106-STAMP: Decoding Patterns in Spatial Transcriptomics
This article from Nature Methods detailing a new computational method called STAMP (Spatial Transcriptomics Analysis with topic Modeling to uncover spatial Patterns), which is designed for the analysis of spatial transcriptomics data. STAMP is an interpretable, spatially aware dimension reduction method that utilizes a deep generative model to identify biologically relevant, low-dimensional spatial "topics" and associated gene modules. The authors demonstrate that STAMP outperforms competing dimension reduction and clustering algorithms across various datasets, including mouse hippocampus…
The skinny
The skinny isn't ready yet — notes appear once the transcript is processed.