Researchers developed VirtuousMultiTaste, a machine-learning tool to distinguish between sweet, umami, and bitter tastes based on a compound's molecular structures and underlying physicochemical characteristics.
By Pooja Toshniwal PahariaReviewed by Danielle Ellis, B.Sc.Jul 31 2024 In a recent study published in npj Science of Food , researchers developed VirtuousMultiTaste, a machine-learning tool to distinguish between sweet, umami, and bitter tastes based on a compound's molecular structures and underlying physicochemical characteristics.
About the study In the present study, researchers used machine learning and heuristic optimization approaches to anticipate different taste experiences in chemicals. The researchers used ensemble dimensionality reductions using Pareto-based optimization algorithms to improve prediction accuracy, decrease chosen features, and simplify classification. The optimization targets included Accuracy , Selected Features Number Minimization 1, F1 Score 10, Precision , F2 Score 1, Recall , the area under the receiver operating characteristic curve , Manhattan Distance 1, and Trees Minimization 1 .
The researchers assessed model applicability by comparing the similarity between tested substances and chemicals used during training. They used Morgan Fingerprints and the Tanimoto Similarity Index to obtain average similarity scores between test and training compounds and compared VirtuousMultiTaste to previously developed VirtuousBitterSweet and VirtuousUmami taste predictors.
Chemicals Chocolate Coffee Compound Food Technology
United Kingdom Latest News, United Kingdom Headlines
Similar News:You can also read news stories similar to this one that we have collected from other news sources.
Researchers develop machine learning model to identify disease subtypesResearchers from the Hebrew University of Jerusalem have developed a machine learning approach to identify potential subtypes in diseases, significantly enhancing the field of disease classification and treatment strategies. The study, led by Ph.D. student Dan Ofer and Prof.
Read more »
Weill Cornell researchers define three Parkinson's subtypes with machine learningResearchers at Weill Cornell Medicine have used machine learning to define three subtypes of Parkinson's disease based on the pace at which the disease progresses.
Read more »
Researchers learn how cancer cells divide despite treatmentResearchers in the lab of Jean Cook, Ph.D., chair and professor in the Department of Biochemistry and Biophysics, have identified the cellular processes that occur when you take a cancer drug meant to stop rapid cell growth in tumors.
Read more »
Researchers propose new framework for diagnosing obesity based on body fat distribution, not BMIThe system for diagnosing and managing obesity can no longer be about just body mass index (BMI), which is excluding many people who would benefit from obesity treatment.
Read more »
Researchers develop GPT-4-based simulator for biomedical researchThe artificial intelligence (AI) model GPT-4, known from its application in ChatGPT, shows impressive capabilities in biomedical research and can be used in many ways for simulations.
Read more »
Public health researchers detail a post-pandemic way forwardIn the aftermath of the COVID-19 pandemic, the U.S. public health system must focus on critical questions of accountability, politicization and updating data systems if it is to do its job well and maintain the trust of the American people, according to a new report from the Colorado School of Public Health.
Read more »