EUVIMEDOpdag EUVIMED
Open access · CC BY-NC-ND 4.0

VAIV bio-discovery service using transformer model and retrieval augmented generation

Seonho Kim, Juntae Yoon

BMC Bioinformatics · 2024

DOI: 10.1186/s12859-024-05903-6 ↗

At a glance

Journal article in BMC Bioinformatics, 2024. Written by Seonho Kim and 1 co-authors. Institution: Department of Computer Science, Sogang University, 35, Baekbeom-Ro, Mapo-Gu, Seoul, Korea. shkim.lex@gmail.com. Major MEDLINE topics: Natural Language Processing. Cited 5 times so far (Crossref); 34 references. The full text is freely available (open access, CC BY-NC-ND 4.0). Funded by: National Research Foundation of Korea (NRF).

AbstractSubjectsBibliografiske oplysningerCiteRelated studies

Abstract (original language)

BACKGROUND: There has been a considerable advancement in AI technologies like LLM and machine learning to support biomedical knowledge discovery. MAIN BODY: We propose a novel biomedical neural search service called 'VAIV Bio-Discovery', which supports enhanced knowledge discovery and document search on unstructured text such as PubMed. It mainly handles with information related to chemical compound/drugs, gene/proteins, diseases, and their interactions (chemical compounds/drugs-proteins/gene including drugs-targets, drug-drug, and drug-disease). To provide comprehensive knowledge, the system offers four search options: basic search, entity and interaction search, and natural language search. We employ T5slim_dec, which adapts the autoregressive generation task of the T5 (text-to-text transfer transformer) to the interaction extraction task by removing the self-attention layer in the decoder block. It also assists in interpreting research findings by summarizing the retrieved search results for a given natural language query with Retrieval Augmented Generation (RAG). The search engine is built with a hybrid method that combines neural search with the probabilistic search, BM25. CONCLUSION: As a result, our system can better understand the context, semantics and relationships between terms within the document, enhancing search accuracy. This research contributes to the rapidly evolving biomedical field by introducing a new service to access and discover relevant knowledge.

Subjects

MeSH terms (MEDLINE)

Natural Language ProcessingData MiningKnowledge DiscoveryPubMedSearch EngineMachine LearningInformation Storage and RetrievalNeural Networks, Computer

Author keywords

Biomedical interaction extractionEmbeddingLLMNatural language processingNeural searchRAGT5Text miningTransformer

Authors and institutions

  • Department of Computer Science, Sogang University, 35, Baekbeom-Ro, Mapo-Gu, Seoul, Korea. shkim.lex@gmail.com.
  • VAIV Company Inc, 97, Dokseodang-Ro, Yongsan-Gu, Seoul, Korea. jtyoon@vaiv.kr.

Funding

  • National Research Foundation of Korea (NRF)

Cite

APA

Kim, S., & Yoon, J. (2024). VAIV bio-discovery service using transformer model and retrieval augmented generation. BMC Bioinformatics. https://doi.org/10.1186/s12859-024-05903-6

Vancouver

Kim S, Yoon J. VAIV bio-discovery service using transformer model and retrieval augmented generation. BMC Bioinformatics. 2024. doi:10.1186/s12859-024-05903-6

BibTeX
@article{Kim2024,
  author = {Kim, Seonho and Yoon, Juntae},
  title = {VAIV bio-discovery service using transformer model and retrieval augmented generation},
  journal = {BMC Bioinformatics},
  year = {2024},
  doi = {10.1186/s12859-024-05903-6}
}
Start for free →