Predicting how genetic changes affect protein function using AI

Extending the utility and performance of variant effect predictors with protein language models

NIH-funded research University of California, San Francisco · NIH-11254907

Using advanced protein-focused AI to give clearer, more reliable predictions about whether specific genetic changes may cause disease for people with genetic test results.

Quick facts

Grant typeR01 grant
Study typeNIH-funded research
Funding institutionUniversity of California, San Francisco NIH-funded
Lab location1 site (San Francisco, United States)
Project IDNIH-11254907 on NIH RePORTER

What this research studies

This project uses artificial intelligence models trained on protein sequences to better predict the effects of changes in your genes on protein function. Researchers will combine AI with 3D protein structure information, related gene data, and existing clinical databases to improve interpretation of genetic test results. They will also compare AI predictions to lab-based functional tests and look at whole-haplotype (combined variant) effects to reflect how real genetic backgrounds influence outcomes. The goal is to reduce the number of "variants of unknown significance" and make genetic findings more actionable for patients.

Who could benefit from this research

Good fit: People who have undergone genetic testing and received unclear or uncertain protein-coding variant results, or those with suspected inherited conditions tied to protein-altering variants, would be most relevant.

Not a fit: People whose conditions are not related to protein-altering genetic variants or who have not had genetic sequencing are unlikely to benefit directly from this project.

Why it matters

Potential benefit: If successful, this work could make genetic test reports more informative, reduce uncertain results, and help guide diagnosis and treatment decisions.

How similar studies have performed: Early studies show protein language models can improve variant prediction, but combining them with 3D structures, clinical data, and whole-haplotype analyses is a newer approach that still needs real-world validation.

Where this research is happening

San Francisco, United States

Researchers

About this research

  1. This is an active NIH-funded research project — typically early-stage science, not a clinical trial accepting patient enrollment.
  2. Some NIH-funded labs run parallel clinical studies or seek volunteers for related work. To check, contact the principal investigator or institution listed above.
  3. For full project details, budget, and progress reports, visit the official NIH RePORTER page below.
Last reviewed 2026-06-09 by the Find a Trial editorial team. Information on this page is for educational purposes and is not medical advice. Always consult qualified healthcare professionals about clinical trial participation.