Development of constrictional microchannels and the recurrent neural network in single-cell protein analysis
Introduction: As the golden approach of single-cell analysis, fluorescent flow cytometry can estimate single-cell proteins with high throughputs, which, however, cannot translate fluorescent intensities into protein numbers.Methods: This study reported a fluorescent flow cytometry based on constrict...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2023-05-01
|
| Series: | Frontiers in Bioengineering and Biotechnology |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fbioe.2023.1195940/full |
| _version_ | 1797834411913248768 |
|---|---|
| author | Ting Zhang Ting Zhang Xiao Chen Xiao Chen Deyong Chen Deyong Chen Deyong Chen Junbo Wang Junbo Wang Junbo Wang Jian Chen Jian Chen Jian Chen |
| author_facet | Ting Zhang Ting Zhang Xiao Chen Xiao Chen Deyong Chen Deyong Chen Deyong Chen Junbo Wang Junbo Wang Junbo Wang Jian Chen Jian Chen Jian Chen |
| author_sort | Ting Zhang |
| collection | DOAJ |
| description | Introduction: As the golden approach of single-cell analysis, fluorescent flow cytometry can estimate single-cell proteins with high throughputs, which, however, cannot translate fluorescent intensities into protein numbers.Methods: This study reported a fluorescent flow cytometry based on constrictional microchannels for quantitative measurements of single-cell fluorescent levels and the recurrent neural network for data analysis of fluorescent profiles for high-accuracy cell-type classification.Results: As a demonstration, fluorescent profiles (e.g., FITC labeled β-actin antibody, PE labeled EpCAM antibody and PerCP labeled β-tubulin antibody) of individual A549 and CAL 27 cells were firstly measured and translated into protein numbers of 0.56 ± 0.43 × 104, 1.78 ± 1.06 × 106 and 8.11 ± 4.89 × 104 of A549 cells (ncell = 10232), and 3.47 ± 2.45 × 104, 2.65 ± 1.19 × 106 and 8.61 ± 5.25 × 104 of CAL 27 cells (ncell = 16376) based on the equivalent model of the constrictional microchannel. Then, the feedforward neural network was used to process these single-cell protein expressions, producing a classification accuracy of 92.0% for A549 vs. CAL 27 cells. In order to further increase the classification accuracies, as a key subtype of the recurrent neural network, the long short-term memory (LSTM) neural network was adopted to process fluorescent pulses sampled in constrictional microchannels directly, producing a classification accuracy of 95.5% for A549 vs. CAL 27 cells after optimization.Discussion: This fluorescent flow cytometry based on constrictional microchannels and recurrent neural network can function as an enabling tool of single-cell analysis and contribute to the development of quantitative cell biology. |
| first_indexed | 2024-04-09T14:37:32Z |
| format | Article |
| id | doaj.art-fcbc388aab864400b6f6e5b2eb55554e |
| institution | Directory Open Access Journal |
| issn | 2296-4185 |
| language | English |
| last_indexed | 2024-04-09T14:37:32Z |
| publishDate | 2023-05-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Bioengineering and Biotechnology |
| spelling | doaj.art-fcbc388aab864400b6f6e5b2eb55554e2023-05-03T12:23:53ZengFrontiers Media S.A.Frontiers in Bioengineering and Biotechnology2296-41852023-05-011110.3389/fbioe.2023.11959401195940Development of constrictional microchannels and the recurrent neural network in single-cell protein analysisTing Zhang0Ting Zhang1Xiao Chen2Xiao Chen3Deyong Chen4Deyong Chen5Deyong Chen6Junbo Wang7Junbo Wang8Junbo Wang9Jian Chen10Jian Chen11Jian Chen12State Key Laboratory of Transducer Technology, Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing, ChinaSchool of Future Technology, University of Chinese Academy of Sciences, Beijing, ChinaState Key Laboratory of Transducer Technology, Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing, ChinaSchool of Future Technology, University of Chinese Academy of Sciences, Beijing, ChinaState Key Laboratory of Transducer Technology, Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing, ChinaSchool of Future Technology, University of Chinese Academy of Sciences, Beijing, ChinaSchool of Electronic, Electrical and Communication Engineering, University of Chinese Academy of Sciences, Beijing, ChinaState Key Laboratory of Transducer Technology, Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing, ChinaSchool of Future Technology, University of Chinese Academy of Sciences, Beijing, ChinaSchool of Electronic, Electrical and Communication Engineering, University of Chinese Academy of Sciences, Beijing, ChinaState Key Laboratory of Transducer Technology, Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing, ChinaSchool of Future Technology, University of Chinese Academy of Sciences, Beijing, ChinaSchool of Electronic, Electrical and Communication