Md Ishtyaq Mahmud, Tania Banerjee
This is a comprehensive review that systematically organizes various AI techniques, resources, challenges, and prospects utilized in the field of genomics.
Due to the vastness and complexity of genomic data, there is a need for a systematic review of effective AI applications and a clear understanding of future challenges.
The paper systematically analyzes and summarizes cases where key AI techniques, such as machine learning, deep learning, NLP, generative models, and explainable AI, are applied to core areas of genomics, including gene sequencing, variant detection, and gene expression analysis.
It details core computational tools, benchmark datasets, and open-source frameworks supporting genomic research. It also presents major challenges like data quality, interpretability, ethical governance, and computational scalability, along with future prospects through advanced architectures like graph neural networks and multimodal deep learning.