A collaborative research team, headed by Professor Lan Yanyan from the Institute for AI Industry Research at Tsinghua University, has achieved a significant breakthrough by developing an AI-driven ultra-high-throughput drug virtual screening platform named DrugCLIP. The groundbreaking findings have been published in the prestigious journal 'Science'. This innovative platform tackles the critical challenge of swiftly identifying effective compounds within the expansive chemical space for targeted drug discovery. Remarkably, the screening speed of DrugCLIP has been accelerated by millions of times compared to conventional methods, while also enhancing predictive accuracy.

Utilizing this cutting-edge platform, the research team has, for the first time ever, conducted a comprehensive drug virtual screening on a scale comparable to the human genome, encompassing approximately 10,000 protein targets. Their efforts involved analyzing and screening over 500 million drug-like small molecules, ultimately enriching a repository of over 2 million potentially active molecules. Furthermore, the protein-ligand screening database constructed by the team has emerged as the largest of its kind globally, and it is now freely available to the international scientific research community.