Integrative Analysis of ATAC-Seq and RNA-Seq through Machine Learning Identifies 10 Signature Genes for Breast Cancer...

Area of Science:

• Genomics
• Epigenetics
• Computational Biology

Background:

• Breast cancer is a complex disease with distinct molecular subtypes.
• Understanding gene regulation requires integrating transcriptome (RNA-seq) and epigenetic (ATAC-seq) data.
• No existing models classify breast cancer subtypes using integrated RNA-seq and ATAC-seq data.

Purpose of the Study:

• To develop a machine learning model for predicting breast cancer intrinsic subtypes.
• To utilize integrative analysis of RNA-seq and ATAC-seq data for subtype classification.
• To identify key genes associated with breast cancer subtypes.

Main Methods:

• Employed machine learning algorithms, including support vector machine (SVM) and recursive feature elimination with cross-validation (RFECV).
• Utilized SHAP (SHapley Additive exPlanations) for feature importance analysis.
• Integrated RNA-seq and ATAC-seq data for comprehensive analysis.

Main Results:

• Identified 10 signature genes (CDH3, ERBB2, TYMS, GREB1, OSR1, MYBL2, FAM83D, ESR1, FOXC1, NAT1) for subtype classification.
• These genes are significantly associated with immune responses, hormone signaling, cancer progression, and cellular proliferation.
• Developed a novel classification model for breast cancer intrinsic subtypes.

Conclusions:

• The integrative analysis of RNA-seq and ATAC-seq data, combined with machine learning, provides a powerful approach for breast cancer subtype classification.
• The identified signature genes offer insights into the molecular mechanisms driving different breast cancer subtypes.
• This model has the potential to improve breast cancer diagnosis and treatment strategies.