New VOICE model predicts gene expression from tissue images

Researchers have developed VOICE, a novel foundation model that integrates vision and omics data to predict single-cell gene expression from H&E stained tissue images. This model aligns cell morphology with gene expression embeddings, utilizing both direct regression and retrieval-based prediction branches. VOICE demonstrates strong generalization capabilities, outperforming previous methods on seven metrics across held-out patients and slides. AI

IMPACT This model could significantly advance biological research by enabling large-scale gene expression analysis from readily available tissue images.

RANK_REASON The cluster contains a research paper detailing a new foundation model for biological data analysis. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.CV →

• H&E stain
• VOICE
• Xenium

• paper
• model release
• other

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →