Jiaheng Cui

Mr. Jiaheng Cui

orcid

Research Focus & Metrics

Academic Career Length

3Years (2024-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
2 July 2024 in Sensors & Diagnostics
Verified
Journal Article
Open access
PDF file
JRJoshua Curtis Rothstein
Joshua Curtis Rothstein
JCJiaheng Cui
Jiaheng Cui
YYYanjun Yang
Yanjun Yang
XCXianyan Chen
Xianyan Chen
Yiping ZhaoYiping Zhao
Yiping Zhao
SERS combined with machine learning was employed using AgNR substrates. The method demonstrates high sensitivity and specificity in detecting and differentiating PFASs in water or methanol samples.

26 July 2025 in Analytical Chemistry
Verified
Journal Article
Open access
JCJiaheng Cui
Jiaheng Cui
XCXianyan Chen
Xianyan Chen
Yiping ZhaoYiping Zhao
Yiping Zhao
Baseline correction is a critical preprocessing step in Raman and surface-enhanced Raman spectroscopy analysis. The adaptive iterative reweighted penalized least-squares (airPLS) method is widely used due to its simplicity and efficiency, but its effectiveness is often hindered by challenges such as baseline smoothness, parameter sensitivity, and inconsistent performance under complex spectral conditions. To address these limitations, we developed an optimized airPLS algorithm (OP-airPLS) that systematically fine-tunes key parameters by using an adaptive grid search method. We further implemented a machine learning model to predict these parameters through spectral shape recognition. A data set of 6000 simulated spectra representing 12 spectral shapes (comprising three peak types and four baseline variations) was used for evaluation. On average, OP-airPLS achieved a percentage improvement (PI) of 96 ± 2%, with the maximum improvement reducing the mean absolute error (MAE) from 0.103 to 5.55 × 10-4 (PI = 99.46 ± 0.06%) and the minimum improvement lowering the MAE from 0.061 to 5.68 × 10-3 (PI = 91 ± 7%). The optimal parameters for each spectral shape were found to reside within a well-defined linear region in the parameter space. While OP-airPLS significantly improved enhanced baseline correction accuracy, it required substantial computational resources and relied on known true baselines. To overcome these constraints, a machine learning approach combining principal component analysis and random forest (PCA-RF) was developed to directly predict optimal parameters from input spectra. The PCA-RF model demonstrated robust performance and achieved an overall PI of 90 ± 10% while requiring only 0.038 s to process each spectrum. When this method is applied to real spectra, its baseline estimation performance is constrained by both the signal-to-noise ratio and the similarity of the spectral shape to the training data.

18 May 2025 in ACS Sensors
Verified
Journal Article
Open access
YLYufang Liu
Yufang Liu
YYYanjun Yang
Yanjun Yang
HLHaoran Lu
Haoran Lu
JCJiaheng Cui
Jiaheng Cui
XCXianyan Chen
Xianyan Chen
Yiping ZhaoYiping Zhao
Yiping Zhao
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 (R2) > 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 R2 > 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.

4 December 2024 in The Analyst
Verified
Journal Article
Open access
PDF file
TWTao Wang
Tao Wang
YYYanjun Yang
Yanjun Yang
HLHaoran Lu
Haoran Lu
JCJiaheng Cui
Jiaheng Cui
XCXianyan Chen
Xianyan Chen
Yiping ZhaoYiping Zhao
Yiping Zhao
A SERS instrument transformation framework based on the penalized functional regression model (SpectraFRM) is proposed for cross-instrument mapping with subsequent machine learning classification to compare transformed spectra with standard spectra.

6 April 2026 in Analytical Chemistry
Verified
Journal Article
Open access
FMFengbo Ma
Fengbo Ma
JCJiaheng Cui
Jiaheng Cui
AKAmit Kumar
Amit Kumar
YYYanjun Yang
Yanjun Yang
XCXianyan Chen
Xianyan Chen
Yiping ZhaoYiping Zhao
Yiping Zhao
Raman and Surface-Enhanced Raman Scattering (SERS) spectroscopy are powerful techniques for molecular identification and characterization, yet widespread adoption is often limited by the lack of accessible, standardized tools for preprocessing, analysis, and data management. Here, we introduce SpectraGuru, an open-source web-based platform designed to provide a comprehensive ecosystem for Raman and SERS research. SpectraGuru integrates a modular workflow for data upload, interactive preprocessing, advanced statistical analysis, and visualization, all accessible through a user-friendly browser interface. The platform's key contributions include a fully open-source, web-based system; comprehensive preprocessing and analysis tools covering tasks such as interpolation, despiking, baseline correction, normalization, peak identification, and multivariate methods like hierarchical clustering, Principal Component Analysis (PCA), and t-distributed stochastic neighbor embedding (t-SNE); and an integrated PostgreSQL database that supports FAIR (Findable, Accessible, Interoperable, Reusable) storage of spectra and metadata to enhance reproducibility and data sharing. Demonstrations with experimental data sets showcase SpectraGuru's ability to transform raw spectra into clean, interpretable data and to reveal meaningful patterns across diverse analytes. By addressing challenges in preprocessing standardization, database integration, and analytical flexibility, SpectraGuru aims to accelerate spectral research and foster community-driven development in Raman and SERS spectroscopy.

25 August 2025 in The Journal of Physical Chemistry A
Verified
Journal Article
Open access
JCJiaheng Cui
Jiaheng Cui
YYYanjun Yang
Yanjun Yang
AKAmit Kumar
Amit Kumar
JMJackelyn Murray
Jackelyn Murray
LJLes Jones
Les Jones
Yiping ZhaoYiping Zhao
Yiping Zhao
Understanding virus-surface interactions is essential for developing effective biosensors, diagnostic tools, and antiviral strategies. In this study, we present a systematic investigation of the adsorption and coadsorption behavior of 12 respiratory viruses, including influenza, RSV, coronaviruses, adenovirus, and metapneumoviruses, using surface-enhanced Raman scattering (SERS) on SiO2-coated silver nanorod array substrates. Both single viruses (SVs) and binary virus mixtures (2VMs) were analyzed in water and normal human saliva, and spectral data were modeled using a modified Brunauer-Emmett-Teller (BET) adsorption framework. Linear least-squares spectral decomposition enabled the extraction of adsorption coefficients that correlate with virus concentration and surface binding affinity. All viruses exhibited multilayer physisorption consistent with Type II isotherms, with the BET constant q varying substantially across virus types. Notably, 2VMs demonstrated a significantly enhanced adsorption behavior, often with q values 4-25 times greater than in SVs, indicating strong cooperative or competitive effects. Saliva modulated virus-surface interactions in virus-specific ways, emphasizing the complexity of adsorption dynamics in physiological environments. These findings highlight the limitations of single-virus calibration for quantitative detection in mixed-virus samples and underscore the need for mixture-aware analytical models in biosensing applications. This work provides a robust framework for mechanistic insight and quantitative modeling of virus adsorption relevant to real-world diagnostics and environmental monitoring.