Fig. 6: Spot2vector enhances spatial gene expression patterns through effective denoising on the human breast cancer dataset.

a Scatterplots comparing the significance (-log(p-value)) of the marker genes after denoising using Spot2vector (x-axis) against raw expression, STAGATE, scVI, and MAGIC (y-axis). Each dot represents a gene (n = 400). b The top panels show the raw and denoised expression distributions of the MUC19 gene using four methods. The middle panels display the corresponding high-expression regions extracted using gene-specific thresholds, and the bottom panels show the gene expression values. c Ripley’s K and L curves of MUC19 gene across raw data and data denoised by four methods. d Boxplots compare the maximum Ripley’s K and L scores for 400 marker genes across raw data and denoised datasets. All box plots range from the first and third quartiles with the median as the horizontal line, while whiskers represent 1.5 times the interquartile range from the lower and upper bounds of the box. Data beyond the end of whiskers are plotted individually.