Plant-derived compounds and artificial intelligence: Outsmarting microbial pathogens and antimicrobial resistance

From the discovery of the first antimicrobial drug to nowadays, the development of antimicrobial resistance (AMR) - a silent pandemic among pathogenic microbes has posed a significant challenge to modern healthcare system, necessitating the exploration of novel molecules with potent antimicrobial property.

This review seeks to deliver a thorough analysis of the diverse categories of plant-derived antimicrobials, including their extraction, biosynthesis, purification processes, antimicrobial mechanisms, formulation strategies, and preclinical translation. Rigorous literature search screening was carried out using Google Scholar, Web of Science, PubMed, and Scopus.

This review represents the first instance of merging artificial intelligence (AI) in advancing phytochemistry research on AMR. Conventional drug development is frequently marked by delayed timeframes, substantial expenses, and complicated issues of target selection, therapeutic efficacy, and safety assessment. Machine learning (ML), deep learning (DL), and natural language processing (NLP), predictive modeling and AI-driven algorithms like BioGPT, DOCK6, SwissADME, DeepTox, etc., facilitate effective drug target selection and toxicity prediction.

Plant-derived secondary metabolites (PSMs) are investigated as a future alternative to traditional medications and are found in stems, leaves, fruits, roots, flowers and seeds of multifaceted plants and proves to be highly effective against various bacterial and fungal pathogen and interferes with the process of quorum sensing and biofilm formation, damages cell membranes and cell wall, enzymes, and induces oxidative stress. Therefore, the review examines contemporary phytochemistry research relevant to the potential development of plant-derived compounds as novel antimicrobial agents.