AI-powered omics-based drug pair discovery for pyroptosis therapy targeting triple-negative breast cancer

Area of Science:

• Biomedical Engineering
• Computational Biology
• Oncology

Background:

• Traditional drug development faces low success rates and long cycles.
• Omics data offers potential for personalized medicine but presents challenges in data heterogeneity and target distribution.
• Triple-negative breast cancer (TNBC) remains a challenging disease with limited treatment options.

Purpose of the Study:

• To develop an intelligent drug discovery framework for pyroptosis therapy in TNBC.
• To rapidly screen and optimize compound drug pairs for precision medicine.
• To establish a novel drug development paradigm for refractory diseases.

Main Methods:

• Data mining of a large TNBC cohort and drug databases.
• Establishment of a biofactor-regulated neural network for drug pair screening.
• Preparation of biomimetic nanococrystals for targeted drug delivery.
• Investigation of nanococrystal mechanisms involving ribosomal stress and pyroptosis induction.

Main Results:

• Identification of an optimized drug combination (mitoxantrone and gambogic acid) for pyroptosis therapy.
• Development of biomimetic nanococrystals for effective drug delivery in TNBC models.
• Elucidation of the mechanism by which nanococrystals regulate pyroptosis genes and immune effects.
• Demonstration of an innovative drug repurposing strategy for refractory cancers.

Conclusions:

• The developed omics-based intelligent framework enables rapid and precise drug discovery.
• This approach repurposes existing drugs for effective treatment of refractory diseases like TNBC.
• The study highlights a promising new paradigm for targeted cancer therapy and precision medicine.