Application of machine learning and deep learning techniques on reverse vaccinology – a systematic literature review

Reverse vaccinology (RV) is recognized as a productive method of vaccine discovery since it may be used to create vaccines for a variety of infectious pathogens. With the potential for machine learning (ML) algorithms to enable quick and precise predictions of vaccine candidates against new infections, RV is of particular relevance. Despite the fact that ML has been used successfully in the past, Deep learning (DL) model-based RV approaches have not been used widely. DL techniques are known to provide more complicated models and better performance for AI applications. This paper supports and reviews the roles of machine learning and Deep Learning in predicting potential vaccine candidates and discovery processes. Our study involved a systematic evaluation of selected publications, identified through a combination of prior knowledge and keyword searches across freely accessible databases. A meticulous screening process, considering contextual relevance, abstract quality, methodology, and full-text content, was employed. The literature review, conducted with a rigorous methodology, encompasses a thorough analysis of articles focusing on machine learning and deep learning techniques. © The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2025.