#machine learning
Sep 2026
SpaFactor: Lightweight Spatial Context-Aware Gene Program Modeling for Histology-to-Transcriptomics Inference
This work introduces SpaFactor, a lightweight and efficient low-rank morphology-program-gene factorization framework that demonstrates that lightweight joint modeling of tissue context and gene programs can improve both predictive accuracy and biological fidelity.
Shi-Ting Ruan, Xi-Tong Ling, Qi-Ming He et al.
· arXiv.org · 0 citations