This study proposed a deep learning (DL) algorithm to predict survival in patients with colon adenocarcinoma (COAD) based on multi-omics integration. The survival-sensitive model was constructed using an autoencoder for DL implementation based on The Cancer Genome Atlas (TCGA) data of patients with COAD. The autoencoder framework was compared to PCA, NMF, t-SNE, and univariable Cox-PH model for identifying survival-related features. The prognostic robustness of the inferred survival risk groups was validated using three independent confirmation cohorts. Differential expression analysis, Pearson's correlation analysis, construction of miRNA-target gene network, and function enrichment analysis were performed. Two risk groups with significant survival differences were identified in TCGA set using the autoencoder-based model (log-rank p-value = 5.51e-07). The autoencoder framework showed superior performance compared to PCA, NMF, t-SNE, and the univariable Cox-PH model based on the C-index, log-rank p-value, and Brier score. The robustness of the classification model was successfully verified in three independent validation sets. There were 1271 differentially expressed genes, 10 differentially expressed miRNAs, and 12 hypermethylated genes between the survival risk groups. Among these, miR-133b and its target genes (GNB4, PTPRZ1, RUNX1T1, EPHA7, GPM6A, BICC1, and ADAMTS5) were used to construct a network. These genes were significantly enriched in ECM-receptor interaction, focal adhesion, PI3K-Akt signaling pathway, and glucose metabolism-related pathways. The risk subgroups obtained through a multi-omics data integration pipeline using the DL algorithm had good robustness. miR-133b and its target genes could be potential diagnostic markers. The results would assist in elucidating the possible pathogenesis of COAD.

中文翻译：

---

使用深度学习算法通过多组学数据集成对结肠腺癌患者进行生存预测。


本研究提出了一种基于多组学整合的深度学习（DL）算法来预测结肠腺癌（COAD）患者的生存率。生存敏感模型是根据 COAD 患者的癌症基因组图谱 (TCGA) 数据，使用自动编码器进行深度学习构建的。将自动编码器框架与 PCA、NMF、t-SNE 和单变量 Cox-PH 模型进行比较，以识别与生存相关的特征。使用三个独立的确认队列验证了推断的生存风险组的预后稳健性。进行差异表达分析、Pearson相关分析、miRNA-靶基因网络构建、功能富集分析。使用基于自动编码器的模型（对数秩 p 值 = 5.51e-07）在 TCGA 集中确定了两个具有显着生存差异的风险组。与 PCA、NMF、t-SNE 和基于 C 指数、对数秩 p 值和 Brier 评分的单变量 Cox-PH 模型相比，自动编码器框架表现出优越的性能。分类模型的稳健性在三个独立的验证集中得到了成功验证。生存风险组之间存在1271个差异表达基因、10个差异表达miRNA和12个高甲基化基因。其中，miR-133b 及其靶基因（GNB4、PTPRZ1、RUNX1T1、EPHA7、GPM6A、BICC1 和 ADAMTS5）用于构建网络。这些基因在 ECM-受体相互作用、粘着斑、PI3K-Akt 信号通路和葡萄糖代谢相关通路中显着富集。使用DL算法通过多组学数据集成管道获得的风险亚组具有良好的稳健性。 miR-133b 及其靶基因可能是潜在的诊断标记。 该结果将有助于阐明 COAD 可能的发病机制。