PNNGS, a multi-convolutional parallel neural network for genomic selection

被引:2
作者
Xie, Zhengchao [1 ]
Weng, Lin [1 ]
He, Jingjing [1 ]
Feng, Xianzhong [2 ]
Xu, Xiaogang [3 ]
Ma, Yinxing [1 ]
Bai, Panpan [1 ]
Kong, Qihui [1 ]
机构
[1] Zhejiang Lab, Res Ctr Life Sci Comp, Hangzhou, Peoples R China
[2] Chinese Acad Sci, Northeast Inst Geog & Agroecol, Key Lab Soybean Mol Design Breeding, Changchun, Peoples R China
[3] Zhejiang Gongshang Univ, Sch Comp Sci & Technol, Hangzhou, Peoples R China
关键词
deep learning; parallelism; genomic selection; plant breeding; stratified sampling; SUPPORT VECTOR REGRESSION; GENETIC ARCHITECTURE; PREDICTION;
D O I
10.3389/fpls.2024.1410596
中图分类号
Q94 [植物学];
学科分类号
071001 ;
摘要
Genomic selection (GS) can accomplish breeding faster than phenotypic selection. Improving prediction accuracy is the key to promoting GS. To improve the GS prediction accuracy and stability, we introduce parallel convolution to deep learning for GS and call it a parallel neural network for genomic selection (PNNGS). In PNNGS, information passes through convolutions of different kernel sizes in parallel. The convolutions in each branch are connected with residuals. Four different Lp loss functions train PNNGS. Through experiments, the optimal number of parallel paths for rice, sunflower, wheat, and maize is found to be 4, 6, 4, and 3, respectively. Phenotype prediction is performed on 24 cases through ridge-regression best linear unbiased prediction (RRBLUP), random forests (RF), support vector regression (SVR), deep neural network genomic prediction (DNNGP), and PNNGS. Serial DNNGP and parallel PNNGS outperform the other three algorithms. On average, PNNGS prediction accuracy is 0.031 larger than DNNGP prediction accuracy, indicating that parallelism can improve the GS model. Plants are divided into clusters through principal component analysis (PCA) and K-means clustering algorithms. The sample sizes of different clusters vary greatly, indicating that this is unbalanced data. Through stratified sampling, the prediction stability and accuracy of PNNGS are improved. When the training samples are reduced in small clusters, the prediction accuracy of PNNGS decreases significantly. Increasing the sample size of small clusters is critical to improving the prediction accuracy of GS.
引用
收藏
页数:16
相关论文
共 61 条
[51]   GenNet framework: interpretable deep learning for predicting phenotypes from genetic data [J].
van Hilten, Arno ;
Kushner, Steven A. ;
Kayser, Manfred ;
Arfan Ikram, M. ;
Adams, Hieab H. H. ;
Klaver, Caroline C. W. ;
Niessen, Wiro J. ;
Roshchupkin, Gennady V. .
COMMUNICATIONS BIOLOGY, 2021, 4 (01)
[52]   Scientific discovery in the age of artificial intelligence [J].
Wang, Hanchen ;
Fu, Tianfan ;
Du, Yuanqi ;
Gao, Wenhao ;
Huang, Kexin ;
Liu, Ziming ;
Chandak, Payal ;
Liu, Shengchao ;
Van Katwyk, Peter ;
Deac, Andreea ;
Anandkumar, Anima ;
Bergen, Karianne ;
Gomes, Carla P. ;
Ho, Shirley ;
Kohli, Pushmeet ;
Lasenby, Joan ;
Leskovec, Jure ;
Liu, Tie-Yan ;
Manrai, Arjun ;
Marks, Debora ;
Ramsundar, Bharath ;
Song, Le ;
Sun, Jimeng ;
Tang, Jian ;
Velickovic, Petar ;
Welling, Max ;
Zhang, Linfeng ;
Coley, Connor W. ;
Bengio, Yoshua ;
Zitnik, Marinka .
NATURE, 2023, 620 (7972) :47-60
[53]   DNNGP, a deep neural network-based method for genomic prediction using multi-omics data in plants [J].
Wang, Kelin ;
Abid, Muhammad Ali ;
Rasheed, Awais ;
Crossa, Jose ;
Hearne, Sarah ;
Li, Huihui .
MOLECULAR PLANT, 2023, 16 (01) :279-293
[54]   A Novel hybrid genetic algorithm for kernel function and parameter optimization in support vector regression [J].
Wu, Chih-Hung ;
Tzeng, Gwo-Hshiung ;
Lin, Rong-Ho .
EXPERT SYSTEMS WITH APPLICATIONS, 2009, 36 (03) :4725-4735
[55]   A transformer-based genomic prediction method fused with knowledge-guided module [J].
Wu, Cuiling ;
Zhang, Yiyi ;
Ying, Zhiwen ;
Li, Ling ;
Wang, Jun ;
Yu, Hui ;
Zhang, Mengchen ;
Feng, Xianzhong ;
Wei, Xinghua ;
Xu, Xiaogang .
BRIEFINGS IN BIOINFORMATICS, 2024, 25 (01)
[56]   Machine learning bridges omics sciences and plant breeding [J].
Yan, Jun ;
Wang, Xiangfeng .
TRENDS IN PLANT SCIENCE, 2023, 28 (02) :199-210
[57]   Rice yield response to climate and price policy in high-latitude regions of China [J].
Yu, Yan ;
Clark, J. Stephen ;
Tian, Qingsong ;
Yan, Fengxian .
FOOD SECURITY, 2022, 14 (05) :1143-1157
[58]   Genome-wide analysis of deletions in maize population reveals abundant genetic diversity and functional impact [J].
Zhang, Xiao ;
Zhu, Yonghui ;
Kremling, Karl A. G. ;
Romay, M. Cinta ;
Bukowski, Robert ;
Sun, Qi ;
Gao, Shibin ;
Buckler, Edward S. ;
Lu, Fei .
THEORETICAL AND APPLIED GENETICS, 2022, 135 (01) :273-290
[59]   Genome-wide association mapping reveals a rich genetic architecture of complex traits in Oryza sativa [J].
Zhao, Keyan ;
Tung, Chih-Wei ;
Eizenga, Georgia C. ;
Wright, Mark H. ;
Ali, M. Liakat ;
Price, Adam H. ;
Norton, Gareth J. ;
Islam, M. Rafiqul ;
Reynolds, Andy ;
Mezey, Jason ;
McClung, Anna M. ;
Bustamante, Carlos D. ;
McCouch, Susan R. .
NATURE COMMUNICATIONS, 2011, 2
[60]   Genomic selection in hybrid breeding [J].
Zhao, Yusheng ;
Mette, Michael F. ;
Reif, Jochen C. .
PLANT BREEDING, 2015, 134 (01) :1-10