Project Grant R35GM166362

This Project Grant, awarded by the National Institute of General Medical Sciences (NIGMS) under the Biomedical Research and Research Training program (CFDA 93.859), provides $466,125 in federal funding to New York University School of Medicine to advance artificial intelligence (AI) methodologies for predicting the molecular effects of genetic mutations. Awarded on July 15, 2026, with a completion date of March 31, 2031, the research will integrate large-scale experimental datasets with protein language models (PLMs) to develop enhanced variant effect prediction (VEP) tools that characterize complex, multi-dimensional mutation effects rather than generating simple binary classifications of damaging or neutral variants.

The primary deliverable is the development and refinement of AI models capable of predicting specific molecular phenotypes associated with genetic mutations, including protein expression, stability, and activity. By training and fine-tuning PLMs on experimental data, the research aims to distinguish between different molecular mechanisms of mutation-induced damage—such as protein misfolding and degradation versus disruption of protein binding—thereby providing more precise understanding of how mutations cause disease. This work addresses a critical gap in current genomic AI capabilities and will establish a more scalable, cost-effective alternative to time-consuming and expensive experimental methods for genome-scale analysis of mutation effects.