UC San Diego researchers have developed AI-powered virtual cell models using 4D imaging to predict cellular responses to drugs, potentially expediting drug development.
Key Details
- 1Researchers used 4D lattice light-sheet microscopy to image mitochondria in cells treated with 25 drugs, generating 40,000 single-cell movies.
- 2A deep learning model, MitoSpace, was trained on this dataset to autonomously group cell responses and predict energetic cell states based solely on mitochondrial shapes.
- 3MitoSpace achieved 75% accuracy in grouping drug mechanisms using 4D data, versus 56% with 2D images.
- 4A separate physics-based digital twin of a cell replicated mitochondrial behaviors observed in real 4D microscopy data, including drug effects.
- 5The combined approach may dramatically reduce lab experiments, increasing efficiency for research in cancer, Alzheimer’s, diabetes, and rare diseases.
- 6UC San Diego has filed patents and started a company based on this technology.
Why It Matters
This innovation bridges advanced imaging, AI pattern recognition, and dynamic modeling, offering a template for future research in imaging-based AI and personalized medicine. Applying these virtual models could lead to faster, less resource-intensive evaluation of drug effects and disease mechanisms, crucial for translational radiology and biomedical imaging communities.
Source
EurekAlert
Related News
•EurekAlert
UVA's $4M NIH Grant Backs AI to Optimize Cardiac MRI Therapies
UVA secures $4 million NIH funding to develop GenStrain, an AI model using MRI data to personalize cardiac pacing therapies.
•EurekAlert
Machine Learning Models Predict Cancer Risk with Routine Health Data
Researchers developed machine learning models using routinely collected health data to predict individual risk for 20 common cancers, outperforming traditional methods for several cancer types.
•EurekAlert
Duke Receives $25M to Lead National Trustworthy AI Hub for Dementia and Aging
Duke University has launched a $25 million national center to make AI for aging and dementia clinically robust and trustworthy.