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
[1]   Optimization of genomic selection training populations with a genetic algorithm [J].
Akdemir, Deniz ;
Sanchez, Julio I. ;
Jannink, Jean-Luc .
GENETICS SELECTION EVOLUTION, 2015, 47
[2]   Accuracy of genomic selection for alfalfa biomass yield in different reference populations [J].
Annicchiarico, Paolo ;
Nazzicari, Nelson ;
Li, Xuehui ;
Wei, Yanling ;
Pecetti, Luciano ;
Brummer, E. Charles .
BMC GENOMICS, 2015, 16
[3]   Exome sequencing and analysis of 454,787 UK Biobank participants [J].
Backman, Joshua D. ;
Li, Alexander H. ;
Marcketta, Anthony ;
Sun, Dylan ;
Mbatchou, Joelle ;
Kessler, Michael D. ;
Benner, Christian ;
Liu, Daren ;
Locke, Adam E. ;
Balasubramanian, Suganthi ;
Yadav, Ashish ;
Banerjee, Nilanjana ;
Gillies, Christopher E. ;
Damask, Amy ;
Liu, Simon ;
Bai, Xiaodong ;
Hawes, Alicia ;
Maxwell, Evan ;
Gurski, Lauren ;
Watanabe, Kyoko ;
Kosmicki, Jack A. ;
Rajagopal, Veera ;
Mighty, Jason ;
Jones, Marcus ;
Mitnaul, Lyndon ;
Stahl, Eli ;
Coppola, Giovanni ;
Jorgenson, Eric ;
Habegger, Lukas ;
Salerno, William J. ;
Shuldiner, Alan R. ;
Lotta, Luca A. ;
Overton, John D. ;
Cantor, Michael N. ;
Reid, Jeffrey G. ;
Yancopoulos, George ;
Kang, Hyun M. ;
Marchini, Jonathan ;
Baras, Aris ;
Abecasis, Goncalo R. ;
Ferreira, Manuel A. R. .
NATURE, 2021, 599 (7886) :628-+
[4]   Genomic selection performs as effectively as phenotypic selection for increasing seed yield in soybean [J].
Bandillo, Nonoy B. B. ;
Jarquin, Diego ;
Posadas, Luis G. G. ;
Lorenz, Aaron J. J. ;
Graef, George L. L. .
PLANT GENOME, 2023, 16 (01)
[5]   Application of Genomic Selection at the Early Stage of Breeding Pipeline in Tropical Maize [J].
Beyene, Yoseph ;
Gowda, Manje ;
Perez-Rodriguez, Paulino ;
Olsen, Michael ;
Robbins, Kelly R. ;
Burgueno, Juan ;
Prasanna, Boddupalli M. ;
Crossa, Jose .
FRONTIERS IN PLANT SCIENCE, 2021, 12
[6]   Genomic Selection in the Era of Next Generation Sequencing for Complex Traits in Plant Breeding [J].
Bhat, Javaid A. ;
Ali, Sajad ;
Salgotra, Romesh K. ;
Mir, Zahoor A. ;
Dutta, Sutapa ;
Jadon, Vasudha ;
Tyagi, Anshika ;
Mushtaq, Muntazir ;
Jain, Neelu ;
Singh, Pradeep K. ;
Singh, Gyanendra P. ;
Prabhu, K. V. .
FRONTIERS IN GENETICS, 2016, 7
[7]   A Ranking Approach to Genomic Selection [J].
Blondel, Mathieu ;
Onogi, Akio ;
Iwata, Hiroyoshi ;
Ueda, Naonori .
PLOS ONE, 2015, 10 (06)
[8]   Accelerating Tomato Breeding by Exploiting Genomic Selection Approaches [J].
Cappetta, Elisa ;
Andolfo, Giuseppe ;
Di Matteo, Antonio ;
Barone, Amalia ;
Frusciante, Luigi ;
Ercolano, Maria Raffaella .
PLANTS-BASEL, 2020, 9 (09) :1-14
[9]   Skewed distribution of leaf color RGB model and application of skewed parameters in leaf color description model [J].
Chen, Zhengmeng ;
Wang, Fuzheng ;
Zhang, Pei ;
Ke, Chendan ;
Zhu, Yan ;
Cao, Weixing ;
Jiang, Haidong .
PLANT METHODS, 2020, 16 (01)
[10]   Genetic Architecture of Maize Kernel Composition in the Nested Association Mapping and Inbred Association Panels [J].
Cook, Jason P. ;
McMullen, Michael D. ;
Holland, James B. ;
Tian, Feng ;
Bradbury, Peter ;
Ross-Ibarra, Jeffrey ;
Buckler, Edward S. ;
Flint-Garcia, Sherry A. .
PLANT PHYSIOLOGY, 2012, 158 (02) :824-834