Predicting how different patients' cells respond to medicines
Machine Learning for Drug Response Prediction
This work uses AI to predict which medicines will work for specific cell types and to make those predictions more useful for real patients.
Quick facts
| Grant type | NIH-funded research |
|---|---|
| Study type | NIH-funded research |
| Funding institution | University of Michigan at Ann Arbor NIH-funded |
| Lab location | 1 site (Ann Arbor, United States) |
| Project ID | NIH-11170464 on NIH RePORTER |
What this research studies
As a patient, I would expect this project to use machine-learning models trained on lab-grown cell lines to learn patterns of drug response. The team plans to improve how models work across different labs and experiment types and to move the predictions from cells toward human patients. They will fine-tune large language models to pull drug information from the scientific literature and incorporate genetic diversity and tumor evolution into predictions. The aim is to make drug-response predictions more reliable so doctors could eventually choose treatments that better match a patient’s cells or tumor.
Who could benefit from this research
Good fit: Patients with cancer or other conditions where genetic changes in cells guide treatment decisions would be the most likely to benefit.
Not a fit: People without diseases driven by cell-type or genetic differences, or whose care does not rely on targeted drugs, may not see direct benefits.
Why it matters
Potential benefit: If successful, this could help doctors choose more effective, personalized treatments and speed up drug development.
How similar studies have performed: Previous machine-learning work has shown promise predicting drug effects in cell lines, but translating those results reliably to human patients remains difficult and less proven.
Where this research is happening
Ann Arbor, United States
- University of Michigan at Ann Arbor — Ann Arbor, United States (Active)
Researchers
- Principal investigator: Guan, Yuanfang — University of Michigan at Ann Arbor
- Study coordinator: Guan, Yuanfang
About this research
- This is an active NIH-funded research project — typically early-stage science, not a clinical trial accepting patient enrollment.
- Some NIH-funded labs run parallel clinical studies or seek volunteers for related work. To check, contact the principal investigator or institution listed above.
- For full project details, budget, and progress reports, visit the official NIH RePORTER page below.