From traditional to data-driven medicinal chemistry: A case study

•A data-driven medicinal chemistry model was explored in drug discovery.•Data science methods were used by medicinal chemists to varying extents.•Data analytics and visualization notably improved project time efficiency.•Predictive modeling was under-utilized but contributed to IP generation.•A concept was devised to educate next-generation medicinal chemists. Artificial intelligence (AI) and data science are beginning to impact drug discovery. It usually takes considerable time and efforts until new scientific concepts or technologies make a transition from conceptual stages to practical applicability and experience values are gathered. Especially for computational approaches, demonstrating measurable impact on drug discovery projects is not a trivial task. A pilot study at Daiichi Sankyo Company has attempted to integrate data science into practical medicinal chemistry and quantify the impact, as reported herein. Although characteristic features and focal points of early-phase drug discovery naturally vary at different pharmaceutical companies, the results of this pilot study indicate significant potential of data-driven medicinal chemistry and suggest new models for internal training of next-generation medicinal chemists