Insight into the Structure–Odor Relationship of Molecules: A Computational Study Based on Deep Learning
Molecules with pleasant odors, unacceptable odors, and even serious toxicity are closely related to human social life. It is impractical to identify the odors of molecules in large quantities (particularly hazardous odors) using experimental methods. Computer-aided methods have currently attracted i...
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-07-01
|
| Series: | Foods |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2304-8158/11/14/2033 |
| _version_ | 1797439575668293632 |
|---|---|
| author | Weichen Bo Yuandong Yu Ran He Dongya Qin Xin Zheng Yue Wang Botian Ding Guizhao Liang |
| author_facet | Weichen Bo Yuandong Yu Ran He Dongya Qin Xin Zheng Yue Wang Botian Ding Guizhao Liang |
| author_sort | Weichen Bo |
| collection | DOAJ |
| description | Molecules with pleasant odors, unacceptable odors, and even serious toxicity are closely related to human social life. It is impractical to identify the odors of molecules in large quantities (particularly hazardous odors) using experimental methods. Computer-aided methods have currently attracted increasing attention for the prediction of molecular odors. Here, through models based on multilayer perceptron (MLP) and physicochemical descriptors (MLP-Des), MLP and molecular fingerprint, and convolutional neural network (CNN), we conduct the two-class prediction of odor/no odor, fruity/no odor, floral/no odor, and woody/no odor, and the multi-class prediction of fruity/flowery/woody/no odor on our newly refined molecular odor datasets. We show that three kinds of predictors can robustly predict molecular odors. The MLP-Des model not only exhibits the best prediction results (the AUC values are 0.99 and 0.86 for the two- and multi-classification models, respectively) but can also well reflect the characteristics of the structure–odor relationship of molecules. The CNN model takes 2D molecular images as input and can automatically extract the structural features related to molecular odors. The proposed models are of great help for the prediction of molecular odorants, understanding the underlying relationship between chemical structure and odor perception, and the discovery of new odorous and/or hazardous molecules. |
| first_indexed | 2024-03-09T11:54:59Z |
| format | Article |
| id | doaj.art-e8d65768d06c4892a4e058d7bd92389f |
| institution | Directory Open Access Journal |
| issn | 2304-8158 |
| language | English |
| last_indexed | 2024-03-09T11:54:59Z |
| publishDate | 2022-07-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Foods |
| spelling | doaj.art-e8d65768d06c4892a4e058d7bd92389f2023-11-30T23:10:38ZengMDPI AGFoods2304-81582022-07-011114203310.3390/foods11142033Insight into the Structure–Odor Relationship of Molecules: A Computational Study Based on Deep LearningWeichen Bo0Yuandong Yu1Ran He2Dongya Qin3Xin Zheng4Yue Wang5Botian Ding6Guizhao Liang7Key Laboratory of Biorheological Science and Technology, Ministry of Education, Bioengineering College, Chongqing University, Chongqing 400044, ChinaKey Laboratory of Biorheological Science and Technology, Ministry of Education, Bioengineering College, Chongqing University, Chongqing 400044, ChinaKey Laboratory of Biorheological Science and Technology, Ministry of Education, Bioengineering College, Chongqing University, Chongqing 400044, ChinaKey Laboratory of Biorheological Science and Technology, Ministry of Education, Bioengineering College, Chongqing University, Chongqing 400044, ChinaKey Laboratory of Biorheological Science and Technology, Ministry of Education, Bioengineering College, Chongqing University, Chongqing 400044, ChinaKey Laboratory of Biorheological Science and Technology, Ministry of Education, Bioengineering College, Chongqing University, Chongqing 400044, ChinaKey Laboratory of Biorheological Science and Technology, Ministry of Education, Bioengineering College, Chongqing University, Chongqing 400044, ChinaKey Laboratory of Biorheological Science and Technology, Ministry of Education, Bioengineering College, Chongqing University, Chongqing 400044, ChinaMolecules with pleasant odors, unacceptable odors, and even serious toxicity are closely related to human social life. It is impractical to identify the odors of molecules in large quantities (particularly hazardous odors) using experimental methods. Computer-aided methods have currently attracted increasing attention for the prediction of molecular odors. Here, through models based on multilayer perceptron (MLP) and physicochemical descriptors (MLP-Des), MLP and molecular fingerprint, and convolutional neural network (CNN), we conduct the two-class prediction of odor/no odor, fruity/no odor, floral/no odor, and woody/no odor, and the multi-class prediction of fruity/flowery/woody/no odor on our newly refined molecular odor datasets. We show that three kinds of predictors can robustly predict molecular odors. The MLP-Des model not only exhibits the best prediction results (the AUC values are 0.99 and 0.86 for the two- and multi-classification models, respectively) but can also well reflect the characteristics of the structure–odor relationship of molecules. The CNN model takes 2D molecular images as input and can automatically extract the structural features related to molecular odors. The proposed models are of great help for the prediction of molecular odorants, understanding the underlying relationship between chemical structure and odor perception, and the discovery of new odorous and/or hazardous molecules.https://www.mdpi.com/2304-8158/11/14/2033odor predictionhazardous moleculesmultilayer perceptron (MLP)convolutional neural network (CNN) |
| spellingShingle | Weichen Bo Yuandong Yu Ran He Dongya Qin Xin Zheng Yue Wang Botian Ding Guizhao Liang Insight into the Structure–Odor Relationship of Molecules: A Computational Study Based on Deep Learning Foods odor prediction hazardous molecules multilayer perceptron (MLP) convolutional neural network (CNN) |
| title | Insight into the Structure–Odor Relationship of Molecules: A Computational Study Based on Deep Learning |
| title_full | Insight into the Structure–Odor Relationship of Molecules: A Computational Study Based on Deep Learning |
| title_fullStr | Insight into the Structure–Odor Relationship of Molecules: A Computational Study Based on Deep Learning |
| title_full_unstemmed | Insight into the Structure–Odor Relationship of Molecules: A Computational Study Based on Deep Learning |
| title_short | Insight into the Structure–Odor Relationship of Molecules: A Computational Study Based on Deep Learning |
| title_sort | insight into the structure odor relationship of molecules a computational study based on deep learning |
| topic | odor prediction hazardous molecules multilayer perceptron (MLP) convolutional neural network (CNN) |
| url | https://www.mdpi.com/2304-8158/11/14/2033 |
| work_keys_str_mv | AT weichenbo insightintothestructureodorrelationshipofmoleculesacomputationalstudybasedondeeplearning AT yuandongyu insightintothestructureodorrelationshipofmoleculesacomputationalstudybasedondeeplearning AT ranhe insightintothestructureodorrelationshipofmoleculesacomputationalstudybasedondeeplearning AT dongyaqin insightintothestructureodorrelationshipofmoleculesacomputationalstudybasedondeeplearning AT xinzheng insightintothestructureodorrelationshipofmoleculesacomputationalstudybasedondeeplearning AT yuewang insightintothestructureodorrelationshipofmoleculesacomputationalstudybasedondeeplearning AT botianding insightintothestructureodorrelationshipofmoleculesacomputationalstudybasedondeeplearning AT guizhaoliang insightintothestructureodorrelationshipofmoleculesacomputationalstudybasedondeeplearning |