AI-genomics synergy for drug repurposing in breast cancer: an interpretability-driven framework

Area of Science:

• Oncology
• Genomics
• Artificial Intelligence

Background:

• Genomic heterogeneity in breast cancer presents challenges for traditional drug discovery.
• Drug repurposing is a promising but complex strategy for overcoming these challenges.

Purpose of the Study:

• To review artificial intelligence (AI)-driven computational approaches for breast cancer drug repurposing.
• To propose an integrated framework for linking AI findings to clinical translation in precision oncology.

Main Methods:

• Examination of AI-driven computational methods, including signature-based and multi-modal frameworks.
• Integration of multi-omics data to uncover drug-gene-disease relationships.
• Development of an interpretability-driven framework.

Main Results:

• AI enables the generation of subtype-specific drug repurposing hypotheses by integrating diverse biological data.
• The proposed framework aims to bridge mechanistic validation and clinical translation.
• Focus on enhancing transparency and actionability in precision oncology.

Conclusions:

• AI-driven strategies offer a powerful approach to address the complexities of breast cancer drug discovery and repurposing.
• An integrated, interpretability-driven framework is crucial for translating computational findings into effective clinical applications.
• This review highlights the potential of AI to advance precision oncology for breast cancer treatment.