EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

PlantGPT: An Arabidopsis‐Based Intelligent Agent that Answers Questions about Plant Functional Genomics

Ruixiang Zhang iD, Yu Wang, Weiyang Yang, Jun Wen, Weizhi Liu, Shipeng Zhi, Guangzhou Li, Nan Chai, Jiaqi Huang, Yongyao Xie, Xianrong Xie, Letian Chen iD und 3 weitere

Advanced Science · 2025-08 · 12 (30)

DOI: 10.1002/advs.202503926 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Advanced Science, online erschienen am 21.05.2025. Verfasst von Ruixiang Zhang und 14 weiteren Autor:innen. Beteiligte Einrichtung: Guangdong Basic Research Center of Excellence for Precise Breeding of Future Crops, Guangdong Laboratory for Lingnan Modern Agriculture, State Key La…. Hauptthemen laut MEDLINE: Arabidopsis, Genomics, Genome, Plant. Die Arbeit wurde bisher 21-mal zitiert (Crossref) und nennt 40 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China, Biological Breeding-National Science and Technology Major Project, Guangdong Basic Research Center of Excellence for Precise Breeding of Future Crops Major Project.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Research into plant gene function is crucial for developing strategies to increase crop yields. The recent introduction of large language models (LLMs) offers a means to aggregate large amounts of data into a queryable format, but the output can contain inaccurate or false claims known as hallucinations. To minimize such hallucinations and produce high‐quality knowledge‐based outputs, the abstracts of over 60 000 plant research articles are compiled into a Chroma database for retrieval‐augmented generation (RAG). Then linguistic data are used from 13 993 Arabidopsis ( Arabidopsis thaliana ) phenotypes and 23 323 gene functions to fine‐tune the LLM Llama3‐8B, producing PlantGPT, a virtual expert in Arabidopsis phenotype–gene research. By evaluating answers to test questions, it is demonstrated that PlantGPT outperforms general LLMs in answering specialized questions. The findings provide a blueprint for functional genomics research in food crops and demonstrate the potential for developing LLMs for plant research modalities. To provide broader access and facilitate adoption, the online tool http://www.plantgpt.icu is developed, which will allow researchers to use PlantGPT in their scientific investigations.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

ArabidopsisGenomicsGenome, Plant

Stichwörter der Autor:innen

functional genomicslarge language modelsplant gene function retrieval‐augmented generation

Autor:innen und Institutionen

  • Guangdong Basic Research Center of Excellence for Precise Breeding of Future Crops, Guangdong Laboratory for Lingnan Modern Agriculture, State Key Laboratory for Conservation and Utilization of Subtropical Agro-Bioresou…
  • School of Life Sciences, Institute for Immunology, State Key Laboratory of Membrane Biology, China Ministry of Education Key Laboratory of Protein Sciences, Tsinghua University, Beijing, 100084, China.
  • Department of Automation, Tsinghua University, Beijing, 100084, China.
  • Department of Medicine, Tsinghua University, Beijing, 100084, China.
  • Engineering Research Center of Protection and Utilization of Plant Resources, College of Bioscience and Biotechnology, Shenyang Agricultural University, Shenyang, 110866, China.

ORCID-Profile: Ruixiang Zhang, Letian Chen, Miao Gu, Yao-Guang Liu, Qinlong Zhu

Förderung

  • National Natural Science Foundation of China
  • Biological Breeding-National Science and Technology Major Project
  • Guangdong Basic Research Center of Excellence for Precise Breeding of Future Crops Major Project
  • Invigorate the Seed Industry of Guangdong Province

Zitieren

APA

Zhang, R., Wang, Y., Yang, W., Wen, J., Liu, W., Zhi, S., Li, G., Chai, N., Huang, J., Xie, Y., Xie, X., Chen, L., Gu, M., Liu, Y. G., & Zhu, Q. (2025). PlantGPT: An Arabidopsis‐Based Intelligent Agent that Answers Questions about Plant Functional Genomics. Advanced Science, 12(30). https://doi.org/10.1002/advs.202503926

Vancouver

Zhang R, Wang Y, Yang W, Wen J, Liu W, Zhi S, et al. PlantGPT: An Arabidopsis‐Based Intelligent Agent that Answers Questions about Plant Functional Genomics. Advanced Science. 2025;12(30). doi:10.1002/advs.202503926

BibTeX
@article{Zhang2025,
  author = {Zhang, Ruixiang and Wang, Yu and Yang, Weiyang and Wen, Jun and Liu, Weizhi and Zhi, Shipeng and Li, Guangzhou and Chai, Nan and Huang, Jiaqi and Xie, Yongyao and Xie, Xianrong and Chen, Letian and Gu, Miao and Liu, Yao-Guang and Zhu, Qinlong},
  title = {PlantGPT: An Arabidopsis‐Based Intelligent Agent that Answers Questions about Plant Functional Genomics},
  journal = {Advanced Science},
  year = {2025},
  volume = {12},
  number = {30},
  doi = {10.1002/advs.202503926}
}
Kostenlos starten →