Leveraging Deep Learning to Predict the Antimicrobial Activity of Peptides Derived from Marine Symbiotic Bacteria: A Bioinformatics Study

The escalating global crisis of antimicrobial resistance (AMR) has intensified the search for novel antibiotic agents, with antimicrobial peptides (AMPs) emerging as promising therapeutic candidates due to their broad-spectrum activity and lower propensity for inducing resistance. Marine symbiotic bacteria, residing in diverse and extreme ecological niches, represent an underexplored reservoir of bioactive peptides with unique structural and functional characteristics. However, traditional discovery methods, relying on cultivation, chromatography, and conventional bioassays, are labor-intensive, low-throughput, and prone to rediscovering known compounds. Recent advances in deep learning have transformed this landscape by enabling rapid, high-throughput screening of genomic and metagenomic data to predict AMPs with remarkable accuracy. This review synthesizes current advances in deep learning-based bioinformatics approaches for predicting antimicrobial peptides derived from marine symbiotic bacteria. We examine the computational frameworks employed, including convolutional neural networks, recurrent neural networks, transformer-based architectures, and protein language models, and evaluate their performance in mining marine metagenomic datasets. We discuss the integration of multi-omics data, ribosome profiling, and structural prediction tools such as AlphaFold in the discovery pipeline. Furthermore, we address the challenges of dataset bias, model interpretability, and experimental validation that currently limit clinical translation. By bridging marine microbiology with computational intelligence, this review highlights the transformative potential of deep learning in accelerating the discovery of next-generation antimicrobial therapeutics from marine symbiotic bacteria.

کلیدواژه ها:

Deep Learning ، Antimicrobial Peptides ، Marine Symbiotic Bacteria ، Bioinformatics ، Drug Discovery ، Antimicrobial Resistance