English(EN) GC-MoE: Genomics-Guided Cell-Type-Specific Mixture of Experts for Histology-Based Single-Cell Spatial Transcriptomics

新的GC-MoE模型可从组织学图像预测细胞基因表达

作者 PulseAugur 编辑部 · [2 个来源] · 2026-06-01 16:01

研究人员开发了GC-MoE，一种从组织病理学图像估计单细胞基因表达的新方法。该方法利用基因组引导的专家混合模型来预测细胞类型概率和基因表达，旨在减少昂贵的单细胞测量需求。该系统结合了细胞类型特异性预测器和注意力模块，以捕获基因程序和邻近细胞的上下文，与现有方法相比显示出改进的结果。 AI

影响该方法通过从标准组织学图像预测基因表达，有望显著降低空间转录组学研究的成本和复杂性。

排序理由该集群包含一篇详细介绍特定科学任务新方法的学术论文。

AI 生成摘要 · Google Gemini · 来自 2 个来源。我们如何撰写摘要 →

报道来源 [2]

arXiv cs.AI TIER_1 English(EN) · Kaito Shiku, Ahtisham Fazeel Abbasi, Ryoma Bise, Yuichiro Iwashita, Kazuya Nishimura, Andreas Dengel, Muhammad Nabeel Asim · 2026-06-02 04:00

GC-MoE: Genomics-Guided Cell-Type-Specific Mixture of Experts for Histology-Based Single-Cell Spatial Transcriptomics

arXiv:2606.02424v1 Announce Type: cross Abstract: Histology-based single-cell spatial transcriptomics (ST) estimation aims to predict gene expression for individual cells from histopathological images and cell locations, reducing the need for costly single-cell ST measurements. U…
arXiv cs.AI TIER_1 English(EN) · Muhammad Nabeel Asim · 2026-06-01 16:01

GC-MoE: Genomics-Guided Cell-Type-Specific Mixture of Experts for Histology-Based Single-Cell Spatial Transcriptomics

Histology-based single-cell spatial transcriptomics (ST) estimation aims to predict gene expression for individual cells from histopathological images and cell locations, reducing the need for costly single-cell ST measurements. Unlike existing histology-to-ST methods that mainly…