生物信息学2025，Vol.23Issue(1)：40-49,10.DOI:10.12113/202311005
基于迁移学习的空间转录组数据解卷积算法
A deconvolution algorithm based on transfer learning for spatial transcriptomics
陈子睿 1杨博然 1何田韵 1李建 2周光华3
作者信息
- 1. 哈尔滨工业大学 数学学院,哈尔滨 150001
- 2. 成都医学院,成都 610500
- 3. 国家卫生健康委统计信息中心,北京 100044
- 折叠
摘要
Abstract
Spatial transcriptomics sequencing technology captures spatial location information of multiple cells,but single-cell resolution cannot be achieved,which hampers the analysis of spatial patterns of cell type heterogeneity and gene expression specificity.The cell type deconvolution algorithm(STDN)based on DenseNet network structure and CORAL domain adaptive theory is proposed for spatial transcriptomics data.STDN learns cell type information about introduced single-cell RNA sequencing(scRNA-seq)data and migrates it to ST data using a transfer learning model.Thus,the purpose of predicting the cell type composition and proportion of each capture site(Spot)in the ST data is achieved.In this paper,four factual scRNA-seq datasets and simulated matching ST datasets show that STDN can effectively recover cell type transcription profiles and their proportions in Spots,and is superior to other deconvolution algorithms.By deconvolution of ST data from mouse hippocampus and human pancreatic ductal adenocarcinoma,STDN identifies multiple cell types in tissues,resolves the high heterogeneity of tissues and cancers,and laid a foundation for studying the pathogenesis of the disease.关键词
空间转录组数据/解卷积/DenseNet/CORALKey words
Spatial transcriptomics data/Deconvolution/DenseNet/CORAL分类
数学引用本文复制引用
陈子睿,杨博然,何田韵,李建,周光华..基于迁移学习的空间转录组数据解卷积算法[J].生物信息学,2025,23(1):40-49,10.
