EUVIMEDOpdag EUVIMED
Open access · CC BY 4.0

SynVectorDB: embedding-based retrieval system for synthetic biology parts

Hao Li, Jiani Hu, Jie Song iD, Wei Zhou

Database · 2026

DOI: 10.1093/database/baaf088 ↗

At a glance

Journal article in Database, 2026. Written by Hao Li and 3 co-authors. Institution: Department of Endodontics, Shanghai Ninth People's Hospital, Shanghai Jiao Tong University School of Medicine, College of Stomatology, Shanghai Jiao …. Major MEDLINE topics: Synthetic Biology, Software, Information Storage and Retrieval, Databases, Genetic. Cited 2 times so far (Crossref); 17 references. The full text is freely available (open access, CC BY 4.0). Funded by: National Natural Science Foundation of China.

AbstractSubjectsBibliografiske oplysningerCiteRelated studies

Abstract (original language)

Synthetic biology part discovery faces significant challenges due to inconsistent data organization and limited semantic search capabilities across existing repositories. We developed SynVectorDB, an embedding-based retrieval system that addresses these limitations through methodological innovations in data integration and AI-driven semantic search. Our approach integrates 19 850 biological parts from multiple sources (Addgene, iGEM Registry, laboratory collections), implementing systematic curation protocols that resulted in 7656 parts achieving verified status through literature-based validation and reliability assessment. We introduce a novel three-level hierarchical classification system organizing parts into functionally coherent categories (DNA Elements, RNA Elements, Coding Sequences, and Application Constructs) with detailed subcategorization. The core technical contribution employs BGE-M3 multilingual embeddings within a scalable vector database architecture to enable semantic similarity matching that significantly outperforms keyword-based retrieval methods. Standardized curation workflows enhance data comparability and search accuracy across heterogeneous sources. The dual deployment architecture ensures high performance through cloud services while maintaining open-source accessibility and deployment flexibility. The system maintains SBOL3 compatibility while providing innovative solutions for biological part organization and retrieval. Database URL: SynVectorDB is available in multiple deployment modes: web interface (https://svdb.sjtu.bio), local installation and source code (https://github.com/AilurusBio/synbio-parts-db), and MCP server integration for AI assistants (https://www.npmjs.com/package/synvectordb).

Subjects

MeSH terms (MEDLINE)

Synthetic BiologySoftwareInformation Storage and RetrievalDatabases, GeneticBiocuration

Authors and institutions

  • Department of Endodontics, Shanghai Ninth People's Hospital, Shanghai Jiao Tong University School of Medicine, College of Stomatology, Shanghai Jiao Tong University, Shanghai, 200011, China.
  • National Center for Stomatology, National Clinical Research Center for Oral Diseases, Shanghai Key Laboratory of Stomatology, Shanghai, 200025, China.
  • Research and Development Department, Beijing Xunzhu Biotechnology Co. Ltd., Beijing, 100080, China.
  • School of Chemistry and Molecular Biosciences, The University of Queensland, Brisbane, QLD, 4072, Australia.

ORCID profiles: Jie Song

Funding

  • National Natural Science Foundation of China

Cite

APA

Li, H., Hu, J., Song, J., & Zhou, W. (2026). SynVectorDB: embedding-based retrieval system for synthetic biology parts. Database. https://doi.org/10.1093/database/baaf088

Vancouver

Li H, Hu J, Song J, Zhou W. SynVectorDB: embedding-based retrieval system for synthetic biology parts. Database. 2026. doi:10.1093/database/baaf088

BibTeX
@article{Li2026,
  author = {Li, Hao and Hu, Jiani and Song, Jie and Zhou, Wei},
  title = {SynVectorDB: embedding-based retrieval system for synthetic biology parts},
  journal = {Database},
  year = {2026},
  doi = {10.1093/database/baaf088}
}
Start for free →