journal article·2025-09-17Open access

Harnessing Explainable AI to Explore Structure–Activity Relationships in Artificial Olfaction

Yota Fukui, Kosuke Minami, Genki Yoshikawa, Koji Tsuda, Ryo Tamura

ACS Applied Materials & Interfaces· Volume 17· Issue 37

Abstract

Chemical sensor arrays mimic the mammalian olfactory system to achieve artificial olfaction, and receptor materials resembling olfactory receptors are being actively developed. To realize practical artificial olfaction, it is essential to provide guidelines for developing effective receptor materials based on the structure-activity relationship. In this study, we demonstrated the visualization of the relationship between sensing signal features and odorant molecular features using an explainable AI (XAI) technique. We focused on classification tasks and employed a convolutional neural network (CNN) and score-class activation mapping (Score-CAM) methods. The results obtained from analyzing the 94 odor samples prepared using pure solvents indicate that the information regarding the active receptor materials and data points in the signals and the structure-activity relationship could be accurately extracted. Therefore, using XAI techniques to analyze sensor signals from odor data is an important technique for advancing artificial olfaction.
Source: openalex_inverted_index · Quality: baseline

Research context

OpenAlex topics: Olfactory and Sensory Function Studies · Advanced Chemical Sensor Technologies · Neurobiology and Insect Physiology Research

SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.

Affiliations

Graduate School of Frontier Sciences, The University of Tokyo, 5-1-5 Kashiwanoha, Kashiwa, Chiba 277-8568, Japan

Center for Basic Research on Materials, National Institute for Materials Science, 1-1 Namiki, Tsukuba, Ibaraki 305-0044, Japan

Research Center for Macromolecules and Biomaterials, National Institute for Materials Science, 1-1 Namiki, Tsukuba, Ibaraki 305-0044, Japan

Materials Science and Engineering, Graduate School of Pure and Applied Science, University of Tsukuba, 1-1-1 Tennodai, Tsukuba, Ibaraki 305-8571, Japan

References (48)

Show source-provided references
1. Hamauzu H. · Sagyo Kogai (Industrial Public Nuisance) · 5 · 718
2. 10.1152/physrev.00021.200510.1152/physrev.00021.2005 ↗
3. 10.1016/0925-4005(94)87085-310.1016/0925-4005(94)87085-3 ↗
4. 10.1016/0009-2614(93)E1419-H10.1016/0009-2614(93)E1419-H ↗
5. 10.1063/1.11140710.1063/1.111407 ↗
6. 10.1021/cr068121q10.1021/cr068121q ↗
7. 10.3390/s9070509910.3390/s90705099 ↗
8. 10.3390/s2122762010.3390/s21227620 ↗
9. 10.3390/pr901016410.3390/pr9010164 ↗
10. 10.3390/bios1209076210.3390/bios12090762 ↗
11. 10.1016/j.snb.2004.12.00510.1016/j.snb.2004.12.005 ↗
12. 10.1016/j.snb.2009.04.03010.1016/j.snb.2009.04.030 ↗
13. 10.1021/acs.analchem.7b0238910.1021/acs.analchem.7b02389 ↗
14. 10.1038/s41598-017-03875-710.1038/s41598-017-03875-7 ↗
15. 10.1021/acssensors.8b0045010.1021/acssensors.8b00450 ↗
16. 10.1371/journal.pone.019847510.1371/journal.pone.0198475 ↗
17. 10.1021/cr950068a10.1021/cr950068a ↗
18. Zhou, B.; Khosla, A.; Lapedriza, A.; Oliva, A.; Torralba, A. Learning Deep Features for Discriminative Localization, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR); IEEE, 2016; pp 2921–2929.10.1109/CVPR.2016.319 ↗
19. Selvaraju, R. R.; Cogswell, M.; Das, A.; Vedantam, R.; Parikh, D.; Batra, D. Grad-CAM: Visual Explanations From Deep Networks via Gradient-Based Localization, Proceedings of the IEEE International Conference on Computer Vision; IEEE, 2017; pp 618–626.10.1109/ICCV.2017.74 ↗
20. Muhammad, M. B.; Yeasin, M. Eigen-CAM: Class Activation Map Using Principal Components, 2020 International Joint Conference on Neural Networks (IJCNN); IEEE, Glasgow, United Kingdom, 2020; pp 1–7.10.1109/IJCNN48605.2020.9206626 ↗
21. Desai, S.; Ramaswamy, H. G. Ablation-CAM: Visual Explanations for Deep Convolutional Network via Gradient-Free Localization, 2020 International Joint Conference on Neural Networks (IJCNN); IEEE, Snowmass Village, CO, USA, 2020; pp 972–980.10.1109/WACV45572.2020.9093360 ↗
22. Wang, H.; Wang, Z.; Du, M.; Yang, F.; Zhang, Z.; Ding, S.; Mardziel, P.; Hu, X. Score-CAM: Score-Weighted Visual Explanations for Convolutional Neural Networks arXiv 2020 10.48550/arXiv.1910.01279.10.48550/arXiv.1910.01279 ↗
23. 10.1021/nl103901a10.1021/nl103901a ↗
24. 10.1021/la304671910.1021/la3046719 ↗
25. 10.1016/j.proeng.2012.09.33910.1016/j.proeng.2012.09.339 ↗
26. 10.3390/s12111587310.3390/s121115873 ↗
27. 10.1038/s41598-019-46164-110.1038/s41598-019-46164-1 ↗
28. 10.1038/s41598-021-91210-610.1038/s41598-021-91210-6 ↗
29. 10.1039/D3DD00215B10.1039/D3DD00215B ↗
30. 10.1039/C5CC07230A10.1039/C5CC07230A ↗
31. Qi, P.F.; Meng, Q.H.; Zeng, M. A CNN-Based Simplified Data Processing Method for Electronic Noses, 2017 ISOCS/IEEE International Symposium on Olfaction and Electronic Nose (ISOEN); IEEE, 2017; pp 1–3.10.1109/ISOEN.2017.7968887 ↗
32. 10.1109/ACCESS.2019.289275410.1109/ACCESS.2019.2892754 ↗
33. 10.1016/j.sna.2020.11187410.1016/j.sna.2020.111874 ↗
34. TensorFlow, https://www.tensorflow.org/ (accessed May 19, 2025).
35. scikit-learn: machine learning in Python─-scikit-learn 1.6.1 documentation. https://scikit-learn.org/stable/index.html (accessed May 19, 2025).
36. 10.1016/j.dib.2015.01.00310.1016/j.dib.2015.01.003 ↗
37. 10.1016/j.jfoodeng.2019.07.02310.1016/j.jfoodeng.2019.07.023 ↗
38. 10.1016/j.snb.2020.12892110.1016/j.snb.2020.128921 ↗
39. 10.1016/j.talanta.2014.02.01610.1016/j.talanta.2014.02.016 ↗
40. 10.1021/cr980102w10.1021/cr980102w ↗
41. 10.3390/s703026710.3390/s7030267 ↗
42. 10.1016/j.aca.2008.02.06810.1016/j.aca.2008.02.068 ↗
43. 10.3390/s1701021310.3390/s17010213 ↗
44. 10.1063/5.003904510.1063/5.0039045 ↗
45. 10.3390/bios1302015210.3390/bios13020152 ↗
46. 10.1021/cr068104110.1021/cr0681041 ↗
47. 10.1002/adma.20070166710.1002/adma.200701667 ↗
48. 10.1039/C8AY01224E10.1039/C8AY01224E ↗