GC-MoE: Genomics-Guided Cell-Type-Specific Mixture of Experts for Histology-Based Single-Cell Spatial Transcriptomics
Researchers have developed GC-MoE, a novel method for estimating gene expression in individual cells from histology images. This approach uses a Mixture-of-Experts model guided by genomic data to predict cell-type probabilities and gene expression. The system incorporates cell-type-specific predictors and attention mechanisms to capture gene programs and neighboring cell context, showing improved performance over existing methods. AI
IMPACT Introduces a new computational model for biological research, potentially improving the efficiency of gene expression analysis.