Summarized by Masters of Longevity from Singularity Hub.
A protein-based AI virtual cell article that explains how researchers built and tested a model to predict which drug pairs might work best for individual triple-negative breast cancer samples.
Key Takeaways
- The model was trained on over 38 million protein measurements from 18 breast cancer cell lines treated with 63 drugs and 59 combinations.
- ProteinTalks scored known effective drug combinations higher and identified new candidate two-drug pairs validated in patient-derived cell samples.
- Using proteomics from three patients, the model recommended regimens that inhibited tumor cell growth at lower doses than standard therapies.
