EUVIMEDEUVIMED entdecken
Open Access

Development of Large Language Model Specialized into Microbiome Datasets: an Application of Self-Evaluation and Scoring Comparison with Conventional Natural Language Processing Markers

Chan Kyu Park, Sung Hwan Bae, Hyeon Woo Park, Nam Su Oh, Young Jun Kim, Young-Wan Kim, Tae Jin Cho, Ying Li, Jianmin Chai, Jiangchao Zhao, Hyung Taek Cho, Ji Hoon Jung und 3 weitere

Journal of Microbiology and Biotechnology · 2026

DOI: 10.4014/jmb.2511.11050 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Microbiology and Biotechnology, 2026. Verfasst von Chan Kyu Park und 14 weiteren Autor:innen. Beteiligte Einrichtung: Department of Food and Biotechnology, Korea University, Sejong 30019, Republic of Korea. Hauptthemen laut MEDLINE: Large Language Models, Natural Language Processing, Gastrointestinal Microbiome, Microbiota. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 16 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar. Gefördert von: Ministry of Food and Drug Safety, Korea Institute for Advancement of Technology, Ministry of Trade, Industry and Energy.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The gut microbiome plays a fundamental role in host metabolism, immune regulation, and disease development. With the rapid accumulation of multi-omics and literature data, the microbiome field now faces the challenge of efficiently extracting scientific insights from massive, heterogeneous datasets. Artificial intelligence (AI) and large language models (LLMs) provide promising tools to address this complexity by enabling integrative analysis and knowledge synthesis across diverse biological sources. In this study, we developed METABOLISM, a microbiome-specialized LLM fine-tuned on 160,000 scientific abstracts to enhance literature-based contextual understanding of microbiome-liver interactions and related biological mechanisms. Using LoRA-based parameter-efficient training, METABOLISM was optimized for domain-specific reasoning and response generation. Model performance was evaluated through both automated Phi-4 scoring (a large language model-based evaluator for relevance, informativeness, and fluency) and structured human expert rubric assessments involving 20 domain specialists. The fine-tuned METABOLISM achieved superior relevance and clarity scores (mean > 7.5 ± 0.06) compared with general-purpose LLMs such as Gemma-3-12B-IT and ChatGPT-4o. Correlation analysis revealed weak to moderate negative relationships (R = -0.65, p < 0.0001) between traditional NLP metrics (BLEU, ROUGE) and human expert rubric scores, with a similar trend observed for correlations with Phi-4-based automated evaluation scores, indicating the limitations of surface-level similarity measures in biomedical contexts. Overall, our findings demonstrate that microbiome-adapted LLMs can effectively distill high-volume scientific data into biologically meaningful insights, supporting more efficient and interpretable research in microbiology and systems biology.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Large Language ModelsNatural Language ProcessingGastrointestinal MicrobiomeMicrobiotaHumansArtificial IntelligenceGenerative Artificial Intelligence

Stichwörter der Autor:innen

BioinformaticsDomain adaptationHuman evaluationLarge language modelMicrobiomePhi-4 metric

Autor:innen und Institutionen

  • Department of Food and Biotechnology, Korea University, Sejong 30019, Republic of Korea.
  • Guangdong Provincial Key Laboratory of Animal Molecular Design and Precise Breeding, Foshan University, Foshan 528225, P.R. China.
  • Guangdong Laboratory for Lingnan Modern Agriculture, South China Agricultural University, Guangzhou 510642, China.
  • The Bioinformatix, Gwangmyeong 14348, Republic of Korea.
  • College of Korean Medicine, Kyung Hee University, Seoul 02447, Republic of Korea.
  • Department of Health Behavior and Nutrition Sciences, University of Delaware, Newark, DE 19711, USA.

Förderung

  • Ministry of Food and Drug Safety
  • Korea Institute for Advancement of Technology
  • Ministry of Trade, Industry and Energy

Zitieren

APA

Park, C. K., Bae, S. H., Park, H. W., Oh, N. S., Kim, Y. J., Kim, Y. W., Cho, T. J., Li, Y., Chai, J., Zhao, J., Cho, H. T., Jung, J. H., Park, J., Kim, T. G., & Kim, J. K. (2026). Development of Large Language Model Specialized into Microbiome Datasets: an Application of Self-Evaluation and Scoring Comparison with Conventional Natural Language Processing Markers. Journal of Microbiology and Biotechnology. https://doi.org/10.4014/jmb.2511.11050

Vancouver

Park CK, Bae SH, Park HW, Oh NS, Kim YJ, Kim YW, et al. Development of Large Language Model Specialized into Microbiome Datasets: an Application of Self-Evaluation and Scoring Comparison with Conventional Natural Language Processing Markers. Journal of Microbiology and Biotechnology. 2026. doi:10.4014/jmb.2511.11050

BibTeX
@article{Park2026,
  author = {Park, Chan Kyu and Bae, Sung Hwan and Park, Hyeon Woo and Oh, Nam Su and Kim, Young Jun and Kim, Young-Wan and Cho, Tae Jin and Li, Ying and Chai, Jianmin and Zhao, Jiangchao and Cho, Hyung Taek and Jung, Ji Hoon and Park, Jinbong and Kim, Tae Gyun and Kim, Jae Kyeom},
  title = {Development of Large Language Model Specialized into Microbiome Datasets: an Application of Self-Evaluation and Scoring Comparison with Conventional Natural Language Processing Markers},
  journal = {Journal of Microbiology and Biotechnology},
  year = {2026},
  doi = {10.4014/jmb.2511.11050}
}
Kostenlos starten →