Steven N. Hart

The paper enhances missense variant classification in intrinsically disordered regions by integrating IDR-specific features with existing predictors, significantly improving PR-AUC scores.

The paper uses case-control data from over 400,000 women to classify BRCA1 and BRCA2 variants, finding high consistency with ClinVar annotations for 785 previously unclassified variants.

This study evaluates breast cancer risks associated with pathogenic variant type and location in BRCA2 and other genes, finding differential risks based on variant position.

This study evaluates how generative AI-generated protein structures improve LOF activity prediction in breast cancer genes compared to experimental structures and other predictors.

The paper functionally characterizes BRCA2 variants using saturation genome editing and classifies them clinically, finding functionally abnormal variants are associated with increased cancer risk.

This paper evaluates workflow management systems for genomics research and clinical use, comparing their features and suitability across different environments and use cases.

The paper develops a tool to estimate mutation prevalence in hereditary cancer genes based on clinical and demographic factors using data from 150,000 multi-gene panel tests.

BRCA-ML is a machine learning model trained to predict the functional impact of missense variants in BRCA1 and BRCA2 genes, outperforming existing methods.

This study compares the accuracy and performance of Sentieon DNASeq and GATK for single-sample variant calling, finding they are nearly identical in accuracy with Sentieon being faster and more scalable.

This paper introduces a robust image registration method for re-stained histological WSIs, reducing registration errors and enabling subcellular-level analysis.

This study benchmarks GATK3.8 and GATK4 to evaluate performance improvements and cost trade-offs in genomic variant calling.