AI-Driven Variant Annotation for Precision Oncology in Breast Cancer

Abstract

Interpreting the functional impact of genomic variants remains a major challenge in precision oncology, particularly in breast cancer, where many variants of unknown significance (VUS) lack clear therapeutic guidance. Current annotation strategies focus on frequent driver mutations, leaving rare or understudied variants unclassified and clinically uninformative. Here, we present an AI/ML-driven framework that systematically identifies variants associated with key breast cancer phenotypes, including ESR1 and EZH2 activity, by integrating genomic, transcriptomic, structural, and drug response data. Using DepMap and TCGA datasets, we analyzed >12,000 variants across breast cancer genomes, identifying structurally clustered mutations that share functional consequences with well-characterized oncogenic drivers. This approach reveals that mutations in PIK3CA, TP53, and other genes strongly associate with ESR1 signaling, challenging conventional assumptions about endocrine therapy response. Additionally, EZH2-associated variants emerge in unexpected genomic contexts, suggesting new targets for epigenetic therapies. By shifting from frequency-based to structure-informed classification, we expand the set of potentially actionable mutations, enabling improved patient stratification and drug repurposing strategies. This work provides a scalable, clinically relevant method to accelerate variant annotation, offering new insights into drug sensitivity and resistance mechanisms. Future validation efforts will refine these predictions and integrate clinical outcomes to guide personalized treatment strategies. Our findings highlight the transformative potential of AI/ML in redefining cancer variant interpretation, bridging the gap between genomics, functional biology, and precision medicine. Study HighlightsO_ST_ABSCurrent KnowledgeC_ST_ABSBreast cancer treatment decisions are increasingly guided by genomic profiling, yet most clinical actionability is based on frequent driver mutations (e.g., PIK3CA, TP53, ESR1). Many variants of unknown significance (VUS) remain unclassified, and current annotation methods are slow, relying on manual curation or low-throughput assays, leaving rare mutations uncharacterized. Study FocusThis study applies AI/ML-driven variant annotation to systematically identify mutations that drive key breast cancer phenotypes, such as ESR1 and EZH2 activity, beyond currently known mutations. By using structural and functional clustering, we assess whether rare and understudied mutations can be prioritized for clinical relevance. Key Findings[bullet] Analyzed >12,000 variants across breast cancer genomes, integrating multi-omic and structural data. [bullet]Identified strong ESR1-associated mutations in PIK3CA, TP53, and other genes, expanding the landscape of actionable mutations. [bullet]Discovered EZH2-associated variants in unexpected contexts, revealing potential epigenetic therapy targets. [bullet]Demonstrated that spatial clustering of mutations within proteins predicts functional consequences, even for rare mutations. Clinical and Translational Impact[bullet] Scalable AI-powered framework accelerates variant annotation and functional classification. [bullet]Enables faster identification of actionable mutations and improves patient stratification for targeted therapies. [bullet]Provides a data-driven approach to refine clinical trial design, expanding therapy options for patients lacking clear genomic-based treatment guidance.