Trained on thousands of images, the model is now able to accurately separate true aging from mere toxicity or normal changes, providing a quick and visual way to screen for compounds that drive cancer cells into permanent decline.
“This technology builds on previous observations that senescent cells develop distinct senescence-associated morphological profiles (SAMPs), which can be easily assessed in traditionally difficult senescence identification situations, such as high-throughput screening,” the researchers wrote in the study.
The research team used SAM-Score to screen more than 10,000 experimental compounds and identified a compound called QM5928 that induces senescence in multiple types of cancer cells, but does not kill them.
Researchers believe this compound is worthy of further study. QM5928 was unique in that it was effective against cancers resistant to known drugs (such as palbociclib), which do not necessarily work in cancers with high p16 expression.
“Through the application of SAMP-Score, we identified QM5928, a novel senescence-promoting compound that can induce senescence in a variety of Sen-Mark+ cancers and has potential utility as a tool molecule to explore the mechanisms and pathways by which senescence induction occurs in these cells,” the research study states.
Researchers offer new ways to detect and measure cancer treatments by combining machine learning and high-resolution imaging.
SAMP-Score could pave the way for the emergence of treatments that harness the body’s natural aging process to fight cancer, primarily for patients with treatment-resistant tumors.
