Award
NIH Reporter #1R21HG014015-01
From Text to Translation: Using Language Models to Resolve and Classify Variants
Recipient
Brigham and Women's Hospital, Boston, MA, United States
Award Amount
$240,647.00
Ceiling
$240,647.00
Awarded
August 15, 2025
Identifier
1R21HG014015-01
Development of deep learning methods using language models to improve classification of genetic variants and enhance genomic medicine.
Description
This project aims to develop deep learning methods to resolve uncertain genetic variant classifications using language models. It leverages clinical reports from genetic screenings to predict pathogenicity and improve genomic medicine. The project involves optimizing text classification models, explainability methods, and knowledge graphs to enhance variant interpretation.