EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

MAPLE: interpretable deep learning identifies selective antimicrobial peptides using joint evolutionary–physicochemical analysis

Hao Liu, Yi Shi, Feiyu Guo, Jinyi Wang, Jiaqian Li, Guangji Wang, De-Chuan Zhan, Haiping Hao, Guo Yu iD

Briefings in Bioinformatics · 2026

DOI: 10.1093/bib/bbag318 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Briefings in Bioinformatics, 2026. Verfasst von Hao Liu und 8 weiteren Autor:innen. Beteiligte Einrichtung: State Key Laboratory of Natural Medicines, Key Laboratory of Drug Metabolism, China Pharmaceutical University, No. 24 Tongjiaxiang, Gulou District, N…. Hauptthemen laut MEDLINE: Antimicrobial Peptides, Deep Learning, Computational Biology. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 99 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Lingang Laboratory.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Antimicrobial peptides (AMPs) are promising alternatives to conventional antibiotics, yet early translation is often hindered by the perceived coupling between antibacterial potency and mammalian toxicity. This assumption complicates prioritization: highly active candidates are frequently suspected to be hemolytic, while existing multi-task predictors rarely reveal where selectivity resides in sequence space. Here, we present Multifunctional AMP Learning Engine (MAPLE), an interpretable dual-stream framework for AMP identification and systematic category-specific functional profiling across 14 activity categories directly from peptide sequences. MAPLE combines protein language model embeddings with explicit physicochemical descriptors, enabling robust task-specific prediction under severe label imbalance. Across the benchmark dataset and a sequence-non-overlapping independent validation set, MAPLE achieves consistently well-balanced performance, including on low-prevalence but clinically relevant endpoints. Building on this predictive basis, we conduct systematic k-mer enrichment to map motif-level selectivity and show that potency–hemolysis coupling is motif-regime-dependent rather than universal. Motifs most strongly enriched for antibacterial activity exhibit reduced hemolytic overlap and occupy a physicochemical regime characterized by moderate cationicity, lower hydrophobicity, and higher amphipathicity. We further provide a proof-of-concept prioritization workflow leveraging antibacterial-selective motifs, with structural modeling yielding conformations consistent with amphipathic α-helices. Despite limitations of predominantly binary annotations and incomplete structural integration, MAPLE offers reproducible sequence-level hypotheses and prioritization principles to support the engineering of potent and safer AMPs.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Antimicrobial PeptidesDeep LearningComputational BiologyHemolysisHumansAmino Acid Sequence

Stichwörter der Autor:innen

antimicrobial peptidesfunctional profilinghemolysis predictionmotif interpretabilityprotein language modelstherapeutic selectivity

Substanzen

Antimicrobial Peptides

Autor:innen und Institutionen

  • State Key Laboratory of Natural Medicines, Key Laboratory of Drug Metabolism, China Pharmaceutical University, No. 24 Tongjiaxiang, Gulou District, Nanjing 210009, China.
  • School of Basic Medicine and Clinical Pharmacy, China Pharmaceutical University, No. 639 Longmian Avenue, Jiangning District, Nanjing 211198, China.
  • Institute of Innovative Drug, China Pharmaceutical University, No. 639 Longmian Avenue, Jiangning District, Nanjing 211198, China.
  • National Key Laboratory for Novel Software Technology, Nanjing University, No. 163 Xianlin Avenue, Qixia District, Nanjing 210023, China.
  • School of Artificial Intelligence, Nanjing University, No. 163 Xianlin Avenue, Qixia District, Nanjing 210023, China.

ORCID-Profile: Guo Yu

Förderung

  • Lingang Laboratory

Zitieren

APA

Liu, H., Shi, Y., Guo, F., Wang, J., Li, J., Wang, G., Zhan, D. C., Hao, H., & Yu, G. (2026). MAPLE: interpretable deep learning identifies selective antimicrobial peptides using joint evolutionary–physicochemical analysis. Briefings in Bioinformatics. https://doi.org/10.1093/bib/bbag318

Vancouver

Liu H, Shi Y, Guo F, Wang J, Li J, Wang G, et al. MAPLE: interpretable deep learning identifies selective antimicrobial peptides using joint evolutionary–physicochemical analysis. Briefings in Bioinformatics. 2026. doi:10.1093/bib/bbag318

BibTeX
@article{Liu2026,
  author = {Liu, Hao and Shi, Yi and Guo, Feiyu and Wang, Jinyi and Li, Jiaqian and Wang, Guangji and Zhan, De-Chuan and Hao, Haiping and Yu, Guo},
  title = {MAPLE: interpretable deep learning identifies selective antimicrobial peptides using joint evolutionary–physicochemical analysis},
  journal = {Briefings in Bioinformatics},
  year = {2026},
  doi = {10.1093/bib/bbag318}
}
Kostenlos starten →