Fuzzy Expert System based on a Novel Hybrid Stem Cell (HSC) Algorithm for Classification of Micro Array Data

Area of Science:

• Bioinformatics
• Computational Biology
• Genomics

Background:

• Microarray data analysis is crucial for understanding genetic variants in diseases.
• High dimensionality of gene expression samples necessitates automated analysis systems.
• Fuzzy expert systems offer superior classification compared to traditional methods, but knowledge acquisition remains a challenge.

Purpose of the Study:

• To propose an innovative Hybrid Stem Cell (HSC) algorithm for designing a fuzzy classification system.
• To extract informative rules and form membership functions from microarray datasets.
• To enhance the accuracy of microarray data analysis for disease-related genetic variants.

Main Methods:

• Utilized Ant Colony Optimization and Stem Cell algorithm for fuzzy classification system design.
• Introduced Adaptive Stem Cell Optimization (ASCO) to refine membership function points.
• Employed Mutual Information to identify the most informative genes from large datasets.

Main Results:

• The proposed Hybrid Stem Cell (HSC) algorithm demonstrated superior performance in fuzzy system precision.
• Evaluated using five diverse microarray datasets, confirming the algorithm's effectiveness.
• Achieved more precise fuzzy classification compared to existing methodologies.

Conclusions:

• The Hybrid Stem Cell (HSC) algorithm offers a precise and effective approach for microarray data analysis.
• This method addresses knowledge acquisition challenges in fuzzy classification for genetic studies.
• The findings suggest a significant advancement in automated analysis of complex biological datasets.