College of Electronic Engineering / College of Artificial Intelligence, South China Agricultural University, Guangzhou 510642, China.
Guangdong Provincial Key Laboratory of Plant Molecular Breeding, South China Agricultural University, Guangzhou 510642, China.
Spectrochim Acta A Mol Biomol Spectrosc. 2023 Sep 5;297:122720. doi: 10.1016/j.saa.2023.122720. Epub 2023 Apr 9.
Monitoring (including prediction and visualization) the gene modulated cadmium (Cd) accumulation in rice grains is one of the most important steps for identification of key transporter genes responsible for grain Cd accumulation and breeding low grain-Cd-accumulating rice cultivars. A method to predict and visualize the gene modulated ultralow Cd accumulation in brown rice grains based on the hyperspectral image (HSI) technology is proposed in this study. Firstly, the Vis-NIR HSIs of brown rice grain samples with 48Cd content levels induced by gene modulation (ranging from 0.0637 to 0.1845 mg/kg) are collected using HSI system. Then, Kernel-ridge (KRR) and random forest (RFR) regression models based on full spectral data and the data after feature dimension reduction (FDR) with kernel principal component analysis (KPCA) and truncated singular value decomposition (TSVD) algorithms are established to predict the Cd contents. RFR model shows poor performance due to the over-fitting based on the full spectral data, while the KRR model can obtain a good predict accuracy with R of 0.9035, RMSEP of 0.0037 and RPD of 3.278. After the FDR of the full spectral data, the RFR model combined with TSVD reaches the optimum prediction accuracy with R of 0.9056, RMSEP of 0.0074 and RPD of 3.318, and the best prediction precision of KRR model can also be further enhanced by TSVD with R of 0.9224, RMSEP of 0.0067 and RPD of 3.512. Finally, the visualization of the predicted Cd accumulation in brown rice grains are realized based on the best regression model (KRR + TSVD). The results of this work indicate that Vis-NIR HSI has great potential for detection and visualization gene modulation induced ultralow Cd accumulation and transport in rice crops.
监测（包括预测和可视化）基因调控的水稻籽粒镉（Cd）积累是鉴定负责籽粒 Cd 积累的关键转运基因和培育低籽粒 Cd 积累水稻品种的最重要步骤之一。本研究提出了一种基于高光谱图像（HSI）技术预测和可视化糙米基因调控的超低 Cd 积累的方法。首先，使用 HSI 系统采集了 48Cd 含量水平（范围为 0.0637 至 0.1845mg/kg）诱导的基因调控糙米籽粒的可见-近红外 HSI。然后，建立了基于全谱数据和经过核主成分分析（KPCA）和截断奇异值分解（TSVD）算法的特征降维（FDR）后数据的核脊（KRR）和随机森林（RFR）回归模型，以预测 Cd 含量。RFR 模型由于基于全谱数据的过拟合而表现不佳，而 KRR 模型可以通过 R=0.9035、RMSEP=0.0037 和 RPD=3.278 获得良好的预测精度。对全谱数据进行 FDR 后，与 TSVD 结合的 RFR 模型达到了最佳预测精度，R=0.9056、RMSEP=0.0074 和 RPD=3.318，而 KRR 模型通过 TSVD 也可以进一步提高最佳预测精度，R=0.9224、RMSEP=0.0067 和 RPD=3.512。最后，基于最佳回归模型（KRR+TSVD）实现了糙米中预测 Cd 积累的可视化。本工作的结果表明，可见-近红外 HSI 具有检测和可视化基因调控诱导的水稻作物超低 Cd 积累和转运的巨大潜力。
