Artificial intelligence (AI) has emerged as a powerful tool in human genetics, enabling the analysis and interpretation of complex datasets generated by nextgeneration sequencing, single-cell profiling, and large population biobanks. Traditional statistical and computational methods struggle with the scale, noise, and heterogeneity of these data, whereas AI approaches, particularly machine learning (ML) and deep learning (DL), are uniquely suited to uncover hidden patterns and make clinically relevant predictions. Current applications of AI in genetics include identifying the possible effects of genomic mutations, data base genome mapping, genomic control, and association of different biological data. There has also been some progress in diagnostics of rare diseases, pharmacogenomics, genome-wide association studies (GWAS), and polygenic risk scores analysis. AI has also influenced precision medicine. The use of deep variant, alpha fold, and AI-aided clinical tools are important milestones to note in the arms of genomic medicine. Regardless of progress clinical decision support systems still face challenges like lack interpret interface, reproducibility of data, and equity issues related to privacy. This review aims to describe the dominions in the application AI to human genetics, success tracking, flaws and relief for AI stems from.
Review Article
English
P. 43-51