Biosynthetic gene clusters (BGCs) are groups of clustered genes found in bacteria, fungi, and some plants and animals that are crucial for synthesizing secondary metabolites. In recent years, genome mining of BGCs has emerged as a prominent research focus, particularly in natural product discovery and drug development. Compared to traditional experimental methods, applying computational techniques has significantly enhanced the efficiency of BGC identification and annotation, thereby facilitating the discovery of novel metabolites. The advent of artificial intelligence, particularly machine learning models and more advanced deep learning algorithms, has significantly enhanced both the speed and precision of BGC mining. This review offers a comprehensive introduction to currently developed BGC databases and prediction tools, highlighting the potential of machine learning technologies in BGC mining. Additionally, it summarizes the challenges computational methods face in this area and discusses future research directions.