{"title":"Detection of ppb-Level SO2 at Room Temperature Based on Bi2O2Se Nanosheets.","authors":"Xinxin He,Xuanyu Ren,Xuyang An,Ping Guo,Yinhua Hu,Tiezhu Liu,Jia Zhang","doi":"10.1021/acssensors.5c00237","DOIUrl":"https://doi.org/10.1021/acssensors.5c00237","url":null,"abstract":"Monitoring sulfur dioxide (SO2) is crucial for protecting human health as exposure to this pollutant can cause respiratory and cardiovascular illnesses, particularly in vulnerable populations. The primary materials currently used for detecting SO2 are metal oxides. However, it is still a challenge to detect SO2 at the parts per billion (ppb) level via these materials even when operated at high temperatures. Herein, we propose a highly sensitive SO2 sensor that operates at room temperature (RT). The sensing material employed is the hydrothermally synthesized bismuth oxyselenide (Bi2O2Se) nanosheets. The Bi2O2Se sensor exhibits a response value of 34% to 1 ppm SO2 and a detection limit of 20 ppb, which surpasses most SO2 sensors reported to date. The superior sensitivity and selectivity of Bi2O2Se nanoppbsheets toward SO2 are attributed to their strong adsorption energy (-0.76 eV) and significant electron transfer (2.205 e) between Bi2O2Se and SO2 molecules, as confirmed by density functional theory (DFT) calculations. Finally, a wireless SO2 sensing system is designed and implemented based on the SO2 sensor, enabling the detection of trace-level SO2 in indoor environments such as factories and laboratories, thereby protecting the well-being of personal further.","PeriodicalId":24,"journal":{"name":"ACS Sensors","volume":"54 1","pages":""},"PeriodicalIF":8.9,"publicationDate":"2025-05-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144087757","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"化学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Synergistic Integration of Laser Oxidation and Long Short-Term Memory for Advanced Odor Classification in Next-Generation Artificial Olfactory Systems.","authors":"Hyeokjin Kwon,Jiho Park,Hyun Woo Jang,Hyeongtae Lim,Sohee Kim,Samhwan Kim,Jae Eun Jang,Hyuk-Jun Kwon,Ji-Woong Choi","doi":"10.1021/acssensors.5c00152","DOIUrl":"https://doi.org/10.1021/acssensors.5c00152","url":null,"abstract":"Emulating and enhancing human olfactory capabilities, artificial olfactory technology provides adept detection of subtle odors, gases, and various chemical substances. Metal oxide semiconductors (MOSs) are ideal materials for next-generation artificial olfactory devices due to their outstanding gas sensing performance, characterized high sensitivity, high response speed, and robust stability, as well as their compatibility with microfabrication. For broader applications, developing a comprehensive database of diverse odorants is crucial, which necessitates expanding the types of MOS channels in artificial olfactory devices. This paper reports a laser-induced oxidation-based artificial olfactory device using a 7 × 3 sensor array composed of three metal oxides (SnO2-x, ZnOx, and WO3-x). By analyzing the response pattern of various odorants using a deep neural network, the device achieved 95.2% accuracy in classifying eight single odor molecules. Additionally, it successfully deconvoluted the types and concentrations of two odor mixtures and classified ten types of wine with accuracies of 91.3% and 92.5%, respectively. Furthermore, this study identified the proper number and arrangement of sensors for next-generation e-nose development. Our innovative artificial olfactory system can be integrated into various fields, such as the aromatic industry and virtual reality, making it a beneficial technology for future artificial olfaction applications.","PeriodicalId":24,"journal":{"name":"ACS Sensors","volume":"55 1","pages":""},"PeriodicalIF":8.9,"publicationDate":"2025-05-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144097809","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"化学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"A CRISPR/Cas12a-Assisted SERS Nanosensor for Highly Sensitive Detection of HPV DNA.","authors":"Jianqing Ye,Yongshi Shen,Zhizhong Lin,Luyun Xu,Lingna Wang,Xueliang Lin,Baoxing Huang,Zhiqing Ma,Zongyang Yu,Duo Lin,Wenjuan Chen,Shangyuan Feng","doi":"10.1021/acssensors.5c00547","DOIUrl":"https://doi.org/10.1021/acssensors.5c00547","url":null,"abstract":"The lack of timely and effective screening and diagnosis is a major contributing factor to the high mortality rate of cervical cancer in low-income countries and resource-limited regions. Therefore, the