文献类型： 外文期刊

作者： Gan, Yu ¹ ; Liu, Zhenya ¹ ; Zhang, Fan ¹ ; Xu, Qi ² ; Wang, Xu ¹ ; Xue, Hui ¹ ; Su, Xiangnian ¹ ; Ma, Wenqi ² ; Long, Qiming ² ; Ma, Anqi ² ; Huang, Guizhou ² ; Liu, Wenwen ² ; Xu, Xiaodong ¹ ; Sun, Lei ³ ; Zhang, Yingchun ² ; Liu, Yuting ² ; Fang, Xinyue ² ; Li, Chaochao ¹ ; Yang, Xuanwen ¹ ; Wei, Pengcheng ¹ ; Fan, Xiucai ³ ; Zhang, Chuan ⁴ ; Zhang, Pengpai ¹ ; Liu, Chonghuai ³ ; Zhou, Lianzhu ¹ ; Zhang, Zhiwu ⁵ ; Wang, Yiwen ¹ ; Liu, Zhongjie ¹ ; Zhou, Yongfeng ¹ ;

作者机构： 1.Chinese Acad Trop Agr Sci, Trop Crops Genet Resources Inst, Natl Key Lab Trop Crop Breeding, Xueyuan Rd, Haikou 571101, Peoples R China

2.Chinese Acad Agr Sci, Agr Genom Inst Shenzhen,Minist Agr & Rural Affairs, Shenzhen Branch,Key Lab Synthet Biol, Guangdong Lab Lingnan Modern Agr,Natl Key Lab Trop, Shenzhen, Peoples R China

3.Chinese Acad Agr Sci, Zhengzhou Fruit Res Inst, Southern End Weilai Rd, Zhengzhou 450009, Peoples R China

4.Chinese Acad Agr Sci, Zhengzhou Fruit Res Inst, Zhengzhou, Peoples R China

5.Xinjiang Acad Agr Sci, Inst Hort Crops, State Key Lab Genet Improvement & Germplasm Innova, Key Lab Genome Res & Genet Improvement Xinjiang Ch, Nanchang Rd, Urumqi 830091, Peoples R China

6.Henan Univ, Sch Life Sci, Minglun St, Kaifeng 475004, Peoples R China

7.Chongqing Med Univ, Women & Childrens Hosp, Dept Prenatal Diag Ctr, Chongqing 401147, Peoples R China

8.China Resources Res Inst Sci & Technol, Inst Life & Hlth, Pak Shek Kok Rd, Hong Kong 999077, Peoples R China

期刊名称：HORTICULTURE RESEARCH （ 影响因子：8.5； 五年影响因子：9.1 ）

ISSN： 2662-6810

年卷期： 2025 年 12 卷 8 期

页码：

收录情况： SCI

摘要： Crop pests significantly reduce crop yield and threaten global food security. Conventional pest control relies heavily on insecticides, leading to pesticide resistance and ecological concerns. However, crops and their wild relatives exhibit varied levels of pest resistance, suggesting the potential for breeding pest-resistant varieties. This study integrates deep learning (DL)/machine learning (ML) algorithms, plant phenomics, quantitative genetics, and transcriptomics to conduct genomic selection (GS) of pest resistance in grapevine. Building deep convolutional neural networks (DCNNs), we accurately assess pest damage on grape leaves, achieving 95.3% classification accuracy (VGG16) and a 0.94 correlation in regression analysis (DCNN-PDS). The pest damage was phenotyped as binary and continuous traits, and genome resequencing data from 231 grapevine accessions were combined in a Genome-Wide Association Studies, which maps 69 quantitative trait locus (QTLs) and 139 candidate genes involved in pest resistance pathways, including jasmonic acid, salicylic acid, and ethylene. Combining this with transcriptome data, we pinpoint specific pest-resistant genes such as ACA12 and CRK3, which are crucial in herbivore responses. ML-based GS demonstrates a high accuracy (95.7%) and a strong correlation (0.90) in predicting pest resistance as binary and continuous traits in grapevine, respectively. In general, our study highlights the power of DL/ML in plant phenomics and GS, facilitating genomic breeding of pest-resistant grapevine.