<p>Recently, antibodies have been considered essential therapeutics for combating diseases, especially viral infections. However, limited information on antibody structures has impeded their development. The interactions promoting antigen binding are determined by the structures of the six loops that comprise the complementarity-determining regions (CDRs). Artificial Intelligence (AI) technologies are overcoming many limitations by using co-evolution information from homologous proteins to predict protein function and structure and develop drug discovery. This study introduces an overview of computational methods for artificial intelligence for producing antibody structure and design and covers databases used, CDR loops, structural elements crucial to binding, and computer predictors of antibody structure and features; it highlights that Deep Learning (DL) techniques are essential for improving antibody structure prediction. Using various principles and methods, these techniques have significantly advanced the ability to predict novel antibody structures for binding.</p>