Related Experiment Video
Updated: Sep 28, 2025
07:46
Microfluidic Co-Culture Models for Dissecting the Immune Response in in vitro Tumor Microenvironments
Published on: April 30, 2021
4.9K
Integration of a microfluidic multicellular coculture array with machine learning analysis to predict adverse
Lor Huai Chong1,2,3, Terry Ching1,4,5, Hui Jia Farm6
1Department of Biomedical Engineering, National University of Singapore, 4 Engineering Drive 3, #04-08, Singapore 117583, Singapore.
Lab on a Chip
|March 29, 2022
Summary
A new in vitro drug screening platform accurately predicts skin sensitization potential. This multicellular array and machine learning model improve drug safety by identifying adverse cutaneous reactions early.
Area of Science:
- Pharmacology
- Toxicology
- Biotechnology
Background:
- Adverse cutaneous reactions are severe drug side effects requiring human-specific in vitro screening.
- Existing in vitro models fail to capture complex liver-immune-dermal interactions for predicting skin sensitization.
- Predicting drug-induced skin reactions is crucial for enhancing drug safety.
Purpose of the Study:
- To develop and validate a novel in vitro drug screening platform for predicting skin sensitization potential.
- To model the complex mechanisms underlying adverse cutaneous drug reactions.
- To integrate multi-tissue interactions and machine learning for accurate drug risk assessment.
Main Methods:
- A microfluidic multicellular array (MCA) co-culturing hepatocytes, antigen-presenting cells, keratinocytes, and fibroblasts.
- Assays measuring drug metabolite generation, immunogenicity, and apoptosis.
- Machine learning algorithms (SVM, PCA) integrating multiple readouts for classification.
Main Results:
- The MCA platform achieved 87.5% accuracy, 75% specificity, and 100% sensitivity in predicting skin sensitization for 11 FDA-labeled drugs.
- The system successfully modeled drug metabolite-induced apoptosis via FasL.
- Prospective analysis of obeticholic acid (OCA) identified its skin-sensitizing potential.
Conclusions:
- The novel MCA platform offers a robust in vitro method for predicting drug-induced skin sensitization.
- This approach enhances drug safety by enabling early identification of potential adverse cutaneous reactions.
- The platform can elucidate mechanisms of action for skin sensitization, aiding in drug development.
