The article "Molecular Fragmentation as a Crucial Step in the AI-Based Drug Development Pathway" by Shao Jinsong, Jia Qifeng, Chen Xing, Yajie Hao, and Li Wang, provides a comprehensive overview of the current state of molecular fragmentation techniques in the context of AI-driven drug discovery. The authors highlight the importance of molecular fragmentation in understanding and representing chemical space, which is crucial for the effective use of Generative Pre-trained Transformers (GPT) models in drug development. They discuss various approaches to molecular fragmentation, including sequence-based and structure-based methods, and their applications in fragment-based drug discovery (FBDD). The review emphasizes the advantages of FBDD over traditional high-throughput screening methods, such as higher sensitivity, smaller compound libraries, and increased drug efficiency. The authors also address the challenges and future directions in molecular fragmentation, including the need for more efficient and accurate methods, the preservation of fragmentation information, and the evaluation of molecular fragment quality. The article concludes with a discussion on the selection of molecular fragments for FBDD and the importance of a well-curated fragment library.The article "Molecular Fragmentation as a Crucial Step in the AI-Based Drug Development Pathway" by Shao Jinsong, Jia Qifeng, Chen Xing, Yajie Hao, and Li Wang, provides a comprehensive overview of the current state of molecular fragmentation techniques in the context of AI-driven drug discovery. The authors highlight the importance of molecular fragmentation in understanding and representing chemical space, which is crucial for the effective use of Generative Pre-trained Transformers (GPT) models in drug development. They discuss various approaches to molecular fragmentation, including sequence-based and structure-based methods, and their applications in fragment-based drug discovery (FBDD). The review emphasizes the advantages of FBDD over traditional high-throughput screening methods, such as higher sensitivity, smaller compound libraries, and increased drug efficiency. The authors also address the challenges and future directions in molecular fragmentation, including the need for more efficient and accurate methods, the preservation of fragmentation information, and the evaluation of molecular fragment quality. The article concludes with a discussion on the selection of molecular fragments for FBDD and the importance of a well-curated fragment library.