目的:肺腺癌(LUAD)是非小细胞肺癌最常见的亚型。了解肿瘤进展的分子机制具有重要的临床意义。本研究旨在鉴定与LUAD亚型相关的新型分子标记,以提高LUAD亚型分类的精度为目标。此外,优化工作旨在从患者生存分析的角度增强洞察力。
方法:我们提出了一种创新的特征选择方法,该方法侧重于LUAD分类,这是全面和强大的。所提出的方法整合了来自癌症基因组图谱(TCGA)的多组学数据,并利用了最大相关性和最小冗余的协同组合,最小绝对收缩和选择运算符,和Boruta算法。这些选定的特征被部署在六个机器学习分类器中:逻辑回归,随机森林,支持向量机,天真的贝叶斯,k-最近邻居,XGBoost
结果:所提出的方法实现了LR的0.9958的接收器工作特征曲线下面积(AUC)。值得注意的是,包含拷贝数的复合模型的准确性和AUC,甲基化,以及外显子表达的RNA测序数据,基因,和miRNA成熟链超过了具有单组学数据或其他多组学组合的模型的准确性和AUC指标。生存分析,揭示了SVM分类器的最佳分类,表现优于TCGA。为了增强模型的可解释性,利用SHapley加法扩张(SHAP)值来阐明每个特征对预测的影响。基因本体论(GO)富集分析确定了重要的生物过程,分子功能,和与LUAD亚型相关的细胞成分。
结论:总之,我们的特征选择过程,基于TCGA多组数据,结合多个机器学习分类器,熟练地鉴定了肺腺癌的分子亚型及其相应的重要基因。我们的方法可以增强LUAD的早期发现和诊断,加快靶向治疗的发展,最终,延长患者生存时间。
OBJECTIVE: Lung adenocarcinoma (LUAD) is the most common subtype of non-small cell lung cancer. Understanding the molecular mechanisms underlying tumor progression is of great clinical significance. This study aims to identify novel molecular markers associated with LUAD subtypes, with the goal of improving the precision of LUAD subtype classification. Additionally, optimization efforts are directed towards enhancing insights from the perspective of patient survival analysis.
METHODS: We propose an innovative feature-selection approach that focuses on LUAD classification, which is comprehensive and robust. The proposed method integrates multi-omics data from The Cancer Genome Atlas (TCGA) and leverages a synergistic combination of max-relevance and min-redundancy, least absolute shrinkage and selection operator, and Boruta algorithms. These selected features were deployed in six machine-learning classifiers: logistic regression, random forest, support vector machine, naive Bayes, k-Nearest Neighbor, and XGBoost.
RESULTS: The proposed approach achieved an area under the receiver operating characteristic curve (AUC) of 0.9958 for LR. Notably, the accuracy and AUC of a composite model incorporating copy number, methylation, as well as RNA- sequencing data for expression of exons, genes, and miRNA mature strands surpassed the accuracy and AUC metrics of models with single-omics data or other multi-omics combinations. Survival analyses, revealed the SVM classifier to elicit optimal classification, outperforming that achieved by TCGA. To enhance model interpretability, SHapley Additive exPlanations (SHAP) values were utilized to elucidate the impact of each feature on the predictions. Gene Ontology (GO) enrichment analysis identified significant biological processes, molecular functions, and cellular components associated with LUAD subtypes.
CONCLUSIONS: In summary, our feature selection process, based on TCGA multi-omics data and combined with multiple machine learning classifiers, proficiently identifies molecular subtypes of lung adenocarcinoma and their corresponding significant genes. Our method could enhance the early detection and diagnosis of LUAD, expedite the development of targeted therapies and, ultimately, lengthen patient survival.