Supplementary Table 3. Unsupervised learning of cross-modal mappings in multi-omics data for survival stratification of gastric cancerPredicted subgroup label of samples in TCGA set
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.

Supplementary Table 4. Unsupervised learning of cross-modal mappings in multi-omics data for survival stratification of gastric cancerTop 30 mRNA features and top 45 methylation features according to ANOVA F value
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.

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
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.

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
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.

Supplementary Table 2. Unsupervised learning of cross-modal mappings in multi-omics data for survival stratification of gastric cancerDetermination of optimal cluster number K
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.

Supplementary Table 2. Unsupervised learning of cross-modal mappings in multi-omics data for survival stratification of gastric cancerDetermination of optimal cluster number K
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.

Supplementary Table 3. Unsupervised learning of cross-modal mappings in multi-omics data for survival stratification of gastric cancerPredicted subgroup label of samples in TCGA set
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.

Supplementary Table 4. Unsupervised learning of cross-modal mappings in multi-omics data for survival stratification of gastric cancerTop 30 mRNA features and top 45 methylation features according to ANOVA F value
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.

Supplementary Table 1. Unsupervised learning of cross-modal mappings in multi-omics data for survival stratification of gastric cancerSelection of optimal hidden layer presentation nodes
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.

Supplementary Table 1. Unsupervised learning of cross-modal mappings in multi-omics data for survival stratification of gastric cancerSelection of optimal hidden layer presentation nodes
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.