Masaitis Deividas, Urniezius Renaldas, Simutis Rimvydas, Vaitkus Vygandas, Matukaitis Mindaugas, Kemesis Benas, Galvanauskas Vytautas, Sinkevicius Benas
Department of Automation, Kaunas University of Technology, LT-51367 Kaunas, Lithuania.
Entropy (Basel). 2023 Sep 6;25(9):1302. doi: 10.3390/e25091302.
Accurate estimations of the concentrations of soluble compounds are crucial for optimizing bioprocesses involving (). This study proposes a hybrid model structure that leverages off-gas analysis data and physiological parameters, including the average biomass age and specific growth rate, to estimate soluble compounds such as acetate and glutamate in fed-batch cultivations We used a hybrid recurrent neural network to establish the relationships between these parameters. To enhance the precision of the estimates, the model incorporates ensemble averaging and information gain. Ensemble averaging combines varying model inputs, leading to more robust representations of the underlying dynamics in bioprocesses. Our hybrid model estimates acetates with 1% and 8% system precision using data from the first site and the second site at GSK plc, respectively. Using the data from the second site, the precision of the approach for other solutes was as fallows: isoleucine -8%, lactate and glutamate -9%, and a 13% error for glutamine., These results, demonstrate its practical potential.
准确估计可溶性化合物的浓度对于优化涉及（）的生物过程至关重要。本研究提出了一种混合模型结构，该结构利用废气分析数据和生理参数（包括平均生物量年龄和比生长速率）来估计补料分批培养中醋酸盐和谷氨酸等可溶性化合物。我们使用混合递归神经网络来建立这些参数之间的关系。为了提高估计的精度，该模型采用了总体平均和信息增益。总体平均结合了不同的模型输入，从而更稳健地表示生物过程中的潜在动态。我们的混合模型分别使用葛兰素史克公司第一工厂和第二工厂的数据，以1%和8%的系统精度估计醋酸盐。使用第二工厂的数据，该方法对其他溶质的精度如下：异亮氨酸为-8%，乳酸和谷氨酸为-9%，谷氨酰胺的误差为13%。这些结果证明了其实际潜力。
