Researchers developed PRTS, a deep learning model that infers single-cell spatial transcriptomics from standard H&E-stained tissue images.
Key Details
- 1PRTS stands for Pathology-driven Reconstruction of Transcriptomic States.
- 2It predicts an expression matrix for 1,820 genes at single-cell resolution from H&E images.
- 3The method provides 27x higher resolution than traditional spatial transcriptomics spot technologies.
- 4Validated on mouse brain, human lung cancer, and breast cancer datasets.
- 5PRTS identified 21 cell subtypes and matched key gene expression patterns to ground truth.
- 6Potential applications include diagnostics, cancer subtyping, and drug discovery.
Why It Matters
PRTS could enable cost-effective, scalable spatial transcriptomics directly from routinely collected pathology slides, advancing both research and diagnostics where gene expression mapping was previously prohibitively expensive or impractical.
Source
EurekAlert
Related News
•EurekAlert
Stanford's SleepFM AI Predicts 130 Disease Risks from Polysomnography
Stanford researchers have developed SleepFM, an AI model that predicts over 100 diseases using one night of sleep study data.
•EurekAlert
MIT and Microsoft Use AI to Develop Molecular Sensors for Early Cancer Detection
MIT and Microsoft researchers created an AI model to design peptide-based sensors for ultra-early cancer detection by detecting cancer-specific enzymes.
•EurekAlert
AI-Enhanced ECGs Enable Early COPD Detection Across Large Cohorts
Mount Sinai researchers show that deep learning applied to ECGs can detect COPD early and accurately across diverse populations.