Layer-Specific Source-Anchored Transfer Learning for Multi-Omics Survival Prediction in Younger Breast Cancer Patients

Background: Younger breast cancer patients (<50 years) often present with more aggressive disease and distinct molecular characteristics, yet predictive models for this group are underpowered due to small sample sizes. Most existing models are built on older populations and may not translate directly, particularly across multiple omics data types. To address this, we developed Layered Source-Anchored Transfer Elastic Net (LSAT-EN), which adaptively borrows from the older source cohort while allowing borrowing strength to vary across omics layers according to their similarity between source and target cohorts, while performing EN variable selection. Methods: Patients aged >=60, >=55, and >=50 years were used as the source to improve prediction in patients aged <50 years. LSAT-EN were evaluated in group-correlated simulations and in TCGA-BRCA integrating 6 omics layers. Binary survival at 2-4 years was assessed by AUC; censored survival by Harrell's C-index and 2-5-year inverse probability of censoring weighted (IPCW) AUC. Results: In simulation, LSAT-EN achieved the highest AUC under moderate source-target heterogeneity (sigma^2=0.25; 0.747- 0.802), outperforming GAS-EN (0.735-0.767), overall EN (0.683-0.710), individual EN (0.646-0.767), and glmtrans EN (0.640-0.733) across target training sample sizes (nT). Its advantage was greatest under higher source-target heterogeneity (sigma^2=4), particularly with small nT, where LSAT-EN achieved AUCs of 0.689- 0.789 compared with 0.590-0.771 across competing methods. In TCGA-BRCA data, LSAT-EN improved discrimination relative to overall and individual EN in all binary and Cox models across all time horizons and source age groups. The method also identified clinically/ biologically important mRNA and miRNA, as well as useful candidate miRNA-mRNA pairs, indicating powerful biomarker discovery capability. Conclusion: LSAT-EN is a powerful TL method for improving prediction for younger breast cancer patients; The framework may support prediction in other underrepresented populations with limited target-cohort data to advance cancer disparity ML research.