DAG-HEART: Directed Acyclic Graph-Guided Health Equity-Aware Representation Transfer Learning Framework for Breast Cancer
- 1University of Nebraska Medical Center
Abstract
Breast cancer outcome prediction remains challenging for underrepresented populations because genomic datasets are demographically imbalanced and conventional multi-omics integration largely relies on undirected molecular similarity. We developed DAG-HEART, a directed acyclic graph-guided multi-omics transfer-learning framework that extends our previous transfer learning strategy with data augmentation. Using TCGA-BRCA mRNA, miRNA, and DNA-methylation data, DAG-HEART was evaluated for progression-free interval prediction in a data-minority group. DAG-guided nonlinear integration consistently improved predictive performance relative to direction-agnostic and correlation-based representations, while biologically motivated directional constraints generally outperformed reversed or unconstrained structures. Recurrently selected features converged on extracellular-matrix and regulatory pathways and supported clinically meaningful risk stratification. DAG-HEART provides an interpretable strategy for combining directed multi-omics structure with transfer learning under data imbalance across racial groups.
Related
- PDI-Spot: A Robust Representation Learning Framework for Identifying Energetic Hotspots in Protein–DNA Complexes
- Directed forgetting and working-memory load reduce outcome-selective Pavlovian-to-instrumental transfer in humans
- High-dimensional hippocampus representation facilitates learning of low-dimensional abstract representation and supports generalization
- Tri-Modality Representation Learning for Molecular Property Prediction
- Increased monetary incentives enhance goal-directed reinforcement learning but fail to suppress automatic learning processes
BibTeX
@misc{baek2026dagheart,
title = {{DAG-HEART: Directed Acyclic Graph-Guided Health Equity-Aware Representation Transfer Learning Framework for Breast Cancer}},
author = {M. Baek and J. Wang and S. Wan},
howpublished = {bioRxiv},
year = {2026},
month = aug,
doi = {10.64898/2026.08.31.748384},
url = {https://www.biorxiv.org/content/10.64898/2026.08.31.748384v1},
note = {CC BY-NC-ND},
}
RIS
TY - UNPB
TI - DAG-HEART: Directed Acyclic Graph-Guided Health Equity-Aware Representation Transfer Learning Framework for Breast Cancer
AU - M. Baek
AU - J. Wang
AU - S. Wan
PY - 2026
DA - 2026/08/31
PB - bioRxiv
DO - 10.64898/2026.08.31.748384
UR - https://www.biorxiv.org/content/10.64898/2026.08.31.748384v1
AB - Breast cancer outcome prediction remains challenging for underrepresented populations because genomic datasets are demographically imbalanced and conventional multi-omics integration largely relies on undirected molecular similarity. We developed DAG-HEART, a directed acyclic graph-guided multi-omics transfer-learning framework that extends our previous transfer learning strategy with data augmentation. Using TCGA-BRCA mRNA, miRNA, and DNA-methylation data, DAG-HEART was evaluated for progression-free interval prediction in a data-minority group. DAG-guided nonlinear integration consistently improved predictive performance relative to direction-agnostic and correlation-based representations, while biologically motivated directional constraints generally outperformed reversed or unconstrained structures. Recurrently selected features converged on extracellular-matrix and regulatory pathways and supported clinically meaningful risk stratification. DAG-HEART provides an interpretable strategy for combining directed multi-omics structure with transfer learning under data imbalance across racial groups.
ER -