CyAnno : A semi-automated approach for cell type annotation of mass cytometry datasets
Preprint
Abstract
For immune system monitoring in large-scale studies at the single-cell resolution using CyTOF, (semi-)automated computational methods are applied for annotating live cells of mixed cell types. Here, we show that the live cell pool can be highly enriched with undefined heterogeneous cells, i.e. ‘ungated’ cells, and that current (semi-)automated approaches ignore their modeling resulting in misclassified annotations. Therefore, we introduce ‘CyAnno’, a novel semi-automated approach for deconvoluting the unlabeled cytometry dataset based on a machine learning framework utilizing manually gated training data that allows the integrative modeling of ‘gated’ cell types and the ‘ungated’ cells. By applying this framework on several CyTOF datasets, we demonstrated that including the ‘ungated’ cells can lead to a significant increase in the prediction accuracy of the ‘gated’ cell types. CyAnno can be used to identify even a single cell type, including rare cells, with higher efficacy than current state-of-the-art semi-automated approaches.Keywords
All Related Versions
- Published version: Bioinformatics, 37 (22), 4164.
This publication has 25 references indexed in Scilit:
- Automated cell type discovery and classification through knowledge transferBioinformatics, 2017
- Comparison of clustering methods for high‐dimensional single‐cell flow and mass cytometry dataCytometry Part A, 2016
- XGBoost2016
- Automated mapping of phenotype space with single-cell dataNature Methods, 2016
- Flow cytometry: basic principles and applicationsCritical Reviews in Biotechnology, 2016
- The end of gating? An introduction to automated analysis of high dimensional cytometry dataEuropean Journal of Immunology, 2015
- Immune monitoring technology primer: flow and mass cytometryJournal for ImmunoTherapy of Cancer, 2015
- Data-Driven Phenotypic Dissection of AML Reveals Progenitor-like Cells that Correlate with PrognosisCell, 2015
- Mass Cytometry: Technique for Real Time Single Cell Multitarget Immunoassay Based on Inductively Coupled Plasma Time-of-Flight Mass SpectrometryAnalytical Chemistry, 2009
- Learning representations by back-propagating errorsNature, 1986