Inferring disease progressive stages in single-cell transcriptomics using a weakly-supervised deep learning approach

Abstract

Application of single-cell/nucleus genomic sequencing to patient-derived tissues offers potential solutions to delineate disease mechanisms in human. However, individual cells in patient-derived tissues are in different pathological stages, and hence such cellular variability impedes subsequent differential gene expression analyses. To overcome such heterogeneity issue, we present a novel deep learning approach, scIDST, that infers disease progressive levels of individual cells with weak supervision framework. The inferred disease progressive cells displayed significant differential expression of disease-relevant genes, which could not be detected by comparative analysis between patients and healthy donors. In addition, we demonstrated that pretrained models by scIDST are applicable to multiple independent data resources, and advantageous to infer cells related to certain disease risks and comorbidities. Taken together, scIDST offers a new strategy of single-cell sequencing analysis to identify bona fide disease-associated molecular features.