Division of Computer Applications, ICAR-Indian Agricultural Statistics Research Institute, Pusa, New Delhi, 110012, India.
ICAR-National Institute for Plant Biotechnology, Pusa, New Delhi, 110012, India.
Funct Integr Genomics. 2024 Oct 25;24(6):201. doi: 10.1007/s10142-024-01474-0.
Anti-nutrient factors are inherently present in almost all major crops, which impede the absorption of crucial vitamins and minerals upon human consumption. The commonly found anti-nutrients in food crops are saponins, tannins, lectins, and phytates etc. Currently, there is a lack of computational server for identification of proteins that encode for anti-nutritional factors in plants. Consequently, this study represents a computational approach aimed at distinguishing between proteins encoding anti-nutritional factors and those providing essential nutrients. In this work, machine learning algorithms have been employed to identify plant specific anti-nutrient factor proteins from protein sequences by using compositional features. Achieving a five-fold cross-validation training performance of 94.34% AUC-ROC and 94.13% AUC-PR with extreme gradient boosting surpasses the performance of other methods such as support vector machine, random forest, and adaptive boosting. These results suggest the proposed approach is highly reliable in predicting plant-specific anti-nutritional factor proteins. The resulting prediction models have led to the development of an online server named ANPS, freely available at https://nipb-bi.icar.gov.in .
抗营养因子几乎存在于所有主要作物中，这些因子会在人类食用时阻碍关键维生素和矿物质的吸收。在食物作物中常见的抗营养因子有皂素、单宁、凝集素和植酸盐等。目前，缺乏用于鉴定植物中编码抗营养因子的蛋白质的计算服务器。因此，本研究代表了一种计算方法，旨在区分编码抗营养因子的蛋白质和提供必需营养素的蛋白质。在这项工作中，我们使用组成特征，通过机器学习算法从蛋白质序列中识别植物特异性抗营养因子蛋白。使用极端梯度提升算法在五重交叉验证训练中的性能达到 94.34% AUC-ROC 和 94.13% AUC-PR，超过了支持向量机、随机森林和自适应提升等其他方法的性能。这些结果表明，所提出的方法在预测植物特异性抗营养因子蛋白方面具有很高的可靠性。所得到的预测模型导致了一个名为 ANPS 的在线服务器的开发，可在 https://nipb-bi.icar.gov.in 免费获得。
