Several studies have used machine learning methods for OD prediction. The smells of odorants have been labeled with odor descriptors (ODs), such as ‘sweet,’ ‘fruity,’ and ‘green.’ These data introduce the possibility of using data-driven approaches in molecular structure-odor studies. Therefore, we aim to develop a feature-free method that allows interpretation of the extracted features.Īt present, approximately 4000 odorants have been labeled with their corresponding odor. In contrast, feature-free methods flexibly extract features according to the properties to be predicted however, the models are not often interpretable. Although feature-based methods use fixed features, the resulting model usually provides some interpretability. In molecular property prediction, the interpretability of the model is particularly important, as model interpretability allows us to investigate the relationship between molecular structure and different properties at the molecular, atomic, and subatomic levels. In addition to predicting molecular properties such as water solubility and lipophilicity, feature-free methods use artificial neural networks to predict additional essential properties, such as the molecular energy, dipole moment and molecular dynamics, allowing us to compute this information faster than using computational chemistry methods. Feature-free methods predict specific molecular properties by automatically extracting molecule features that are related to those properties using methods such as graph neural networks or graph kernels. Feature-based methods take the generated fixed molecular features (such as molecular fingerprints and molecular parameters) as model inputs and use various algorithms (e.g., random forest and support vector machines) to predict the molecular properties. These methods can be divided into feature-based methods and feature-free methods according to the type of data that are input into the model. Machine learning has been applied in a wide range of fields, including physics and chemistry, and various molecular structure property prediction methods have been proposed. Thus, to date, the relationship between molecular structure and odor remains difficult to specify. Therefore, special training is required to label the odors of substances, which increases the difficulty of labeling the odors of chemical compounds. In addition to the subtle relationship between molecular structure and odor, aspects such as sex, age, and disease history can affect odor perception. A previous study showed that molecules with similar structures may have very different odors, while molecules with similar odors may have completely distinct structures.
However, studying the odors of different substances is challenging. Studies on this relationship may lead to predictions of the odor of a molecule, odor synthesis, and even the artificial synthesis of molecules with specific odors. The relationship between molecular structure and odor quality is an essential research topic. Smell plays an important role in all aspects of life and is thus an important property of all compounds. For the 19 odor descriptors that achieved F1 values greater than 0.45, we also attempt to summarize the relationship between the molecular substructures and odor quality through the attention matrix. Finally, we collect 4462 molecules and their odor descriptors and use the proposed model to infer 98 odor descriptors, obtaining an average F1 value of 0.33. The attention matrix is visualized to investigate the substructure annotation performance of the attention mechanism, and we find that certain atoms in the target substructures are accurately annotated. The SMILES data of 100,000 molecules are collected and used to predict the existence of molecular substructures, and our proposed model achieves an F1 value of 0.98. In this paper, we describe the construction of a Transformer model for predicting molecular properties and interpreting the prediction results. The Transformer model is widely used in natural language processing and computer vision, and the attention mechanism included in the Transformer model can identify relationships between inputs and outputs. Many works have attempted to explain the molecular structure-odor relationship from chemical and data-driven perspectives. Molecules with similar structures, such as a molecule and its optical isomer, may have completely different odors, whereas molecules with completely distinct structures may have similar odors. The relationships between molecular structures and their properties are subtle and complex, and the properties of odor are no exception.
0 kommentar(er)
