SAMP-Score: a morphology-based machine learning classification method for screening pro-senescence compounds in p16...

Area of Science:

• Oncology
• Cell Biology
• Biotechnology

Background:

• Senescence identification lacks universal biomarkers, hindering pro-senescence therapeutic development.
• Basal-like breast cancer (BLBC) often exhibits senescence hallmarks (Sen-Mark+), yet has limited treatment options.
• Novel pro-senescence compounds are needed for Sen-Mark+ cancers.

Purpose of the Study:

• To develop a machine learning tool for identifying senescence induction in Sen-Mark+ cancers.
• To address the challenge of senescence identification in difficult-to-treat cancer subtypes.
• To discover novel pro-senescence compounds for therapeutic applications.

Main Methods:

• Developed SAMP-Score, a machine learning classification tool.
• Utilized senescence-associated morphological profiles (SAMPs) for classification.
• Applied the tool to identify senescence induction in Sen-Mark+ cancers.

Main Results:

• SAMP-Score effectively identifies senescence induction in Sen-Mark+ cancers.
• Identified distinct senescence-associated morphological profiles (SAMPs).
• Facilitated high-throughput screening for senescence identification.

Conclusions:

• SAMP-Score enables identification of senescence induction in challenging cancer contexts.
• Discovered QM5928, a novel pro-senescence compound.
• QM5928 induces senescence in Sen-Mark+ cancers and can be used to study senescence pathways.