Additional file 9 of Systematic interrogation of mutation groupings reveals divergent downstream expression programs within key cancer genes

Additional file 9: Figure S8. Adding copy number alterations to subgrouping classifiers. We augmented our classification tasks by adding deep amplifications and deep deletions to each subgrouping where there were at least five of one of these two types of mutations present in the corresponding gene within the cohort. Here we compare the classification performance of the best found subgrouping containing CNAs (y-axis) to the gene-wide task (x-axis) for each cancer gene with enumerated subgroupings in each cohort. We include here these figures for the METABRIC-(LumA) and TCGA-BRCA(LumA) cohorts and for the remaining cohorts at our data portal under Figures/S8 - CNA Subgrouping AUC Comparisons. The names of these figures have the format (expr-source)__(cohort)__copy-comparisons_Ridge.svg.

补充文件9：图S8。将拷贝数变异（copy number alterations）纳入亚组分类器。本研究通过为每个亚组添加深度扩增与深度缺失来拓展分类任务，筛选规则为：队列中对应基因需存在至少5个上述两类突变之一。针对每个队列中各已枚举亚组的癌症基因，我们将最优的纳入拷贝数变异的亚组的分类性能（纵轴）与全基因分类任务的分类性能（横轴）进行对比。本研究在此展示METABRIC-(LumA)队列与TCGA-BRCA(LumA)队列的相关图表，其余队列的相关图表可于本团队数据门户的"Figures/S8 - CNA亚组AUC（受试者工作特征曲线下面积）对比"栏目中获取。此类图表的命名格式为(expr-source)__(cohort)__copy-comparisons_Ridge.svg。