An optimization procedure using artificial neural networks was developed to determine the optimal combination of parameters, such as medium culture, initial pH, temperature and time of fermentation for maximal trypanocidal metabolites production by Aspergillus fumigatus. A data set of 81 experiments was carried out and an artificial neural network was trained to identify the optimal conditions for this process. Good correlation was obtained between the experimental and predicted values of lysis of the trypomastigote forms of Trypanosoma cruzi (r2 = 0.9990). The simulations of fermentation performance were undertaken on combinations of input variables and the highest level of activity against T. cruzi was obtained from the chloroform extract of the modified Jackson medium culture, initial pH of 6.0, incubated at 40 degrees C for 144 h. It displayed lysis of 95% of the trypomastigote forms of T. cruzi and the red blood cells remained normal.

中文翻译：

---

使用神经网络改善烟曲霉产生的锥虫代谢产物。

开发了使用人工神经网络的优化程序，以确定参数的最佳组合，例如培养基培养，初始pH，发酵温度和发酵时间，以最大程度地产生烟曲霉的锥虫代谢产物。进行了81个实验的数据集，并训练了一个人工神经网络来确定该过程的最佳条件。在克氏锥虫的锥mas形式的实验值和预测值之间获得了良好的相关性（r2 = 0.9990）。发酵性能的模拟是在输入变量的组合下进行的，从改良的Jackson培养基培养物的氯仿提取物中获得了最高的抗克鲁氏酵母活性，初始pH为6.0，在40摄氏度下孵育144小时。