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

Machine Learning Prediction and Experimental Validation of Antimicrobial Peptide Activity Differences against Gram-Positive and Gram-Negative Bacteria

Peicheng Lu, Wenhao Li, Muhammad Zubair, Leyu Li, Guomin Han iD, Ying Chu iD

ACS Omega · 18.08.2026 · 11 (32) · 47517-47527

DOI: 10.1021/acsomega.6c01772 ↗

Kurz gefasst

Fachartikel in der Zeitschrift ACS Omega, online erschienen am 03.08.2026. Verfasst von Peicheng Lu und 5 weiteren Autor:innen. Beteiligte Einrichtung: School of Life Sciences, Anhui Agricultural University, Hefei 230036, China. Die Arbeit nennt 57 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0). Gefördert von: Jiangsu Commission of Health, Project 333 of Jiangsu Province, Changzhou Longcheng Talent Program specific project for foreign talents.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Antimicrobial peptides (AMPs) are primary candidates for addressing bacterial resistance. Although their target spectrum specificity varies significantly between Gram-positive and Gram-negative bacteria, current predictive models generally lack experimental validation. In this study, we constructed various machine learning models based on known sequences to systematically evaluate the performance of k-mer frequencies, physicochemical properties, and hybrid features in distinguishing the AMP target specificity. Results indicated that the random forest model based on eight key physicochemical properties performed best, achieving a test set accuracy of 82.09% with balanced classification and robust generalization. Feature importance analysis revealed that hydrophilicity and isoelectric point (pI) are the core physicochemical factors determining the target spectrum differences. The model was rigorously validated through a dual-track approach: first, via the synthesis and in vitro testing of 18 novel protozoan-derived AMPs (overall accuracy 66.67%) and, second, through a blind test on 55 independent external sequences, achieving a robust accuracy of 81.82%. Furthermore, the framework successfully identified candidates with potent activity against multidrug-resistant pathogens including Pseudomonas aeruginosa and Klebsiella pneumoniae. This experimentally validated predictive framework provides a reliable computational tool for the high-throughput screening and rational design of targeted antimicrobial peptides.

Autor:innen und Institutionen

  • School of Life Sciences, Anhui Agricultural University, Hefei 230036, China.
  • Central Laboratory, Jiangsu University Affiliated Wujin Hospital, Changzhou 213017, China.
  • National Engineering Laboratory of Crop Stress Resistance Breeding, Anhui Agricultural University, Hefei 230036, China.
  • Jiangsu Key Laboratory of Medical Science and Laboratory Medicine, Jiangsu University, Zhenjiang 212013, China.

ORCID-Profile: Guomin Han, Ying Chu

Förderung

  • Jiangsu Commission of Health
  • Project 333 of Jiangsu Province
  • Changzhou Longcheng Talent Program specific project for foreign talents
  • Jiangsu Key Laboratory of Medical Science and Laboratory Medicine
  • Jiangsu Excellent Postdoctoral Program

Zitieren

APA

Lu, P., Li, W., Zubair, M., Li, L., Han, G., & Chu, Y. (2026). Machine Learning Prediction and Experimental Validation of Antimicrobial Peptide Activity Differences against Gram-Positive and Gram-Negative Bacteria. ACS Omega, 11(32), 47517-47527. https://doi.org/10.1021/acsomega.6c01772

Vancouver

Lu P, Li W, Zubair M, Li L, Han G, Chu Y. Machine Learning Prediction and Experimental Validation of Antimicrobial Peptide Activity Differences against Gram-Positive and Gram-Negative Bacteria. ACS Omega. 2026;11(32):47517-47527. doi:10.1021/acsomega.6c01772

BibTeX
@article{Lu2026,
  author = {Lu, Peicheng and Li, Wenhao and Zubair, Muhammad and Li, Leyu and Han, Guomin and Chu, Ying},
  title = {Machine Learning Prediction and Experimental Validation of Antimicrobial Peptide Activity Differences against Gram-Positive and Gram-Negative Bacteria},
  journal = {ACS Omega},
  year = {2026},
  volume = {11},
  number = {32},
  pages = {47517--47527},
  doi = {10.1021/acsomega.6c01772}
}
Kostenlos starten →