Description
bert_token_classifier_ner_bc2gm_gene is a BERT-based token classification model fine-tuned for Named Entity Recognition (NER) of genes and proteins.
It is trained on biomedical data and can recognize mentions of gene and protein names in scientific and clinical text.
Predicted Entities
B-GENE/PROTEIN, O, I-GENE/PROTEIN, PAD
How to use
from sparknlp.base import DocumentAssembler
from sparknlp_jsl.annotator import MedicalBertForTokenClassifier
from sparknlp.annotator import Tokenizer, NerConverter
from pyspark.ml import Pipeline
document_assembler = (
DocumentAssembler()
.setInputCol("text")
.setOutputCol("document")
)
tokenizer = (
Tokenizer()
.setInputCols(["document"])
.setOutputCol("token")
)
token_classifier = (
MedicalBertForTokenClassifier.pretrained(
"bert_token_classifier_ner_bc2gm_gene_onnx",
"en",
"clinical/models"
)
.setInputCols(["token", "document"])
.setOutputCol("ner")
.setCaseSensitive(True)
)
ner_converter = (
NerConverterInternal()
.setInputCols(["document", "token", "ner"])
.setOutputCol("ner_chunk")
)
pipeline = Pipeline(stages=[
document_assembler,
tokenizer,
token_classifier,
ner_converter
])
test_sentence = "ROCK-I, Kinectin, and mDia2 can bind the wild type forms of both RhoA and Cdc42 in a GTP-dependent manner in vitro. These results support the hypothesis that in the presence of tryptophan the ribosome translating tnaC blocks Rho ' s access to the boxA and rut sites, thereby preventing transcription termination."
data = spark.createDataFrame([[test_sentence]]).toDF("text")
model = pipeline.fit(data)
result = model.transform(data)
from johnsnowlabs import nlp, medical
document_assembler = nlp.DocumentAssembler()\
.setInputCol("text")\
.setOutputCol("document")
tokenizer = nlp.Tokenizer()\
.setInputCols(["document"])\
.setOutputCol("token")
token_classifier = medical.BertForTokenClassifier.pretrained(
"bert_token_classifier_ner_bc2gm_gene_onnx",
"en",
"clinical/models"
)\
.setInputCols(["token", "document"])\
.setOutputCol("ner")\
.setCaseSensitive(True)
ner_converter = medical.NerConverterInternal()\
.setInputCols(["document", "token", "ner"])\
.setOutputCol("ner_chunk")
pipeline = Pipeline(stages=[
document_assembler,
tokenizer,
token_classifier,
ner_converter
])
test_sentence = "ROCK-I, Kinectin, and mDia2 can bind the wild type forms of both RhoA and Cdc42 in a GTP-dependent manner in vitro. These results support the hypothesis that in the presence of tryptophan the ribosome translating tnaC blocks Rho ' s access to the boxA and rut sites, thereby preventing transcription termination."
data = spark.createDataFrame([[test_sentence]]).toDF("text")
model = pipeline.fit(data)
result = model.transform(data)
import com.johnsnowlabs.nlp.base.DocumentAssembler
import com.johnsnowlabs.nlp.annotators.Tokenizer
import com.johnsnowlabs.nlp.annotators.ner.NerConverter
import com.johnsnowlabs.nlp.annotators.classifier.dl.MedicalBertForTokenClassifier
import org.apache.spark.ml.Pipeline
val documentAssembler = new DocumentAssembler()
.setInputCol("text")
.setOutputCol("document")
val tokenizer = new Tokenizer()
.setInputCols("document")
.setOutputCol("token")
val tokenClassifier = MedicalBertForTokenClassifier
.pretrained("bert_token_classifier_ner_bc2gm_gene_onnx", "en", "clinical/models")
.setInputCols(Array("token", "document"))
.setOutputCol("ner")
.setCaseSensitive(true)
val nerConverter = new NerConverterInternal()
.setInputCols(Array("document", "token", "ner"))
.setOutputCol("ner_chunk")
val pipeline = new Pipeline()
.setStages(Array(
documentAssembler,
tokenizer,
tokenClassifier,
nerConverter
))
val testSentence = "ROCK-I, Kinectin, and mDia2 can bind the wild type forms of both RhoA and Cdc42 in a GTP-dependent manner in vitro. These results support the hypothesis that in the presence of tryptophan the ribosome translating tnaC blocks Rho ' s access to the boxA and rut sites, thereby preventing transcription termination."
val data = Seq(testSentence).toDF("text")
val model = pipeline.fit(data)
val result = model.transform(data)
Results
+---------+------------+
|text |entity |
+---------+------------+
|ROCK-I |GENE/PROTEIN|
|Kinectin |GENE/PROTEIN|
|mDia2 |GENE/PROTEIN|
|RhoA |GENE/PROTEIN|
|Cdc42 |GENE/PROTEIN|
|tnaC |GENE/PROTEIN|
|Rho |GENE/PROTEIN|
|boxA |GENE/PROTEIN|
|rut sites|GENE/PROTEIN|
+---------+------------+
Model Information
| Model Name: | bert_token_classifier_ner_bc2gm_gene_onnx |
| Compatibility: | Healthcare NLP 6.1.1+ |
| License: | Licensed |
| Edition: | Official |
| Input Labels: | [document, token] |
| Output Labels: | [ner] |
| Language: | en |
| Size: | 403.7 MB |
| Case sensitive: | true |
| Max sentence length: | 128 |