The discovery of new functionalities through the study of human physiology has contributed toward the evolution of Artificial Immune Systems. The present work investigates a new architecture through observations of natural immunological behavior, for which application to known algorithms contributed toward an improved performance. This paper considers a boarding where the antibodies are grouped in an organized way and from an evolutionary process the antibodies that belong to these groupings can improve the adaptive immune reply to a determined antigen. Thus, antibodies of the same class are in the same grouping. Others techniques were implemented such as Clonalg, MLP and K-NN to compare this new model.