Vis-NIR wavelength selection for non-destructive discriminant analysis of breed screening of transgenic sugarcane

Abstract

The Savitzky–Golay (SG) method and moving-window waveband screening are applied to a coupling model of principal component (PCA) and linear discriminant analyses (LDA). An SG-pretreatment-based method (MW-PCA-LDA) for spectral pattern recognition is proposed, which is successfully employed for the non-destructive recognition of transgenic sugarcane leaves using visible (Vis) and near-infrared (NIR) diffuse reflectance spectroscopy. A Kennard–Stone-algorithm-based process of calibration, prediction and validation in consideration of uniformity and representative was performed to produce objective models. A total of 456 samples of sugarcane leaves in the elongation stage were collected from a planted field. These samples were composed of 306 transgenic samples containing both Bacillus thuringiensis (Bt) and bialaphos resistance (Bar) genes, and 150 non-transgenic samples. According to the spectral recognition effects, two parallel optimal SG modes were selected. The one of the 1^st order derivative, 3^rd degree polynomial and 25 smoothing points was taken as an example to pretreat the diffuse reflectance spectra. Based on the MW-PCA-LDA method, the optimal waveband was 768 nm to 822 nm, the optimal PC combination was PC₁–PC₃ and the corresponding validation recognition rates of transgenic and non-transgenic samples achieved 99.1% and 98.0%, respectively. The results show that Vis-NIR spectroscopy combined with SG pretreatment and the MW-PCA-LDA method can be used for accurate recognition of transgenic sugarcane leaves and provides a quick and convenient means of screening transgenic sugarcane breeding for large-scale agricultural production.