New HistoGPA framework predicts spatial gene expression from histology images

Researchers have developed HistoGPA, a novel framework designed to predict spatial gene expression from histology images. This approach conditions gene priors based on tissue context, allowing for more accurate predictions by adapting local morphology and gene embeddings to the broader slide context. HistoGPA demonstrated superior performance across ten cancer types in the HEST-1k dataset, achieving the highest macro-averaged gene-wise Pearson correlation coefficient and better recovery of cancer-associated gene expression patterns. AI

IMPACT This framework could improve the accuracy of gene expression prediction from medical imaging, aiding in disease research and diagnostics.

RANK_REASON The item is an academic paper detailing a new computational framework for biological data analysis. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.CV →

• alphaXiv
• CatalyzeX Code Finder for Papers
• Connected Papers
• CORE Recommender
• DagsHub
• Gotit.pub
• HEST-1k
• HistoGPA
• Hugging Face
• Influence Flower
• Litmaps
• Pearson product-moment correlation coefficient
• ScienceCast
• scite Smart Citations

• paper
• other

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