Artificial intelligence redefines agricultural genetics by unlocking the enigma of genomic complexity

Artificial intelligence (AI) has transformed agricultural genetics, especially in the context of crop improvement strategies. Traditional breeding faces challenges such as polyploidy, high level of genomic heterogeneity, and complex gene-trait associations. By combining multi-omics data researchers learn more about the genetic and molecular basis of important agricultural traits. However, statistical methods are often insufficient to address the data complexity. By contrast, AI techniques, such as machine learning (ML) and deep learning (DL), are emerging as powerful tools to explore complexity. Algorithms such as random forests (RF) and support vector machines (SVM) can support genomic selection (GS) and trait value prediction. Furthermore, DL models such as convolutional neural networks (CNN) and long short-term memory networks (LSTM) dominate high-throughput phenotyping and time series analyses, providing accurate predictions for crop yield, disease resistance, and genotype adaptation. Large language models (LLMs) are able to integrate complex omics data. AI models can analyze large dataset, generated by genomics, transcriptomics, proteomics, metabolomics, and phenomic applications because algorithms can combine different inputs, such as DNA sequences, gene expression profiles, protein–protein interaction networks, metabolite concentrations, and phenotypic data under specific environmental conditions. The integration of individual models can improve prediction accuracy by reducing resource inputs and automating labor-intensive tasks involved in breeding programs. Some recent AI methods, such as gradient boosting machines (GBMs) and Transformer models, are increasingly being used to improve scalability and accuracy of predictive analytics. This review summarizes major advances in AI applications in agricultural genetics, highlighting the strengths and limitations of different ML and DL models and their role in integrating complex datasets. The study highlights the importance of artificial intelligence in understanding genomic complexity and promoting the development of innovative methods to improve crop performance