AI to predict and improve CAR T cell cancer therapy

Multimodal AI modeling of T cell therapies to predict patient response and nominate advanced cell design strategies

NIH-funded research Stanford University · NIH-11467177

This project builds AI tools to predict how people will respond to CAR T cell cancer treatments and to suggest molecular changes to make the cells safer and more effective.

Quick facts

Grant typeNIH-funded research
Study typeNIH-funded research
Funding institutionStanford University NIH-funded
Lab location1 site (Stanford, United States)
Project IDNIH-11467177 on NIH RePORTER

What this research studies

You will be hearing about AI systems that learn from detailed cell-level data, tumor images, and clinical records to forecast who will benefit from CAR T cell therapy and who might have side effects. One model (tcellGPT) uses single-cell and molecular profiles of the infused CAR T product, and another (tnicheAI) analyzes tumor images to find suppressive areas in the tumor environment. The two models are combined into tcellAI so doctors and researchers can see a fuller picture that includes the infusion product, the tumor, and patient health details. Clinicians and bioethicists are involved throughout to help protect privacy and fairness as the tools are developed.

Who could benefit from this research

Good fit: Ideal candidates are people with cancers being considered for or already scheduled to receive CAR T cell therapy at participating medical centers.

Not a fit: People without cancer or those who are not eligible for CAR T cell therapy are unlikely to benefit directly from this work.

Why it matters

Potential benefit: If successful, these tools could help clinicians personalize CAR T treatments, reduce toxic side effects, and speed development of better engineered cell therapies.

How similar studies have performed: Some prior studies have used machine learning to find predictors of CAR T outcomes, but combining single-cell, spatial pathology, and clinical data to also nominate cell-engineering strategies is a newer, less-tested approach.

Where this research is happening

Stanford, 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 2026-06-10 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.