Adaptive multi-omics integration framework for breast cancer survival analysis.

Area of Science:

• Oncology
• Bioinformatics
• Genomics

Background:

• Breast cancer is a significant global health challenge.
• Novel prognostic and therapeutic strategies are needed.
• Multi-omics data offers potential for deeper biological insights.

Purpose of the Study:

• To integrate multi-omics data (genomics, transcriptomics, epigenomics) for breast cancer.
• To identify molecular signatures driving progression and impacting survival.
• To optimize integration and feature selection using genetic programming.

Main Methods:

• Utilized The Cancer Genome Atlas (TCGA) multi-omics data.
• Employed genetic programming for adaptive integration and feature selection.
• Developed a three-component framework: preprocessing, GP-based integration/selection, and model development.

Main Results:

• Achieved a concordance index (C-index) of 78.31 on the training set (5-fold CV).
• Obtained a C-index of 67.94 on the test set.
• Demonstrated improved breast cancer survival analysis through integrated multi-omics.

Conclusions:

• Adaptive multi-omics integration shows promise for enhancing breast cancer survival analysis.
• Highlights the importance of inter-layer molecular interactions.
• Presents a flexible framework applicable to other cancer types.