Department of Biology, Faculty of Science, University of Jiroft, Jiroft, 78671-61167, Iran.
Department of Biotechnology, Faculty of Agriculture and Natural Resources, Imam Khomeini International University (IKIU), Qazvin, 34149-16818, Iran.
BMC Plant Biol. 2024 Oct 16;24(1):970. doi: 10.1186/s12870-024-05662-9.
Nanoparticles impose multidimensional effects on living cells that significantly vary among different studies. Machine learning (ML) methods are recommended to elucidate more consistence and predictable relations among the affected parameters. In this study, nine ML algorithms [Support-Vector Regression (SVR), Linear, Bagging, Stochastic Gradient Descent (SGD), Gaussian Process, Random Sample Consensus (RANSAC), Partial Least Squares (PLS), Kernel Ridge, and Random Forest] were applied to evaluate their efficiency in predicting the effects of zinc oxide nanoparticles (ZnO NPs: 0.5, 1, 5, 25, and 125 µM) and microparticles (ZnO MPs: 1, 5, 25, and 125 µM) on Carum copticum. The plant root/shoot biomass; number of leaves, branches, umbellates, and flowers; protein content; reducing sugars; phenolic compounds; chlorophylls (a, b, Total); carotenoids; anthocyanins; HO; proline; malondialdehyde (MDA); tissue zinc content; superoxide dismutase (SOD) activity; and media ΔpH were measured and considered input variables. All levels of ZnO MPs treatments increased growth parameters compared to the control (ZnSO). The highest shoot/root fresh and dry mass were recorded at 5 µM ZnO MPs compared with the control. The root fresh/dry mass under ZnO NPs treatments was more sensitive than shoot parameters. The number of flowers increased by 134 and 79% in MPs and NPs treatments compared to the control, respectively. ZnO NPs reduced protein content by up to 81% in 125 µM NPs compared to ZnSO. Reducing sugar content increased to 25, 40 and 36% in 5, 25, 125 µM MPs and 67, 68, 26, 26 and 21% in 0.5, 1, 5, 25 and 125 µM NPs treatments, respectively. The pH alteration was more significant under NPs and affected zinc uptake. All levels of ZnO NPs treatments increased growth parameters compared to the control. All ML algorithms showed varied efficiencies in predicting the nonlinear relationships among parameters, with higher efficiency in predicting the behavior of root and shoot dry mass, root fresh weight and number of flowers according to R index. The model obtained from SVR with the radial basis function (RBF) kernel was selected as a comprehensive model for predicting and determining the efficacy of the results.
纳米颗粒对活细胞产生多维度的影响，不同研究之间存在显著差异。推荐使用机器学习 (ML) 方法来阐明受影响参数之间更一致和可预测的关系。在这项研究中，应用了九种 ML 算法 [支持向量回归 (SVR)、线性、袋装、随机梯度下降 (SGD)、高斯过程、随机抽样共识 (RANSAC)、偏最小二乘 (PLS)、核岭回归和随机森林] 来评估它们在预测氧化锌纳米颗粒 (ZnO NPs: 0.5、1、5、25 和 125 μM) 和微颗粒 (ZnO MPs: 1、5、25 和 125 μM) 对 Carum copticum 影响的效率。测量并考虑了植物根/茎生物量；叶片、枝条、伞形花序和花的数量；蛋白质含量；还原糖；酚类化合物；叶绿素 (a、b、总)；类胡萝卜素；花青素；HO；脯氨酸；丙二醛 (MDA)；组织锌含量；超氧化物歧化酶 (SOD) 活性；以及介质 ΔpH 作为输入变量。与 ZnSO 相比，所有 ZnO MPs 处理水平均增加了生长参数。与对照相比，在 5 μM ZnO MPs 处理下记录到最高的茎/根鲜重和干重。与地上部分参数相比，ZnO NPs 处理下的根鲜重/干重更敏感。与对照相比， MPs 和 NPs 处理下的花数分别增加了 134%和 79%。与 ZnSO 相比，在 125 μM NPs 处理下，蛋白质含量降低了 81%。还原糖含量在 5、25、125 μM MPs 处理中分别增加了 25%、40%和 36%，在 0.5、1、5、25 和 125 μM NPs 处理中分别增加了 67%、68%、26%、26%和 21%。 NPs 处理下 pH 值变化更为显著，并影响锌的吸收。与对照相比，所有 ZnO NPs 处理水平均增加了生长参数。所有 ML 算法在预测参数之间的非线性关系方面表现出不同的效率，根据 R 指数，预测根和茎干重、根鲜重和花数的行为具有更高的效率。选择具有径向基函数 (RBF) 核的 SVR 模型作为综合模型，用于预测和确定结果的功效。
