Optimized SNP Selection for Rheumatoid Arthritis Using Genetic Algorithm and Arithmetic Optimization Algorithm

Optimized Single Nucleotide Polumorphisms (SNP) selection enhances genetic risk prediction for rheumatoid arthritis. Genetic Algorithm (GA) and Arithmetic Optimization Algorithm (AOA) improve SNP selection efficiency. Evolutionary techniques refine polygenic risk score-based predictions with high accuracy. GA applies crossover and mutation for diverse SNP prioritization. AOA further optimizes selections by exploring new SNP combinations. Integration of these methods achieves superior performance over conventional approaches. The dataset includes top-ranked SNPs from rheumatoid arthritis genome-wide association studies. Polygenic risk scores quantify genetic susceptibility across different SNP variations. Performance evaluation considers accuracy, precision, recall, and F 1-score metrics. The method achieves 99% accuracy with an F1-score of 0.9954. Precision reaches 98%, while recall remains high at 99%. Results demonstrate significant improvements in SNP prioritization and ranking efficiency. Compared to traditional selection techniques, enhanced accuracy and predictive performance are observed. GA ensures comprehensive SNP selection, while AOA refines optimal solutions. The approach reduces computational complexity while maintaining high predictive accuracy. Performance evaluation highlights robustness in real-world genetic datasets. GA and AOA together optimize SNP selection strategies for improved rheumatoid arthritis risk estimation. The study contributes to advancements in computational genomics and disease prediction. Future research will explore larger datasets for further validation. The proposed method provides a scalable solution for complex trait analysis in rheumatoid arthritis.