scHILL: deciphering individual-level immune cell heterogeneity with single-cell RNA sequencing data.

Abstract

Deep learning frameworks have been developed for interpreting single-cell RNA sequencing (scRNA-seq) data and have demonstrated excellent performance across a range of tasks. However, existing methods remain limited in their ability to characterize heterogeneity at the individual level. To address this gap, we present scHILL, a framework that integrates a masked autoencoder (MAE) with a multilayer perceptron (MLP) to decipher phenotypic heterogeneity arises from immune cell heterogeneity among individuals under specific disease conditions. The MAE, pretrained with data augmentation, enables self-supervised feature learning without labels and effectively mitigates the challenge of limited sample size. The MLP further generates a score for each individual to quantify the functional significance of cells and genes. Across multiple datasets, scHILL outperforms existing methods in phenotype prediction and reveals individual-level immune cell heterogeneity in infectious disease, autoimmune disease, and cancer. scHILL provides a generalizable framework for interpreting individual-level scRNA-seq data, thereby facilitating the future realization of personalized medicine.