Fecha de publicación: -- Fuente: Food Processing During the production of protein powders and fermented products, such as kefir and Parmesan cheese, bitter-tasting peptides can form, which can 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 AI-based method that can predict the bitterness of peptides. It can also be used to design new, bitter-tasting peptides from scratch.

Bitter-tasting peptides are produced during the enzymatic or chemical breakdown of proteins and pose a particular challenge in the production of fermented foods or protein hydrolysates. At the same time, they can possess physiological properties that can, for example, contribute to the regulation of hunger and satiety.

“To make plant-based protein sources more attractive for food production and to use them more sustainably, we need to better understand which peptides taste bitter and what structural features characterise them. AI-based methods can also make an important contribution here,” said Antonella Di Pizio, principal investigator of the current study, which also involved researchers from the Technical University of Munich and Pompeu Fabra University in Barcelona.

To develop the AI-supported bioinformatics method, the team led by Di Pizio combined a protein language model — which the team had previously trained using approximately 500 known bitter-tasting peptides — with the BitterPep-GCN prediction model they had recently developed. This is a so-called graph convolutional network (GCN), a specialised form of artificial neural networks used to analyse structured data.

Based on this, the researchers first generated 161 new peptide sequences that had not yet been experimentally characterised. They then identified those candidates that, according to the model predictions, were highly likely to taste bitter or non-bitter.

They had the most promising of these peptides synthesised and then tasted by a trained sensory panel. In most cases, the AI predictions were confirmed: of the 31 peptides tested, the test subjects correctly classified 25 as bitter or non-bitter. In addition, the research team identified numerous previously unknown bitter and non-bitter-tasting peptides.



A computer model of a human bitter taste receptor (centre) with the bound tripeptide tri-tryptophan (top, yellow-orange). The simulation shows the peptide bound in the receptor pocket. Image credit: Florian Bößl/Leibniz-LSB@TUM

“Our results show that not only can the bitterness of peptides be predicted, but that our new AI-based method can also be used to specifically design new bitter-tasting peptides,” said Alexandra Steuer, first author of the study and a doctoral student in Di Pizio’s Molecular Modeling research group. “This brings us significantly closer to the goal of proactively controlling taste characteristics,” Di Pizio said.

The scientist said the research is ready to be implemented in application frameworks: “In the long term, these new findings could help to specifically control the formation of bitter-tasting peptides during food production. This would be particularly relevant for plant-based, protein-rich foods, whose acceptance often suffers due to undesirable flavour notes.”

The research has been published in the Journal of Cheminformatics.

Top image credit: iStock.com/fcafotodigital