Predicting how genetic differences affect health with network models and AI

Linking Variants to Multi-scale Phenotypes via a Synthesis of Subnetwork Inference and Deep Learning

NIH-funded research University of Wisconsin-Madison · NIH-11137133

This project uses AI plus knowledge of biological pathways to predict how people's genetic differences influence diseases and traits.

Quick facts

Grant typeU01 cooperative agreement
Study typeNIH-funded research
Funding institutionUniversity of Wisconsin-Madison NIH-funded
Lab location1 site (Madison, United States)
Project IDNIH-11137133 on NIH RePORTER

What this research studies

From a patient's view, researchers are building computer tools that combine what we know about genes and pathways with machine learning to explain how genetic changes lead to health problems. The approach links variant effects on individual genes into networks of interacting genes and trains deep-learning models on large datasets to learn genotype-to-phenotype relationships. The team will use active learning to choose the most informative lab experiments and guide consortium studies that generate more human data. Ultimately the work aims to produce tools that help interpret genetic test results and guide follow-up research or diagnoses.

Who could benefit from this research

Good fit: People with rare or undiagnosed genetic conditions, or those with genetic variants of uncertain significance, would be the most relevant candidates to benefit or contribute data.

Not a fit: Patients whose conditions are not caused by genetic variation or who need immediate changes in clinical care are unlikely to see direct benefit from this grant's work.

Why it matters

Potential benefit: If successful, this work could make it easier to interpret genetic test results, shorten diagnostic odysseys, and point to biological pathways for potential treatments.

How similar studies have performed: There are existing variant-prediction tools that work in some cases, but combining subnetwork models with deep learning and active learning is a newer approach that remains under evaluation.

Where this research is happening

Madison, 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 2026-06-13 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.