Supplementary Table 5: Unsupervised learning of cross-modal mappings in multi-omics data for survival stratification of gastric cancer

Supplementary Table 5. Unsupervised learning of cross-modal mappings in multi-omics data for survival stratification of gastric cancerSignificant pathways for up-regulated and down-regulated genes<br>AbstractPurpose: This study presents a survival-stratification model based on muti-omics integration using BiDNNs in GC. Methods: Based on the survival-related representation features yielded by BiDNNs through integrating transcriptomics and epigenomics data, K-means clustering analysis was performed to cluster tumor samples into different survival subgroups. The BiDNNs-based model was validated using 10-fold cross-validation and in two independent confirmation cohorts. Results: Using the BiDNNs-based survival stratification model, patients were grouped into two survival subgroups with log-rank P value=9.05E-05. The subgroups classification was robustly validated in 10-fold cross-validation (C-index=0.65±0.02) and in two confirmation cohorts (E-GEOD-26253, C-index=0.609; E-GEOD-62254, C-index=0.706). Conclusion: We propose and validate a robust and stable BiDNNs-based survival stratification model in GC.<br>

补充表5. 用于胃癌生存分层的多组学数据跨模态映射无监督学习<br>上调与下调基因的显著富集通路<br>摘要<br>研究目的：本研究构建了基于双向深度神经网络（BiDNNs）的胃癌多组学整合生存分层模型。研究方法：本研究通过双向深度神经网络整合转录组学与表观基因组学数据，提取生存相关表征特征，随后采用K均值聚类分析将肿瘤样本划分为不同生存亚组。该基于双向深度神经网络的模型通过10折交叉验证及两个独立验证队列进行验证。研究结果：基于该双向深度神经网络的生存分层模型可将患者划分为两个生存亚组，对数秩检验P值为9.05×10^-5。该亚组分类在10折交叉验证中得到稳健验证（一致性指数C-index=0.65±0.02），并在两个验证队列中得到验证：E-GEOD-26253队列C-index=0.609；E-GEOD-62254队列C-index=0.706。研究结论：本研究提出并验证了一种稳健可靠的基于双向深度神经网络的胃癌生存分层模型。