Classify multicategory outcome in patients with lung adenocarcinoma using clinical, transcriptomic and clinico-transcriptomic data: machine learning versus multinomial models.
Classify multicategory outcome in patients with lung adenocarcinoma using clinical, transcriptomic and clinico-transcriptomic data: machine learning versus multinomial models.
复制标题
DOI：
--
复制
发表时间：
2020
影响因子：
5.3
通讯作者：
Fei Deng;Lanlan Shen;He Wang;Lanjing Zhang
中科院分区：
文献类型：
--
作者：
Fei Deng;Lanlan Shen;He Wang;Lanjing Zhang
多类别生存结果的分类对于精准肿瘤学非常重要。机器学习 (ML) 算法已用于对某些癌症类型的多类别生存结果进行准确分类，但尚未用于肺腺癌的多类别生存结果。因此，我们比较了 3 种 ML 模型（随机森林、支持向量机 [SVM]、多层感知器）和多项逻辑回归 (Mlogit) 模型的性能，以使用 TCGA 对肺腺癌的 4 类生存结果进行分类。 Mlogit 模型总体表现与 SVM 和多层感知器模型相似（微平均曲线下面积=0.82），而随机森林模型较差。令人惊讶的是，单独的转录组数据和临床转录组数据似乎足以准确地对这些患者的 4 类生存结果进行分类，但没有单独使用临床数据的模型表现良好。值得注意的是，NDUFS5、P2RY2、PRPF18、CCL24、ZNF813、MYL6、FLJ41941、POU5F1B 和 SUV420H1 是与无病生存相关且与其他结果呈负相关的顶级基因。同样，BDKRB2、TERC、DNAJA3、MRPL15、SLC16A13、CRHBP 和 ACSBG2 分别与进展存活相关，GAL3ST3、AD2、RAB41、HDC 和 PLEKHG1 分别与疾病死亡相关，同时也与其他结果呈负相关。这些交联基因可用于风险分层和未来的治疗开发。
Classification of multicategory survival-outcome is important for precision oncology. Machine learning (ML) algorithms have been used to accurately classify multi-category survival-outcome of some cancer-types, but not yet that of lung adenocarcinoma. Therefore, we compared the performances of 3 ML models (random forests, support vector machine [SVM], multilayer perceptron) and multinomial logistic regression (Mlogit) models for classifying 4-category survival-outcome of lung adenocarcinoma using the TCGA. Mlogit model overall performed similar to SVM and multilayer perceptron models (micro-average area under curve=0.82), while random forests model was inferior. Surprisingly, transcriptomic data alone and clinico-transcriptomic data appeared sufficient to accurately classify the 4-category survival-outcome in these patients, but no models using clinical data alone performed well. Notably, NDUFS5, P2RY2, PRPF18, CCL24, ZNF813, MYL6, FLJ41941, POU5F1B, and SUV420H1 were the top-ranked genes that were associated with alive without disease and inversely linked to other outcomes. Similarly, BDKRB2, TERC, DNAJA3, MRPL15, SLC16A13, CRHBP and ACSBG2 were associated with alive with progression and GAL3ST3, AD2, RAB41, HDC, and PLEKHG1 associated with dead with disease, respectively, while also inversely linked other outcomes. These cross-linked genes may be used for risk-stratification and future treatment development.