Optical photothermal infrared (OPTIR) spectroscopy assisted by machine learning for lactic acid bacteria identification at strain level

The Analyst 2026

View at publisher
Authors: Paul Lagneaux, Nathan Widjaja, Bastien Lagneaux, Thi Kim Chi Nguyen, Hélène Licandro, Pascale Winckler, Yves Waché
DOI: 10.1039/d5an01093d
Cited by: 5
References: 29

Abstract

, covering both intra- and inter-species diversity. Spectral data from LAB were acquired using a mIRage LS OPTIR system, preprocessed, and used to train a fully connected neural network for each level. The models achieved macro F1-scores of 97% for species level and 91% for strain level classification. These results demonstrate the potential of OPTIR, when integrated with machine learning, as a robust tool for high-resolution bacterial classification, with promising applications in microbiological quality control, probiotic selection, and microbial ecology.

Fields of Study & Subjects

Spectroscopy Techniques in Biomedical and Chemical Research Advanced Chemical Sensor Technologies Photoacoustic and Ultrasonic Imaging

Publication details

Journal / source
The Analyst
Publisher
Royal Society of Chemistry (RSC)
Volume
151
Issue
4
Pages
1172–1181
Publication date
1 January 2026
Language
EN