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

https://mdr.nims.go.jp/datasets/ed13bd2c-4132-4ef5-bb7d-90a1171e93eb

## File

- [harnessing-explainable-ai-to-explore-structure-activity-relationships-in-artificial-olfaction.pdf](https://mdr.nims.go.jp/filesets/dce9b861-a583-464e-9818-5037715570bd/download) ([Detail](https://mdr.nims.go.jp/filesets/dce9b861-a583-464e-9818-5037715570bd.md))

## Id

ed13bd2c-4132-4ef5-bb7d-90a1171e93eb

## Local identifier



## Visibility

open_to_public

## State

published

## Created at

2025-11-26T20:10:23.758590Z

## Updated at

2025-11-27T23:30:17.043351Z

## Published at

2025-11-27T23:22:41.974316Z

## Doi



## First published url

https://doi.org/10.1021/acsami.5c13990

## Date published

2025-09-17

## Recorded date published

2025-9-17

## Resource type

journal_article

## Manuscript type

vor

## Collection



## Title

- title: Harnessing Explainable AI to Explore Structure–Activity Relationships in
    Artificial Olfaction
  title_type: original
  lang: en

## Description

- description: 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.
  description_type: abstract
  lang: und

## Creator

- name: Yota Fukui
  role: author
- name: Kosuke Minami
  role: author
  orcid: https://orcid.org/0000-0003-4145-1118
- name: Genki Yoshikawa
  role: author
  orcid: https://orcid.org/0000-0002-9136-8964
- name: Koji Tsuda
  role: author
  orcid: https://orcid.org/0000-0002-4288-1606
- name: Ryo Tamura
  role: author
  orcid: https://orcid.org/0000-0002-0349-358X

## Contact agent



## Publisher

organization: American Chemical Society (ACS)

## Managing organization



## Keyword

- subject: MSS
  schema: not_defined
- subject: XAI
  schema: not_defined

## Rights

- identifier: https://creativecommons.org/licenses/by/4.0/

## Other identifier(s)



## Data origin



## Embargo



## Journal

- title: ACS Applied Materials & Interfaces
  issn: '19448244'
  volume: '17'
  issue: '37'
  start_page: 52728
  end_page: 52737

## Conference



## Related item



## Funding



## Instrument



## Instrument operator



## Instrument managing organization



## Measurement method



## Specimen



## Chemical composition



## Structure for specimen



## Structural feature for specimen



## Specific property for specimen



## Process for specimen treatment



## Computational method



## Energy level/transition state



## Software



## Custom property



## Fileset

- id: dce9b861-a583-464e-9818-5037715570bd
  filename: harnessing-explainable-ai-to-explore-structure-activity-relationships-in-artificial-olfaction.pdf
  content_type: application/pdf
  size: 9609698
  md5: ee1e5f0aca6f72582ef2daa5c252a464

## Thumbnail

fileset_id: dce9b861-a583-464e-9818-5037715570bd
filename: harnessing-explainable-ai-to-explore-structure-activity-relationships-in-artificial-olfaction.pdf