development of a rapid, sensitive, and easily deployable diagnostic tool for HPV DNA is of critical importance. In this study, we present a novel high-sensitivity and high-specificity detection method for HPV16 and HPV18 by integrating the CRISPR/Cas12a system with surface-enhanced Raman scattering (SERS) technology. This method leverages the trans-cleavage activity of the CRISPR/Cas12a system, which cleaves biotin-modified spherical nucleic acids (Biotin-SNA) in the presence of target DNA, releasing free Biotin-DNA. The released Biotin-DNA preferentially binds to streptavidin-modified magnetic beads (SAV-MB), reducing the capture of Biotin-SNA by SAV-MB and thereby significantly enhancing detection sensitivity. This method offers the potential for point-of-care diagnostics as it operates efficiently at 37 °C without the need for thermal cycling. Using standard DNA samples, we demonstrated that this biosensor achieved detection limits as low as 209 copies/μL and 444 copies/μL within 95 min. When combined with recombinase polymerase amplification (RPA), the sensor demonstrated enhanced sensitivity, enabling detection of target DNA at concentrations as low as 1 copy/μL within approximately 50 min. Furthermore, validation with clinical samples confirmed the feasibility and practical applicability of this method. This novel SERS-based sensor offers a new and effective tool in the prevention and detection of cervical cancer.","PeriodicalId":24,"journal":{"name":"ACS Sensors","volume":"128 1","pages":""},"PeriodicalIF":8.9,"publicationDate":"2025-05-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144087759","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"化学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Investigation of the DNA Methylation-Modified 8-17 DNAzyme Functions via Sensitive Catalytic Hairpin Self-Assembly Reaction.","authors":"Wanxue Wang,Guoying Li,Xinghui Zhou,Xiaofang Ding,Feng Zhang,Yaoyao Shu,Yanqiong Liu,Haiou Ma,Lang Zhang,Danping Chen","doi":"10.1021/acssensors.5c00581","DOIUrl":"https://doi.org/10.1021/acssensors.5c00581","url":null,"abstract":"8-17 DNAzyme is a well-known versatile nucleic acid tool for achieving a specific cleavage function, and thus, investigation of 8-17 DNAzyme functions can prove to be of great significance. The conventional epigenetic modification on DNAzyme may pave a new way for the study of catalytic properties. Herein, the most abundant and best characterized modifications 5-methylcytosine (5mC) and N6-methyladenosine (m6A) are introduced into the central catalytic core and stem sequence of 8-17 DNAzyme to evaluate the cleavage activity. The modified 8-17 DNAzymes are arranged to recognize and cleave single-stranded DNA (ssDNA) substrates that contain a 5'-rAG-3' motif, producing large numbers of short ssDNA and leaving different amounts of undegraded ssDNA because of their disparate excision efficiency. Meanwhile, the undegraded ssDNA is used as new substrates for triggering the catalytic hairpin self-assembly (CHA) reaction. Benefiting from the facile and sensitive CHA reaction, the methylation-induced fluctuations of cleavage activity can be directly amplified and detected. Moreover, dioxygenase ten-eleven translocation protein 2 (Tet 2) offers a possibility for exploring the reversibility of methylation-modified DNAzymes through a demethylation process. In this study, we found that both 5mC and m6A modifications in the circular catalytic core might lead to a significant inhibition effect on the catalytic activity of 8-17 DNAzyme. However, little variation was observed when the stem region was labeled with 5mC. Additionally, the alkaline condition (pH = 9.5) enabled the partial recovery of cleavage activity for DNAzyme-19-5mC (∼52.9%). More impressively, these 8-17 DNAzymes were employed to study the regulation of miRNA-21 level in nonsmall cell lung cancer (A549) cells and human cervical cancer (HeLa) cells, revealing that the decrease of intracellular miRNA-21 content showed positive correlation with the death of tested cells. This study would hopefully advance the epigenetics research and dramatically expand the biosensing application of DNAzymes.","PeriodicalId":24,"journal":{"name":"ACS Sensors","volume":"234 1","pages":""},"PeriodicalIF":8.9,"publicationDate":"2025-05-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144087755","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"化学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Extracting True Virus SERS Spectra and Augmenting Data for Improved Virus