Spatially-regularized imputation of spatial transcriptomes from single-cell reference

Recent spatial transcriptomics technologies offer a lens of observing the spatial distribution of RNA transcripts in tissues, yet achieving a whole-genome-level spatial landscape remains technically challenging. Multiple computational methods hence have been proposed to impute missing genes from a single-cell reference dataset, while they lack mechanisms of explicitly encoding spatial patterns in their modeling.<br> <br> To fill the research gaps, we introduced a computational model, TransImp, that leverages a spatial auto-correlation metric as a regularization for imputing missing features in ST. Evaluation results from multiple platforms demonstrate that TransImp remarkably preserves the spatial patterns and achieves robust and state-of-the-art accuracy for imputing missing features, including both matched modality and unseen nascent RNAs. -------------------- This repository includes all the input data (data.tar.gz) and output data (output.tar.gz) for generating figures and tables in results.<br>