Successful visualization of the odor discrimination process in an AI-assisted olfactory sensor
Guides the design of optimal receptor materials for specific odorant molecules
2025-11-10
(Press-News.org)
NIMS has been developing chemical sensors as a key component of the artificial olfaction technology (olfactory sensors), with the aim of putting this technology into practical use. In this study, explainable AI (XAI) was used to reveal how chemical sensors discriminate among various odorant molecules. The findings may help guide the selection of receptor materials for developing high-performance chemical sensors capable of detecting odorant molecules. The achievement is expected not only to improve the performance of artificial olfaction but also to advance understanding of human olfactory mechanisms. This research was published online in ACS Applied Materials & Interfaces on September 9, 2025.
Background
The sense of smell plays an essential role in our daily lives, including food safety, environmental monitoring, medical diagnosis and the creation of comfortable living spaces. Artificial olfaction technologies (olfactory sensors), which mimic the human sense of smell, use multiple chemical sensors to detect odorant molecules and employ artificial intelligence (AI) to classify and identify them.
However, current AI-assisted artificial olfaction has yet to reach practical application due to the limited sensitivity and discrimination accuracy of existing chemical sensors. Addressing this challenge will require higher-performance chemical sensors, particularly through the development of receptor materials capable of more effectively detecting odorant molecules.
In conventional artificial olfaction systems, AI has classified and identified odorant molecules without a full understanding of which receptor materials respond to which molecules. Revealing the response characteristics of specific receptor materials will enable the development of optimal materials for discriminating target odorants and the selection of receptor materials that achieve more accurate odor discrimination.
Key Findings
NIMS measured the responses of 94 odorant molecules using an MSS (membrane-type surface stress sensor) equipped with 14 receptor materials and analyzed the data with explainable AI (XAI), a technique that visualizes which parts of the data the AI relies on when discriminating among odorant molecules.
The analysis revealed that the key portions of sensor responses used for identification vary depending on the specific combinations of odorant molecules and receptor materials. For example, receptor materials containing aromatic rings were found to be important for identifying aromatic molecules.
This approach is expected to enable efficient selection of receptor materials tailored to target odorant molecules and guide the development of materials capable of identifying molecules that are otherwise difficult to detect. In addition, by revealing not only how the AI discriminates but also on what basis it makes predictions, XAI may offer important clues to understanding the mechanisms of odors and human olfaction.
Future Outlook
This technology can be used not only to facilitate the development of receptor materials but also to select the optimal sensor from multiple options based on the intended application. In addition to supporting material development, it can contribute to the advancement of olfactory sensor devices, thereby accelerating the practical application of artificial olfaction and deepening our understanding of human olfaction.
Other Information
This project was carried out by Yota Fukui (Trainee, Center for Basic Research on Materials (CBRM), NIMS at the time of this project), Koji Tsuda (Invited Researcher, CBRM, NIMS), Ryo Tamura (Team Leader, CBRM, NIMS), Kosuke Minami (Principal Researcher, Research Center for Macromolecules and Biomaterials (RCMB), NIMS) and Genki Yoshikawa (Group Leader, RCMB, NIMS).
This research was published online in ACS Applied Materials & Interfaces on September 9, 2025. END
ELSE PRESS RELEASES FROM THIS DATE:
2025-11-10
New research from Intermountain Health in Salt Lake City finds that patients diagnosed with peripheral arterial disease (PAD) who also have atrial fibrillation (AFib) face a significantly higher risk of major adverse cardiovascular events (MACE).
The Intermountain study analyzed long-term data of Intermountain Health patients with PAD and found that AFib was present in approximately one in four PAD patients, making this combination far more common than previously recognized.
More importantly, Intermountain researchers found the presence of AFib nearly doubles the risk of major adverse cardiovascular events in patients compared to PAD alone.
Irregular heart rhythms are called arrhythmias. ...
2025-11-10
While some risk factors for cancer can be mitigated through lifestyle choices such as diet or exercise, aging is not one of them. In the case of pancreatic cancer, it also can limit treatment options if a patient is too frail to be safely treated with surgery or other alternatives.