Classification and Quantification","authors":"Yufang Liu, Yanjun Yang, Haoran Lu, Jiaheng Cui, Xianyan Chen, Ping Ma, Wenxuan Zhong, Yiping Zhao","doi":"10.1021/acssensors.4c03397","DOIUrl":"https://doi.org/10.1021/acssensors.4c03397","url":null,"abstract":"Surface-enhanced Raman spectroscopy (SERS) is a transformative tool for infectious disease diagnostics, offering rapid and sensitive species identification. However, background spectra in biological samples complicate analyte peak detection, increase the limit of detection, and hinder data augmentation. To address these challenges, we developed a deep learning framework utilizing dual neural networks to extract true virus SERS spectra and estimate concentration coefficients in water for 12 different respiratory viruses. The extracted spectra showed a high similarity to those obtained at the highest viral concentration, validating their accuracy. Using these spectra and the derived concentration coefficients, we augmented spectral data sets across varying virus concentrations in water. XGBoost models trained on these augmented data sets achieved overall classification and concentration prediction accuracy of 92.3% with a coefficient of determination (<i>R</i><sup>2</sup>) > 0.95. Additionally, the extracted spectra and coefficients were used to augment data sets in saliva backgrounds. When tested against real virus-in-saliva spectra, the augmented spectra-trained XGBoost models achieved 91.9% accuracy in classification and concentration prediction with <i>R</i><sup>2</sup> > 0.9, demonstrating the robustness of the approach. By delivering clean and uncontaminated spectra, this methodology can significantly improve species identification, differentiation, and quantification and advance SERS-based detection and diagnostics.","PeriodicalId":24,"journal":{"name":"ACS Sensors","volume":"233 1","pages":""},"PeriodicalIF":8.9,"publicationDate":"2025-05-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144083352","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"化学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
ACS SensorsPub Date : 2025-05-17DOI: 10.1021/acssensors.5c00204
Hongqiang Wang, Jiayu Sun, Qingqing Zou, Bin Du, Hui Liu, Yanan Luan, Xin Wang, Xiaohai Yang, Qing Wang, Kemin Wang
{"title":"Wash-Free Isolation and Quantification of Tumor-Derived Exosomes via In Situ-Formed Hydrogel","authors":"Hongqiang Wang, Jiayu Sun, Qingqing Zou, Bin Du, Hui Liu, Yanan Luan, Xin Wang, Xiaohai Yang, Qing Wang, Kemin Wang","doi":"10.1021/acssensors.5c00204","DOIUrl":"https://doi.org/10.1021/acssensors.5c00204","url":null,"abstract":"The isolation and detection of exosomes as tumor markers are of vital importance for the early diagnosis, therapeutic monitoring, and mechanistic studies of tumors. Here, exosomes derived from breast cancer cells were chosen as model targets, and a wash-free, enzyme-free, handheld mini centrifugation method based on hydrogels was developed to effectively isolate and detect breast cancer exosomes. Dual aptamers (CD63-T1 and EpCAM-T2) were employed to specifically recognize and capture breast cancer exosomes. This specific recognition triggered the formation of hybridization chain reaction (HCR) nanostructures on the captured exosomes through the interaction of hairpin 1 and the alginate complex (H1-Alg) and hairpin 2 (H2-Cy3). The interaction of Ca<sup>2+</sup> and alginate enabled the in situ formation of a hydrogel on the exosome surface. Subsequent low-speed centrifugation using a handheld mini centrifuge facilitated the efficient isolation of the exosomes, thereby eliminating the need for tedious washing steps. Utilizing the classical chelation reaction of ethylene diamine tetraacetic acid (EDTA) with Ca<sup>2+</sup>, the hydrogel can be rapidly cleaved for enzyme-free release of exosomes. The method demonstrated excellent capture and release efficiencies of approximately 85% and 98%, respectively, for specific cancerous exosomes. Notably, the exosomes isolated by the hydrogel system retained excellent biological activity, making them suitable for further analysis and potential applications. Meanwhile, the highly sensitive detection of breast cancer exosomes based on this strategy could also be achieved with a lower limit of detection as low as 3.2 × 10<sup>3</sup> particles/mL. This work provides a novel and cost-effective strategy for the effective isolation and detection of tumor-derived exosomes, which can help to promote the subsequent application of exosomes in research.","PeriodicalId":24,"journal":{"name":"ACS