Author(s): Pereira, João Santos ; Pires, David
Date: 2025
Persistent ID: http://hdl.handle.net/10400.14/55796
Origin: Veritati - Repositório Institucional da Universidade Católica Portuguesa
Subject(s): Artificial intelligence; Epitope prediction; Machine learning; Reverse vaccinology; Tuberculosis; Vaccines
Tuberculosis is a long-standing global health challenge. Yet, so far, all efforts to develop an effective vaccine that surpasses the limitations of the century-old BCG vaccine have been unsuccessful. This calls for new technological solutions that can aid researchers in digesting decades of data and predict the solutions with the highest successful outcomes. This chapter discusses how Artificial Intelligence (AI) can be leveraged to enhance each stage of vaccine development. AI, particularly machine learning (ML) techniques, can assist in antigen identification, epitope prediction, and the design of immunogens, thus streamlining the vaccine development process. We highlight some key AI-driven tools of reverse vaccinology and predictive models that allow researchers to analyse vast biological datasets, enhancing the accuracy and speed of candidate screening. We also acknowledge the many challenges that need to be overcome to improve vaccine development and deployment, the difficulties in integrating AI into existing processes and the need for high-quality datasets and computational power. This underscores the necessity for interdisciplinary collaboration to overcome these barriers and fully realise the potential of AI in creating effective TB vaccines.
