Nanoparticles are being used in many areas in biotechnology. Silver nanoparticles are the most frequently used ones among the others, because of their eco-friendly natures. Biosynthetic silver nanoparticles have some beneficial effects on plant tissue cultures. However, their effects have rarely been investigated. In this study, biosynthetic nanoparticles were used at 0, 1, 2 and 4 mg/L concentration in order to determine their effects on Digitalis purpurea node cultures. At the first stage of experimental data analyses, MANOVA was employed to understand the significant growth parameters of D. purpurea plantlets. At the second stage, an artifical neural network (ANN) model was designed and tested under a wide range of input parameters (concentration of silver nanoparticles). The statistical differences between shoot elongations, single and multiple shoot formations, root formations, root fresh and dry weights were not found significant. However, the difference between shoot and total fresh weights, shoot and total dry weights (the significant variables) were found statistically significant. Optimum silver nanoparticle concentration for plantlet growth was detected as 2 mg/L. Biomass accumulations were enhanced up to 2,4 times. The results showed that ANN model provided a good prediction for the plant growth parameters and can be adapted for in vitro large-scale production.

纳米颗粒已在生物技术的许多领域中使用。银纳米颗粒由于其生态友好的性质而成为最常用的纳米颗粒。生物合成的银纳米颗粒对植物组织培养具有一些有益的作用。但是，对其作用的研究很少。在这项研究中，以0、1、2和4 mg / L的浓度使用生物合成纳米颗粒，以确定它们对洋地黄结节培养的影响。在实验数据分析的第一阶段，使用MANOVA来了解紫D的重要生长参数。苗。在第二阶段，设计了人工神经网络（ANN）模型，并在各种输入参数（银纳米颗粒浓度）下进行了测试。没有发现枝条伸长率，单枝和多枝芽形成，根系形成，根鲜重和干重之间的统计学差异。然而，发现枝条和总鲜重，枝条和总干重之间的差异（显着变量）在统计学上是显着的。检测到的用于幼苗生长的最佳银纳米颗粒浓度为2 mg / L。生物质积累提高了2.4倍。结果表明，人工神经网络模型为植物的生长参数提供了良好的预测，可用于体外大规模生产。