TY - JOUR
T1 - SELF-Former
T2 - multi-scale gene filtration transformer for single-cell spatial reconstruction
AU - Chen, Tianyi
AU - Wei, Xindian
AU - Xie, Lianxin
AU - Zhang, Yunfei
AU - Liu, Cheng
AU - Shen, Wenjun
AU - Wu, Si
AU - Wong, Hau-San
PY - 2024/11
Y1 - 2024/11
N2 - The spatial reconstruction of single-cell RNA sequencing (scRNA-seq) data into spatial transcriptomics (ST) is a rapidly evolving field that addresses the significant challenge of aligning gene expression profiles to their spatial origins within tissues. This task is complicated by the inherent batch effects and the need for precise gene expression characterization to accurately reflect spatial information. To address these challenges, we developed SELF-Former, a transformer-based framework that utilizes multi-scale structures to learn gene representations, while designing spatial correlation constraints for the reconstruction of corresponding ST data. SELF-Former excels in recovering the spatial information of ST data and effectively mitigates batch effects between scRNA-seq and ST data. A novel aspect of SELF-Former is the introduction of a gene filtration module, which significantly enhances the spatial reconstruction task by selecting genes that are crucial for accurate spatial positioning and reconstruction. The superior performance and effectiveness of SELF-Former's modules have been validated across four benchmark datasets, establishing it as a robust and effective method for spatial reconstruction tasks. SELF-Former demonstrates its capability to extract meaningful gene expression information from scRNA-seq data and accurately map it to the spatial context of real ST data. Our method represents a significant advancement in the field, offering a reliable approach for spatial reconstruction.© The Author(s) 2024. Published by Oxford University Press.
AB - The spatial reconstruction of single-cell RNA sequencing (scRNA-seq) data into spatial transcriptomics (ST) is a rapidly evolving field that addresses the significant challenge of aligning gene expression profiles to their spatial origins within tissues. This task is complicated by the inherent batch effects and the need for precise gene expression characterization to accurately reflect spatial information. To address these challenges, we developed SELF-Former, a transformer-based framework that utilizes multi-scale structures to learn gene representations, while designing spatial correlation constraints for the reconstruction of corresponding ST data. SELF-Former excels in recovering the spatial information of ST data and effectively mitigates batch effects between scRNA-seq and ST data. A novel aspect of SELF-Former is the introduction of a gene filtration module, which significantly enhances the spatial reconstruction task by selecting genes that are crucial for accurate spatial positioning and reconstruction. The superior performance and effectiveness of SELF-Former's modules have been validated across four benchmark datasets, establishing it as a robust and effective method for spatial reconstruction tasks. SELF-Former demonstrates its capability to extract meaningful gene expression information from scRNA-seq data and accurately map it to the spatial context of real ST data. Our method represents a significant advancement in the field, offering a reliable approach for spatial reconstruction.© The Author(s) 2024. Published by Oxford University Press.
KW - single-cell RNA sequence
KW - spatial transcriptomics
KW - transformer
KW - multi-scale
KW - gene filtration
UR - https://www.webofscience.com/wos/woscc/full-record/WOS:001332424100004
UR - https://www.scopus.com/record/pubmetrics.uri?eid=2-s2.0-85206650903&origin=recordpage
UR - http://www.scopus.com/inward/record.url?scp=85206650903&partnerID=8YFLogxK
U2 - 10.1093/bib/bbae523
DO - 10.1093/bib/bbae523
M3 - RGC 21 - Publication in refereed journal
SN - 1467-5463
VL - 25
JO - Briefings in Bioinformatics
JF - Briefings in Bioinformatics
IS - 6
M1 - bbae523
ER -