Sensors","volume":"76 1","pages":""},"PeriodicalIF":8.9,"publicationDate":"2025-05-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144066971","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"化学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Wearable, Breathable, and Wireless Gas Sensor Enables Highly Selective Exhaled Ammonia Detection and Real-Time Noninvasive Illness Diagnosis","authors":"Haipeng Dong, Xiaowei Li, Yu Liu, Wanying Cheng, Chaohan Han, Yunpeng Yin, Xinghua Li, Changlu Shao, Yichun Liu","doi":"10.1021/acssensors.4c03468","DOIUrl":"https://doi.org/10.1021/acssensors.4c03468","url":null,"abstract":"Wearable gas sensors capable of real-time analysis of exhaled breath have been identified as ideal devices for noninvasive illness diagnosis. However, due to their inherent rigidity and brittleness, as well as high cross-sensitivity, conventional semiconductor gas sensors face significant challenges in achieving high flexibility, robustness, and selective exhaled breath analysis. Herein, we propose a wearable gas sensor by anchoring a SnS<sub>2</sub> nanosheets/polyaniline (PANI) sensing layer in situ onto a permeable and flexible yttria-stabilized zirconia (YSZ) nanofiber substrate for the analysis of exhaled NH<sub>3</sub>. The cross-linked meshes of the YSZ network and the abundant voids between SnS<sub>2</sub> nanosheets effectively release the stress concentration in YSZ/SnS<sub>2</sub>/PANI films, enabling the sensor to withstand severe folding/bending deformation. The organic PANI sheath endows the YSZ/SnS<sub>2</sub>/PANI-based gas sensor with enhanced toughness (0.66 kJ·m<sup>–3</sup>), stable electrical connection, and excellent robustness. The unique protonation/deprotonation sensing mechanism, coupled with the heterojunction effect of the sensing layer, ensures outstanding selectivity (sensor immunity coefficient ≈ 69%) and a high response to NH<sub>3</sub>. To support wearable applications, the sensing signals from the wearable sensor are transmitted wirelessly via Bluetooth and displayed on a smartphone. This work greatly advances the application of a wearable semiconductor sensor in personal disease diagnosis.","PeriodicalId":24,"journal":{"name":"ACS Sensors","volume":"148 1","pages":""},"PeriodicalIF":8.9,"publicationDate":"2025-05-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144067001","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"化学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
ACS SensorsPub Date : 2025-05-17DOI: 10.1021/acssensors.5c00028
Yue Liu, Fengchun Tian, James A. Covington, Zhiyuan Wu, Li Hu, Hantao Li
{"title":"Bioinspired Substrate Structures for High-Performance Room-Temperature Chemiresistive Gas Sensors","authors":"Yue Liu, Fengchun Tian, James A. Covington, Zhiyuan Wu, Li Hu, Hantao Li","doi":"10.1021/acssensors.5c00028","DOIUrl":"https://doi.org/10.1021/acssensors.5c00028","url":null,"abstract":"In the field of gas sensors, there is a growing demand for efficient gas detection. Current research mainly focuses on the selection and optimization of sensing materials, while the geometry of sensors is often ignored. Most sensors are designed with simple planar or cylindrical geometries. In this work, biomimetic sensor structures were built, inspired by the olfactory turbinate of the Labrador retriever. Computational fluid dynamics (CFD) simulations revealed that the biomimetic structure enhances sensing performance by optimizing the flow field distribution and increasing the local concentration and surface adsorption concentration around the sensor. To validate these biomimetic structures, we developed high-performance room-temperature chemiresistive gas sensors. We shaped the flexible sensors into forms mimicking canine turbinates and validated the impact of these structures on sensor performance. Experimental results show that the biomimetic sensors have an average response of 390% to 100 ppm of NH<sub>3</sub>, which is 5.62 times higher than that of traditional, non-biomimetic sensors.","PeriodicalId":24,"journal":{"name":"ACS Sensors","volume":"41 1","pages":""},"PeriodicalIF":8.9,"publicationDate":"2025-05-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144067090","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"化学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"A Versatile Self-Powered Photoelectrochemical-Colorimetric Dual-Mode Immunosensing Platform Based on a 3D BiOI Nanoflower Functionalized by Bi Doping and Morphology Engineering.","authors":"Zhiquan An,Xiaoyu Jian,Jiateng