BitterMasS: Predicting Bitterness from Mass Spectra.

Bitter compounds are common in nature and among drugs. Previously, machine learning tools were developed to predict bitterness from the chemical structure. However, known structures are estimated to represent only 5-10% of the metabolome, and the rest remain unassigned or "dark". We present BitterMasS, a Random Forest classifier that was trained on 5414 experimental mass spectra of bitter and nonbitter compounds, achieving precision = 0.83 and recall = 0.90 for an internal test set. Next, the model was tested against spectra newly extracted from the literature 106 bitter and nonbitter compounds and for additional spectra measured for 26 compounds. For these external test cases, BitterMasS exhibited 67% precision and 93% recall for the first and 58% accuracy and 99% recall for the second. The spectrum-bitterness prediction strategy was more effective than the spectrum-structure-bitterness prediction strategy and covered more compounds. These encouraging results suggest that BitterMasS can be used to predict bitter compounds in the metabolome without the need for structural assignment of individual molecules. This may enable identification of bitter compounds from metabolomics analyses, for comparing potential bitterness levels obtained by different treatments of samples and for monitoring bitterness changes overtime.

Bitter Odorants and Odorous Bitters: Toxicity and Human TAS2R Targets.

Flavor is perceived through the olfactory, taste, and trigeminal systems, mediated by designated GPCRs and channels. Signal integration occurs mainly in the brain, but some cross-reactivities occur at the receptor level. Here, we predict potential bitterness and taste receptors targets for thousands of odorants. BitterPredict and BitterIntense classifiers suggest that 3-9% of flavor and food odorants have bitter taste, but almost none are intensely bitter. About 14% of bitter molecules are expected to have an odor. Bitterness is more common for unpleasant smells such as fishy, amine, and ammoniacal, while non-bitter odorants often have pleasant smells. Experimental toxicity values suggest that fishy ammoniac smells are more toxic than pleasant smells, regardless of bitterness. TAS2R14 is predicted as the main bitter receptor for odorants, confirmed by in vitro profiling of 10 odorants. The activity of bitter odorants may have implications for physiology due to ectopic expression of taste and smell receptors.

HyFactor: A Novel Open-Source, Graph-Based Architecture for Chemical Structure Generation.

Graph-based architectures are becoming increasingly popular as a tool for structure generation. Here, we introduce novel open-source architecture HyFactor in which, similar to the InChI linear notation, the number of hydrogens attached to the heavy atoms was considered instead of the bond types. HyFactor was benchmarked on the ZINC 250K, MOSES, and ChEMBL data sets against conventional graph-based architecture ReFactor, representing our implementation of the reported DEFactor architecture in the literature. On average, HyFactor models contain some 20% less fitting parameters than those of ReFactor. The two architectures display similar validity, uniqueness, and reconstruction rates. Compared to the training set compounds, HyFactor generates more similar structures than ReFactor. This could be explained by the fact that the latter generates many open-chain analogues of cyclic structures in the training set. It has been demonstrated that the reconstruction error of heavy molecules can be significantly reduced using the data augmentation technique. The codes of HyFactor and ReFactor as well as all models obtained in this study are publicly available from our GitHub repository: https://github.com/Laboratoire-de-Chemoinformatique/HyFactor.