An international research team led by the Hong Kong University of Science and Technology (HKUST) has developed an artificial intelligence (AI)-based model that uses genetic information to predict an individual’s risk of developing Alzheimer’s disease (AD) well before symptoms occur. This groundbreaking study paves the way for using deep learning methods to predict the risks of diseases and uncover their molecular mechanisms; this could revolutionize the diagnosis of, interventions for, and clinical research on AD and other common diseases such as cardiovascular diseases.
Researchers led by HKUST’s President, Prof. Nancy IP, in collaboration with the Chair Professor and Director of HKUST’s Big Data Institute, Prof. CHEN Lei, investigated whether AI—specifically deep learning models—can model AD risk using genetic information. The team established one of the first deep learning models for estimating AD polygenic risks in both European-descent and Chinese populations. Compared to other models, these deep learning models more accurately classify patients with AD and stratify individuals into distinct groups based on disease risks associated with alterations of various biological processes. Read More...
HKUST President Prof. Nancy IP (center, front row), Director of HKUST’s Big Data Institute Prof. CHEN Lei (second left, front row), HKUST Division of Life Science Research Professor Prof. Amy FU (first right, front row), Hong Kong Center for Neurodegenerative Diseases (HKCeND) Chief Scientific Officer Dr. Fanny IP (first left, front row) and the first author of the research paper Prof. Fred ZHOU Xiaopu (second right, front row) take a group photo with other members of the research team.
To discover and thoroughly demonstrate the newly identified noncanonical cleavage mechanism, the Hong Kong University of Science and Technology (HKUST) research team, led by Prof. Tuan Anh Nguyen, Assistant Professor of the Division of Life Science, used several sophisticated techniques, such as miRNA sequencing, pri-miRNA structure analysis, and high-throughput pri-miRNA cleavage assays for approximately 260,000 pri-miRNA sequences. In contrast to the canonical mechanism, the noncanonical mechanism does not rely on several essential protein and RNA elements required for the canonical mechanism.
Ice surfaces have a thin layer of water below its melting temperature of 0℃. Such premelting phenomenon is important for skating and snowflake growth. Similarly, liquid often crystallizes into a thin layer of crystal on a flat substrate before reaching its freezing temperature, i.e. prefreezing. The thickness of the surface layer usually increases and diverges as approaching the phase transition (such as melting and freezing) temperature. Besides premelting and prefreezing, whether similar surface phenomenon exists as a precursor of a phase transition has rarely been explored.