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

Research output: Contribution to conferencePaper

5 Citations (Scopus)
4 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 languageEnglish
Pages1253-1257
DOIs
Publication statusPublished Online - 13 Jan 2021
Event2020 IEEE International Conference on Bioinformatics and Biomedicine (BIBM) - Seoul, Korea (South)
Duration: 16 Dec 202019 Dec 2020

Conference

Conference2020 IEEE International Conference on Bioinformatics and Biomedicine (BIBM)
Period16/12/2019/12/20

Keywords

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

Fingerprint

Dive into the research topics of 'Artificial neural network system for cell classification using single cell RNA expression'. Together they form a unique fingerprint.

Cite this