A statistical framework for disease classification with scRNA-Seq Data.

Motivation: Bulk RNA-sequencing based disease classification obscures cell-type specific signals by aggregating gene expression across heterogeneous tissues. Although single-cell RNA-seq tackles this limitation, summarizing and deriving patient-level predictors while retaining biological interpretability remains challenging. Standard sparse methods, such as lasso, often select arbitrary scattered gene sets without leveraging the underlying cell type structures revealed by single-cell data. Results: We introduce a two-stage statistical framework for interpretable patient-level disease classification from single-cell data. We first construct a gene-by-cell-type pseudobulk matrix that summarize single-cell expression for each patient. We then fit a multinomial logistic regression model with sparse group lasso penalty, inducing sparsity at both the cell type and gene levels. Across datasets of systemic lupus erythematosus, COVID-19, and colorectal cancer, our framework either matched or outperformed lasso and random forest baselines. Importantly, our models recovered biologically coherent, cell-type specific gene signatures consistent with known disease mechanisms, demonstrating improved interpretability without sacrificing predictive accuracy. Availability: The scSGL R package implementing the Sparse Group Lasso classification frame-work described in this paper is available at https://github.com/zhiweixiao/scSGL (version 0.99.1). Code to reproduce the actual cross-validation, model fitting, and prediction analyses on the three datasets reported here is available at https://github.com/zhiweixiao/scSGL-manuscript.