Abstract
The dichotomy of sweet and bitter tastes is a salient evolutionary feature of human gustatory system with an innate attraction to sweet taste and aversion to bitterness. A better understanding of molecular correlates of bitter-sweet taste gradient is crucial for identification of natural as well as synthetic compounds of desirable taste on this axis. While previous studies have advanced our understanding of the molecular basis of bitter-sweet taste and contributed models for their identification, there is ample scope to enhance these models by meticulous compilation of bitter-sweet molecules and utilization of a wide spectrum of molecular descriptors. Towards these goals, our study provides a structured compilation of bitter, sweet and tasteless molecules and state-of-the-art machine learning models for bitter-sweet taste prediction (BitterSweet). We compare different sets of molecular descriptors for their predictive performance and further identify important features as well as feature blocks. The utility of BitterSweet models is demonstrated by taste prediction on large specialized chemical sets such as FlavorDB, FooDB, SuperSweet, Super Natural II, DSSTox, and DrugBank. To facilitate future research in this direction, we make all datasets and BitterSweet models publicly available, and present an end-to-end software for bitter-sweet taste prediction based on freely available chemical descriptors.
Highlights
Perception of taste is a complex sensation evolved in humans primarily to respond to naturally occurring food-derived chemicals[1]
BitterSweetForest[22] is perhaps the only study till date to look at the dichotomy of bitter-sweet taste prediction, utilizing bitter, sweet compounds from BitterDB14 and SuperSweet[23] respectively, towards the development of molecular fingerprints based Random Forest model
While the Ridge Logistic Regression (RLR)-Principal Component Analysis (PCA) model based on ChemoPy descriptors achieved the best F1-score (0.816) and exceeded the F1-scores achieved by e-Bitter (0.712), BitterPredict(0.783), and BitterX (0.577 F1-score), other BitterSweet models were found to be competitive (0.737–0.778)
Summary
Perception of taste is a complex sensation evolved in humans primarily to respond to naturally occurring food-derived chemicals[1]. BitterSweetForest[22] is perhaps the only study till date to look at the dichotomy of bitter-sweet taste prediction, utilizing bitter, sweet compounds from BitterDB14 and SuperSweet[23] respectively, towards the development of molecular fingerprints based Random Forest model. While these studies have advanced our understanding of the molecular correlates of bitter-sweet taste and contributed predictive models, there is ample scope for improvement via a meticulous compilation of bitter-sweet molecules and utilization of a wide spectrum of molecular descriptors. These studies have relied exclusively on threshold-based metrics such as sensitivity and specificity–which are highly sensitive to the specific cut-offs used–to evaluate the performance of their models
Sign-in/Register to view highlights & summary 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 callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
