Integrating single-cell RNA-seq datasets with substantial batch effects
Name
12864_2025_Article_12126.pdf
Size
2.96 MB
Format
Adobe PDF
Checksum (MD5)
531e9028049cdf288e59a2107716d2f0
Author(s)
Hrovatin, Karin
Moinfar, Amir Ali
Zappia, Luke
Parikh, Shrey
Lapuerta, Alejandro T.
Lengerich, Ben
Kellis, Manolis
Theis, Fabian J.
Date Issued
October 30, 2025
Journal
BMC Genomics
Publisher
BioMed Central
Citation
Hrovatin, K., Moinfar, A., Zappia, L. et al. Integrating single-cell RNA-seq datasets with substantial batch effects. BMC Genomics 26, 974 (2025).
Version
Final published version
Abstract
Integration of single-cell RNA-sequencing (scRNA-seq) datasets is standard in scRNA-seq analysis. Nevertheless, current computational methods struggle to harmonize datasets across systems such as species, organoids and primary tissue, or different scRNA-seq protocols, including single-cell and single-nuclei. Conditional variational autoencoders (cVAE) are a popular integration method, however, existing strategies for stronger batch correction have limitations. Increasing the Kullback–Leibler divergence regularization does not improve integration and adversarial learning removes biological signals. Here, we propose sysVI, a cVAE-based method employing VampPrior and cycle-consistency constraints. We show that sysVI integrates across systems and improves biological signals for downstream interpretation of cell states and conditions.
MIT Department
Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory
Broad Institute of MIT and Harvard
Terms of Use
Creative Commons Attribution
Persistent DSpace Link
DOI of Published Version
https://doi.org/10.1186/s12864-025-12126-3
