Fig. 1: Overview of STORIES.
From: STORIES: learning cell fate landscapes from spatial transcriptomics using optimal transport
a, STORIES takes as an input spatial transcriptomics through time. b, STORIES learns the parameters θ of a neural network \({J}_{\theta }\) representing the differentiation potential of a cell based on its transcriptomic profile. The objective function is based on FGW, which leverages both the transcriptomic profile and the spatial coordinates. c, The gradient of the function \({J}_{\theta }\) delivers a velocity that can be used to perform trajectory inference. The potential itself is a natural alternative to pseudotime and allows the study of gene trends along differentiation. Finally, STORIES can highlight possible transcription factors regulating differentiation.
