{
  "id": 9173169,
  "title": "AI model predicts peptide bitterness and enables novel flavor design",
  "url": "https://urgent.news/2026/09/22/ai-model-predicts-peptide-bitterness-and-enables-novel-flavor-design",
  "topic": "ai",
  "section": "AI",
  "published": "2026-09-22T18:20:03.000Z",
  "source": {
    "name": "Phys.org",
    "slug": "phys-org",
    "url": "https://phys.org/news/2026-09-ai-peptide-bitterness-enables-flavor.html"
  },
  "original_language": "en",
  "account": "Scientists have developed an AI-based method that can predict the bitterness of peptides, which can be found in fermented foods and protein powders, according to a study published in npj Science of Food. Bitter-tasting peptides can form during the breakdown of proteins and pose challenges in food production, but the new AI model can also design new, bitter-tasting peptides from scratch. The researchers combined a protein language model with a specialized neural network called BitterPep-GCN, generating 161 new peptide sequences that were then tested by a sensory panel. The AI predictions were confirmed in 25 out of 31 cases, and the researchers identified several previously unknown bitter and non-bitter peptides. This breakthrough could help control bitterness in protein-rich foods, making them more appealing and nutritious.",
  "summary": "During the production of fermented products such as kefir, Parmesan, or mountain cheese, as well as in the production of protein powders, bitter-tasting peptides can form, which impair the taste and thus the acceptability of the products. A research team led by the Leibniz Institute for Food Systems Biology at the Technical University of Munich has now developed and successfully tested an…",
  "key_points": [
    "AI model predicts peptide bitterness",
    "Enables novel flavor design in foods",
    "Confirmed 25 out of 31 bitter peptide predictions"
  ],
  "editors_take": null,
  "illustration": null,
  "coverage": {
    "outlets": 1,
    "also_reported_by": []
  },
  "ai_generated": true,
  "disclaimer": "Summaries, key points and the editor’s take are written by software from other outlets’ reporting and may contain errors — always check the linked original."
}