数字农科院2.0

A plasticity-aware machine learning framework for genomic prediction and resource-efficient wheat breeding under multi-environment conditions

文献类型： 外文期刊

作者： Lei Li;Cong Zhao;Huihui Li;Xi Tian;Jindong Liu;Duoxia Wang;Keyi Wang;Shuaipeng Fei;Guoliang Wan;Jianqi Zeng;Yachao Dong;Jixin Li;Yidan Jia;Yong Zhang;Xianchun Xia;Xin Ma;Yong He;Yonggui Xiao

作者机构：

关键词： Cross-environment prediction;Genomic selection;Machine learning;Phenotypic plasticity;Smart agriculture;Wheat breeding

期刊名称： Computers and Electronics in Agriculture

ISSN： 0168-1699

年卷期： 2026 年 243 卷

页码：

收录情况： SCIE（2025版） ; ; EI（2025版）

摘要： Smart and data-driven breeding requires models that can reliably predict genotype performance across variable environments while minimizing field experimentation costs. Phenotypic plasticity provides a quantitative descriptor of genotype-environment response, yet it is rarely operationalized within predictive machine-learning systems. Here, we propose a Plasticity-Aware Genomic Selection (PA-GS) framework, which reformulates cross-environment prediction as a supervised machine-learning problem augmented with plasticity-derived features. Plasticity is quantified from multi-environment phenomic data using line-to-population regression slopes, and integrated with genomic markers to improve model generalization and decision support. Using a recombinant inbred line wheat population tested across eight environments for five agronomic traits (grain yield, thousand-kernel weight, kernel number per spike, spike number, and plant height), PA-GS demonstrated robust out-of-environment prediction and enabled systematic analysis of accuracy–cost trade-offs under reduced training scenarios. With only 50% of genotypes evaluated in three environments, the framework achieved prediction accuracies of 0.70 for plant height, 0.54 for kernel number per spike, and 0.59 for thousand-kernel weight, indicating substantial reductions in field trial requirements without loss of predictive reliability. By embedding phenotypic plasticity as machine-learned features, PA-GS provides a scalable, explainable, and resource-efficient digital framework applicable to smart breeding pipelines and computational decision-support systems in agriculture, extending beyond crop or species-specific implementations.

分类号：

  • 相关文献

[1]Editorial: Remote sensing for field-based crop phenotyping. Jiangang Liu,Zhenjiang Zhou,Bo Li. 2024

[2]Development of Machine Learning Methods for Accurate Prediction of Plant Disease Resistance. Liu, Qi,Zuo, Shi-min,Peng, Shasha,Zhang, Hao,Peng, Ye,Li, Wei,Xiong, Yehui,Lin, Runmao,Feng, Zhiming,Li, Huihui,Yang, Jun,Wang, Guo-Liang,Kang, Houxiang. 2024

[3]An interpretable integrated machine learning framework for genomic selection. Jinbu Wang,Jia Zhang,Wenjie Hao,Wencheng Zong,Mang Liang,Fuping Zhao,Longchao Zhang,Lixian Wang,Huijiang Gao,Ligang Wang. 2025

[4]Leveraging Automated Machine Learning for Environmental Data-Driven Genetic Analysis and Genomic Prediction in Maize Hybrids. He, Kunhui,Yu, Tingxi,Gao, Shang,Chen, Shoukun,Li, Liang,Zhang, Xuecai,Huang, Changling,Xu, Yunbi,Wang, Jiankang,Prasanna, Boddupalli M.,Hearne, Sarah,Li, Xinhai,Li, Huihui. 2025

[5]智慧农业背景下的作物信息学：以信息获取、分析和智能决策为例. 李家其,,徐雯颍,,叶婷,,吴晗,,姚雪,,吴洪洪*. 2021

[6]Chromosome changes after polyploidization in Triticeae. Wang, Qiu-Xia,Gao, Ai-Nong,Yang, Xin-Ming,Li, Li-Hui,Wang, Qiu-Xia. 2014

[7]Development and Application of EST-Based Markers Specific for Chromosome Arms of Rye (Secale cereale L.). Xu, H.,Yin, D.,An, D.,Li, L.,Wang, Q.,Li, X.,Yang, X.,Liu, W.. 2012

