Classification of PBMC cell types using scRNAseq, ANN, and incremental learning

Single cell transcriptomics (SCT) technology reveals gene expression of individual cells. Peripheral blood mononuclear cells (PBMC) are important diagnostic targets in immunology. In this study, we obtained and standardized 27 SCT data sets, derived from healthy PBMC samples using 10x SCT. We used artificial neural networks (ANN) to assess the ability of ANN to classify main PBMC cell types. Incremental learning by the gradual addition of new data sets to ANN training improved classification. The overall prediction accuracy of the final step of incremental learning reached 93% in 4-class classification.

[1]  Stephanie C. Hicks,et al.  A systematic evaluation of single-cell RNA-sequencing imputation methods , 2020, Genome Biology.

[2]  Lubomir T. Chitkushev,et al.  Single-cell mRNA Profiles in PBMC , 2020, 2020 IEEE International Conference on Bioinformatics and Biomedicine (BIBM).

[3]  C. Slingluff,et al.  Shipping blood to a central laboratory in multicenter clinical trials: effect of ambient temperature on specimen temperature, and effects of temperature on mononuclear cell yield, viability and immunologic function , 2011, Journal of Translational Medicine.

[4]  Fabian J Theis,et al.  Current best practices in single‐cell RNA‐seq analysis: a tutorial , 2019, Molecular systems biology.

[5]  Alexey M. Kozlov,et al.  Eleven grand challenges in single-cell data science , 2020, Genome Biology.

[6]  Ashwinikumar Kulkarni,et al.  Beyond bulk: a review of single cell transcriptomics methodologies and applications. , 2019, Current opinion in biotechnology.

[7]  Danna Zhou,et al.  d. , 1934, Microbial pathogenesis.

[8]  Grace X. Y. Zheng,et al.  Massively parallel digital transcriptional profiling of single cells , 2016, Nature Communications.

[9]  Vladimir Brusic,et al.  Classification of Five Cell Types from PBMC Samples using Single Cell Transcriptomics and Artificial Neural Networks , 2019, 2019 IEEE International Conference on Bioinformatics and Biomedicine (BIBM).

[10]  Aviv Regev,et al.  Systematic comparison of single-cell and single-nucleus RNA-sequencing methods , 2020, Nature Biotechnology.

[11]  Joanne Lannigan,et al.  Does FACS perturb gene expression? , 2015, Cytometry. Part A : the journal of the International Society for Analytical Cytology.

[12]  A. Herbelin,et al.  Phenotype of NK-Like CD8(+) T Cells with Innate Features in Humans and Their Relevance in Cancer Diseases , 2017, Front. Immunol..

[13]  Tanya Barrett,et al.  The Gene Expression Omnibus Database , 2016, Statistical Genomics.

[14]  S. Teichmann,et al.  Exponential scaling of single-cell RNA-seq in the past decade , 2017, Nature Protocols.

[15]  Yongmei Huang,et al.  The single-cell sequencing: new developments and medical applications , 2019, Cell & Bioscience.

[16]  C. Kleiveland,et al.  Peripheral Blood Mononuclear Cells , 2015 .

[17]  Nuno A. Fonseca,et al.  Expression Atlas update—an integrated database of gene and protein expression in humans, animals and plants , 2015, Nucleic Acids Res..

[18]  Xianwen Ren,et al.  Direct Comparative Analyses of 10X Genomics Chromium and Smart-seq2 , 2019, bioRxiv.