中文摘要：全球法律和消费者对转基因生物鉴别的需求日益增长。本文将太赫兹时域光谱技术与化学计量学方法相结合，来研究抗草甘膦大豆种子和常规大豆种子及其杂交后代无损鉴别的可行性。作者对预处理过的一阶导数、二阶导数和标准正态变量用主成分分析（PCA）、最小二乘支持向量机（LS-SVM）和PCA反向传播神经网络（PCA-BPNN）来进行基于基因型的大豆种子分类。研究发现，利用LS-SVM和SNV光谱预处理形成的可视化分类可以看到抗草甘膦大豆种子、杂交大豆种子、常规大豆种子间的显著差异。研究结果表明，太赫兹光谱技术与化学计量学方法相结合将是一种从非转基因种子中区分转基因大豆种子的高效且不需任何样品制备的方法。
外文摘要：Discrimination of genetically modified organisms is increasingly demanded by legislation and consumers worldwide. The feasibility of a non-destructive discrimination of glyphosate-resistant and conventional soybean seeds and their hybrid descendants was examined by terahertz time-domain spectroscopy system combined with chemometrics. Principal component analysis (PCA), least squares-support vector machines (LS-SVM) and PCA-back propagation neural network (PCA-BPNN) models with the first and second derivative and standard normal variate (SNV) transformation pre-treatments were applied to classify soybean seeds based on genotype. Results demonstrated clear differences among glyphosate-resistant, hybrid descendants and conventional non-transformed soybean seeds could easily be visualized with an excellent classification (accuracy was 88.33% in validation set) using the LS-SVM and the spectra with SNV pre-treatment. The results indicated that THz spectroscopy techniques together with chemometrics would be a promising technique to distinguish transgenic soybean seeds from non-transformed seeds with high efficiency and without any major sample preparation.
作者：Liu, Wei；Liu, Changhong；Chen, Feng；等
作者单位：合肥工业大学
期刊名称：SCIENTIFIC REPORTS
期刊影响因子：5.228
出版年份：2016
出版刊次：10
点击下载：太赫兹光谱技术对转基因大豆种子的鉴别研究