Ma,Minjie Li,Bihong Zhang,Liang-Hong Guo","doi":"10.1021/acssensors.5c00822","DOIUrl":"https://doi.org/10.1021/acssensors.5c00822","url":null,"abstract":"Photoelectrochemical-colorimetric (PEC-CL) dual-mode detection integrates PEC and CL advantages for bioanalysis but often faces low efficiency, complex conditions, and performance trade-offs due to different signal transduction materials. Here, BiOI was functionalized by Bi0 self-doping and morphology engineering, forming a 3D Bi-doped BiOI nanoflower with excellent PEC and CL properties. This material was innovatively developed as a single transduction material for self-powered PEC-CL dual-mode detection. The synergistic enhancement of photoelectric conversion and peroxidase (POD)-like activity was systematically investigated. Using γH2AX, a genotoxicity biomarker, as a model, a self-powered PEC sandwich immunosensor was constructed with ITO/Au as the photocathode, BiOI-Ab2 as the signal probe, and CdIn2S4 as the photoanode. Upon γH2AX recognition, BiOI was introduced on the photocathode via an immunoreaction. The well-matched energy levels between Au and BiOI, along with the dual-photoelectrode effect, enable a sensitive \"signal-on\" PEC analysis. Simultaneously, a sandwich immunoreaction involving the BiOI-labeled secondary antibody occurred in the microplate containing H2O2 and 3,3',5,5'-tetramethylbenzidine (TMB), among which BiOI-catalyzed H2O2 produced reactive oxygen species, which further oxidized TMB to produce color, thus achieving the high-throughput visual detection of γH2AX. The PEC-CL dual-mode sensor exhibited broad linear ranges (0.1 pg/mL to 1000 ng/mL for PEC, 1 pg/mL to 500 ng/mL for CL) with ultralow detection limits of 23.9 and 330 fg/mL, respectively. The sensitivity of PEC mode is 100-fold higher than the ELISA method. Moreover, the practicability of the PEC-CL immunosensor was verified in cell lysates exposed to known genotoxic compounds. This sensing platform is versatile, which allows the detection of other biomarkers by changing the recognition element.","PeriodicalId":24,"journal":{"name":"ACS Sensors","volume":"14 1","pages":""},"PeriodicalIF":8.9,"publicationDate":"2025-05-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144065675","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"化学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
ACS SensorsPub Date : 2025-05-15DOI: 10.1021/acssensors.5c0063010.1021/acssensors.5c00630
Wangze Ni, Tao Wang*, Yu Wu, Lechen Chen, Min Zeng, Jianhua Yang, Nantao Hu, Bowei Zhang, Fuzhen Xuan and Zhi Yang*,
{"title":"Robust Odor Detection in Electronic Nose Using Transfer-Learning Powered Scentformer Model","authors":"Wangze Ni, Tao Wang*, Yu Wu, Lechen Chen, Min Zeng, Jianhua Yang, Nantao Hu, Bowei Zhang, Fuzhen Xuan and Zhi Yang*, ","doi":"10.1021/acssensors.5c0063010.1021/acssensors.5c00630","DOIUrl":"https://doi.org/10.1021/acssensors.5c00630https://doi.org/10.1021/acssensors.5c00630","url":null,"abstract":"<p >Mimicking the olfactory system of humans, the use of electronic noses (E-noses) for the detection of odors in nature has become a hot research topic. This study presents a novel E-nose based on deep learning architecture called Scentformer, which addresses the limitations of the current E-nose like a narrow detection range and limited generalizability across different scenarios. Armed with a self-adaptive data down-sampling method, the E-nose is capable of detecting 55 different natural odors with the classification accuracy of 99.94%, and the model embedded in the E-nose is analyzed using Shapley Additive exPlanations analysis, providing a quantitative interpretation of the E-nose performance. Furthermore, leveraging Scentformer’s transfer learning ability, the E-nose efficiently adapts to new odors and gases. Rather than retraining all layers of the model on the new odor data set, only the fully connected layers need to be trained for the pretrained model. Using only 1‰ data of the retrained model, the pretrained model-based E-nose can also achieve classification accuracies of 99.14% across various odor and gas concentrations. This provides a robust approach to the detection of diverse direct current signals in real-world applications.</p>","PeriodicalId":24,"journal":{"name":"ACS Sensors","volume":"10 5","pages":"3704–3712 3704–3712"},"PeriodicalIF":8.2,"publicationDate":"2025-05-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144114568","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"化学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}