Researchers use AI to find the next generation of sugar alternatives
Beijing (ANTARA) — Using known compounds with sweet and bitter tastes, researchers developed predictive models to distinguish desirable from undesirable taste characteristics.
The models were then used to screen three chemical databases containing around 50.7 million molecules. The process identified promising sweetener candidates while filtering out compounds predicted to taste bitter.
The researchers then used machine learning and molecular docking to simulate how the candidate compounds bind to the sole human sweet-taste receptor. The detailed structure of the proteins that make up the receptor was published last year.
After refining the initial results, the researchers narrowed the list to 556 potential sweeteners, and ultimately selected 92 candidates based on their promising predicted characteristics and suitability for future testing.
According to the researchers, many of the selected compounds have chemical structures that differ from those of existing sweeteners, potentially paving the way for entirely new types of sugar alternatives.
The findings, published in the journal Food Chemistry, show how artificial intelligence (AI) and molecular modelling could speed up the discovery of new sweeteners and help reduce undesirable bitter or metallic aftertastes—a challenge that has concerned the industry for years.
Source: jawawa.id (https://jawawa.id/newsitem/researchers-use-ai-to-find-the-next-generation-of-sugar-alternatives-1794239558)
Originally published by Antara (Indonesian) (https://www.antaranews.com/berita/5842651/peneliti-gunakan-ai-demi-temukan-alternatif-gula-generasi-berikutnya), translated from Indonesian