EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC-ND 4.0

AI-Guided Discovery of Antimicrobial Peptides Against Multidrug-Resistant Bacterial Biofilms

Muzammal Zainab

Journal of Biological and Allied Health Sciences · 13.06.2026 · 6 (1)

DOI: 10.56536/jbahs.v6i1.199 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Biological and Allied Health Sciences, online erschienen am 13.06.2026. Verfasst von Muzammal Zainab. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Multidrug-resistant bacterial infections are a major threat to modern medicine, particularly when pathogens form biofilms. Biofilms increase antimicrobial tolerance by creating a protective extracellular matrix, promoting altered metabolic states, restricting antimicrobial penetration and supporting persistent bacterial subpopulations. Antimicrobial peptides are promising alternatives to conventional antibiotics because many display broad-spectrum activity, membrane-targeting mechanisms, antibiofilm potential and immunomodulatory effects. However, their clinical translation remains limited by toxicity, proteolytic instability, poor selectivity and high discovery costs. Artificial intelligence offers an opportunity to accelerate antimicrobial peptide discovery by predicting antimicrobial activity, antibiofilm potential, toxicity and stability before experimental validation. This paper presents a proposed computational–experimental research framework for AI-guided discovery of antimicrobial peptides against multidrug-resistant biofilm-forming bacteria. The proposed design integrates antimicrobial peptide databases, physicochemical descriptor extraction, protein-language-model embeddings, supervised machine learning, generative peptide design, multi-objective filtering and biosafety-conscious laboratory validation. The proposed framework is expected to generate a prioritised shortlist of novel or optimised antimicrobial peptide candidates with predicted antibacterial, antibiofilm and low-toxicity profiles. Expected outputs include validated predictive models, candidate-ranking tables, antibiofilm screening outcomes and a reproducible translational pipeline. AI-guided peptide discovery may reduce early-stage screening burden and improve candidate prioritisation. However, major limitations include dataset bias, inconsistent antibiofilm annotations, poor external validation, safety concerns and uncertainty in translating in silico predictions into clinically useful therapeutics. AI-guided discovery of antimicrobial peptides against multidrug-resistant bacterial biofilms is a highly relevant and impactful PhD research direction in biological sciences, biotechnology, microbiology and computational biology. A carefully designed IMRAD-based project can contribute to antimicrobial resistance research while remaining feasible for UK doctoral training

Zitieren

APA

Zainab, M. (2026). AI-Guided Discovery of Antimicrobial Peptides Against Multidrug-Resistant Bacterial Biofilms. Journal of Biological and Allied Health Sciences, 6(1). https://doi.org/10.56536/jbahs.v6i1.199

Vancouver

Zainab M. AI-Guided Discovery of Antimicrobial Peptides Against Multidrug-Resistant Bacterial Biofilms. Journal of Biological and Allied Health Sciences. 2026;6(1). doi:10.56536/jbahs.v6i1.199

BibTeX
@article{Zainab2026,
  author = {Zainab, Muzammal},
  title = {AI-Guided Discovery of Antimicrobial Peptides Against Multidrug-Resistant Bacterial Biofilms},
  journal = {Journal of Biological and Allied Health Sciences},
  year = {2026},
  volume = {6},
  number = {1},
  doi = {10.56536/jbahs.v6i1.199}
}
Kostenlos starten →