A Systematic Review: Deep Learning for Analyzing Genomic Data to Discover Evolutionary Patterns

With the advancement of genetic sequencing technologies and the increase in the volume of biological data, deep learning (DL) has been adopted as one of the advanced data analysis methods in computational biology and genomic data analyzing. This review studied the articles published between 2020 and 2025 in which deep learning models were used to analyze genomic data. The results of this study show that convolutional neural networks (CNN) have been most widely used in genomic data analysis, while RNN, LSTM, and GNN methods have also been used in some applications such as time series data analysis, gene expression prediction, and molecular interaction discovery. The average accuracy of deep learning models in 2020 was about 88%, which increased to more than 93% in 2025. This improvement has been driven by advances in deep learning architectures, increased quality and volume of genomic data, and the use of hybrid models such as CNN+LSTM and GNN+CNN. In addition, most of the research has focused on cancer diagnosis, genetic diseases, and multi-omics data analysis. However, challenges remain, including multi-omics integration, explainable AI, fusion of genomic and image data, and transfer learning, which require further research. The results of this study indicate that deep learning in genomics data analysis can play an important role in discovering genetic patterns, improving the accuracy of disease diagnosis, and developing personalized therapeutic approaches. In the future, the development of multimodal deep learning models, interpretable methods (XAI), and the use of GNN for the analysis of gene networks and chromosomal interactions could lead to significant advances in this field.