研究人员推出了一种名为Cellina的新框架，旨在预测细胞在不同空间邻域背景下表达会如何变化。该方法将“组织图谱反事实”形式化为空间干预，通过重塑细胞连接或修改邻域表达来实现。Cellina将细胞的内在状态与其空间背景分离开来，在涉及数百万个结直肠癌和鼠标大脑组织细胞的基准测试中表现优于现有方法。 AI
排序理由 该集群包含一篇详细介绍新计算框架及其在生物数据集上性能的学术论文。
AI 生成摘要 · Google Gemini · 来自 3 个来源。 我们如何撰写摘要 →
Cellina框架预测空间背景下的细胞表达变化
报道来源 [3]
-
使用监督解耦查询组织图上的反事实
arXiv:2606.08493v1 Announce Type: cross Abstract: \textit{Tissue graph counterfactuals} ask how a cell's expression would change under altered spatial neighbor contexts. Such queries are central to predicting cell behavior in tissues, but lack a unified definition, with existing …
-
使用监督解耦查询组织图上的反事实
\textit{Tissue graph counterfactuals} ask how a cell's expression would change under altered spatial neighbor contexts. Such queries are central to predicting cell behavior in tissues, but lack a unified definition, with existing methods targeting specific intervention types or t…
-
使用监督解耦查询组织图上的反事实
Tissue graph counterfactuals ask how a cell's expression would change under altered spatial neighbor contexts. Such queries are central to predicting cell behavior in tissues, but lack a unified definition, with existing methods targeting specific intervention types or treating c…