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.

附加文件9：图S8。将拷贝数变异（copy number alterations, CNA）纳入亚组分类器构建流程。本研究通过向亚组中加入深度扩增与深度缺失特征来扩充分类任务集：当对应基因在该队列中存在至少5个上述两类突变中的任意一类时，即纳入该特征。本研究针对各队列中已完成亚组枚举的每一个癌症基因，将包含CNA的最优亚组分类性能（纵坐标）与全基因层面分类任务的分类性能（横坐标）进行对比。本研究在此展示METABRIC-(LumA)队列、TCGA-BRCA(LumA)队列，以及本研究数据门户中Figures/S8 - CNA亚组AUC对比路径下其余队列的对应图表。此类图表的命名格式为：(expr-source)__(cohort)__copy-comparisons_Ridge.svg。