serine/threonine kinase 1]:::BRK... | protein-coding gene :: gene with protein product:::protein-coding gene :: gene w... |
| EGFR | GENE | HGNC:3236 | EGFR [epidermal growth factor receptor] | HGNC:3236:::HGNC:3229:::HGNC:3697:::HGNC:16898:::HGNC:12691:::HGNC:4194:::HGNC:2... | 0.0000:::0.0178:::0.0428:::0.0500:::0.0497:::0.0533:::0.0555:::0.0581:::0.0600::... | EGFR [epidermal growth factor receptor]:::EGF [epidermal growth factor]:::FGR [F... | protein-coding gene :: gene with protein product:::protein-coding gene :: gene w... |
| KRAS | GENE | HGNC:6407 | KRAS [KRas proto-oncogene, GTPase] | HGNC:6407:::HGNC:58375:::HGNC:6406:::HGNC:56729:::HGNC:15865:::HGNC:6308:::HGNC:... | 0.0000:::0.1054:::0.1097:::0.1096:::0.1083:::0.1161:::0.1178:::0.1234:::0.1186::... | KRAS [KRas proto-oncogene, GTPase]:::KDNBY [KDM5D neighbour, Y-linked]:::KRASP1 ... | protein-coding gene :: gene with protein product:::non-coding RNA :: RNA, long n... |
Model Information
| Model Name: | sbiobertresolve_hgnc_2026 |
| Compatibility: | Healthcare NLP 6.4.1+ |
| License: | Licensed |
| Edition: | Official |
| Input Labels: | [sbert_embeddings] |
| Output Labels: | [resolution] |
| Language: | en |
| Size: | 260.2 MB |
| Case sensitive: | false |