Non-invasive real-time investigation of colorectal cells tight junctions by Raman microspectroscopy analysis combined with machine learning algorithms for organ-on-chip applications - research

Sep 21, 2026

Non-invasive real-time Raman microspectroscopy is developed to examine structural and biochemical alterations of tight junctions in a Caco-2 cell-based intestinal epithelial model before and after calcium-chelating treatment. Supervised machine learning classifies multiple epithelium damage conditions, reaching 91.9% accuracy with only seven selected features. Two data-splitting strategies, sample-based and spectra-based, are compared. Raman findings are validated using TEER measurements and immunofluorescence staining. The approach enables high-spatial-resolution monitoring of dynamic biomolecular changes for organ-on-chip and related biomedical applications.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages16

Reading Time40 min

AccessFree to download

Introduction

Methods

Results

Discussion

TYPE Original Research PUBLISHED 11 November 2024 DOI 10.3389/fbioe.2024.1458404 OPEN ACCESS EDITED BY Jose Manuel Garcia-Aznar, University of Zaragoza, Spain REVIEWED BY Wei Zhang, The University of Utah, United States Yuzhu Liu, Nanjing University of Information Science and Technology, China *CORRESPONDENCE E. Sciurti, [elisa.sciurti@cnr.it](elisa.sciurti@cnr.it) RECEIVED 02 July 2024 ACCEPTED 25 October 2024 PUBLISHED 11 November 2024 CITATION Calogiuri A, Bellisario D, Sciurti E, Blasi L, Esposito V, Casino F, Siciliano P and Francioso L (2024) Non-invasive real-time investigation of colorectal cells tight junctions by Raman microspectroscopy analysis combined with machine learning algorithms for organ-onchip applications. Front. Bioeng. Biotechnol. 12:1458404 . doi: 10.3389/fbioe.2024.1458404 COPYRIGHT © 2024 Calogiuri, Bellisario, Sciurti, Blasi, Esposito, Casino, Siciliano and Francioso. This isan open-access article distributed under the terms of the Creative Commons Attribution License (CC BY) . The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner(s) are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms. Non-invasive real-time investigation of colorectal cells tight junctions by Raman microspectroscopy analysis combined with machine learning algorithms for organ-on-chip applications A. Calogiuri, D. Bellisario, E. Sciurti*, L. Blasi, V. Esposito, F. Casino, P. Siciliano and L. Francioso Institute for Microelectronics and Microsystems IMM-CNR, Via per Monteroni “Campus Ecotekne”, Lecce, Italy Introduction: Colorectal cancer is the third most common malignancy in developed countries. Diagnosis strongly depends on the pathologist ’s expertise and laboratory equipment, and patient survival is inﬂuenced by the cancer ’s stage at detection. Non-invasive spectroscopic techniques can aid early diagnosis, monitor disease progression, and assess changes in physiological parameters in both heterogeneous samples and advanced platforms like Organ-on-Chip (OoC) . Methods: In this study, Raman microspectroscopy combined with Machine Learning was used to analyse structural and biochemical changes in a Caco-2 cell-based intestinal epithelial model before and after treatment with a calcium chelating agent. Results: The Machine Learning (ML) algorithm successfully classiﬁed different epithelium damage conditions, achieving an accuracy of 91.9% using only 7 features. Two data-splitting approaches, “sample-based” and “spectra-based,”were also compared. Further, Raman microspectroscopy results were conﬁrmed by TEER measurements and immunoﬂuorescence staining. Discussion: Experimental results demonstrate that this approach, combined with supervised Machine Learning, can investigate dynamic biomolecular changes in real-time with high spatial resolution. This represents a promising non-invasive alternative technique for characterizing cells and biological barriers in organoids and OoC platforms, with potential applications in cytology diagnostics, tumor monitoring, and drug efﬁcacy analysis . KEYWORDS micro-Raman spectroscopy, machine learning, principal component analysis (PCA), Caco-2 cells, organ-on-chip Frontiers in Bioengineering and Biotechnology 01 [frontiersin.org](frontiersin.org) 1 Introduction Micro-Raman spectroscopy is a technique of great interest that combines Raman spectroscopy with optical microscopy to study the chemical composition of microscopic samples (Mariani et al., 2010) . For several years, it has been considered a potential tool for biological and medical applications (Pappas et al., 2000) . Raman spectroscopy has several limitations in biological tissue analysis. Its inherently weak signal requires long acquisition times, while tis

FAQs

What technique is used to investigate colorectal cell tight junctions in real time?

Raman microspectroscopy is used to analyze structural and biochemical changes in a Caco-2 intestinal epithelial model, combined with supervised machine learning for classification.

How accurate is the machine learning classification and what features are used?

The algorithm classifies different epithelium damage conditions with 91.9% accuracy using only 7 features.

How are the Raman microspectroscopy results validated?

Results are confirmed with TEER measurements and immunofluorescence staining.

Sep 21, 2026

Uploaded by Seraphina