In the context of fast and significant technological transformations, it is natural for innovative artificial intelligence (AI) methods to emerge for the design of bioactive molecules. In this study, we demonstrated that the design of mimetic antibodies (MA) can be achieved using a combination of software and algorithms traditionally employed in molecular simulation. This combination, organized as a genetic algorithm (GA), has the potential to address one of the main challenges in the design of bioactive molecules: GA convergence occurs rapidly due to the careful selection of initial populations based on intermolecular interactions at antigenic surfaces. Experimental immunoenzymatic tests prove that the GA succ... More
In the context of fast and significant technological transformations, it is natural for innovative artificial intelligence (AI) methods to emerge for the design of bioactive molecules. In this study, we demonstrated that the design of mimetic antibodies (MA) can be achieved using a combination of software and algorithms traditionally employed in molecular simulation. This combination, organized as a genetic algorithm (GA), has the potential to address one of the main challenges in the design of bioactive molecules: GA convergence occurs rapidly due to the careful selection of initial populations based on intermolecular interactions at antigenic surfaces. Experimental immunoenzymatic tests prove that the GA successfully optimized the molecular recognition capacity of one of the MA. One of the significant results of this study is the discovery of new structural motifs, which can be designed in an original and innovative way based on the MA structure itself, eliminating the need for preexisting databases. Through the GA developed in this study, we demonstrated the application of a new protocol capable of guiding experimental methods in the development of new bioactive molecules.
