Predicting detailed gene maps from routine tissue images
Developing informatics tools to predict virtual spatial transcriptomics data with single-cell resolution in large-scale studies
This project builds computer tools that use standard pathology images to create detailed maps of where genes are active across tissues, to help researchers working with many patient samples.
Quick facts
| Grant type | R01 grant |
|---|---|
| Study type | NIH-funded research |
| Funding institution | University of Pennsylvania NIH-funded |
| Lab location | 1 site (Philadelphia, United States) |
| Project ID | NIH-11177945 on NIH RePORTER |
What this research studies
Researchers will train machine-learning models to read routine H&E-stained histology slides and predict spatial gene expression at near single-cell detail. They will combine limited experimental spatial transcriptomics data with large collections of histology images to teach and validate the models. The team plans to produce software that can generate 'virtual' spatial transcriptomics for big sample sets like biobanks, reducing cost and turnaround time. These virtual maps would let scientists study links between tissue gene patterns and clinical outcomes across large patient groups.
Who could benefit from this research
Good fit: Ideal candidates are people whose tissue samples and H&E slides are stored in biobanks or pathology archives and who have consented to research use of their samples.
Not a fit: Patients without available tissue samples, without consent for research use, or with conditions not represented in the training data may not see direct benefit from this work.
Why it matters
Potential benefit: If successful, this could let clinicians and researchers generate detailed gene maps from inexpensive tissue images, speeding research and enabling large-scale studies that might reveal new disease markers or therapeutic targets.
How similar studies have performed: Prior studies have shown links between histology features and gene activity, but producing large-scale, single-cell-resolution virtual spatial maps from images is a newer and still-developing approach.
Where this research is happening
Philadelphia, United States
- University of Pennsylvania — Philadelphia, United States (Active)
Researchers
- Principal investigator: Li, Mingyao — University of Pennsylvania
- Study coordinator: Li, Mingyao
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.