1
|
He J, Weng L, Xu X, Chen R, Peng B, Li N, Xie Z, Sun L, Han Q, He P, Wang F, Yu H, Bhat JA, Feng X. DEKR-SPrior: An Efficient Bottom-Up Keypoint Detection Model for Accurate Pod Phenotyping in Soybean. PLANT PHENOMICS (WASHINGTON, D.C.) 2024; 6:0198. [PMID: 38939747 PMCID: PMC11209727 DOI: 10.34133/plantphenomics.0198] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Grants] [Track Full Text] [Figures] [Subscribe] [Scholar Register] [Received: 01/08/2024] [Accepted: 05/16/2024] [Indexed: 06/29/2024]
Abstract
The pod and seed counts are important yield-related traits in soybean. High-precision soybean breeders face the major challenge of accurately phenotyping the number of pods and seeds in a high-throughput manner. Recent advances in artificial intelligence, especially deep learning (DL) models, have provided new avenues for high-throughput phenotyping of crop traits with increased precision. However, the available DL models are less effective for phenotyping pods that are densely packed and overlap in in situ soybean plants; thus, accurate phenotyping of the number of pods and seeds in soybean plant is an important challenge. To address this challenge, the present study proposed a bottom-up model, DEKR-SPrior (disentangled keypoint regression with structural prior), for in situ soybean pod phenotyping, which considers soybean pods and seeds analogous to human people and joints, respectively. In particular, we designed a novel structural prior (SPrior) module that utilizes cosine similarity to improve feature discrimination, which is important for differentiating closely located seeds from highly similar seeds. To further enhance the accuracy of pod location, we cropped full-sized images into smaller and high-resolution subimages for analysis. The results on our image datasets revealed that DEKR-SPrior outperformed multiple bottom-up models, viz., Lightweight-OpenPose, OpenPose, HigherHRNet, and DEKR, reducing the mean absolute error from 25.81 (in the original DEKR) to 21.11 (in the DEKR-SPrior) in pod phenotyping. This paper demonstrated the great potential of DEKR-SPrior for plant phenotyping, and we hope that DEKR-SPrior will help future plant phenotyping.
Collapse
Affiliation(s)
- Jingjing He
- Zhejiang Laboratory, Hangzhou 311100, Zhejiang, China
| | - Lin Weng
- Zhejiang Laboratory, Hangzhou 311100, Zhejiang, China
| | - Xiaogang Xu
- School of Computer Science and Technology,
Zhejiang Gongshang University, Hangzhou 310012, Zhejiang, China
| | - Ruochen Chen
- Zhejiang Laboratory, Hangzhou 311100, Zhejiang, China
| | - Bo Peng
- Zhejiang Laboratory, Hangzhou 311100, Zhejiang, China
| | - Nannan Li
- Zhejiang Laboratory, Hangzhou 311100, Zhejiang, China
| | - Zhengchao Xie
- Zhejiang Laboratory, Hangzhou 311100, Zhejiang, China
| | - Lijian Sun
- Zhejiang Laboratory, Hangzhou 311100, Zhejiang, China
| | - Qiang Han
- Zhejiang Laboratory, Hangzhou 311100, Zhejiang, China
| | - Pengfei He
- Zhejiang Laboratory, Hangzhou 311100, Zhejiang, China
| | - Fangfang Wang
- Zhejiang Laboratory, Hangzhou 311100, Zhejiang, China
| | - Hui Yu
- Key Laboratory of Soybean Molecular Design Breeding, Northeast Institute of Geography and Agroecology,
Chinese Academy of Sciences, Changchun 130102, Jilin, China
| | | | - Xianzhong Feng
- Key Laboratory of Soybean Molecular Design Breeding, Northeast Institute of Geography and Agroecology,
Chinese Academy of Sciences, Changchun 130102, Jilin, China
| |
Collapse
|
2
|
Dwivedi SL, Heslop-Harrison P, Amas J, Ortiz R, Edwards D. Epistasis and pleiotropy-induced variation for plant breeding. PLANT BIOTECHNOLOGY JOURNAL 2024. [PMID: 38875130 DOI: 10.1111/pbi.14405] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Subscribe] [Scholar Register] [Received: 11/18/2023] [Revised: 05/07/2024] [Accepted: 05/24/2024] [Indexed: 06/16/2024]
Abstract
Epistasis refers to nonallelic interaction between genes that cause bias in estimates of genetic parameters for a phenotype with interactions of two or more genes affecting the same trait. Partitioning of epistatic effects allows true estimation of the genetic parameters affecting phenotypes. Multigenic variation plays a central role in the evolution of complex characteristics, among which pleiotropy, where a single gene affects several phenotypic characters, has a large influence. While pleiotropic interactions provide functional specificity, they increase the challenge of gene discovery and functional analysis. Overcoming pleiotropy-based phenotypic trade-offs offers potential for assisting breeding for complex traits. Modelling higher order nonallelic epistatic interaction, pleiotropy and non-pleiotropy-induced variation, and genotype × environment interaction in genomic selection may provide new paths to increase the productivity and stress tolerance for next generation of crop cultivars. Advances in statistical models, software and algorithm developments, and genomic research have facilitated dissecting the nature and extent of pleiotropy and epistasis. We overview emerging approaches to exploit positive (and avoid negative) epistatic and pleiotropic interactions in a plant breeding context, including developing avenues of artificial intelligence, novel exploitation of large-scale genomics and phenomics data, and involvement of genes with minor effects to analyse epistatic interactions and pleiotropic quantitative trait loci, including missing heritability.
