Fig. 5From: Identification of BGN positive fibroblasts as a driving factor for colorectal cancer and development of its related prognostic model combined with machine learningDevelopment of BGN + Fib-related risk signature (BGNFRS) using machine learningA. Module correlation heatmap. B. Scatter plot showing the correlation between MEturquoise module and high BGN + Fib infiltration group. C-D. KEGG/GO analysis. E. Construction of 101 prediction models using various combinations of algorithms and calculation of C-index for each dataset; The C-index ranges from 0 to 1, with values closer to 1 indicating better predictive performance. F. Distribution and differences of BGN + Fib-related risk signature (BGNFRS) in single-cell data. G. Spatial localization of BGN + Fib and BGNFRS in spatial transcriptomicsBack to article page