AI-Driven Discovery of Skin Anti-Aging Targets
The CellOS virtual cell model decodes the cell states and molecular mechanisms behind skin aging, then predicts how perturbing candidate targets affects senescence, inflammation, and extracellular matrix metabolism. The goal: anti-aging targets grounded in real biology.
Project Background
An international cosmetics company sought to expand an anti-aging product development system grounded in cell biology mechanisms, conducting anti-aging target research and exploring candidate intervention mechanisms to inform subsequent active ingredient screening and efficacy evaluation.
痛点
| 1 | Skin aging involves many cell types and signaling pathways with complex key mechanisms |
| 2 | Target effects vary by cell type, making intervention outcomes hard to predict |
| 3 | A large number of candidate targets makes conventional experimental screening costly |
| 4 | Weak links between targets and anti-aging efficacy, with little systematic mechanistic evidence |
Solution
| 1 | Build a skin cell state model with CellOS to decode the mechanisms regulating aging |
| 2 | Use AuraPert to predict the effects of gene perturbations on aging-related pathways |
| 3 | Combine cell type information with prediction results to prioritize anti-aging targets for validation |
| 4 | Validate the biological roles of candidate targets through skin cell functional assays |
核心价值
Discover novel anti-aging targets with potential intervention value
Improve candidate target screening efficiency and reduce trial-and-error costs
Reveal target mechanisms of action to strengthen the scientific basis for product development
Support active ingredient research and drive innovation in functional skincare
Case Gallery
