Kos Gregor, Sieger Markus, McMullin David, Zahradnik Celine, Sulyok Michael, Öner Tuba, Mizaikoff Boris, Krska Rudolf
a Department of Atmospheric and Oceanic Sciences , McGill University , Montreal , QC , Canada.
b Institute of Analytical and Bioanalytical Chemistry , Ulm University , Ulm , Germany.
Food Addit Contam Part A Chem Anal Control Expo Risk Assess. 2016 Oct;33(10):1596-1607. doi: 10.1080/19440049.2016.1217567. Epub 2016 Aug 16.
The rapid identification of mycotoxins such as deoxynivalenol and aflatoxin B in agricultural commodities is an ongoing concern for food importers and processors. While sophisticated chromatography-based methods are well established for regulatory testing by food safety authorities, few techniques exist to provide a rapid assessment for traders. This study advances the development of a mid-infrared spectroscopic method, recording spectra with little sample preparation. Spectral data were classified using a bootstrap-aggregated (bagged) decision tree method, evaluating the protein and carbohydrate absorption regions of the spectrum. The method was able to classify 79% of 110 maize samples at the European Union regulatory limit for deoxynivalenol of 1750 µg kg and, for the first time, 77% of 92 peanut samples at 8 µg kg of aflatoxin B. A subset model revealed a dependency on variety and type of fungal infection. The employed CRC and SBL maize varieties could be pooled in the model with a reduction of classification accuracy from 90% to 79%. Samples infected with Fusarium verticillioides were removed, leaving samples infected with F. graminearum and F. culmorum in the dataset improving classification accuracy from 73% to 79%. A 500 µg kg classification threshold for deoxynivalenol in maize performed even better with 85% accuracy. This is assumed to be due to a larger number of samples around the threshold increasing representativity. Comparison with established principal component analysis classification, which consistently showed overlapping clusters, confirmed the superior performance of bagged decision tree classification.
农产品中脱氧雪腐镰刀菌烯醇和黄曲霉毒素B等霉菌毒素的快速鉴定一直是食品进口商和加工商关注的问题。虽然基于复杂色谱法的方法已被食品安全当局用于监管检测，但几乎没有技术能为贸易商提供快速评估。本研究推动了中红外光谱法的发展，该方法只需很少的样品制备就能记录光谱。光谱数据使用自助聚合（袋装）决策树方法进行分类，评估光谱中的蛋白质和碳水化合物吸收区域。该方法能够在欧盟脱氧雪腐镰刀菌烯醇监管限量为1750 µg/kg时，对110个玉米样品中的79%进行分类，并且首次在黄曲霉毒素B含量为8 µg/kg时，对92个花生样品中的77%进行分类。一个子集模型揭示了对品种和真菌感染类型的依赖性。在模型中可以将使用的CRC和SBL玉米品种合并，分类准确率从90%降至79%。去除感染轮枝镰孢菌的样品，数据集中只留下感染禾谷镰孢菌和黄色镰孢菌的样品，分类准确率从73%提高到79%。玉米中脱氧雪腐镰刀菌烯醇500 µg/kg的分类阈值表现更好，准确率达到85%。这被认为是由于阈值附近的样品数量较多，代表性增强。与已确立的主成分分析分类方法（其聚类始终存在重叠）进行比较，证实了袋装决策树分类的优越性能。
