EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC-ND 4.0

Decoding genetic basis of nitrogen-use efficiency in maize using AI-generated deep phenotypes

Haoyan Yang, Lingju Zeng, Xiangjian Gou, Yang Shao, Xianlong Song, Shuang Zhang, Xiaoyan Qian, Zhenwei Zhang, Xiao Wang, Haitao Li, Bo Peng, Juliet Nkiruka Anyanwu und 18 weitere

Molecular Plant · 2026-11 · 19 (11) · 2198-2219

DOI: 10.1016/j.molp.2026.08.005 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Molecular Plant, 2026-11. Verfasst von Haoyan Yang und 29 weiteren Autor:innen. Beteiligte Einrichtung: National Key Laboratory of Crop Genetic Improvement, Huazhong Agricultural University, Wuhan 430070, China; Hubei Hongshan Laboratory, Wuhan 430070, …. Hauptthemen laut MEDLINE: Zea mays, Nitrogen, Artificial Intelligence. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 85 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0). Gefördert von: German Research Foundation, Ministry of Science and Technology of the People's Republic of China, National Natural Science Foundation of China.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Improving nitrogen-use efficiency (NUE) is essential for sustainable agriculture, yet conventionally measured plant characteristics have limited value as NUE proxies. Here, we show that artificial intelligence (AI) can uncover previously unrecognized phenotypic variation associated with NUE, showing genetic variation that is largely missed by conventional phenotypes. We trained a convolutional neural network (CNN) on 25,080 maize images to learn features that distinguish how plants respond to low- and high-nitrogen (N) conditions, achieving 96.7% accuracy. The learned features were defined as deep phenotypes. Compared with conventional phenotypes, deep phenotypes showed greater phenotypic variation and higher heritability, enabling the identification of 523 significant loci compared with 21 for conventional phenotypes. We next investigated candidate genes underlying these loci and used these findings to interpret the learned features. Lower CNN layers largely reflected visual patterns overlapping with conventional phenotypes, whereas deeper layers encoded additional features associated with N-responsive genetic variation. To validate candidate genes identified by the AI framework, we functionally characterized Liguleless2 (LG2), a basic-leucine zipper transcription factor, and demonstrated that lg2 mutants exhibit enhanced root architecture and increased N-uptake efficiency. Field trials of 200 hybrids across diverse N environments further supported the AI findings, with each beneficial allele increasing ear weight by an average of 18 g per plot under low-N conditions. These results show how integrating AI and biology can uncover biologically relevant variation underlying complex traits such as NUE and enhance the interpretability of AI models.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Zea maysNitrogenArtificial IntelligencePhenotypeConvolutional Neural NetworksPlant Proteins

Stichwörter der Autor:innen

artificial intelligencedeep phenotypegeneticshigh-throughput phenotypingnitrogen-use efficiency

Substanzen

NitrogenPlant Proteins

Autor:innen und Institutionen

  • National Key Laboratory of Crop Genetic Improvement, Huazhong Agricultural University, Wuhan 430070, China; Hubei Hongshan Laboratory, Wuhan 430070, China.
  • Department of Agronomy, Iowa State University, Ames, IA 50011-1051, USA.
  • Department of Crop and Soil Sciences, Washington State University, Pullman, WA 99164, USA.
  • Provincial Key Laboratory of Agrobiology, Jiangsu Academy of Agricultural Sciences, Nanjing 210014, China.
  • Max Planck Institute of Molecular Plant Physiology, Am Mühlenberg 1, 14476 Potsdam-Golm, Germany; Program Center MetaCom, Leibniz Institute of Plant Biochemistry, Weinberg 3, Halle (Saale) 06120, Germany.
  • Biotechnology Research Institute, Chinese Academy of Agricultural Sciences, Beijing 100081, China.

Förderung

  • German Research Foundation
  • Ministry of Science and Technology of the People's Republic of China
  • National Natural Science Foundation of China

Zitieren

APA

Yang, H., Zeng, L., Gou, X., Shao, Y., Song, X., Zhang, S., Qian, X., Zhang, Z., Wang, X., Li, H., Peng, B., Anyanwu, J. N., Zheng, Z., Han, L., Zhou, L., Bulut, M., Song, P., Yang, W., Xiao, Y., …, & Guo, T. (2026). Decoding genetic basis of nitrogen-use efficiency in maize using AI-generated deep phenotypes. Molecular Plant, 19(11), 2198-2219. https://doi.org/10.1016/j.molp.2026.08.005

Vancouver

Yang H, Zeng L, Gou X, Shao Y, Song X, Zhang S, et al. Decoding genetic basis of nitrogen-use efficiency in maize using AI-generated deep phenotypes. Molecular Plant. 2026;19(11):2198-2219. doi:10.1016/j.molp.2026.08.005

BibTeX
@article{Yang2026,
  author = {Yang, Haoyan and Zeng, Lingju and Gou, Xiangjian and Shao, Yang and Song, Xianlong and Zhang, Shuang and Qian, Xiaoyan and Zhang, Zhenwei and Wang, Xiao and Li, Haitao and Peng, Bo and Anyanwu, Juliet Nkiruka and Zheng, Zihao and Han, Linqian and Zhou, Ling and Bulut, Mustafa and Song, Peng and Yang, Wanneng and Xiao, Yingjie and Li, Wenqiang and Dai, Mingqiu and Qiu, Fazhan and Zhang, Jian and Wang, Baobao and Fernie, Alisdair R and Wang, Haiyang and Zhao, Han and Li, Xianran and Yan, Jianbing and Guo, Tingting},
  title = {Decoding genetic basis of nitrogen-use efficiency in maize using AI-generated deep phenotypes},
  journal = {Molecular Plant},
  year = {2026},
  volume = {19},
  number = {11},
  pages = {2198--2219},
  doi = {10.1016/j.molp.2026.08.005}
}
Kostenlos starten →