AI tools to read hidden DNA that controls genes

Developing Novel Deep-Learning Based Methods for Deciphering Non-Coding Gene Regulatory Code

NIH-funded research State University New York Stony Brook · NIH-11225269

This project uses advanced AI to find hidden DNA changes that may drive brain and lung cancers and help point to important genetic causes.

Quick facts

Grant typeR01 grant
Study typeNIH-funded research
Funding institutionState University New York Stony Brook NIH-funded
Lab location1 site (Stony Brook, United States)
Project IDNIH-11225269 on NIH RePORTER

What this research studies

If I have brain or lung cancer, researchers are building advanced AI that treats DNA like a language to find hidden non-coding changes that may drive my cancer. They will improve and fine-tune models called DNABERT and DNABERT-2 using tumor and normal DNA to detect combinations of somatic and germline variants that disrupt gene regulation. The tools are designed to rank which non-coding changes are most likely harmful so doctors and scientists can follow up. Although mostly computational, the work uses human cancer sequencing data and aims to guide future tests or treatments.

Who could benefit from this research

Good fit: Ideal candidates are people with diagnosed brain or lung cancer who have had or are willing to provide tumor and normal DNA sequencing data.

Not a fit: People without brain or lung cancer or those who do not have genomic sequencing data are unlikely to receive direct benefit from this work.

Why it matters

Potential benefit: If successful, this could help identify hidden genetic changes in tumors and suggest new diagnostic markers or treatment targets for brain and lung cancer patients.

How similar studies have performed: Related foundation models like DNABERT and DNABERT-2 have shown strong performance on genomic prediction tasks, but applying deep learning to prioritize combinations of non-coding variants in cancer remains an emerging area.

Where this research is happening

Stony Brook, 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.