Genetic Algorithms and Neural Networks: a Fusion for Bioinformatics Advancements

EasyChair Preprint 12448

Abstract

In the field of bioinformatics, the integration of genetic algorithms (GAs) and neural networks (NNs) has emerged as a promising approach for addressing complex biological problems. This fusion leverages the complementary strengths of GAs in optimization and NNs in pattern recognition to tackle challenges such as gene expression analysis, protein structure prediction, and biomarker discovery. This paper provides a comprehensive review of the synergy between GAs and NNs in bioinformatics applications. Firstly, it elucidates the fundamentals of both GAs and NNs, highlighting their capabilities and limitations. Subsequently, it explores how GAs can be utilized to optimize NN architectures, parameters, and training processes, leading to enhanced performance and robustness. Moreover, it discusses the incorporation of NNs within GAs for fitness evaluation, population initialization, and solution representation, enabling efficient exploration of solution spaces in bioinformatics problems. Furthermore, this paper presents case studies and examples illustrating the successful integration of GAs and NNs in diverse bioinformatics tasks, including gene regulatory network inference, protein-ligand docking, and disease classification. These examples demonstrate the efficacy of GA-NN fusion in addressing real-world challenges and achieving competitive results compared to traditional methods.

Keyphrases: Bioinformatics, Genetic Algorithms, neural networks

@booklet{EasyChair:12448,
  author    = {Jane Elsa and Jack Milson},
  title     = {Genetic Algorithms and Neural Networks: a Fusion for Bioinformatics Advancements},
  howpublished = {EasyChair Preprint 12448},
  year      = {EasyChair, 2024}}