Using neural networks with a newly designed structure, the master thesis replaces unreliable expert methods for inserting regulatory sites into promoters. This is the first use of artificial intelligence to modify promoters in this way. Newly structured models of neural networks were created. Based on the outputs of the test data a laboratory experiment was conducted. According to the neural network design, ten constructs were created by inserting a regulatory site into the promoter. Significant regulation has been achieved in almost a third of cases. However, with a slight modification of the experiment, another set of constructs could be validated. The estimated result would then mean the success of regulation on sixty percent of proposals.