.png){kind=icon}
返回
Nonnegative spatial factorization applied to spatial genomics
.png){kind=icon}
OA
AI
DOI：10.1038/s41592-022-01687-w.png)
.png){kind=icon}
.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Nonnegative matrix factorization (NMF) is widely used to analyze high-dimensional count data because, in contrast to real-valued alternatives such as factor analysis, it produces an interpretable parts-based representation. However, in applications such as spatial transcriptomics, NMF fails to incorporate known structure between observations. Here, we present nonnegative spatial factorization (NSF), a spatially-aware probabilistic dimension reduction model based on transformed Gaussian processes that naturally encourages sparsity and scales to tens of thousands of observations. NSF recovers ground truth factors more accurately than real-valued alternatives such as MEFISTO in simulations, and has lower out-of-sample prediction error than probabilistic NMF on three spatial transcriptomics datasets from mouse brain and liver. Since not all patterns of gene expression have spatial correlations, we also propose a hybrid extension of NSF that combines spatial and nonspatial components, enabling quantification of spatial importance for both observations and features. A TensorFlow implementation of NSF is available from https://github.com/willtownes/nsf-paper.
Keyword:
GENE-EXPRESSION
AI总结
对已上传原文的论文进行重点信息的提取，主要内容包括：简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。
期刊
IF:
32.1
论文数:
7.2K
被引数:
12.7W
机构
引用论文
Identifying temporal and spatial patterns of variation from multimodal data using MEFISTO使用MEFISTO从多模态数据中识别变化的时空模式.png)
NATURE METHODSOAAI
NATURE METHODSIF32.1
OAAI分享收藏Gene Expression Omnibus: NCBI gene expression and hybridization array data repository基因表达综合: NCBI基因表达和杂交阵列数据库NUCLEIC ACIDS RESEARCH
OAAI
NUCLEIC ACIDS RESEARCHIF13.1
OAAI分享收藏分享收藏GiniClust2: a cluster-aware, weighted ensemble clustering method for cell-type detectionGiniClust2: 一种用于细胞类型检测的聚类感知加权集成聚类方法GENOME BIOLOGYOAAI
GENOME BIOLOGYIF9.4
OAAI分享收藏An experimental evaluation of point-of-interest recommendation in location-based social networksOAAI
OAAI分享收藏From Louvain to Leiden: guaranteeing well-connected communities从鲁汶到莱顿: 保证良好连接的社区SCIENTIFIC REPORTSOAAI
SCIENTIFIC REPORTSIF3.9
OAAI分享收藏Binding of a 4-Methyl-4-Aza-Steroid to 5α-Reductase of Rat Liver and Prostate Microsomes4-甲基-4-氮杂-类固醇与大鼠肝脏和前列腺微粒体的5 α-还原酶的结合
PREAI
分享收藏Squidpy: a scalable framework for spatial omics analysisSquidpy: 一个可扩展的空间组学分析框架NATURE METHODSOAAI
NATURE METHODSIF32.1
OAAI分享收藏
查看更多内容