Improving large language models for miRNA information extraction via prompt engineering
This study established high-quality miRNA datasets to support information extraction and knowledge discovery. The overall performance of LLMs in this study proved limited, and challenges remain in processing miRNA-related information extraction. However, optimized prompt combinations can substantially improve performance. Future work should focus on further refinement of LLMs to accelerate the discovery and application of potential diagnostic and therapeutic targets.
Authors
- Erman Wu
- Jiao Wang (ORCID: https://orcid.org/0000-0003-2790-7828)
- Rongrong Wu
- Yiqing Zhou (ORCID: https://orcid.org/0000-0002-4553-5207)
- Hui Zong (ORCID: https://orcid.org/0000-0002-9142-5017)
- Bairong Shen (ORCID: https://orcid.org/0000-0003-2899-1531)
- Chengqi Zhang (ORCID: https://orcid.org/0000-0001-5715-7154)
- Jiakun Li (ORCID: https://orcid.org/0000-0003-1487-4967)
- Tong Tang
- Yingbo Zhang
Institutions
- Chinese Academy of Tropical Agricultural Sciences (CN)
- Universidade da Coruña (ES)
- Sichuan University (CN)
- Soochow University (CN)
- West China Hospital of Sichuan University (CN)
- Tropical Crops Genetic Resources Institute (CN)
Publication Details
- Journal
- Computer Methods and Programs in Biomedicine
- Published
- 2025-08-20
- DOI
- https://doi.org/10.1016/j.cmpb.2025.109033
- Citations
- 1
- Primary Topic
- Topic Modeling
- Type
- article
- Field-Weighted Citation Impact
- 2.48
Funders
- National Natural Science Foundation of China
- Sichuan Province Science and Technology Support Program