EUVIMEDEUVIMED entdecken
Übersichtsarbeit

AI-Driven Prediction of Allergenicity and Toxicity in Novel Plant-Based Peptides

Chi-Ching Lee iD, Tolulope Joshua Ashaolu iD

Journal of Agricultural and Food Chemistry · 11.11.2026 · 74 (44) · 34683-34700

DOI: 10.1021/acs.jafc.6c13356 ↗

Kurz gefasst

Übersichtsarbeit in der Zeitschrift Journal of Agricultural and Food Chemistry, online erschienen am 02.11.2026. Verfasst von Chi-Ching Lee und 1 weiteren Autor:innen. Beteiligte Einrichtung: Faculty of Engineering and Natural Sciences, Department of Food Engineering, Istanbul Sabahattin Zaim University, No: 281, Halkali Street, Halkali, K…. Hauptthemen laut MEDLINE: Allergens, Peptides, Artificial Intelligence, Plant Proteins. Die Arbeit nennt 94 Literaturangaben.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Peptides from plant sources have antihypertensive, antioxidative, and antimicrobial properties but also entail a risk of allergic and toxic reactions that cannot be detected in conventional wet-lab assays. This review examines deep learning techniques and protein language models for their prediction, from linear motifs screening to transformers (BERT, ESM). The best-performing tools achieve high sensitivity (pLM4Alg 96.2%, ToxinPred3 95.8%) but low specificity and positive predictive value (pLM4Alg 92.8% and 81.7%), meaning that most predictions are false positives. There are four major constraints on the generalization capabilities of these tools: scoring of native peptides while proteolytic processing yields post-translational modifications and neoantigens; training samples correspond to IgE binding, not clinical manifestations, and are biased toward well-characterized organisms; T-cell immunity, microbiome, and organ-specific toxicity are scarcely modeled; and regulatory agencies do not consider in silico predictions sufficient. AI currently serves best as a prioritization filter, not a replacement for biological assays.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

AllergensPeptidesArtificial IntelligencePlant ProteinsPlantsHumansAnimalsPrediction Algorithms

Stichwörter der Autor:innen

allergenartificial intelligencebioactive peptidesexplainable AIfood safetyplant proteinprotein language modelstoxicity

Substanzen

AllergensPeptidesPlant Proteins

Autor:innen und Institutionen

  • Faculty of Engineering and Natural Sciences, Department of Food Engineering, Istanbul Sabahattin Zaim University, No: 281, Halkali Street, Halkali, Kuçukçekmece34303, Istanbul, Turkiye.
  • Department of Food Technologies, Faculty of Technologies, Klaipėdos Valstybinė Kolegija/Higher Education Institution, Klaipėdos91274, Lithuania.
  • Institute for Global Health Innovations, Duy Tan University, Da Nang550000, Vietnam.
  • Faculty of Medicine, Duy Tan University, Da Nang550000, Vietnam.
  • Department of Food Biotechnology, Albert Kazmer Mosonmagyarovar Faculty, Széchenyi István University, Egyetem Sqr. 1, Gyor9026, Hungary.

ORCID-Profile: Chi-Ching Lee, Tolulope Joshua Ashaolu

Zitieren

APA

Lee, C. C., & Ashaolu, T. J. (2026). AI-Driven Prediction of Allergenicity and Toxicity in Novel Plant-Based Peptides. Journal of Agricultural and Food Chemistry, 74(44), 34683-34700. https://doi.org/10.1021/acs.jafc.6c13356

Vancouver

Lee CC, Ashaolu TJ. AI-Driven Prediction of Allergenicity and Toxicity in Novel Plant-Based Peptides. Journal of Agricultural and Food Chemistry. 2026;74(44):34683-34700. doi:10.1021/acs.jafc.6c13356

BibTeX
@article{Lee2026,
  author = {Lee, Chi-Ching and Ashaolu, Tolulope Joshua},
  title = {AI-Driven Prediction of Allergenicity and Toxicity in Novel Plant-Based Peptides},
  journal = {Journal of Agricultural and Food Chemistry},
  year = {2026},
  volume = {74},
  number = {44},
  pages = {34683--34700},
  doi = {10.1021/acs.jafc.6c13356}
}
Kostenlos starten →