Label-free macrophage phenotype classification using machine learning methods
- Hourani, Tetiana, Perez-Gonzalez, Alexis, Khoshmanesh, Khashayar, Luwor, Rodney, Achuthan, Adrian, Baratchi, Sara, O’Brien-Simpson, Neil, Al-Hourani, Akram
- Authors: Hourani, Tetiana , Perez-Gonzalez, Alexis , Khoshmanesh, Khashayar , Luwor, Rodney , Achuthan, Adrian , Baratchi, Sara , O’Brien-Simpson, Neil , Al-Hourani, Akram
- Date: 2023
- Type: Text , Journal article
- Relation: Scientific Reports Vol. 13, no. 1 (2023), p.
- Full Text:
- Reviewed:
- Description: Macrophages are heterogeneous innate immune cells that are functionally shaped by their surrounding microenvironment. Diverse macrophage populations have multifaceted differences related to their morphology, metabolism, expressed markers, and functions, where the identification of the different phenotypes is of an utmost importance in modelling immune response. While expressed markers are the most used signature to classify phenotypes, multiple reports indicate that macrophage morphology and autofluorescence are also valuable clues that can be used in the identification process. In this work, we investigated macrophage autofluorescence as a distinct feature for classifying six different macrophage phenotypes, namely: M0, M1, M2a, M2b, M2c, and M2d. The identification was based on extracted signals from multi-channel/multi-wavelength flow cytometer. To achieve the identification, we constructed a dataset containing 152,438 cell events each having a response vector of 45 optical signals fingerprint. Based on this dataset, we applied different supervised machine learning methods to detect phenotype specific fingerprint from the response vector, where the fully connected neural network architecture provided the highest classification accuracy of 75.8% for the six phenotypes compared simultaneously. Furthermore, by restricting the number of phenotypes in the experiment, the proposed framework produces higher classification accuracies, averaging 92.0%, 91.9%, 84.2%, and 80.4% for a pool of two, three, four, five phenotypes, respectively. These results indicate the potential of the intrinsic autofluorescence for classifying macrophage phenotypes, with the proposed method being quick, simple, and cost-effective way to accelerate the discovery of macrophage phenotypical diversity. © 2023, The Author(s).
- Authors: Hourani, Tetiana , Perez-Gonzalez, Alexis , Khoshmanesh, Khashayar , Luwor, Rodney , Achuthan, Adrian , Baratchi, Sara , O’Brien-Simpson, Neil , Al-Hourani, Akram
- Date: 2023
- Type: Text , Journal article
- Relation: Scientific Reports Vol. 13, no. 1 (2023), p.
- Full Text:
- Reviewed:
- Description: Macrophages are heterogeneous innate immune cells that are functionally shaped by their surrounding microenvironment. Diverse macrophage populations have multifaceted differences related to their morphology, metabolism, expressed markers, and functions, where the identification of the different phenotypes is of an utmost importance in modelling immune response. While expressed markers are the most used signature to classify phenotypes, multiple reports indicate that macrophage morphology and autofluorescence are also valuable clues that can be used in the identification process. In this work, we investigated macrophage autofluorescence as a distinct feature for classifying six different macrophage phenotypes, namely: M0, M1, M2a, M2b, M2c, and M2d. The identification was based on extracted signals from multi-channel/multi-wavelength flow cytometer. To achieve the identification, we constructed a dataset containing 152,438 cell events each having a response vector of 45 optical signals fingerprint. Based on this dataset, we applied different supervised machine learning methods to detect phenotype specific fingerprint from the response vector, where the fully connected neural network architecture provided the highest classification accuracy of 75.8% for the six phenotypes compared simultaneously. Furthermore, by restricting the number of phenotypes in the experiment, the proposed framework produces higher classification accuracies, averaging 92.0%, 91.9%, 84.2%, and 80.4% for a pool of two, three, four, five phenotypes, respectively. These results indicate the potential of the intrinsic autofluorescence for classifying macrophage phenotypes, with the proposed method being quick, simple, and cost-effective way to accelerate the discovery of macrophage phenotypical diversity. © 2023, The Author(s).
- Akagi, Jin, Skommer, Joanna, Matuszek, Anna, Takeda, Kazuo, Fujimura, Yuu, Khoshmanesh, Khashayar, Kalantar-zadeh, Kourosh, Mitchell, Arnan, Errington, Rachel, Smith, Paul, Darzynkiewicz, Zbigniew, Wlodkowic, Donald
- Authors: Akagi, Jin , Skommer, Joanna , Matuszek, Anna , Takeda, Kazuo , Fujimura, Yuu , Khoshmanesh, Khashayar , Kalantar-zadeh, Kourosh , Mitchell, Arnan , Errington, Rachel , Smith, Paul , Darzynkiewicz, Zbigniew , Wlodkowic, Donald
- Date: 2013
- Type: Text , Conference paper
- Relation: Microfluidics, BioMEMS, and Medical Microsystems XI
- Full Text: false
- Reviewed:
- Description: Measurement of apoptotic markers in tumors can be directly correlated with the cell cycle phase using flow cytometry (FCM). The conventional DNA content analysis requires cell permeabilization to stain nuclei with fluorescent probes such as propidium iodide or use of a costly UV-excitation line for Hoechst 33342 probe. The access to FCM is also still limited to centralized core facilities due to its inherent high costs and complex operation. This work describes development and proof-of-concept validation of a portable and user-friendly microfluidic flow cytometer (μFCM) that can perform multivariate real time analysis on live cells using sampling volumes as small as 10 microliters. The μFCM system employs disposable microfluidic cartridges fabricated using injection molding in poly(methylmethacrylate) transparent thermoplastic. Furthermore, the dedicated and miniaturized electronic hardware interface enables up to six parameter detection using a combination of spatially separated solid-state 473 (10 mW) and 640 nm (20 mW) lasers and x-y stage for rapid laser alignment adjustment. We provide new evidence that a simple 2D flow focusing on a chip is sufficient to measure cellular DNA content in live tumor cells using a far-red DNA probe DRAQ5. The feasibility of using the μFCM system for a dose-response profiling of investigational anti-cancer agents on human hematopoietic cancer cells is also demonstrated. The data show that μFCM can provide a viable novel alternative to conventional FCM for multiparameter detection of caspase activation and dissipation of mitochondrial inner membrane potential (ΔΨm) in relation to DNA content (cell cycle phase) in live tumor cells.
- Description: Measurement of apoptotic markers in tumors can be directly correlated with the cell cycle phase using flow cytometry (FCM). The conventional DNA content analysis requires cell permeabilization to stain nuclei with fluorescent probes such as propidium iodide or use of a costly UV-excitation line for Hoechst 33342 probe. The access to FCM is also still limited to centralized core facilities due to its inherent high costs and complex operation. This work describes development and proof-of-concept validation of a portable and user-friendly microfluidic flow cytometer (
- «
- ‹
- 1
- ›
- »