Extended Data Fig. 2: Validation of the automated single-cell classification for H&E.

a. Scatter plot showing the correlation between H&E-based adjacent-tumor lymphocytes/stromal and pathology TIL estimates in diagnostic samples (n = 98 diagnostic slides/patients). b. Scatter plots showing the correlations between H&E-based cancer cellularity estimate and ASCAT/VAF purity scores (n = 238 regions; 83 patients). c. Scatter plot showing the correlation between H&E-based estimate of lymphocyte percentage among all cells and RNA-seq-based CD8 signature using the Danaher et al. method³⁰ (n = 142 regions; 56 patients). d. Scatter plot showing the correlation between H&E-based estimate of lymphocyte percentage among all cells and CD8⁺ cell percentage in IHC in the diagnostic samples (n = 100 diagnostic slides/patients). e. Scatter plots showing the correlation between H&E-based lymphocyte percentage versus pathological scores of overall lymphocytic cell fraction, and adjacent-tumor lymphocytes/stromal versus pathology TIL estimates in an external cohort (LATTICe-A, n = 80 diagnostic slides/patients). f. Illustrative example to show the spatial alignment of TTF1/CD45/SMA-stained IHC and H&E images obtained using sequential staining on the same tissue microarray section for biological validation. g. Scatter plot showing the correlation between stromal cell percentage determined by H&E and SMA⁺ cell percentage per LUAD image tiles of size 100µm² (n = 144). The experiment was conducted once using one TMA (n = 33 cores/patients). The shading indicates 95% confidence interval.