目的探索TAR DNA结合蛋白43(transactive response DNA binding protein 43,TDP-43)在氧化应激诱导的小鼠神经元(neuro-2a,N2a)细胞损伤及小鼠痛觉敏化中的作用及机制。方法①为评估最佳诱导浓度,不同浓度的H_(2)O_(2)处理N2a细胞分为4...目的探索TAR DNA结合蛋白43(transactive response DNA binding protein 43,TDP-43)在氧化应激诱导的小鼠神经元(neuro-2a,N2a)细胞损伤及小鼠痛觉敏化中的作用及机制。方法①为评估最佳诱导浓度,不同浓度的H_(2)O_(2)处理N2a细胞分为4组:对照组、200μmol/L H_(2)O_(2)组、400μmol/L H_(2)O_(2)组和800μmol/L H_(2)O_(2)组。②为评估最佳诱导时间,400μmol/L H_(2)O_(2)处理N2a细胞分为4组:对照组、6 h H_(2)O_(2)组、12 h H_(2)O_(2)组和24 h H_(2)O_(2)组。③为验证线粒体DNA(mitochondria DNA,mtDNA)释放途径,使用环孢素(cyclosporin,CsA)抑制线粒体通透性转换孔(mitochondrial permeability transition pore,mPTP)分为3组:对照组、24 h H_(2)O_(2)组和24 h H_(2)O_(2)+CsA组。④为验证TDP-43介导的细胞损伤机制,siRNA抑制TDP-43后分为3组:对照组、24 h H_(2)O_(2)组、24 h H_(2)O_(2)+siTDP-43组。⑤采用CCK-8检测细胞活性,EdU检测细胞增殖,Western blot检测TDP-43、神经元标志物(neuronal nuclei,NeuN)、环状GMP-AMP合酶(cylic GMP-AMP synthase,cGAS)和干扰素基因刺激因子(stimulator of interferon,STING)表达,qPCR检测mtDNA,免疫染色观察细胞内TDP-43表达变化,Calcein AM染色评估mPTP开放。⑥为验证TDP-43在神经病理性疼痛(neuropathic pain,NP)中的作用,将24只6~8周健康SPF级雄性C57BL/6J小鼠(体质量25~30 g)使用随机数字表法分为3组:对照组、慢性压迫性损伤(chronic constriction injury,CCI)组、CCI+siTDP-43组,术前1 d和术后7、14、21 d进行鞘内注射siTDP-43;术前1 d和术后1、3、5、7、14、21 d通过von Frey纤维丝和热辐射法测定小鼠机械痛阈值和热痛阈值,免疫荧光检测术后21 d腰段(L5-L6)脊髓背角中TDP-43与NeuN的变化。结果氧化应激刺激诱导N2a中TDP-43蛋白表达增加,刺激mtDNA通过mPTP释放,上调cGAS、STING的表达,影响N2a的细胞活性(P<0.05);CsA抑制mPTP通道的开放并减少mtDNA释放(P<0.05);下调TDP-43的表达后可显著降低mtDNA的释放,抑制cGAS和STING的表达,并恢复N2a细胞的增殖能力(P<0.05)。CCI术后5 d,小鼠机械痛阈值和热痛阈值出现明显下降并持续至21 d(P<0.05);CCI小鼠术后21 d脊髓背角神经元中TDP-43表达增加(P<0.05);鞘内注射siRNA抑制TDP-43后,可提高CCI小鼠的机械痛阈值和热痛阈值(P<0.05)。结论氧化应激诱导神经元细胞TDP-43蛋白增加,刺激mtDNA通过mPTP释放到细胞质,激活cGAS/STING通路,导致神经元损伤并加重CCI小鼠痛觉敏化。展开更多
针对甘肃高比例新能源双边现货市场价格数据的非线性特征以及主流损失函数的缺陷,本文主要研究如何使用Huber损失函数与神经网络精确模拟日前电力现货价格的时间序列,旨在系统解决甘肃日前电力现货价格预测时反向传播损失函数的选择。...针对甘肃高比例新能源双边现货市场价格数据的非线性特征以及主流损失函数的缺陷,本文主要研究如何使用Huber损失函数与神经网络精确模拟日前电力现货价格的时间序列,旨在系统解决甘肃日前电力现货价格预测时反向传播损失函数的选择。首先分析了甘肃电力现货市场的运行特点及问题,建立了其电力现货价格的神经网络模型;为了模型的优化建立了反向传播算法中损失函数应该满足的期望属性,并筛选出满足属性的Huber损失函数用于甘肃电力市场现货价格预测,还对市场因素的相关性进行了分析;通过实证研究,在MSE、MAE和Huber上训练了RNN神经网络,发现利用2024年1月1日至2024年6月30日期间甘肃电力现货价格数据在Huber上训练的模型比在MSE和MAE上训练的模型提供了更准确的日前电价预测,Huber函数是训练神经网络预测甘肃日前电力现货价格的最佳选择。而且Huber函数的回溯结果和稳定性比MSE和MAE都好,即利用Huber损失函数预测数据的精准性和稳定性更强。