Collapse
Affiliation(s)
| | - Pat Heslop-Harrison
- Key Laboratory of Plant Resources Conservation and Sustainable Utilization, South China Botanical Garden, Chinese Academy of Sciences, Guangzhou, China
- Department of Genetics and Genome Biology, Institute for Environmental Futures, University of Leicester, Leicester, UK
| | - Junrey Amas
- Centre for Applied Bioinformatics, School of Biological Sciences, University of Western Australia, Perth, WA, Australia
| | - Rodomiro Ortiz
- Department of Plant Breeding, Swedish University of Agricultural Sciences, Alnarp, Sweden
| | - David Edwards
- Centre for Applied Bioinformatics, School of Biological Sciences, University of Western Australia, Perth, WA, Australia
| |
Collapse
|
3
|
Zhang Y, Bhat JA, Zhang Y, Yang S. Understanding the Molecular Regulatory Networks of Seed Size in Soybean. Int J Mol Sci 2024; 25:1441. [PMID: 38338719 PMCID: PMC10855573 DOI: 10.3390/ijms25031441] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/27/2023] [Revised: 01/22/2024] [Accepted: 01/23/2024] [Indexed: 02/12/2024] Open
Abstract
Soybean being a major cash crop provides half of the vegetable oil and a quarter of the plant proteins to the global population. Seed size traits are the most important agronomic traits determining the soybean yield. These are complex traits governed by polygenes with low heritability as well as are highly influenced by the environment as well as by genotype x environment interactions. Although, extensive efforts have been made to unravel the genetic basis and molecular mechanism of seed size in soybean. But most of these efforts were majorly limited to QTL identification, and only a few genes for seed size were isolated and their molecular mechanism was elucidated. Hence, elucidating the detailed molecular regulatory networks controlling seed size in soybeans has been an important area of research in soybeans from the past decades. This paper describes the current progress of genetic architecture, molecular mechanisms, and regulatory networks for seed sizes of soybeans. Additionally, the main problems and bottlenecks/challenges soybean researchers currently face in seed size research are also discussed. This review summarizes the comprehensive and systematic information to the soybean researchers regarding the molecular understanding of seed size in soybeans and will help future research work on seed size in soybeans.
Collapse
Affiliation(s)
- Ye Zhang
- Key Laboratory of Soybean Molecular Design Breeding, State Key Laboratory of Black Soils Conservation and Utilization, Northeast Institute of Geography and Agroecology, Chinese Academy of Sciences, Changchun 130102, China; (Y.Z.); (Y.Z.)
- College of Advanced Agricultural Sciences, University of Chinese Academy of Sciences, Beijing 101408, China
| | | | - Yaohua Zhang
- Key Laboratory of Soybean Molecular Design Breeding, State Key Laboratory of Black Soils Conservation and Utilization, Northeast Institute of Geography and Agroecology, Chinese Academy of Sciences, Changchun 130102, China; (Y.Z.); (Y.Z.)
- College of Advanced Agricultural Sciences, University of Chinese Academy of Sciences, Beijing 101408, China
| | - Suxin Yang
- Key Laboratory of Soybean Molecular Design Breeding, State Key Laboratory of Black Soils Conservation and Utilization, Northeast Institute of Geography and Agroecology, Chinese Academy of Sciences, Changchun 130102, China; (Y.Z.); (Y.Z.)
- College of Advanced Agricultural Sciences, University of Chinese Academy of Sciences, Beijing 101408, China
| |
Collapse
|