PAGE-based transfer learning from single-cell to bulk sequencing enhances model generalization for sepsis diagnosis

作者：Nana Jin, Chuanchuan Nan, Wanyang Li, P. M. F. Lin, Yu Xin, Jun Wang, Yuelong Chen, Yuanhao Wang, Kaijiang Yu, Changsong Wang, Chunbo Chen, Qingshan Geng, Lixin Cheng · 发表于：Briefings in Bioinformatics · 年份：2024 · DOI：10.1093/bib/bbae661 · 被引用次数：9 · 研究领域：Sepsis Diagnosis and Treatment、Digital Imaging for Blood Diseases、Single-cell and spatial transcriptomics

Sepsis, caused by infections, sparks a dangerous bodily response. The transcriptional expression patterns of host responses aid in the diagnosis of sepsis, but the challenge lies in their limited generalization capabilities. To facilitate sepsis diagnosis, we present an updated version of single-cell Pair-wise Analysis of Gene Expression (scPAGE) using transfer learning method, scPAGE2, dedicated to data fusion between single-cell and bulk transcriptome. Compared to scPAGE, the upgrade to scPAGE2 featured ameliorated Differentially Expressed Gene Pairs (DEPs) for pretraining a model in single-cell transcriptome and retrained it using bulk transcriptome data to construct a sepsis diagnostic model, which effectively transferred cell-layer information from single-cell to bulk transcriptome. Seven datasets across three transcriptome platforms and fluorescence-activated cell sorting (FACS) were used for performance validation. The model involved four DEPs, showing robust performance across next-generation sequencing and microarray platforms, surpassing state-of-the-art models with an average AUROC of 0.947 and an average AUPRC of 0.987. Analysis of scRNA-seq data reveals higher cell proportions with JAM3-PIK3AP1 expression in sepsis monocytes, decreased ARG1-CCR7 in B and T cells. Elevated IRF6-HP in sepsis monocytes confirmed by both scRNA-seq and an independent cohort using FACS. Both the superior performance of the model and the in vitro validation of IRF6-HP in monocytes empha...