Accurate, fast and memory efficient quantification of immune cell phenotypes in cytometry using machine learning
Preprint
Abstract
To achieve accurate and reproducible cytometry data analysis, we benchmarked 19 machine learning algorithms for supervised and unsupervised cell classification. The underlying data encompassed 138 million cells from seven independent datasets including conventional flow cytometry, spectral flow cytometry and mass cytometry. We found that tree-based classifiers and in particular Decision Trees, outperformed other approaches in classification accuracy, speed and memory use. High accuracy was achieved even for cell populations rarer than 1% using decision trees. We validated our decision tree-based approach in a clinical setting using diagnostic blood T cell phenotyping of 107 patients. Automatic quantification of CD4 helper T cell phenotypes achieved 99 % accuracy compared to manual expert assessment. Finally, we combined automated data transformation, supervised and unsupervised gating, an application program interface and a user-friendly desktop-application into FACSPy and FACSPyUI, a fast and scalable open-source toolbox for the analysis and visualization of cytometry data.Keywords
This publication has 30 references indexed in Scilit:
- Transformation of multicolour flow cytometry data with OTflow prevents misleading multivariate analysis results and incorrect immunological conclusionsCytometry Part A, 2021
- Current trends in flow cytometry automated data analysis softwareCytometry Part A, 2021
- OMIP‐069: Forty‐Color Full Spectrum Flow Cytometry Panel for Deep Immunophenotyping of Major Cell Subsets in Human Peripheral BloodCytometry Part A, 2020
- CytoNorm: A Normalization Algorithm for Cytometry DataCytometry Part A, 2019
- Dimensionality reduction for visualizing single-cell data using UMAPNature Biotechnology, 2018
- A benchmark for evaluation of algorithms for identification of cellular correlates of clinical outcomesCytometry Part A, 2015
- Data-Driven Phenotypic Dissection of AML Reveals Progenitor-like Cells that Correlate with PrognosisCell, 2015
- FlowSOM: Using self‐organizing maps for visualization and interpretation of cytometry dataCytometry Part A, 2015
- viSNE enables visualization of high dimensional single-cell data and reveals phenotypic heterogeneity of leukemiaNature Biotechnology, 2013
- Critical assessment of automated flow cytometry data analysis techniquesNature Methods, 2013