An Intelligent Genetic Algorithm–Based System for Automated University Course Allocation

Abstract

Micronutrient prediction and enhancement are severe problems in computational biology, which is important in drug discovery, enzyme design, and synthetic biology.The effectiveness of the traditional method sometimes finds it difficult to look through the huge area with the vast primitive minima present in a protein molecule.In this work, we recommend a hybrid computational approach that brings together Genetic Algorithms (GA) and simulated Annealing (SA) to improve protein configuration optimization.The Genetic Algorithm (GA) has sufficiently explored the result area using selection, crossover, and mutation, giving different types of entrant structures.The Simulated Annealing (SA) method is then used to refine the best entrant, ensuring a low-energy, stable conformation.The outcome of this work shows that the combination of the hybrid GA and SA technique is better than a single method used based on energy reduction and structural stability.Moreover, we correlate the optimized structures with real protein conformations from the Protein Data Bank (PDB) using Root Mean Square Deviation (RMSD) analysis to assess biological correctness.The results indicate that our hybrid model can achieve near-native protein structures while maintaining computational efficiency.