JERUSALEM, Nov. 8 (Xinhua) -- Israeli researchers have developed a new machine learning framework that identified 92 candidates for future sugar substitutes from more than 50 million chemical compounds, the Hebrew University of Jerusalem said in a statement on Sunday.
The findings, published in the journal Food Chemistry, show how artificial intelligence and molecular modeling could accelerate the discovery of new sweeteners and reduce unwanted bitter or metallic aftertastes, a challenge that has concerned the industry for years.
Based on known sweet- and bitter-tasting compounds, the researchers developed predictive models to distinguish between desirable and undesirable taste characteristics. They then applied these models to screen three chemical databases containing approximately 50.7 million molecules, identifying promising sweet candidates while filtering out compounds predicted to be bitter.
They then used machine learning and molecular docking to simulate how candidate compounds might bind to the single human sweet-taste receptor, whose component protein molecules' detailed structure was published last year.
After refining the initial results, the researchers narrowed the list to 556 potential sweeteners, and finally selected 92 candidates for their favorable predicted properties and suitability for future testing.
According to the researchers, many of the selected compounds have chemical structures different from those of existing sweeteners, potentially opening the door to entirely new classes of sugar alternatives. ■
