Deep Generative Models for the Discovery of Antiviral Peptides Targeting Dengue Virus: A Systematic Review

Dengue virus (DENV) remains a critical global health challenge, with no approved antiviral treatments currently available. The growing prevalence of DENV infections highlights the urgent need for effective therapeutics. Antiviral peptides (AVPs) have gained significant attention due to their potential to inhibit viral replication. However, traditional drug discovery methods are often time-consuming and resource-intensive. Advances in artificial intelligence, particularly deep generative models (DGMs), offer a promising approach to accelerating AVP discovery. This report provides a comprehensive assessment of the role of DGMs in identifying novel AVPs for DENV. It presents an extensive survey of existing antimicrobial and AVP datasets, peptide sequence feature representations, and the integration of DGMs into computational peptide design. Additionally, in vitro and in silico screening data from previous studies highlight the therapeutic potential of AVPs against DENV. Variational autoencoders and generative adversarial networks have been extensively documented in the literature for their applications in AVP generation. These models have demonstrated a remarkable capacity to generate diverse and structurally viable compounds, significantly expanding the repertoire of potential antiviral candidates. Additionally, this report assesses both the strengths and limitations of DGMs, providing valuable insights for guiding future research directions. As a data-driven and scalable framework, DGMs offer a promising avenue for the rational design of potent AVPs targeting DENV and other emerging viral pathogens, contributing to the advancement of next-generation therapeutic strategies.