Joint Analysis of Single-Cell Data across Cohorts with Missing Modalities

TL;DR

This paper introduces a novel framework for integrating multi-omic single-cell data across cohorts that can handle missing modalities without requiring complete samples, improving analysis tasks like clustering and classification.

Contribution

The proposed framework learns unified cell representations across domains and modalities, enabling imputation and analysis without full-modality reference samples.

Findings

Effective in imputing missing modalities in real-world datasets

Improves cell type clustering and classification accuracy

Provides a robust solution for cross-cohort single-cell analysis

Abstract

Joint analysis of multi-omic single-cell data across cohorts has significantly enhanced the comprehensive analysis of cellular processes. However, most of the existing approaches for this purpose require access to samples with complete modality availability, which is impractical in many real-world scenarios. In this paper, we propose (Single-Cell Cross-Cohort Cross-Category) integration, a novel framework that learns unified cell representations under domain shift without requiring full-modality reference samples. Our generative approach learns rich cross-modal and cross-domain relationships that enable imputation of these missing modalities. Through experiments on real-world multi-omic datasets, we demonstrate that offers a robust solution to single-cell tasks such as cell type clustering, cell type classification, and feature imputation.