EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Evaluating Limits of Machine Learning-Assisted Raman Spectroscopy in Classification of Biological Samples

Aman Yadav iD, Arlin Birkby, Noah Armstrong, Assame Arnob iD, Ming-Hsun Chou, Alma Fernandez, Aart J Verhoef, Zhenhuan Yi iD, Siddhant Gulati iD, Siddhi Kotnis iD, Qing Sun, Katy C Kao und 1 weitere

ACS Omega · 11.08.2026 · 11 (31) · 47122-47134

DOI: 10.1021/acsomega.6c06456 ↗

Kurz gefasst

Fachartikel in der Zeitschrift ACS Omega, online erschienen am 30.07.2026. Verfasst von Aman Yadav und 12 weiteren Autor:innen. Beteiligte Einrichtung: Artie McFerrin Department of Chemical Engineering, Texas A&M University, College Station, Texas 77843, United States. Die Arbeit nennt 54 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: NIGMS NIH HHS, National Science Foundation, U.S. Department of Energy.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Machine learning (ML)-assisted Raman spectroscopy has become a powerful analytical tool for the classification and identification of analytes; however, technical challenges impacting its detection accuracy have not been thoroughly investigated. This study explores experimental factors affecting classification performance. Among the evaluated ML models, ML algorithms show minimal impact on classification accuracy. Instead, experimental factors, including spectral similarity between tested samples and data quality, dominate detection performance. Increases in spectral noise and spectral similarity significantly reduce classification accuracy. In well-controlled samples with low experimental noise, ML-assisted Raman spectroscopy can discriminate lipid mixtures with a composition difference of 1.85 mol %. To assess the effect of biological heterogeneity, we analyzed single-cell Raman spectra from Saccharomyces cerevisiae strains carrying single, double, or triple gene mutations. Intrinsic cell-to-cell variability introduced substantial spectral differences, severely reducing the accuracy of multiclass classification of these genetically similar strains at the single-cell level. Averaging Raman spectra across multiple cells improved classification accuracy by reducing this spectral variability. We also assess the effectiveness of transfer learning across different Raman spectrometers, specifically by applying an ML model trained on one instrument to another Raman spectrometer. Transfer learning can be improved with proper instrument calibration, highlighting the importance of instrument standardization. Overall, our results demonstrate that data quality and spectral similarity are the primary bottlenecks in ML-assisted Raman spectroscopy. Careful attention to sample preparation, data acquisition, measurement conditions, and instrument calibration is critical to achieving robust and reliable classification performance.

Autor:innen und Institutionen

  • Artie McFerrin Department of Chemical Engineering, Texas A&M University, College Station, Texas 77843, United States.
  • Institute for Quantum Science and Engineering, Texas A&M University, College Station, Texas 77843, United States.
  • Department of Physics and Astronomy, Texas A&M University, College Station, Texas 77843, United States.
  • Department of Soil and Crop Sciences, Texas A&M University, College Station, Texas 77843, United States.
  • Interdisciplinary Graduate Program in Genetics and Genomics, Texas A&M University, College Station, Texas 77843, United States.
  • Department of Chemical and Materials Engineering, San Jose State University, San Jose, California 95112-3613, United States.

ORCID-Profile: Aman Yadav, Assame Arnob, Zhenhuan Yi, Siddhant Gulati, Siddhi Kotnis, Hung-Jen Wu

Förderung

  • NIGMS NIH HHS
  • National Science Foundation
  • U.S. Department of Energy
  • National Institute of General Medical Sciences
  • Air Force Office of Scientific Research
  • Welch Foundation
  • Biological and Environmental Research
  • Texas A and M University

Zitieren

APA

Yadav, A., Birkby, A., Armstrong, N., Arnob, A., Chou, M. H., Fernandez, A., Verhoef, A. J., Yi, Z., Gulati, S., Kotnis, S., Sun, Q., Kao, K. C., & Wu, H. J. (2026). Evaluating Limits of Machine Learning-Assisted Raman Spectroscopy in Classification of Biological Samples. ACS Omega, 11(31), 47122-47134. https://doi.org/10.1021/acsomega.6c06456

Vancouver

Yadav A, Birkby A, Armstrong N, Arnob A, Chou MH, Fernandez A, et al. Evaluating Limits of Machine Learning-Assisted Raman Spectroscopy in Classification of Biological Samples. ACS Omega. 2026;11(31):47122-47134. doi:10.1021/acsomega.6c06456

BibTeX
@article{Yadav2026,
  author = {Yadav, Aman and Birkby, Arlin and Armstrong, Noah and Arnob, Assame and Chou, Ming-Hsun and Fernandez, Alma and Verhoef, Aart J and Yi, Zhenhuan and Gulati, Siddhant and Kotnis, Siddhi and Sun, Qing and Kao, Katy C and Wu, Hung-Jen},
  title = {Evaluating Limits of Machine Learning-Assisted Raman Spectroscopy in Classification of Biological Samples},
  journal = {ACS Omega},
  year = {2026},
  volume = {11},
  number = {31},
  pages = {47122--47134},
  doi = {10.1021/acsomega.6c06456}
}
Kostenlos starten →