spRefine denoises and imputes spatial transcriptomic data with a reference-free framework powered by genomic language model

(Downloading may take up to 30 seconds. If the slide opens in your browser, select File -> Save As to save it.)

Click on image to view larger version.

Figure 1.
Figure 1.

The landscape of spRefine and related applications. (A) The computation framework of spRefine as a tool for imputation and denoising. spRefine utilizes prior information from DNA foundation models to help uncover missing gene–gene interactions and gene expressions unmeasured by the raw transcriptomic profiles. (B) The applications of spRefine including spatial domain identification, CCC inference, batch effect correction, and spatial aging clock improvement. (C) spRefine as a pretraining framework for representing phenotype information. spRefine is capable of performing survival prediction, identifying spot-level phenotype information, and predicting disease states.

This Article

  1. Genome Res. 36: 754-768

Preprint Server