Decoding the Role of Epigenetics in Breast Cancer Using Formal Modeling and Machine-Learning Methods

Area of Science:

• Epigenetics
• Cancer Biology
• Computational Biology

Background:

• Breast cancer development involves genetic and epigenetic changes, complicating treatment.
• Epigenetic modifications, like DNA methylation silencing tumor suppressor genes (TSGs), are crucial in cancer progression.
• RUNX3 (Runt-related transcription factor 3) is a TSG suppressed by DNA methyltransferase 1 (DNMT1) hypermethylation in breast cancer, but its role in metastasis is unclear.

Purpose of the Study:

• To model the DNMT1-RUNX3 regulatory network to understand epigenetic silencing in breast cancer metastasis.
• To identify potential therapeutic targets and strategies for epigenetic-based breast cancer treatment.

Main Methods:

• Designed a biological regulatory network (BRN) incorporating DNMT1, RUNX3, p21, c-myc, and p53.
• Applied René Thomas qualitative modeling to analyze network dynamics and predict system behavior.
• Utilized machine learning techniques to classify active and inactive DNMT1 modulators.

Main Results:

• The model demonstrated that oncogene c-myc activation and RUNX3 downregulation promote breast cancer invasion and metastasis.
• Homeostasis was achieved when c-myc was absent and RUNX3 was activated.
• A machine learning model achieved 97% accuracy in classifying DNMT1 inhibitors.

Conclusions:

• Persistent c-myc activation and RUNX3 suppression are key epigenetic events driving breast cancer metastasis.
• DNMT1 is a viable epigenetic drug target for breast cancer therapy.
• Machine learning can effectively identify potential DNMT1 modulators for future drug development.