Artificial neural network system for cell classification using single cell RNA expression

Xin Lin; Jiahui Zhong; Minjie Lyu; Sen Lin; Derin B. Keskin; Guanglan Zhang; Vladimir Brusic; Lou T. Chitkushev

doi:10.1109/BIBM49941.2020.9313498

Artificial neural network system for cell classification using single cell RNA expression

Xin Lin, Jiahui Zhong, Minjie Lyu, Sen Lin, Derin B. Keskin, Guanglan Zhang, Vladimir Brusic, Lou T. Chitkushev

School of Computer Science

Research output: Contribution to conference › Paper

7 Citations (Scopus)

38 Downloads (Pure)

Abstract

We implemented an automated system for single-cell classification using artificial neural networks (ANN). Our system takes single-cell gene expression sparse matrices and trains ANN to classify cell types and subtypes. The assemblies of ANNs predict cell classes by voting. We tested the system in a case study where we trained ANNs with a dataset containing approximately 120,000 single cells and tested the resulting model using an independent data set of 13,000 single cells. The overall accuracy of the 5-class classification was 95%. We trained and tested a total of 100 ANNs in 10 cycles. The prediction system demonstrated excellent reproducibility. The analysis of misclassifications indicated that 2% were likely classification errors, while the remaining 3% were likely due to mislabeled types and subtypes in the test set.

Original language	English
Pages	1253-1257
DOIs	https://doi.org/10.1109/BIBM49941.2020.9313498
Publication status	Published Online - 13 Jan 2021
Event	2020 IEEE International Conference on Bioinformatics and Biomedicine (BIBM) - Seoul, Korea (South) Duration: 16 Dec 2020 → 19 Dec 2020

Conference

Conference	2020 IEEE International Conference on Bioinformatics and Biomedicine (BIBM)
Period	16/12/20 → 19/12/20

Keywords

ANN, automation of cell classification, gene expression, PBMC, prediction system, supervised machine learning

Access to Document

10.1109/BIBM49941.2020.9313498

Xin-BIBM-2020-camerareadyFinal published version, 893 KBLicence: CC BY

http://dx.doi.org/10.1109/BIBM49941.2020.9313498

Cite this

Lin, X., Zhong, J., Lyu, M., Lin, S., Keskin, D. B., Zhang, G., Brusic, V., & Chitkushev, L. T. (2021). Artificial neural network system for cell classification using single cell RNA expression. 1253-1257. Paper presented at 2020 IEEE International Conference on Bioinformatics and Biomedicine (BIBM). Advance online publication. https://doi.org/10.1109/BIBM49941.2020.9313498

@conference{b2c9c2b228d04d3ab4034ea286df7b99,

title = "Artificial neural network system for cell classification using single cell RNA expression",

abstract = "We implemented an automated system for single-cell classification using artificial neural networks (ANN). Our system takes single-cell gene expression sparse matrices and trains ANN to classify cell types and subtypes. The assemblies of ANNs predict cell classes by voting. We tested the system in a case study where we trained ANNs with a dataset containing approximately 120,000 single cells and tested the resulting model using an independent data set of 13,000 single cells. The overall accuracy of the 5-class classification was 95%. We trained and tested a total of 100 ANNs in 10 cycles. The prediction system demonstrated excellent reproducibility. The analysis of misclassifications indicated that 2% were likely classification errors, while the remaining 3% were likely due to mislabeled types and subtypes in the test set.",

keywords = "ANN, automation of cell classification, gene expression, PBMC, prediction system, supervised machine learning, ANN, automation of cell classification, gene expression, PBMC, prediction system, supervised machine learning",

author = "Xin Lin and Jiahui Zhong and Minjie Lyu and Sen Lin and Keskin, {Derin B.} and Guanglan Zhang and Vladimir Brusic and Chitkushev, {Lou T.}",

year = "2021",

month = jan,

day = "13",

doi = "10.1109/BIBM49941.2020.9313498",

language = "English",

pages = "1253--1257",

note = "2020 IEEE International Conference on Bioinformatics and Biomedicine (BIBM) ; Conference date: 16-12-2020 Through 19-12-2020",

}

TY - CONF

T1 - Artificial neural network system for cell classification using single cell RNA expression

AU - Lin, Xin

AU - Zhong, Jiahui

AU - Lyu, Minjie

AU - Lin, Sen

AU - Keskin, Derin B.

AU - Zhang, Guanglan

AU - Brusic, Vladimir

AU - Chitkushev, Lou T.

PY - 2021/1/13

Y1 - 2021/1/13

N2 - We implemented an automated system for single-cell classification using artificial neural networks (ANN). Our system takes single-cell gene expression sparse matrices and trains ANN to classify cell types and subtypes. The assemblies of ANNs predict cell classes by voting. We tested the system in a case study where we trained ANNs with a dataset containing approximately 120,000 single cells and tested the resulting model using an independent data set of 13,000 single cells. The overall accuracy of the 5-class classification was 95%. We trained and tested a total of 100 ANNs in 10 cycles. The prediction system demonstrated excellent reproducibility. The analysis of misclassifications indicated that 2% were likely classification errors, while the remaining 3% were likely due to mislabeled types and subtypes in the test set.

AB - We implemented an automated system for single-cell classification using artificial neural networks (ANN). Our system takes single-cell gene expression sparse matrices and trains ANN to classify cell types and subtypes. The assemblies of ANNs predict cell classes by voting. We tested the system in a case study where we trained ANNs with a dataset containing approximately 120,000 single cells and tested the resulting model using an independent data set of 13,000 single cells. The overall accuracy of the 5-class classification was 95%. We trained and tested a total of 100 ANNs in 10 cycles. The prediction system demonstrated excellent reproducibility. The analysis of misclassifications indicated that 2% were likely classification errors, while the remaining 3% were likely due to mislabeled types and subtypes in the test set.

KW - ANN, automation of cell classification, gene expression, PBMC, prediction system, supervised machine learning

U2 - 10.1109/BIBM49941.2020.9313498

DO - 10.1109/BIBM49941.2020.9313498

M3 - Paper

SP - 1253

EP - 1257

T2 - 2020 IEEE International Conference on Bioinformatics and Biomedicine (BIBM)

Y2 - 16 December 2020 through 19 December 2020

ER -

Artificial neural network system for cell classification using single cell RNA expression

Abstract

Conference

Keywords

Access to Document

Fingerprint

Cite this