In response to the nonlinear characteristics of the bilateral spot market price data for high-proportion new energy in Gansu and the shortcomings of mainstream loss functions, this paper primarily investigates how to use the Huber loss function with neural networks to accurately model the time series of day-ahead electricity spot prices, aiming to systematically address the selection of the backpropagation loss function for day-ahead electricity spot price forecasting in Gansu. Firstly, the operational characteristics and issues of the Gansu electricity spot market are analyzed, and a neural network model for its electricity spot price is established;to optimize the model, the expected properties that the loss function should meet in the backpropagation algorithm are established, and the Huber loss function, which meets the properties, is selected for forecasting the spot price of the Gansu electricity market, and the correlation of market factors is analyzed;through empirical research, Recurrent neural networks (RNN) are trained on MSE, MAE, and Huber, and it is found that using the Gansu electricity spot price data from January 1, 2024, to June 30, 2024, the model trained on Huber provides more accurate day-ahead electricity price forecasts than the models trained on MSE and MAE. The Huber function is the best choice for training neural networks to predict day-ahead electricity spot prices in Gansu. Moreover, the retrospective results and stability of the Huber function are better than those of MSE and MAE;that is, the precision and stability of predicting data using the Huber loss function are stronger.展开更多
文摘目的探索TAR DNA结合蛋白43(transactive response DNA binding protein 43,TDP-43)在氧化应激诱导的小鼠神经元(neuro-2a,N2a)细胞损伤及小鼠痛觉敏化中的作用及机制。方法①为评估最佳诱导浓度,不同浓度的H_(2)O_(2)处理N2a细胞分为4组:对照组、200μmol/L H_(2)O_(2)组、400μmol/L H_(2)O_(2)组和800μmol/L H_(2)O_(2)组。②为评估最佳诱导时间,400μmol/L H_(2)O_(2)处理N2a细胞分为4组:对照组、6 h H_(2)O_(2)组、12 h H_(2)O_(2)组和24 h H_(2)O_(2)组。③为验证线粒体DNA(mitochondria DNA,mtDNA)释放途径,使用环孢素(cyclosporin,CsA)抑制线粒体通透性转换孔(mitochondrial permeability transition pore,mPTP)分为3组:对照组、24 h H_(2)O_(2)组和24 h H_(2)O_(2)+CsA组。④为验证TDP-43介导的细胞损伤机制,siRNA抑制TDP-43后分为3组:对照组、24 h H_(2)O_(2)组、24 h H_(2)O_(2)+siTDP-43组。⑤采用CCK-8检测细胞活性,EdU检测细胞增殖,Western blot检测TDP-43、神经元标志物(neuronal nuclei,NeuN)、环状GMP-AMP合酶(cylic GMP-AMP synthase,cGAS)和干扰素基因刺激因子(stimulator of interferon,STING)表达,qPCR检测mtDNA,免疫染色观察细胞内TDP-43表达变化,Calcein AM染色评估mPTP开放。⑥为验证TDP-43在神经病理性疼痛(neuropathic pain,NP)中的作用,将24只6~8周健康SPF级雄性C57BL/6J小鼠(体质量25~30 g)使用随机数字表法分为3组:对照组、慢性压迫性损伤(chronic constriction injury,CCI)组、CCI+siTDP-43组,术前1 d和术后7、14、21 d进行鞘内注射siTDP-43;术前1 d和术后1、3、5、7、14、21 d通过von Frey纤维丝和热辐射法测定小鼠机械痛阈值和热痛阈值,免疫荧光检测术后21 d腰段(L5-L6)脊髓背角中TDP-43与NeuN的变化。