Marina Bermisheva

PRANA: A Deep Learning Method for Adapting Polygenic Risk Scores to Diverse Ethnic Groups

PRANA adapts polygenic risk scores to non-European populations, improving predictive accuracy by 5%-20% in South Asian, East Asian, and Ashkenazi Jewish populations.

Differences in polygenic score distributions in European ancestry populations: implications for breast cancer risk prediction

This study examines differences in polygenic risk score distributions across European populations and shows how country-specific calibration can improve breast cancer risk prediction.

Breast cancer risks associated with missense variants in breast cancer susceptibility genes

The paper assesses breast cancer risks linked to rare missense variants in five susceptibility genes using logistic and mixture models, finding varying risk contributions across genes.

Common variants in breast cancer risk loci predispose to distinct tumor subtypes

The paper identifies breast cancer risk variants associated with tumor subtypes and shows their differential effects on luminal and non-luminal subtypes.

Rare copy number variants (CNVs) and breast cancer risk

The paper analyzes rare copy number variants (CNVs) in breast cancer cases and controls, identifying associations with known and novel susceptibility loci.

Genome-wide association study identifies 32 novel breast cancer susceptibility loci from overall and subtype-specific analyses

This study identifies 32 new breast cancer susceptibility loci through GWAS, with associations varying by tumor subtype and genetic correlations among subtypes.

Fine-mapping of 150 breast cancer risk regions identifies 178 high confidence target genes

This study fine-maps 150 breast cancer risk regions to identify 178 high confidence target genes using genomic and functional annotations.