Machine learning models to predict sweetness of molecules

Sweetness is a vital taste to which humans are innately attracted. Given the increasing prevalence of type-2 diabetes, it is highly relevant to build computational models to predict the sweetness of small molecules. Such models are valuable for identifying sweeteners with low calorific value. We present regression-based machine learning and deep learning algorithms for predicting sweetness. Toward this goal, we manually curated the most extensive dataset of 671 sweet molecules with known experimental sweetness values ranging from 0.2 to 22,500,000. Gradient Boost and Random Forest Regressors emerged as the best models for predicting the sweetness of molecules with a correlation coefficient of 0.94 and 0.92, respectively. Our models show state-of -the-art performance when compared with previously published studies. Besides making our dataset (Sweet-predDB) available, we also present a user-friendly web server to return the predicted sweetness for small mol-ecules, Sweetpred (https://cosylab.iiitd.edu.in/sweetpred).

Automated summary

Predicting the sweetness of small molecules is becoming increasingly important due to the rise of type-2 diabetes. We developed regression-based machine learning and deep learning algorithms and curated a dataset of 671 sweet molecules with known sweetness values. Our models using Gradient Boost and Random Forest Regressors achieved high accuracy with correlation coefficients of 0.94 and 0.92 respectively.