Interpretable tools to combine multiple molecular tests for cancer and heart disease

Interpretable Bayesian Non-linear statistical learning models for multi-omics data integration

NIH-funded research University of Minnesota · NIH-11194985

Researchers are creating easy-to-understand Bayesian models that blend genomics, proteomics, and other molecular tests to help people with cancer and cardiovascular disease get better predictions about their condition.

Quick facts

Grant typeNIH-funded research
Study typeNIH-funded research
Funding institutionUniversity of Minnesota NIH-funded
Lab location1 site (Minneapolis, United States)
Project IDNIH-11194985 on NIH RePORTER

What this research studies

If I have cancer or heart disease, this project aims to build new statistical tools that combine many types of molecular data (genes, proteins, epigenetics, and transcripts) to find important disease signals. The team will design interpretable Bayesian methods that can capture complex, non-linear relationships across these data types and point to key pathways and molecules. They will apply the methods to large public human datasets like TCGA, dbGaP, and GTEx and to partner-provided patient datasets to find disease subtypes and biomarkers. The researchers plan to release free, user-friendly software so clinicians and scientists can use the tools in future patient care and research.

Who could benefit from this research

Good fit: Ideal candidates are people with cancer or cardiovascular disease who have genomic, proteomic, or other molecular data available in research databases or through collaborating clinical sites.

Not a fit: Patients without molecular testing, without searchable clinical sample data, or with conditions unrelated to the studied molecular markers may not see direct benefit from this work.

Why it matters

Potential benefit: If successful, this work could identify clearer molecular subtypes and better biomarkers that help personalize diagnosis, prognosis, and treatment choices for cancer and heart disease patients.

How similar studies have performed: Previous multi-omics efforts have produced useful biomarkers and disease subtypes, but developing broadly interpretable Bayesian non-linear integration methods at this scale is relatively novel.

Where this research is happening

Minneapolis, 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.
Conditions CancersCardiovascular Diseases
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.