AI model predicts peptide bitterness and enables novel flavor design
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…
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.
Written by urgent.news from Phys.org's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.
