Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Applying BioBERT to Extract Germline Gene-Disease Associations for Building a Knowledge Graph from the Biomedical Literature

Armando D. Diaz Gonzalez, Kevin S. Hughes, Songhui Yue, Sean T. Hayes

TL;DR

The paper tackles the challenge of extracting germline gene-disease associations from biomedical literature to build a scalable knowledge graph. It presents SimpleGermKG, a four-stage pipeline that combines domain dictionaries, BioBERT-based NER, ontology- and rule-based normalization, and a data-source–driven semantic relation to PubMed IDs, yielding a KG with 297 genes, 130 diseases, and 46,747 triples stored in Neo4j. Key contributions include an automated KG construction workflow, explicit disambiguation through Named Entity Normalization, and a part-whole relation framework for linking entities to sources, along with graph-based visualizations. The work enables efficient retrieval and analysis of gene–disease associations at scale and sets the stage for integrating germline knowledge with broader biomedical data sources.

Abstract

Published biomedical information has and continues to rapidly increase. The recent advancements in Natural Language Processing (NLP), have generated considerable interest in automating the extraction, normalization, and representation of biomedical knowledge about entities such as genes and diseases. Our study analyzes germline abstracts in the construction of knowledge graphs of the of the immense work that has been done in this area for genes and diseases. This paper presents SimpleGermKG, an automatic knowledge graph construction approach that connects germline genes and diseases. For the extraction of genes and diseases, we employ BioBERT, a pre-trained BERT model on biomedical corpora. We propose an ontology-based and rule-based algorithm to standardize and disambiguate medical terms. For semantic relationships between articles, genes, and diseases, we implemented a part-whole relation approach to connect each entity with its data source and visualize them in a graph-based knowledge representation. Lastly, we discuss the knowledge graph applications, limitations, and challenges to inspire the future research of germline corpora. Our knowledge graph contains 297 genes, 130 diseases, and 46,747 triples. Graph-based visualizations are used to show the results.

Applying BioBERT to Extract Germline Gene-Disease Associations for Building a Knowledge Graph from the Biomedical Literature

TL;DR

The paper tackles the challenge of extracting germline gene-disease associations from biomedical literature to build a scalable knowledge graph. It presents SimpleGermKG, a four-stage pipeline that combines domain dictionaries, BioBERT-based NER, ontology- and rule-based normalization, and a data-source–driven semantic relation to PubMed IDs, yielding a KG with 297 genes, 130 diseases, and 46,747 triples stored in Neo4j. Key contributions include an automated KG construction workflow, explicit disambiguation through Named Entity Normalization, and a part-whole relation framework for linking entities to sources, along with graph-based visualizations. The work enables efficient retrieval and analysis of gene–disease associations at scale and sets the stage for integrating germline knowledge with broader biomedical data sources.

Abstract

Published biomedical information has and continues to rapidly increase. The recent advancements in Natural Language Processing (NLP), have generated considerable interest in automating the extraction, normalization, and representation of biomedical knowledge about entities such as genes and diseases. Our study analyzes germline abstracts in the construction of knowledge graphs of the of the immense work that has been done in this area for genes and diseases. This paper presents SimpleGermKG, an automatic knowledge graph construction approach that connects germline genes and diseases. For the extraction of genes and diseases, we employ BioBERT, a pre-trained BERT model on biomedical corpora. We propose an ontology-based and rule-based algorithm to standardize and disambiguate medical terms. For semantic relationships between articles, genes, and diseases, we implemented a part-whole relation approach to connect each entity with its data source and visualize them in a graph-based knowledge representation. Lastly, we discuss the knowledge graph applications, limitations, and challenges to inspire the future research of germline corpora. Our knowledge graph contains 297 genes, 130 diseases, and 46,747 triples. Graph-based visualizations are used to show the results.
Paper Structure (15 sections, 2 figures, 1 algorithm)

This paper contains 15 sections, 2 figures, 1 algorithm.

Table of Contents

  1. Introduction
  2. Related Work
  3. Ontology-based Knowledge Graph Construction
  4. Automatic Knowledge Graph Construction
  5. Method
  6. Data Sources
  7. Pre-processing
  8. Named Entity Recognition
  9. Named Entity Normalization
  10. Semantic Relation
  11. Results
  12. Knowledge Graph Construction
  13. Knowledge Graph-based Visualization
  14. Discussion and Future Work
  15. Conclusion

Figures (2)

  • Figure 1: SimpleGermKG Architecture. This figure illustrates the overall workflow of SimpleGermKG. BioBERT is pre-trained on PubMed abstracts to extract germline genes and diseases. Then, ambiguated entities are eliminated and a semantic relation approach is utilized to build a knowledge graph (KG) and improve the interpretability of our results.
  • Figure 2: Graph Representation of Gene-PubMed-disease Associations. Graphs are generated by querying the knowledge graph stored in Neo4j