Scientists at the NCI-Designated Cancer Center at Sanford Burnham Prebys Medical Discovery Institute would like to expand options for these patients with personalized treatments. Many stand to benefit from a therapeutic strategy that factors in age. The average age of a patient diagnosed with pancreatic cancer is 70, and nearly two-thirds of cases are in people over the age of ...
2025-11-10
A psychedelic found in mushrooms is emerging as a potential treatment for alcohol use disorders. This possibility is due to a compound the body converts the psychedelic into called psilocin, but psilocin’s mechanisms remain unclear. Researchers, led by Sarah Magee and Melissa Herman at University of North Carolina at Chapel Hill, explored whether psilocin targets neurons in the central amygdala involved in emotional processing and stress to alter alcohol use in their JNeurosci paper. Herman emphasizes that ...
2025-11-10
In a new JNeurosci paper, Sarah Jessen and colleagues, from the University of Lübeck, explored how infants track their mothers’ voices compared to unfamiliar voices. The researchers also explored whether this vocal processing affects how babies process new faces.
Brain recordings of babies around 7 months old showed that they were far more attuned to the voices of their mothers than strangers. Additionally, neural tracking of unfamiliar faces was stronger when babies heard a stranger’s voice compared to their mother’s voice at the same time. Whether a face ...
2025-11-10
In a new JNeurosci paper, Kahori Kita and colleagues at Johns Hopkins University explored how people switch between intuitive motor skills they know and newly learned movement patterns.
Study volunteers frequently made errors switching between more innate movements and new ones. These errors were largely because people persistently stuck to the movement patterns they used before the switch. Notes Kita, “People made similar errors when switching from the intuitive to the new skill, as when switching from the new skill to the intuitive one.” A second group of people learned two new movement-based skills. It was initially even more difficult for these ...
2025-11-10
A new native bee species with tiny devil-like “horns” named Megachile (Hackeriapis) lucifer has been discovered in Western Australia’s Goldfields, highlighting how much remains unknown about Australia’s native pollinators.
The striking new bee was found during surveys of a critically endangered wildflower Marianthus aquilonarius that grows only in the Bremer Range region, which is between the towns of Norseman and Hyden.
Lead author Curtin Adjunct Research Fellow Dr Kit Prendergast, from the Curtin School of Molecular and Life Sciences, said the female bee’s unusual ...
2025-11-10
About The Article: This Viewpoint describes the U.S. Food and Drug Administration’s intended label updates and removal of black box warnings for menopausal hormone therapy based on current evidence.
Corresponding Author: To contact the corresponding author, Martin A. Makary, MD, MPH, email commissionersoffice@fda.hhs.gov.
To access the embargoed study: Visit our For The Media website at this link https://media.jamanetwork.com/
(doi:10.1001/jama.2025.22259)
Editor’s Note: Please see the article for additional ...
2025-11-10
ST. LOUIS, MO, November 10, 2025 - A new collaborative research team of plant scientists led by Ru Zhang, PhD, associate member, Danforth Plant Science Center has been awarded new funding from the National Science Foundation to investigate how photosynthetic cells retain “heat stress memory” (HSM), a key adaptive mechanism that could help future crops withstand intense and frequent heat waves.
Photosynthesis, the process by which plants convert sunlight into energy, is the key driver of plant growth ...
2025-11-10
Researchers at the University of California San Diego School of Medicine have developed a new approach for identifying individuals with skin cancer that combines genetic ancestry, lifestyle and social determinants of health using a machine learning model. Their model, more accurate than existing approaches, also helped the researchers better characterize disparities in skin cancer risk and outcomes.
Skin cancer is among the most common cancers in the United States, with more than 9,500 new cases diagnosed every day and approximately ...
2025-11-10
November 10, 2025— Adults who experience poverty-level family income—whether sustained or intermittent—over two decades spanning young to mid-adulthood face a significantly higher risk of dying prematurely than those who are never in poverty, according to new research led by Columbia University Mailman School of Public Health. A companion study by the same research team finds that rising unsecured debt—such as credit card debt not tied to an asset—may be one mechanism linking early-life financial hardship to ...
LAST 30 PRESS RELEASES:
[Press-News.org] Successful visualization of the odor discrimination process in an AI-assisted olfactory sensor
Guides the design of optimal receptor materials for specific odorant molecules
