Investigation of the structure-odor relationship using a Transformer model
Abstract The relationships between molecular structures and their properties are subtle and complex, and the properties of odor are no exception. Molecules with similar structures, such as a molecule and its optical isomer, may have completely different odors, whereas molecules with completely disti...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
BMC
2022-12-01
|
| Series: | Journal of Cheminformatics |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s13321-022-00671-y |
| _version_ | 1797973533917184000 |
|---|---|
| author | Xiaofan Zheng Yoichi Tomiura Kenshi Hayashi |
| author_facet | Xiaofan Zheng Yoichi Tomiura Kenshi Hayashi |
| author_sort | Xiaofan Zheng |
| collection | DOAJ |
| description | Abstract The relationships between molecular structures and their properties are subtle and complex, and the properties of odor are no exception. 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. Many works have attempted to explain the molecular structure-odor relationship from chemical and data-driven perspectives. 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. In this paper, we describe the construction of a Transformer model for predicting molecular properties and interpreting the prediction results. 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. 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. 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. 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. |
| first_indexed | 2024-04-11T04:05:38Z |
| format | Article |
| id | doaj.art-cb9c5dd07a0f44299685d66716b1ba98 |
| institution | Directory Open Access Journal |
| issn | 1758-2946 |
| language | English |
| last_indexed | 2024-04-11T04:05:38Z |
| publishDate | 2022-12-01 |
| publisher | BMC |
| record_format | Article |
| series | Journal of Cheminformatics |
| spelling | doaj.art-cb9c5dd07a0f44299685d66716b1ba982023-01-01T12:26:05ZengBMCJournal of Cheminformatics1758-29462022-12-0114111610.1186/s13321-022-00671-yInvestigation of the structure-odor relationship using a Transformer modelXiaofan Zheng0Yoichi Tomiura1Kenshi Hayashi2Graduate School of Information Science and Electrical Engineering, Department of Informatics, Kyushu UniversityGraduate School of Information Science and Electrical Engineering, Department of Informatics, Kyushu UniversityGraduate School of Information Science and Electrical Engineering, Department of Electronics, Kyushu UniversityAbstract The relationships between molecular structures and their properties are subtle and complex, and the properties of odor are no exception. 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. Many works have attempted to explain the molecular structure-odor relationship from chemical and data-driven perspectives. 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. In this paper, we describe the construction of a Transformer model for predicting molecular properties and interpreting the prediction results. 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. 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. 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. 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.https://doi.org/10.1186/s13321-022-00671-yMolecular structure-odor relationTransformer modelOdor descriptor |
| spellingShingle | Xiaofan Zheng Yoichi Tomiura Kenshi Hayashi Investigation of the structure-odor relationship using a Transformer model Journal of Cheminformatics Molecular structure-odor relation Transformer model Odor descriptor |
| title | Investigation of the structure-odor relationship using a Transformer model |
| title_full | Investigation of the structure-odor relationship using a Transformer model |
| title_fullStr | Investigation of the structure-odor relationship using a Transformer model |
| title_full_unstemmed | Investigation of the structure-odor relationship using a Transformer model |
| title_short | Investigation of the structure-odor relationship using a Transformer model |
| title_sort | investigation of the structure odor relationship using a transformer model |
| topic | Molecular structure-odor relation Transformer model Odor descriptor |
| url | https://doi.org/10.1186/s13321-022-00671-y |
| work_keys_str_mv | AT xiaofanzheng investigationofthestructureodorrelationshipusingatransformermodel AT yoichitomiura investigationofthestructureodorrelationshipusingatransformermodel AT kenshihayashi investigationofthestructureodorrelationshipusingatransformermodel |