In recent years, the deep integration of artificial intelligence (AI) with medical education has unveiled new opportunities for teaching《Biochemistry and Molecular Biology》, while also providing novel pathways to address the pedagogical challenge of protein structure and function. Centered on the case of anaplastic lymphoma kinase (ALK) gene mutations in non-small-cell lung cancer (NSCLC), this study integrates AI technology into case-based learning (CBL), constructing an AI-CBL integrated teaching model. This model incorporates an intelligent case-generation system to dynamically build ALK mutation scenarios based on real-world clinical data, thereby tightly connecting molecular biology knowledge with clinical problems. It utilizes AI-powered protein structure prediction tools to accurately visualize the three-dimensional structures of both wild-type and mutant ALK proteins, dynamically simulating the functional abnormalities caused by their conformational changes. Furthermore, a virtual simulation platform is employed to replicate the workflow of ALK gene detection, bridging the gap between theory and practical skills. Consequently, a multi-dimensional teaching system is formed, driven by clinical cases and combining molecular structure analysis with experimental technique validation. The results of teaching practice demonstrate that the three-dimensional visualization, dynamic interactivity, and intelligent analytical capabilities provided by AI technology significantly enhance students’ comprehension depth regarding molecular mechanisms, classroom engagement, and innovative research capabilities. This model establishes a cohesive training pathway spanning “fundamental theory–scientific research thinking–clinical practice”, offering an efficient solution for overcoming teaching difficulties and exploring a viable path for the intelligent transformation of medical education.