At the recent China National Computer Conference, the list of selected scholars for the CCF-Tencent Open Fund in 2023 was announced. In 2023, CCF-Tencent Open Fund received over 230 applications from nearly 90 universities. After a month of reviewing, the review experts conducted a comprehensive evaluation from the scholars’ research ability, research value, academic innovation, and feasibility of the proposed plan. Finally, 1 Distinction Award, 6 Excellence Awards, and 19 Cooperation Awards were selected. Among them, Assist Prof. Zhang Qiang of ZJUI, won the Excellence Award, with the project of Structure-aware Large Language Model for Protein Design and Optimization.
The CCF-Tencent Open Fund project is one of the earliest and most influential enterprise cooperation funds established by the China Computer Federation. I feel very honored to receive the Excellence Award and to be ranked first. Being able to stand out from the 26 funded projects and receive recognition from academic and business experts is a great affirmation of my academic pursuit and research achievements in the past year. This will also encourage me to continue exploring the interdisciplinary field of AI for science and constantly reach new heights, " Assistant Professor Zhang Qiang shared with us.
▲ Assistant Professor Zhang Qiang (fourth from the right) attends the award ceremony
In recent years, deep learning methods have made remarkable progress in protein modeling. However, the mutual correspondence between protein sequence-structure-function is still unclear, and research still faces key challenges such as inaccurate prediction of protein quaternary structure, poor performance of structure-based protein sequence design, and the need for a large amount of label data for sequence optimization. To address these challenges, Assistant Professor Zhang Qiang's award-winning project aims to develop and implement a protein design and optimization method based on a structure aware large language model. This method has taken the lead in constructing the first amino acid knowledge graph AAKG, improving the efficiency of functional protein optimization by nearly three times, and building the world's largest biological sequence vector database, which contains over 1 billion protein and nucleotide sequences. Experiments have shown that this database is 59 times faster than Foldseek TM in retrieving homologous sequences, and the average retrieval accuracy (MAP) has also been improved by 38%.
▲ Overview of Assistant Professor Zhang Qiang's award-winning project
CCF-Tencent Open Fund was jointly initiated by the China Computer Federation (CCF) and Tencent in 2013. For the past 12 years, the Fund has been committed to building a platform for industry-academia cooperation and innovation for young scholars at home and abroad, promoting the sustained value of technology in industrial innovation and social development. This year, the fund released 5 cutting-edge fields with a total of 28 technological research topics, continuing to focus on "artificial intelligence technology", paying attention to the development of cutting-edge technologies, and exploring real application scenarios for enterprises.
Dr. Qiang Zhang obtained his Ph.D. degree and served as a postdoctoral researcher, both at the Department of Computer Science, University College London in the United Kingdom. He was supervised by Prof. Emine Yilmaz, an internationally renowned expert in the field of information retrieval and natural language processing. He has published over forty articles in top-tier academic journals and conferences including Nature Machine Intelligence, Nature Communications, NeurIPS, ICML, ICLR, AAAI and ACL. He has numerous award such as the Great Britain-China Educational Trust in 2020.
