# Integration of unpaired and heterogeneous clinical flow cytometry data

## TL;DR

UVAE is a new method that integrates diverse flow cytometry data from clinical samples to improve analysis and predictions in diseases like COVID-19.

## Contribution

UVAE introduces a semi-supervised variational autoencoder framework for integrating unpaired biomedical data while correcting batch effects and rebalancing cell-type proportions.

## Key findings

- UVAE enables integration of heterogeneous clinical flow cytometry data from multiple panels.
- The model improves downstream prediction tasks by reducing batch effects and enhancing statistical signals of disease-related cell types.
- UVAE effectively handles changes in panel designs during studies and improves longitudinal disease severity predictions.

## Abstract

We introduce the Unbiasing Variational Autoencoder (UVAE), a computational framework for the integration of unpaired biomedical data streams such as clinical flow cytometry. UVAE addresses batch effect correction and data alignment by training a semi-supervised model on partially labeled datasets, enabling simultaneous normalization and integration of diverse data within a shared latent space. The framework implements a probabilistic model for batch effect normalization and balances class contents during training to ensure accurate representation of underlying cell composition. We apply UVAE to integrate heterogeneous clinical flow cytometry data from COVID-19 patients. The integrated data enhances the statistical signal of cell types associated with disease severity, enables clustering of subpopulations without the impediment of batch effects, and improves the performance of longitudinal regression for predicting peak disease severity from temporal patient samples.

•UVAE integrates data from multiple flow cytometry panels collected from clinical samples•UVAE deals effectively with changes to panel designs during study•Data rebalancing during batch correction controls for differences in cell-type proportions•Model-imputed data improves downstream prediction tasks

UVAE integrates data from multiple flow cytometry panels collected from clinical samples

UVAE deals effectively with changes to panel designs during study

Data rebalancing during batch correction controls for differences in cell-type proportions

Model-imputed data improves downstream prediction tasks

Biocomputational method; Bioinformatics