TY  - JOUR
A1  - Chen, Hao
A1  - Nguyen, Nam D.
A1  - Ruffalo, Matthew
A1  - Bar-Joseph, Ziv
T1  - A unified analysis of atlas single-cell data
Y1  - 2025/05/01 
JF  - Genome Research 
JO  - Genome Research 
SP  - 1219 
EP  - 1233 
DO  - 10.1101/gr.279631.124 
VL  - 35 
IS  - 5 
UR  - http://genome.cshlp.org/content/35/5/1219.abstract 
N2  - Recent efforts to generate atlas-scale single-cell data provide opportunities for joint analysis across tissues and modalities. Existing methods use cells as the reference unit, hindering downstream gene-based analysis and removing genuine biological variation. Here we present GIANT, an integration method designed for atlas-scale gene analysis across cell types and tissues. GIANT converts data sets into gene graphs and recursively embeds genes without additional alignment. Applying GIANT to two recent atlas data sets yields unified gene-embedding spaces across human tissues and data modalities. Further evaluations demonstrate GIANT's usefulness in discovering diverse gene functions and underlying gene regulation in cells from different tissues. 
ER  -