Comprehensive brain cell atlases are essential for understanding neural functions and enabling translational insights. As single-cell technologies proliferate across experimental platforms, species, and modalities, these atlases must scale accordingly, calling for data integration framework that aligns heterogeneous datasets without erasing biologically meaningful variations. Existing tools typically address narrow integration settings, forcing researchers to assemble \textit{ad hoc} workflows that may generate artifacts. Here, we introduce multiVIB, a unified probabilistic contrastive learning framework that handles diverse integration scenarios. We show that multiVIB achieves state-of-the-art performance while mitigating spurious alignments. Applied to atlas-scale datasets from the BRAIN Initiative, multiVIB demonstrates robust and scalable integration, including integration of diverse data modalities and reliable preservation of species-specific variations in cross-species integration. These capabilities position multiVIB as a scalable, biologically faithful foundation for constructing next-generation brain cell atlases with the growing landscape of single-cell data.
Yang Xu, Stephen Fleming, Brice Wang, See PDF. multiVIB: A unified probabilistic contrastive learning framework for atlas-scale integration of single-cell multi-omics data. // Cell Reports Methods. – DOI: 10.2139/ssrn.5907768. – URL: https://www.sciencedirect.com/science/article/pii/S2667237526003656?dgcid=rss_sd_all
Yang Xu, Stephen Fleming, Brice Wang, & See PDF multiVIB: A unified probabilistic contrastive learning framework for atlas-scale integration of single-cell multi-omics data. Cell Reports Methods. https://doi.org/10.2139/ssrn.5907768
Yang Xu, et al. “multiVIB: A unified probabilistic contrastive learning framework for atlas-scale integration of single-cell multi-omics data.” Cell Reports Methods. doi:10.2139/ssrn.5907768.
@article{Xu,
title = {multiVIB: A unified probabilistic contrastive learning framework for atlas-scale integration of single-cell multi-omics data},
author = {Xu, Yang and Fleming, Stephen and Wang, Brice and PDF, See},
journal = {Cell Reports Methods},
doi = {10.2139/ssrn.5907768},
url = {https://www.sciencedirect.com/science/article/pii/S2667237526003656?dgcid=rss_sd_all}
}
Похожие статьи
MapMyCells: High-performance mapping of cell-by-gene data to reference brain taxonomiesScott F. Daniel, Changkyu Lee, Tyler Mollenkopf, Matthew Lee, Joel Arbuckle, Elysha Fiabane, Mariano I. Gabitto, Nelson Johansen, Inkar Kapen, Andrew W. Kraft, Hsin-Yu Lai, Su Ying Li, Ryan McGinty, Jeremy A. Miller, Skyler Welch-Moosman, Sven Otto, Lane Sawyer, Noah Shepard, Carol L. Thompson, Andreas Tjärnberg, Jack Waters, Xingjian Zhen, Evan Macosko, Ed Lein, Lydia Ng, Hongkui Zeng, Shoaib Mufti, Zizhen Yao, Mike HawrylyczCell Reports Methods
· Генетика
An integrated single-cell and epigenomic resource for comparative analysis of the basal ganglia from BICANWenjin Zhang, Wubin Ding, Kai Li, Lei Chang, Amit Klein, Cindy Tatiana Báez-Becerra, Jonathan A. Rink, Anna Bartlett, Huaming Chen, Natalie Schenker-Ahmed, Nelson Johansen, Tyler Mollenkopf, Yuanyuan Fu, Yang Xie, Shane Liu, Chanrung Seng, Benpeng Miao, Tianjie Liu, Quan Zhu, Rebecca D. Hodge, Trygve E. Bakken, Ed S. Lein, Michael Hawrylycz, Xiangmin Xu, M. Margarita Behrens, Bing Ren, Joseph R. Ecker, Ting Wang, Daofeng LiCell Reports Methods
· Генетика