Engineering, University of Chinese Academy of Sciences, Beijing, ChinaIntroduction: As the golden approach of single-cell analysis, fluorescent flow cytometry can estimate single-cell proteins with high throughputs, which, however, cannot translate fluorescent intensities into protein numbers.Methods: This study reported a fluorescent flow cytometry based on constrictional microchannels for quantitative measurements of single-cell fluorescent levels and the recurrent neural network for data analysis of fluorescent profiles for high-accuracy cell-type classification.Results: As a demonstration, fluorescent profiles (e.g., FITC labeled β-actin antibody, PE labeled EpCAM antibody and PerCP labeled β-tubulin antibody) of individual A549 and CAL 27 cells were firstly measured and translated into protein numbers of 0.56 ± 0.43 × 104, 1.78 ± 1.06 × 106 and 8.11 ± 4.89 × 104 of A549 cells (ncell = 10232), and 3.47 ± 2.45 × 104, 2.65 ± 1.19 × 106 and 8.61 ± 5.25 × 104 of CAL 27 cells (ncell = 16376) based on the equivalent model of the constrictional microchannel. Then, the feedforward neural network was used to process these single-cell protein expressions, producing a classification accuracy of 92.0% for A549 vs. CAL 27 cells. In order to further increase the classification accuracies, as a key subtype of the recurrent neural network, the long short-term memory (LSTM) neural network was adopted to process fluorescent pulses sampled in constrictional microchannels directly, producing a classification accuracy of 95.5% for A549 vs. CAL 27 cells after optimization.Discussion: This fluorescent flow cytometry based on constrictional microchannels and recurrent neural network can function as an enabling tool of single-cell analysis and contribute to the development of quantitative cell biology.https://www.frontiersin.org/articles/10.3389/fbioe.2023.1195940/fullbiosensorssingle-cell proteomic analysisquantitative flow cytometryconstrictional microchannelrecurrent neural network |
| spellingShingle | Ting Zhang Ting Zhang Xiao Chen Xiao Chen Deyong Chen Deyong Chen Deyong Chen Junbo Wang Junbo Wang Junbo Wang Jian Chen Jian Chen Jian Chen Development of constrictional microchannels and the recurrent neural network in single-cell protein analysis Frontiers in Bioengineering and Biotechnology biosensors single-cell proteomic analysis quantitative flow cytometry constrictional microchannel recurrent neural network |
| title | Development of constrictional microchannels and the recurrent neural network in single-cell protein analysis |
| title_full | Development of constrictional microchannels and the recurrent neural network in single-cell protein analysis |
| title_fullStr | Development of constrictional microchannels and the recurrent neural network in single-cell protein analysis |
| title_full_unstemmed | Development of constrictional microchannels and the recurrent neural network in single-cell protein analysis |
| title_short | Development of constrictional microchannels and the recurrent neural network in single-cell protein analysis |
| title_sort | development of constrictional microchannels and the recurrent neural network in single cell protein analysis |
| topic | biosensors single-cell proteomic analysis quantitative flow cytometry constrictional microchannel recurrent neural network |
| url | https://www.frontiersin.org/articles/10.3389/fbioe.2023.1195940/full |
| work_keys_str_mv | AT tingzhang developmentofconstrictionalmicrochannelsandtherecurrentneuralnetworkinsinglecellproteinanalysis AT tingzhang developmentofconstrictionalmicrochannelsandtherecurrentneuralnetworkinsinglecellproteinanalysis AT xiaochen developmentofconstrictionalmicrochannelsandtherecurrentneuralnetworkinsinglecellproteinanalysis AT xiaochen developmentofconstrictionalmicrochannelsandtherecurrentneuralnetworkinsinglecellproteinanalysis AT deyongchen developmentofconstrictionalmicrochannelsandtherecurrentneuralnetworkinsinglecellproteinanalysis AT deyongchen developmentofconstrictionalmicrochannelsandtherecurrentneuralnetworkinsinglecellproteinanalysis AT deyongchen developmentofconstrictionalmicrochannelsandtherecurrentneuralnetworkinsinglecellproteinanalysis AT junbowang developmentofconstrictionalmicrochannelsandtherecurrentneuralnetworkinsinglecellproteinanalysis AT junbowang developmentofconstrictionalmicrochannelsandtherecurrentneuralnetworkinsinglecellproteinanalysis AT junbowang developmentofconstrictionalmicrochannelsandtherecurrentneuralnetworkinsinglecellproteinanalysis AT jianchen developmentofconstrictionalmicrochannelsandtherecurrentneuralnetworkinsinglecellproteinanalysis AT jianchen developmentofconstrictionalmicrochannelsandtherecurrentneuralnetworkinsinglecellproteinanalysis AT jianchen developmentofconstrictionalmicrochannelsandtherecurrentneuralnetworkinsinglecellproteinanalysis |