PathGene-CSU

该数据集名为PathGene-CSU，包含了1576名肺癌患者，其中大部分被诊断为腺癌或腺鳞癌。所有患者都接受了下一代测序（NGS）检查，从而为每位患者生成了驱动基因突变状态、突变亚型和外显子级别变异位置的标签。该数据集重点关注五个预测任务，包括TP53、EGFR、KRAS和ALK的二元突变状态，并包含了详细的亚型和外显子信息。数据规模涉及1576名患者，任务包括预测驱动基因突变状态、突变亚型、外显子位置以及肿瘤突变负担（TMB）状态。

This dataset is named PathGene-CSU and includes 1576 lung cancer patients, most of whom are diagnosed with adenocarcinoma or adenosquamous carcinoma. All patients received next-generation sequencing (NGS) testing, which generated labels for driver gene mutation status, mutation subtype, and exon-level variant position for each patient. This dataset focuses on five prediction tasks, including the binary mutation statuses of TP53, EGFR, KRAS, and ALK, and contains detailed information on mutation subtypes and exon locations. With a cohort size of 1576 patients, the prediction tasks involved also cover driver gene mutation status, mutation subtype, exon-level variant position, and tumor mutation burden (TMB) status.