ARTIFICIAL INTELLIGENCE IN ANIMAL NUTRIGENOMICS AND GENE EXPRESSION ANALYSIS: CURRENT APPLICATIONS, CHALLENGES AND FUTURE PERSPECTIVES

Resumo

Artificial Intelligence (AI) has rapidly transformed molecular research by expanding the analytical capacity of bioinformatics and enabling the interpretation of increasingly complex biological datasets. This review aimed to discuss the evolution of AI applications in animal nutrigenomics and gene expression analysis, highlighting current applications, methodological challenges, and future perspectives for precision nutrition. A narrative literature review was conducted through a structured bibliographic survey using PubMed, Scopus, Web of Science, ScienceDirect, SpringerLink, and Google Scholar databases. Priority was given to peer-reviewed studies published between 2021 and 2026, while seminal references were included when essential to describe the historical development of bioinformatics and transcriptomic analyses. The selected studies were qualitatively analyzed and organized according to four thematic axes: the evolution from traditional bioinformatics to Artificial Intelligence, current applications of AI in animal nutrigenomics, existing methodological limitations, and future research directions. The reviewed literature demonstrates that AI has expanded the identification of molecular biomarkers, improved multi-omics integration, strengthened predictive models, and enhanced the interpretation of complex transcriptomic datasets. Despite these advances, challenges related to data standardization, biological validation, model interpretability, and the availability of large, high-quality livestock datasets continue to limit broader implementation. Overall, current evidence indicates that AI is reshaping animal nutrigenomics by supporting the transition from descriptive molecular analyses toward predictive approaches capable of anticipating nutritional responses and contributing to precision livestock production.