Adaptive Fuzzy Consensus Clustering Framework for Clustering Analysis of Cancer Data

Area of Science:

• Computational Biology
• Bioinformatics
• Cancer Research

Background:

• Clustering analysis of gene expression profiles is vital for cancer discovery, diagnosis, and treatment.
• Existing tumor clustering methods often lack integration of fuzzy theory and optimization within consensus clustering frameworks.

Purpose of the Study:

• To propose and evaluate novel fuzzy consensus clustering frameworks for improved tumor clustering using gene expression data.
• To enhance cancer diagnosis and treatment by advancing clustering analysis performance.

Main Methods:

• Introduction of a random double clustering based cluster ensemble framework (RDCCE).
• Development of a fuzzy extension model integrated into RDCCE, forming the random double clustering based fuzzy cluster ensemble framework (RDCFCE).
• Proposal of an adaptive version (A-RDCFCE) incorporating a self-evolutionary process for parameter optimization.

Main Results:

• RDCFCE and A-RDCFCE demonstrate strong performance on real cancer gene expression datasets.
• The proposed fuzzy consensus clustering frameworks outperform existing state-of-the-art tumor clustering algorithms.

Conclusions:

• The integration of fuzzy theory and optimization significantly improves tumor clustering performance.
• RDCFCE and A-RDCFCE offer advanced tools for cancer gene expression data analysis, aiding in diagnosis and treatment.