Multiparameter phenotyping of platelets and characterization of the effects of agonists using machine learning.

Researchers

Journal

Modalities

Models

Abstract

Platelet function is driven by the expression of specialized surface markers. The concept of distinct circulating subpopulations of platelets has emerged in recent years, but their exact nature remains debatable.To design a spectral flow cytometry-based phenotyping workflow to provide a more comprehensive characterization, at a global and individual level, of surface markers in resting and activated healthy platelets, and to apply this workflow to investigate how responses differ according to platelet age.A 14-marker flow cytometry panel was developed and applied to vehicle- or agonist-stimulated platelet-rich plasma and whole blood samples obtained from healthy volunteers, or to platelets sorted according to SYTO-13 (Thermo Fisher Scientific) staining intensity as an indicator of platelet age. Data were analyzed using both user-led and independent approaches incorporating novel machine learning-based algorithms.The assay detected differences in marker expression in healthy platelets, at rest and on agonist activation, in both platelet-rich plasma and whole blood samples, that are consistent with the literature. Machine learning identified stimulated populations of platelets with high accuracy (>80%). Similarly, machine learning differentiation between young and old platelet populations achieved 76% accuracy, primarily weighted by forward scatter, cluster of differentiation (CD) 41, side scatter, glycoprotein VI, CD61, and CD42b expression patterns.Our approach provides a powerful phenotypic assay coupled with robust bioinformatic and machine learning workflows for deep analysis of platelet subpopulations. Cleavable receptors, glycoprotein VI and CD42b, contribute to defining shared and unique subpopulations. This adoptable, low-volume approach will be valuable in deep characterization of platelets in disease.© 2024 The Author(s).