Development and Study of a Knowledge Graph for Retrieving the Relationship between BVDV and Related Genes

Background: Bovine viral diarrhea virus（BVDV）can cause diarrhea, abortion, and immunosuppression in cattle, imposing huge economic losses for the global cattle industry. The pathogenic and immune mechanisms of BVDV remain elusive. The development of a BVDV-gene knowledge base can provide clues to reveal the interaction of BVDV with host cells. However, the traditional method of manually establishing a knowledge base is time-consuming and inefficient. The method of developing a knowledge base based on deep learning has noticeably attracted scholars' attention recently. background: Bovine viral diarrhea virus (BVDV) can cause damage to bovine intestinal wall, loss of villi, hindrance of growth and development, weight loss and other adverse effects. The construction of BVDV-gene knowledge base is of great significance for the prevention and treatment of bovine diarrhea diseases and the healthy development of dairy industry. Biomedical literature contains untapped biomedical knowledge, and the traditional method of manually constructing knowledge base is time-consuming and inefficient. Most of them use relational database to store data, which is not conducive to semantic information retrieval. Objective: The study aimed to explore the substitution of deep learning for manual mining of BVDV-related genes and to develop a knowledge graph of the relationship between BVDV and related genes. Methods: A deep learning-based biomedical knowledge graph development method was proposed, which used deep learning to mine biomedical knowledge, model BVDV and various gene concepts, and store data in a graphical database. First, the PubMed database was used as the data source and crawler technology to obtain abstract data on the relationship between BVDV and various host genes. Pre-trained BioBERT model was used for biomedical named entity recognition to obtain all types of gene entities, and the pre-trained BERT model was utilized for relationship extraction to achieve the relationship between BVDV and various gene entities. Then, it was combined with manual proofreading to obtain structured triple data with high accuracy. Finally, the Neo4j graph database was used to store data and to develop the knowledge graph of the relationship between BVDV and related genes. method: First of all, we use PubMed biomedical literature database as the data source and crawler technology to obtain literature abstract data of the relationship between BVDV and various genes. Pre-trained model BioBERT for biomedical named entity recognition to get all kinds of gene entities and pre-trained model BERT for relationship extraction to get the relationship between BVDV and various gene entities. And then combined with manual proofreading to obtain structured triple data with high accuracy. Finally, the Neo4j graph database is used to store the data, and the knowledge graph of the relationship between BVDV and all kinds of genes is constructed Results: The results showed the obtainment of 71 gene entity types, including PRL4, MMP-7, TGIF1, etc. 9 relation types of BVDV and gene entities were obtained, including "can downregulate expression of", "can upregulate expression of", "can suppress expression of", etc. The knowledge graph was developed using deep learning to mine biomedical knowledge combined with manual proofreading, which was faster and more efficient than the traditional method of establishing knowledge base manually, and the retrieval of semantic information by storing data in graph database was also more efficient. Conclusion: A BVDV-gene knowledge graph was preliminarily developed, which provided a basis for studying the interaction between BVDV and host cells. conclusion: The method of using the method of deep learning to mine biomedical knowledge combined with manual proofreading to construct knowledge graph is faster and more efficient than the traditional method of constructing knowledge base manually, and the retrieval of semantic information by storing data in graph database is also more efficient. other: The method of using the method of deep learning to mine biomedical knowledge combined with manual proofreading to construct knowledge graph is faster and more efficient than the traditional method of constructing knowledge base manually.