VOC data-driven evaluation of vehicle cabin odor: from ANN to CNN-BiLSTM.

Emissions of volatile organic compounds (VOCs) in vehicles represent a significant problem, causing unpleasant odors. To mitigate VOCs and odors in vehicles, it is critical to choose interior parts with low odor and VOC emissions. However, prevailing odor evaluation methods are subjective, costly, and potentially harmful to the health of evaluators. In this study, we analyzed 139 automotive interior parts and 92 vehicles, establishing a cost-effective, data-driven method for odor evaluation. The contents of benzene, toluene, ethylbenzene, xylene, styrene, formaldehyde, acetaldehyde, acrolein, and total volatile organic compounds (TVOC) were detected by thermal desorption gas chromatography-mass spectrometry (TD-GC/MS) and high-performance liquid chromatography with an ultraviolet detector (HPLC-UV). Professional odor evaluators assessed the odors, identifying intensity levels from 2.0 to 4.5 in interior parts and 2.5 to 3.5 in whole vehicles. Leveraging this data, we applied four supervised learning algorithms to develop predictive models for the odor intensity of both interior parts and entire vehicles. During model training, we implemented early stopping techniques for the artificial neural network (ANN) and convolutional neural network-bidirectional long short-term memory (CNN-BiLSTM) models, while optimizing the support vector machine (SVM) and extreme gradient boosting (XGBoost) models using the GridSearch algorithm. The evaluation results reveal that the CNN-BiLSTM model performs the best, achieving an average accuracy of 89% for unknown samples within an odor intensity level of 0.5. The root mean square error (RMSE) is 0.24, and the mean absolute error (MAE) is 0.08. The model also underwent a sevenfold cross-validation, achieving an accuracy of 83.43%. Additionally, we employed SHapley Additive exPlanations (SHAP) for the interpretative analysis of the model, which confirmed the consistency of each VOC's odor contribution with human olfactory rules. By predicting odors based on VOCs through supervised learning, this study reduces the costs and enhances the efficiency and applicability of odor assessment across various vehicle interiors.

Accurate prediction of Kp,uu,brain based on experimental measurement of Kp,brain and computed physicochemical properties of candidate compounds in CNS drug discovery.

A mathematical equation model was developed by building the relationship between the fu,b/fu,p ratio and the computed physicochemical properties of candidate compounds, thereby predicting Kp,uu,brain based on a single experimentally measured Kp,brain value. A total of 256 compounds and 36 marketed published drugs including acidic, basic, neutral, zwitterionic, CNS-penetrant, and non-CNS penetrant compounds with diverse structures and physicochemical properties were involved in this study. A strong correlation was demonstrated between the fu,b/fu,p ratio and physicochemical parameters (CLogP and ionized fraction). The model showed good performance in both internal and external validations. The percentages of compounds with Kp,uu,brain predictions within 2-fold variability were 80.0 %-83.3 %, and more than 90 % were within a 3-fold variability. Meanwhile, "black box" QSAR models constructed by machine learning approaches for predicting fu,b/fu,p ratio based on the chemical descriptors are also presented, and the ANN model displayed the highest accuracy with an RMSE value of 0.27 and 86.7 % of the test set drugs fell within a 2-fold window of linear regression. These models demonstrated strong predictive power and could be helpful tools for evaluating the Kp,uu,brain by a single measurement parameter of Kp,brain during lead optimization for CNS penetration evaluation and ranking CNS drug candidate molecules in the early stages of CNS drug discovery.