Additional file 13 of Systematic interrogation of mutation groupings reveals divergent downstream expression programs within key cancer genes

Additional file 13: Figure S12. Comparing cancer gene mutation landscape characteristics across tumor contexts. The best subgroupings in each cohort for all genes with at least one classification task with an AUC of at least 0.7 in two of the cohorts considered in this study. Each pie chart in a panel represents a cohort in which subgrouping mutation classifiers were trained and tested for the gene in question, with pie charts scaled, sliced, and labelled according to the same schema as in Fig. 1. We include here these figures for TP53, PIK3CA, and NFE2L2 and for the remaining genes at our data portal under Figures/S12 - Subgrouping AUC Comparisons by Gene. The names of these figures have the format (gene)__sub-comparisons_Ridge.svg.

补充材料13：图S12。跨肿瘤背景的癌症基因突变景观特征比较。针对本研究纳入的所有基因，若其至少存在一项分类任务，且该任务在两个研究队列（cohort）中的受试者工作特征曲线下面积（AUC，Area Under the Curve）≥0.7，则展示其在每个研究队列中的最优亚组划分结果。每个子图中的饼图代表一个研究队列：针对目标基因的亚组划分突变分类器在此队列中完成训练与测试，饼图的缩放比例、切片划分方式与标注逻辑均与图1保持一致。本部分展示了TP53、PIK3CA与NFE2L2的相关图表，其余基因的对应图表可通过本研究数据门户的「Figures/S12 - Subgrouping AUC Comparisons by Gene」栏目获取。此类图表的文件命名格式为：(基因名)__sub-comparisons_Ridge.svg。