Integration of unpaired single cell omics data by deep transfer graph convolutional network

Yulong Kan, Yunjing Qi, Zhongxiao Zhang, Xikeng Liang, Weihao Wang and Shuilin Jin

PLOS Computational Biology, 2025, vol. 21, issue 1, 1-21

Abstract: The rapid advance of large-scale atlas-level single cell RNA sequences and single-cell chromatin accessibility data provide extraordinary avenues to broad and deep insight into complex biological mechanism. Leveraging the datasets and transfering labels from scRNA-seq to scATAC-seq will empower the exploration of single-cell omics data. However, the current label transfer methods have limited performance, largely due to the lower capable of preserving fine-grained cell populations and intrinsic or extrinsic heterogeneity between datasets. Here, we present a robust deep transfer model based graph convolutional network, scTGCN, which achieves versatile performance in preserving biological variation, while achieving integration hundreds of thousands cells in minutes with low memory consumption. We show that scTGCN is powerful to the integration of mouse atlas data and multimodal data generated from APSA-seq and CITE-seq. Thus, scTGCN shows high label transfer accuracy and effectively knowledge transfer across different modalities.Author summary: Single-cell omics technologies have significantly advanced our ability to study biological systems at an unprecedented resolution and scale. However, integrating the multimodal single-cell data that emerges from these technologies—such as finding cell-to-cell correspondences, gene-peak relationships, and conducting cell pseudotime analysis—remains a complex challenge. Alongside the advancements in single-cell technologies, deep learning (DL), a revolutionary development in artificial intelligence, has transformed our capacity to analyze large-scale data through sophisticated neural network architectures. The efficacy of DL was recently showcased by AlphaFold2’s success in predicting protein structures. In response to these challenges, we propose a flexible deep transfer learning model for the comprehensive analysis of unpaired single-cell multiomics data. Our method not only integrates scRNA-seq and scATAC-seq data but also refines and provides new annotations through this integrated analysis.

Date: 2025
References: Add references at CitEc
Citations:

Downloads: (external link)
https://journals.plos.org/ploscompbiol/article?id=10.1371/journal.pcbi.1012625 (text/html)
https://journals.plos.org/ploscompbiol/article/fil ... 12625&type=printable (application/pdf)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:plo:pcbi00:1012625

DOI: 10.1371/journal.pcbi.1012625

Access Statistics for this article

More articles in PLOS Computational Biology from Public Library of Science
Bibliographic data for series maintained by ploscompbiol ().