结果氧化应激刺激诱导N2a中TDP-43蛋白表达增加,刺激mtDNA通过mPTP释放,上调cGAS、STING的表达,影响N2a的细胞活性(P<0.05);CsA抑制mPTP通道的开放并减少mtDNA释放(P<0.05);下调TDP-43的表达后可显著降低mtDNA的释放,抑制cGAS和STING的表达,并恢复N2a细胞的增殖能力(P<0.05)。CCI术后5 d,小鼠机械痛阈值和热痛阈值出现明显下降并持续至21 d(P<0.05);CCI小鼠术后21 d脊髓背角神经元中TDP-43表达增加(P<0.05);鞘内注射siRNA抑制TDP-43后,可提高CCI小鼠的机械痛阈值和热痛阈值(P<0.05)。结论氧化应激诱导神经元细胞TDP-43蛋白增加,刺激mtDNA通过mPTP释放到细胞质,激活cGAS/STING通路,导致神经元损伤并加重CCI小鼠痛觉敏化。
文摘针对甘肃高比例新能源双边现货市场价格数据的非线性特征以及主流损失函数的缺陷,本文主要研究如何使用Huber损失函数与神经网络精确模拟日前电力现货价格的时间序列,旨在系统解决甘肃日前电力现货价格预测时反向传播损失函数的选择。首先分析了甘肃电力现货市场的运行特点及问题,建立了其电力现货价格的神经网络模型;为了模型的优化建立了反向传播算法中损失函数应该满足的期望属性,并筛选出满足属性的Huber损失函数用于甘肃电力市场现货价格预测,还对市场因素的相关性进行了分析;通过实证研究,在MSE、MAE和Huber上训练了RNN神经网络,发现利用2024年1月1日至2024年6月30日期间甘肃电力现货价格数据在Huber上训练的模型比在MSE和MAE上训练的模型提供了更准确的日前电价预测,Huber函数是训练神经网络预测甘肃日前电力现货价格的最佳选择。而且Huber函数的回溯结果和稳定性比MSE和MAE都好,即利用Huber损失函数预测数据的精准性和稳定性更强。In response to the nonlinear characteristics of the bilateral spot market price data for high-proportion new energy in Gansu and the shortcomings of mainstream loss functions, this paper primarily investigates how to use the Huber loss function with neural networks to accurately model the time series of day-ahead electricity spot prices, aiming to systematically address the selection of the backpropagation loss function for day-ahead electricity spot price forecasting in Gansu. Firstly, the operational characteristics and issues of the Gansu electricity spot market are analyzed, and a neural network model for its electricity spot price is established;to optimize the model, the expected properties that the loss function should meet in the backpropagation algorithm are established, and the Huber loss function, which meets the properties, is selected for forecasting the spot price of the Gansu electricity market, and the correlation of market factors is analyzed;through empirical research, Recurrent neural networks (RNN) are trained on MSE, MAE, and Huber, and it is found that using the Gansu electricity spot price data from January 1, 2024, to June 30, 2024, the model trained on Huber provides more accurate day-ahead electricity price forecasts than the models trained on MSE and MAE. The Huber function is the best choice for training neural networks to predict day-ahead electricity spot prices in Gansu. Moreover, the retrospective results and stability of the Huber function are better than those of MSE and MAE;that is, the precision and stability of predicting data using the Huber loss function are stronger.