Extended Data Fig. 5: Concordance between histology deep-learning and RNA-seq immune classification.

a. Box plot showing the difference in pathology TIL estimates between immune hot and immune cold regions (n = 219). Pathology TIL estimates score fraction of stroma containing TILs, whereas immune classification was defined based on the percentage of lymphocytes in all cells within a slide. b. A confusion matrix to compare RNA-seq and deep-learning histology immune classifications (discarding immune intermediate regions, n = 109 regions (57 LUAD, 37 LUSC, 15 other histology subtypes); 52 patients). The p-value was generated using a two-sided Fisher’s exact test for overlap. c. Box plot showing the difference in the fraction of immune hotspots³⁶ in regions where the two classifications are in agreement (n = 78; labeled as ‘In agreement’) against the discrepant regions (n = 31, labeled as ‘Discrepant’). Each dot represents a region, the median value is indicated by a thick horizontal line; minimum and maximum values are indicated by the extreme points; and the first and third quantiles are represented by the box edges. d. Box plots to support the overall consistency between H&E-deep-learning and RNA-seq methods by comparing different immune scores as well as ASCAT tumor purity between immune hot/high and cold/low tumor regions (all P-values < 0.0001). Top row, H&E-deep-learning immune classification (n = 219; except the ASCAT purity box plot n = 186 regions), bottom row, RNA-seq-derived immune classification (n = 142; except the ASCAT purity box plot, n = 141 regions). For statistical comparisons among groups, a two-sided, non-parametric, unpaired, Wilcoxon signed-rank test was used, unless stated otherwise.