Gosling Research Institute for Plant Preservation, Department of Plant Agriculture, University of Guelph, Guelph, ON, Canada.
Department of Horticultural Science, Faculty of Agriculture, University of Tehran, Karaj, Iran.
Appl Microbiol Biotechnol. 2020 Dec;104(23):10249-10263. doi: 10.1007/s00253-020-10978-1. Epub 2020 Oct 29.
Data-driven models in a combination of optimization algorithms could be beneficial methods for predicting and optimizing in vitro culture processes. This study was aimed at modeling and optimizing a new embryogenesis medium for chrysanthemum. Three individual data-driven models, including multi-layer perceptron (MLP), adaptive neuro-fuzzy inference system (ANFIS), and support vector regression (SVR), were developed for callogenesis rate (CR), embryogenesis rate (ER), and somatic embryo number (SEN). Consequently, the best obtained results were used in the fusion process by a bagging method. For medium reformulation, effects of eight ionic macronutrients on CR, ER, and SEN and effects of four vitamins on SEN were evaluated using data fusion (DF)-non-dominated sorting genetic algorithm-II (NSGA-II) and DF-genetic algorithm (GA), respectively. Results showed that DF models with the highest R had superb performance in comparison with all other individual models. According to DF-NSGAII, the highest ER and SEN can be obtained from the medium containing 14.27 mM NH, 38.92 mM NO, 22.79 mM K, 5.08 mM Cl, 3.34 mM Ca, 1.67 mM Mg, 2.17 mM SO, and 1.44 mM HPO. Based on the DF-GA model, the maximum SEN can be obtained from a medium containing 0.61 μM thiamine, 5.93 μM nicotinic acid, 0.25 μM biotin, and 0.26 μM riboflavin. The efficiency of the established-optimized medium was experimentally compared to Murashige and Skoog medium (MS) for embryogenesis of five chrysanthemum cultivars, and results indicated the efficiency of optimized medium over MS medium.Key points• MLP, SVR, and ANFIS were fused by a bagging method to develop a data fusion model.• NSGA-II and GA were linked to the data fusion model for establishing and optimizing a new embryogenesis medium.• The new culture medium (HNT) had better efficiency than MS medium.
数据驱动模型与优化算法的结合可以成为预测和优化体外培养过程的有益方法。本研究旨在为菊花建立一种新的胚胎发生培养基模型并对其进行优化。为了获得胚状体的数量（SEN）、胚状体发生频率（ER）和愈伤组织诱导率（CR），分别建立了 3 个数据驱动模型，包括多层感知器（MLP）、自适应神经模糊推理系统（ANFIS）和支持向量回归（SVR）。然后，通过袋装法将获得的最佳结果融合在一起。为了对培养基进行配方调整，使用数据融合（DF）-非支配排序遗传算法 II（NSGA-II）和 DF-遗传算法（GA）分别评估了 8 种离子大量营养元素对 CR、ER 和 SEN 的影响，以及 4 种维生素对 SEN 的影响。结果表明，与其他所有单一模型相比，具有最高 R 值的 DF 模型表现出了优异的性能。根据 DF-NSGA-II，从含有 14.27mM NH4+、38.92mM NO3-、22.79mM K+、5.08mM Cl-、3.34mM Ca2+、1.67mM Mg2+、2.17mM SO42-和 1.44mM HPO42-的培养基中可以获得最高的 ER 和 SEN。根据 DF-GA 模型，从含有 0.61μM 硫胺素、5.93μM 烟酸、0.25μM 生物素和 0.26μM 核黄素的培养基中可以获得最大的 SEN。建立的优化培养基的效率通过实验与 Murashige 和 Skoog 培养基（MS）进行了比较，用于五种菊花品种的胚胎发生，结果表明优化培养基比 MS 培养基更有效。
关键点
采用袋装法融合 MLP、SVR 和 ANFIS 建立数据融合模型。
链接 NSGA-II 和 GA 到数据融合模型，以建立和优化新的胚胎发生培养基。
新的培养基（HNT）比 MS 培养基具有更好的效率。
