News Release

Innovative use of hyperspectral data and DCGANs enhances rice protein content estimation

Peer-Reviewed Publication

Nanjing Agricultural University The Academy of Science



Workflow of GPC estimation and GWAS.

view more 

Credit: The authors

A research team used hyperspectral data and deep convolution generative adversarial networks (DCGANs) to improve the accuracy of rice grain protein content (GPC) estimation. By generating simulated data, they enhanced the model's performance, achieving an R² of 0.58 and RRMSE of 6.70%. This technique identified genetic loci related to GPC, including the OsmtSSB1L gene. The study demonstrates the potential of combining hyperspectral technology and DCGANs for efficient genetic analysis and selection of high-quality rice varieties, paving the way for advanced agricultural practices.

Rice (Oryza sativa L.) is a crucial crop feeding over half of the global population. The demand for high-quality, protein-rich rice is rising, making accurate grain protein content (GPC) estimation vital for breeding superior varieties. Despite advances in genomic tools like GWAS, conventional phenotyping remains labor-intensive and costly, creating a bottleneck. Recent developments in optical and spectral imaging offer high-throughput phenotyping solutions. However, small and unbalanced datasets limit model performance and generalization.

A study (DOI: 10.34133/plantphenomics.0200) published in Plant Phenomics on 29 May 2024, aims to address these issues by using a DCGAN to generate simulated data, enhance GPC model accuracy, and explore gene dissection potential.

The research employed hyperspectral data and DCGANs to improve the estimation of rice GPC. Raw and normalized spectral data revealed distinct absorption features crucial for GPC analysis. Simulated data generated by DCGANs after 8,000 epochs closely matched measured data, enhancing model accuracy. The partial least squares regression (PLSR) model using these features achieved high validation accuracy (R2 = 0.58, RRMSE = 6.70%). Additionally, genome-wide association study (GWAS) analysis with simulated data identified significant SNPs, including the OsmtSSB1L gene linked to grain storage protein. This approach demonstrates the potential for high-generalization GPC models, facilitating advanced genetic analysis and breeding of rice varieties.

According to the study's lead researcher, Hengbiao Zheng, “This study provides a new technique for the efficient genetic study of phenotypic traits in rice based on hyperspectral technology.”

In summary, the study developed a method using DCGANs to enhance the estimation of rice GPC through hyperspectral data. This approach demonstrates the potential for integrating DCGANs and hyperspectral technology to improve crop phenotyping and genetic analysis. Looking ahead, further refinement and validation across diverse ecological sites and more extensive datasets will enhance the robustness and applicability of this method, paving the way for more precise and efficient breeding of high-quality rice varieties.





Original Source URL


Hengbiao Zheng1,2*, Weijie Tang2,3*, Tao Yang1*, Meng Zhou1, Caili Guo1, Tao Cheng1,Weixing Cao1, Yan Zhu1, Yunhui Zhang2,3, Xia Yao1


1 National Engineering and Technology Center for Information Agriculture (NETCIA),MARA Key Laboratory of Crop System Analysis and Decision Making, MOE EngineeringResearch Center of Smart Agriculture, Jiangsu Key Laboratory for Information Agriculture,Institute of Smart Agriculture, Nanjing Agricultural University, Nanjing, Jiangsu, China

2 Zhongshan Biological Breeding Laboratory, ZSBBL

3 Provincial Key Laboratory of Agrobiology, Institute of Germplasm Resources andBiotechnology, Jiangsu Academy of Agricultural Sciences, Nanjing, Jiangsu, China

* These authors contributed equally.

Funding information

This work was supported by the National Key Research and Development Program of China (2022YFD2001100), the National Natural Science Foundation of China (32101617), the Fundamental Research Funds for the Central Universities (JSJL2023005), the Zhongshan Biological Breeding Laboratory (ZSBBL-KY2023-05), the Key Independent Research Project of Jiangsu Key Laboratory of Information Agriculture (KLIAZZ2301), and the Jiangsu Collaborative Innovation Center for Modern Crop Production (JCICMCP). We would also like to thank the anonymous reviewers who provided helpful comments for the improvement of the manuscript.

About Plant Phenomics

Plant Phenomics is an Open Access journal published in affiliation with the State Key Laboratory of Crop Genetics & Germplasm Enhancement, Nanjing Agricultural University (NAU) and published by the American Association for the Advancement of Science (AAAS). Like all partners participating in the Science Partner Journal program, Plant Phenomics is editorially independent from the Science family of journals. Editorial decisions and scientific activities pursued by the journal's Editorial Board are made independently, based on scientific merit and adhering to the highest standards for accurate and ethical promotion of science. These decisions and activities are in no way influenced by the financial support of NAU, NAU administration, or any other institutions and sponsors. The Editorial Board is solely responsible for all content published in the journal. To learn more about the Science Partner Journal program, visit the SPJ program homepage.

Disclaimer: AAAS and EurekAlert! are not responsible for the accuracy of news releases posted to EurekAlert! by contributing institutions or for the use of any information through the EurekAlert system.