Abstract
Artificial sweeteners (AS) can elicit the strong sweet sensation with the low or zero calorie, and are widely used to replace the nutritive sugar in the food and beverage industry. However, the safety issue of current AS is still controversial. Thus, it is imperative to develop more safe and potent AS. Due to the costly and laborious experimental-screening of AS, in-silico sweetener/sweetness prediction could provide a good avenue to identify the potential sweetener candidates before experiment. In this work, we curate the largest dataset of 530 sweeteners and 850 non-sweeteners, and collect the second largest dataset of 352 sweeteners with the relative sweetness (RS) from the literature. In light of these experimental datasets, we adopt five machine-learning methods and conformational-independent molecular fingerprints to derive the classification and regression models for the prediction of sweetener and its RS, respectively via the consensus strategy. Our best classification model achieves the 95% confidence intervals for the accuracy (0.91 ± 0.01), precision (0.90 ± 0.01), specificity (0.94 ± 0.01), sensitivity (0.86 ± 0.01), F1-score (0.88 ± 0.01), and NER (Non-error Rate: 0.90 ± 0.01) on the test set, which outperforms the model (NER = 0.85) of Rojas et al. in terms of NER, and our best regression model gives the 95% confidence intervals for the R2(test set) and ΔR2 [referring to |R2(test set)- R2(cross-validation)|] of 0.77 ± 0.01 and 0.03 ± 0.01, respectively, which is also better than the other works based on the conformation-independent 2D descriptors (e.g., 2D Dragon) according to R2(test set) and ΔR2. Our models are obtained by averaging over nineteen data-splitting schemes, and fully comply with the guidelines of Organization for Economic Cooperation and Development (OECD), which are not completely followed by the previous relevant works that are all on the basis of only one random data-splitting scheme for the cross-validation set and test set. Finally, we develop a user-friendly platform “e-Sweet” for the automatic prediction of sweetener and its corresponding RS. To our best knowledge, it is a first and free platform that can enable the experimental food scientists to exploit the current machine-learning methods to boost the discovery of more AS with the low or zero calorie content.
Highlights
Sweet taste, eliciting a pleasant sensation, provides an instinctive means to find the energy source such as the carbohydrates, which usually taste sweet
This eSweet platform can be installed via the simple click of e-Sweet Platform for Sweetener/Sweetness Prediction mouse and can smoothly run both in the modes of graphic userinterface and command-line, which are well tested on the Win7, Win8, and Win10
(1) Visualize and inquiry our curated datasets for the classification of sweetener/nonsweetener or the regression of relative sweetness (RS). (2) Predict the sweetener and its RS with the multiple machine-learning methods by evoking the external scikit-learn (v0.19.1), Keras (v1.1.0), and Theano (v1.0.1) python libraries fully integrated in the free Anaconda (v2-5.2.0) that can be handily installed on the windows in the simple way
Summary
Sweet taste, eliciting a pleasant sensation, provides an instinctive means to find the energy source such as the carbohydrates, which usually taste sweet. According to the content of calorie, these chemically diverse sweeteners can be generally categorized into two types (Dubois and Prakash, 2012): the nutritive sweeteners with the high calorie (e.g., sucrose), and the non-nutritive sweeteners (e.g., saccharin and aspartame) with the low or zero calorie that mainly refer to the artificial sweeteners in this work. The non-nutritive sweeteners are broadly used as the food additives to substitute for the nutritive sweeteners such as sucrose, since the over-consumption of high-calorie nutritive sweeteners in the functional food and beverage will lead to the elevated risks of the metabolic disorders (e.g., type II diabetes) and cardiovascular diseases (Fernstrom, 2015). A multitude of non-nutritive sweeteners with the low calorie yet preserving the sweetness have been manually synthesized or directly extracted from the natural plants to prevent these risks
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
