Classification of Five Cell Types from PBMC Samples using Single Cell Transcriptomics and Artificial Neural Networks

Razin Abdulrauf Shaikh, Jiahui Zhong, Minjie Lyu, Sen Lin, Derin Keskin, Guanglan Zhang, Lou Chitkushev, Vladimir Brusic

Research output: Chapter in Book/Report/Conference proceedingConference contribution

7 Citations (Scopus)

Abstract

We used 27 human single cell transcriptomics (SCT) data sets to develop an artificial neural network (ANN) model for classification of Peripheral Blood Mononuclear Cells (PBMC). We demonstrated that highly accurate models for the classification of PBMC subtypes can be developed by combining multiple independent data sets to form training data sets. A significant data preparation effort was needed for building predictive models. Using a data set of ∼120,000 single cell instances we showed the accuracy of classification of PBMC call of ∼ 90%. Optimization techniques and the addition of new high-quality data sets for model training are expected to improve PBMC subtype classification accuracy.

Original languageEnglish
Title of host publicationProceedings - 2019 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2019
EditorsIllhoi Yoo, Jinbo Bi, Xiaohua Tony Hu
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages2207-2213
Number of pages7
ISBN (Electronic)9781728118673
DOIs
Publication statusPublished - Nov 2019
Externally publishedYes
Event2019 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2019 - San Diego, United States
Duration: Nov 18 2019Nov 21 2019

Publication series

NameProceedings - 2019 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2019

Conference

Conference2019 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2019
CountryUnited States
CitySan Diego
Period11/18/1911/21/19

Keywords

  • ANN
  • Machine Learning
  • PBMC
  • incremental learning
  • scRNAseq

ASJC Scopus subject areas

  • Biochemistry
  • Biotechnology
  • Molecular Medicine
  • Modelling and Simulation
  • Health Informatics
  • Pharmacology (medical)
  • Public Health, Environmental and Occupational Health

Fingerprint Dive into the research topics of 'Classification of Five Cell Types from PBMC Samples using Single Cell Transcriptomics and Artificial Neural Networks'. Together they form a unique fingerprint.

Cite this