Melissa Cline

The paper develops machine learning models to predict pathogenicity of BRCA1 and BRCA2 variants using cancer genomic profiles, improving classification of variants of uncertain significance.

The paper evaluates the performance of functional assays and computational tools in classifying BRCA1 missense variants using a Bayesian framework and empirical validation.

The paper maps MAVE data to human reference sequences to improve variant functional assay utility for genomics applications.

The paper refines ACMG/AMP variant classification criteria for BRCA1 and BRCA2 by calibrating evidence strength and improving classification consistency through expert panel review.

The paper specifies gene-specific rules for interpreting ATM variants using ACMG/AMP guidelines, improving classification accuracy in a pilot study.

The paper models how data sharing affects the classification of genetic variants, showing higher classification probabilities with shared data over time.

The paper develops and applies a computable genotype model within the GA4GH Variation Representation Specification to enable precise and interoperable representation of genomic variation data.

The paper demonstrates federated analysis of BRCA1 and BRCA2 variants in a Japanese cohort to interpret variants of uncertain significance without transferring sensitive data.

The paper introduces the GA4GH Variation Representation Specification (VRS), a framework for precise and federated representation of molecular variation, with a reference implementation and community resources available online.