In many cases, the search for synthetic functional networks of a gene regulatory network model can be a difficult and time-consuming task. In this paper, we present a method that uses the popular SMOTE algorithm to sample synthetic functional networks in order to boost the results obtained by an evolutionary computation framework in a previous stage. We consider threshold Boolean networks for gene regulatory network modeling and apply the proposed method to the search for functional networks of the tryptophan operon in E. coli model. The results confirm the effectiveness of the proposed method by increasing the number of functional networks from fifteen, originally found by an evolutionary computation framework in more than nineteen hours, to twenty-nine in only a few minutes, allowing a more reliable characterization of the neutral space for the biological model.