Related Experiment Video
Updated: Jul 4, 2025
Microfluidic Platform with Multiplexed Electronic Detection for Spatial Tracking of Particles
Published on: March 13, 2017
Machine learning classification of cellular states based on the impedance features derived from microfluidic
Jian Wei1, Wenbing Gao1, Xinlong Yang1
1College of Information Science and Technology, Beijing University of Chemical Technology, No. 15 North 3rd Ring Road, Chaoyang District, Beijing 100029, China.
Abstract:
Mitosis is a crucial biological process where a parental cell undergoes precisely controlled functional phases and divides into two daughter cells. Some drugs can inhibit cell mitosis, for instance, the anti-cancer drugs interacting with the tumor cell proliferation and leading to mitosis arrest at a specific phase or cell death eventually. Combining machine learning with microfluidic impedance flow cytometry (IFC) offers a concise way for label-free and high-throughput classification of drug-treated cells at single-cell level. IFC-based single-cell analysis generates a large amount of data related to the cell electrophysiology parameters, and machine learning helps establish correlations between these data and specific cell states. This work demonstrates the application of machine learning for cell state classification, including the binary differentiations between the G1/S and apoptosis states and between the G2/M and apoptosis states, as well as the classification of three subpopulations comprising a subgroup insensitive to the drug beyond the two drug-induced states of G2/M arrest and apoptosis. The impedance amplitudes and phases used as input features for the model training were extracted from the IFC-measured datasets for the drug-treated tumor cells. The deep neural network (DNN) model was exploited here with the structure (e.g., hidden layer number and neuron number in each layer) optimized for each given cell type and drug. For the H1650 cells, we obtained an accuracy of 78.51% for classification between the G1/S and apoptosis states and 82.55% for the G2/M and apoptosis states. For HeLa cells, we achieved a high accuracy of 96.94% for classification between the G2/M and apoptosis states, both of which were induced by taxol treatment. Even higher accuracy approaching 100% was achieved for the vinblastine-treated HeLa cells for the differentiation between the viable and non-viable states, and between the G2/M and apoptosis states. We also demonstrate the capability of the DNN model for high-accuracy classification of the three subpopulations in a complete cell sample treated by taxol or vinblastine.
Insights
Machine learning combined with microfluidic impedance flow cytometry (IFC) accurately classifies drug-treated cells. This approach enables label-free, high-throughput analysis of cell states, aiding cancer drug development.
Area of Science:
- Cell Biology
- Biophysics
- Computational Biology
Background:
- Mitosis is essential for cell division, and its disruption is a target for anti-cancer drugs.
- Drug-induced cell cycle arrest or apoptosis are key outcomes in cancer therapy.
- Label-free, high-throughput single-cell analysis is crucial for understanding drug effects.
Purpose of the Study:
- To apply machine learning (ML) with microfluidic impedance flow cytometry (IFC) for label-free classification of drug-treated tumor cells.
- To differentiate between various cell states, including G1/S, G2/M arrest, and apoptosis.
- To classify subpopulations of cells, including drug-resistant ones.
Main Methods:
- Utilized IFC to measure electrophysiological parameters of single cells.
- Extracted impedance amplitudes and phases as features for ML model training.
- Employed a deep neural network (DNN) model with optimized structures for cell type and drug-specific classification.
Main Results:
- Achieved high classification accuracies for H1650 and HeLa cells, differentiating between G1/S, G2/M arrest, and apoptosis states.
- Demonstrated high accuracy (approaching 100%) in classifying viable vs. non-viable cells and G2/M arrest vs. apoptosis in vinblastine-treated HeLa cells.
- Successfully classified three subpopulations (drug-insensitive, G2/M arrest, apoptosis) in taxol or vinblastine-treated cells.
Conclusions:
- ML combined with IFC provides a powerful, label-free method for high-throughput single-cell analysis of drug effects.
- The DNN model effectively classifies complex cell states induced by anti-cancer drugs.
- This approach has significant potential for drug discovery and personalized medicine by identifying drug responses and resistance mechanisms.
