BactoRamanBioNet: A Multimodal Neural Network for Bacterial Species Identification Using Raman Spectroscopy and Biological Knowledge
Sensors · 2026
DOI: 10.3390/s26061828 ↗Kurz gefasst
Fachartikel in der Zeitschrift Sensors, 2026. Verfasst von Yaoxue Xu und 6 weiteren Autor:innen. Beteiligte Einrichtung: College of Information Engineering, Sichuan Agricultural University, Ya'an 625014, China. Hauptthemen laut MEDLINE: Spectrum Analysis, Raman, Bacteria, Neural Networks, Computer. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 49 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China, Chengdu Philosophy and Social Science Planning Project, Southwest Sichuan (Ya'an) Rainstorm Laboratory Science and Technology Development.
Abstract (Originalsprache)
Accurate and rapid identification of bacterial species is essential for public health, clinical diagnostics, and environmental monitoring. Although Raman spectroscopy offers a powerful, non-invasive alternative, reliance solely on spectral data often fails to distinguish species with highly similar signatures, particularly when the discriminating features are subtle. This difficulty is frequently compounded by a lack of integrated biological prior knowledge, which can hinder model performance. To address these challenges, we introduce BactoRamanBioNet, a novel multimodal neural network architecture. Our model employs a synergistic approach that utilizes a ResNet-Transformer architecture to capture complex spectral patterns and a CLIP text encoder to incorporate descriptive biological information, thereby enabling highly accurate multimodal classification of bacterial species. Empirical results demonstrate that BactoRamanBioNet achieves a classification accuracy of 98.2% and an F1-score of 98.0%. This performance surpasses the current state-of-the-art deep learning model, ResNet-1D, by 2.4% in accuracy and 2.0% in F1-score. Moreover, our model outperforms traditional classifiers, such as Support Vector Machine (SVM) and Random Forest (RF), by 9.8% and 7.9% in accuracy, respectively, while also exhibiting significant improvements in precision and recall. By establishing a new benchmark in performance and robustness, BactoRamanBioNet offers a powerful and reliable framework for automated microbiological analysis, paving the way for next-generation diagnostic systems.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- College of Information Engineering, Sichuan Agricultural University, Ya'an 625014, China.
- College of Water Resources and Hydropower, Sichuan Agricultural University, Ya'an 625014, China.
- College of Life Science, Sichuan Agricultural University, Ya'an 625014, China.
ORCID-Profile: Junzhuo Song, Yunsen Liang
Förderung
- National Natural Science Foundation of China
- Chengdu Philosophy and Social Science Planning Project
- Southwest Sichuan (Ya'an) Rainstorm Laboratory Science and Technology Development
- Southwest Sichuan (Ya’an) Rainstorm Laboratory Science and Technology Development Fund Project
Zitieren
APA
Xu, Y., Song, J., Zhang, Z., Feng, L., Yang, Y., Liang, Y., & Guo, Y. (2026). BactoRamanBioNet: A Multimodal Neural Network for Bacterial Species Identification Using Raman Spectroscopy and Biological Knowledge. Sensors. https://doi.org/10.3390/s26061828
Vancouver
Xu Y, Song J, Zhang Z, Feng L, Yang Y, Liang Y, et al. BactoRamanBioNet: A Multimodal Neural Network for Bacterial Species Identification Using Raman Spectroscopy and Biological Knowledge. Sensors. 2026. doi:10.3390/s26061828
BibTeX
@article{Xu2026,
author = {Xu, Yaoxue and Song, Junzhuo and Zhang, Zhen and Feng, Lin and Yang, Yalan and Liang, Yunsen and Guo, Yan},
title = {BactoRamanBioNet: A Multimodal Neural Network for Bacterial Species Identification Using Raman Spectroscopy and Biological Knowledge},
journal = {Sensors},
year = {2026},
doi = {10.3390/s26061828}
}
EUVIMED