Automated cell type annotation and exploration of single-cell signaling dynamics using mass cytometry

TL;DR

This paper introduces a new bioinformatics framework for analyzing CyTOF data, enabling automated cell type annotation and predicting patient survival in leukemia using machine learning.

Contribution

The Scaffold framework automates cell type annotation and uses signaling dynamics to improve patient stratification in CyTOF data.

Findings

Scaffold achieves a good balance between sensitivity and specificity for automated cell type annotation.

Signaling protein interactions predicted short-term survival in leukemia patients using XGBoost.

CyTOF data analysis with machine learning improves standard risk-stratification methods.

Abstract

Mass cytometry by time-of-flight (CyTOF) is an emerging technology allowing for in-depth characterization of cellular heterogeneity in cancer and other diseases. Unfortunately, high-dimensional analyses of CyTOF data remain quite demanding. Here, we deploy a bioinformatics framework that tackles two fundamental problems in CyTOF analyses namely (1) automated annotation of cell populations guided by a reference dataset and (2) systematic utilization of single-cell data for effective patient stratification. By applying this framework on several publicly available datasets, we demonstrate that the Scaffold approach achieves good trade-off between sensitivity and specificity for automated cell type annotation. Additionally, a case study focusing on a cohort of 43 leukemia patients reported salient interactions between signaling proteins that are sufficient to predict short-term survival at time of diagnosis using the XGBoost algorithm. Our work introduces an automated and versatile analysis framework for CyTOF data with many applications in future precision medicine projects.

•The Scaffold facilitates automated cell type annotation guided by a reference dataset•DREMI scores and the XGBoost algorithm predict survival in patients with leukemia•Signaling dynamics measured with CyTOF enhance standard risk-stratification methods•Potential to dissect rich single-cell data from CyTOF with machine learning

The Scaffold facilitates automated cell type annotation guided by a reference dataset

DREMI scores and the XGBoost algorithm predict survival in patients with leukemia

Signaling dynamics measured with CyTOF enhance standard risk-stratification methods

Potential to dissect rich single-cell data from CyTOF with machine learning

Bioinformatics; Cancer; Machine learning

Figures