[8]Synthetic hexaploid wheat and its utilization for wheat genetic improvement in China. Li, Jun,Wei, Huiting,Hu, Xiaorong,Zou, Yuchun,Liu, Dengcai,Zhang, Lianquan,Zheng, Youliang,He, Zhouhu,He, Zhouhu,Liu, Dengcai. 2009

[9]Resequencing of 145 Landmark Cultivars Reveals Asymmetric Sub-genome Selection and Strong Founder Genotype Effects on Wheat Breeding in China. 郝晨阳,侯健,李甜,刘红霞,刘旭,张学勇. 2020

[10]Identification and development of a KASP functional marker of TaTAP46-5A associated with kernel weight in wheat (Triticum aestivum). Youfu Zhang,Tian Li,Yuke Geng,Yamei Wang,Yunchuan Liu,Huifang Li,Chenyang Hao,Huajun Wang,Xunwu Shang,Xueyong Zhang. 2021

[11]Resequencing Of 145 Landmark Cultivars Reveals Asymmetric Sub-Genome Selection And Strong Founder Genotype Effects On Wheat Breeding In China. Hao, CY, Jiao, CZ, Hou, J, Li, T, Liu, HX, Wang, YQ, Zheng, J, Liu, H, Bi, ZH, Xu, FF, Zhao, J, Ma, L, Wang, YM, Majeed, U, Liu, X, Appels, R, Maccaferri, M, Tuberosa, R, Lu, HF, Zhang, XY. 2020

[12]Trade-offs and evolution of thermal adaptation in the Irish potato famine pathogen Phytophthora infestans. Yang, Li-Na,Zhu, Wen,Wu, E-Jiao,Yang, Ce,Shang, Li-Ping,Thrall, Peter H.,Burdon, Jeremy J.,Jin, Li-Ping,Zhan, Jiasui.

[13]A dynamic framework for quantifying the genetic architecture of phenotypic plasticity. Wang, Zhong,Lv, Yafei,Xu, Fang,Zhou, Tao,Li, Xin,Feng, Sisi,Wu, Rongling,Pang, Xiaoming,Li, Jiahan,Li, Zhikang,Wu, Rongling.

[14]Long-Term Overgrazing-Induced Memory Decreases Photosynthesis O.f Clonal Offspring In A Perennial Grassland Plant. Ren, WB, Hu, NN, Hou, XY, Zhang, JZ, Guo, HQ, Liu, ZY, Kong, LQ, Wu, ZN, Wang, H, Li, XL. 2017

[15]Sandbur Drought Tolerance Reflects Phenotypic Plasticity Based on the Accumulation of Sugars, Lipids, and Flavonoid Intermediates and the Scavenging of Reactive Oxygen Species in the Root. Zhiyuan Yang,Chao Bai,Peng Wang,Wei Dong Fu,Le Wang,Zhen Song,Xin Xi,Hanwen Wu,Guo-Liang Zhang*,Jia-He Wu. 2021

[16]Nutrient Characteristics In Relation To P.lant Size Of A P erennial Grass Under Grazing Exclusion In Degraded Grassland. Liu, ZY, Baoyin, TGT, Duan, JJ, Yang, GF, Sun, J, Li, XL. 2018

[17]Sublethal dose of warfarin induction promotes the accumulation of warfarin resistance in susceptible Norway rats. Xiaohui Ma,Yan Chen,Yaqi Ying,Yuanzhao Geng,Dawei Wang,Ning Li,Xiao-Hui Liu,Ying Song. 2021

[18]Sandbur drought tolerance reflects phenotypic plasticity based on the accumulation of sugars, lipids, and flavonoid intermediates and the scavenging of reactive oxygen species in the root. Zhiyuan Yang,Chao Bai,Peng Wang,Weidong Fu,Le Wang,Zhen Song,Xin Xi,Hanwen Wu,Guoliang Zhang,Jiahe Wu. 2022

[19]Shoot–Root Interplay Mediates Defoliation-Induced Plant Legacy Effect. Xiliang Li,Zhen Zhang,Fenghui Guo,Junjie Duan,Juan Sun. 2021

[20]Analysis of the Development Status and Prospect of China’s Agricultural Sensor Market under Smart Agriculture. Ning Sun,Beibei Fan,Yahui Ding,Yuanjinsheng Liu,Yuyun Bi,Patience Afi Seglah,Chunyu Gao. 2023

作者其他论文 更多>>