MoLF model predicts pan-cancer gene expression from histology images

Researchers have developed MoLF, a novel generative model designed for predicting pan-cancer spatial gene expression from histology images. This model utilizes a conditional Flow Matching objective and a Mixture-of-Experts architecture to effectively handle the heterogeneity across different cancer types. MoLF demonstrates superior performance compared to existing specialized and foundation models, achieving state-of-the-art results on pan-cancer benchmarks and showing zero-shot generalization to cross-species data. AI

影响 Introduces a new model for histogenomic profiling that could advance cancer research by enabling more scalable and generalized analysis across different cancer types.

排序理由 This is a research paper detailing a new model and its performance on benchmarks. [lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.LG 阅读 →

• arXiv
• Flow Matching
• Mixture-of-Experts
• Susu Hu

• 论文
• 模型发布

AI 生成摘要 · Google Gemini · 来自 1 个来源。 我们如何撰写摘要 →