Abstract: In recent years, the integration of Artificial Intelligence (AI) in scientific research has revolutionized the field of molecular biology and medicine. This keynote speech aims to explore three significant aspects of computational intelligence in molecular biology and medicine. In particular, we will go from basic research to clinical research: bioinformatics, medical informatics, and clinical solutions. By leveraging computational intelligence and generative AI, we have enabled breakthroughs in DNA motif analysis, cancer detection, gene editing, and small-molecule drug discovery.

1. Bioinformatics: DNA motifs and gene regulation
Bioinformatics has been greatly enhanced by AI techniques, particularly in the analysis of DNA motifs and gene regulation. Pattern recognition algorithms have proven instrumental in identifying and understanding the intricate patterns within DNA sequences. These algorithms aid in deciphering gene regulatory elements, enabling researchers to unravel the complexity of genetic networks and their impact on cellular processes. Through AI-powered bioinformatics, we have gained deeper insights into the fundamental mechanisms governing gene expression and regulation.

2. Medical informatics: Cancer detection and localization
AI has played a pivotal role in medical informatics, particularly in the realm of cancer detection and localization. Machine learning algorithms have demonstrated remarkable accuracy in analyzing complex medical data, such as radiological images and genomic profiles. By training models on vast datasets, AI can identify subtle patterns indicative of cancerous cells, assisting in early detection and precise localization of tumors. This breakthrough empowers clinicians to make informed decisions, leading to improved patient outcomes and personalized treatment strategies.

3. Clinical solutions: gene editing and small-molecule drug discovery
AI has propelled clinical solutions to new heights, particularly in gene editing and small-molecule drug discovery. With the aid of diffusion models, researchers can simulate and predict the behavior of genetic modifications and their impact on cellular functions. This enables precise gene editing, offering potential therapeutic interventions for genetic disorders. Additionally, AI-driven drug discovery and docking techniques have accelerated the identification of small-molecule compounds with the potential to target specific disease pathways. By leveraging AI in clinical settings, we are witnessing a paradigm shift towards personalized medicine and tailored treatments.

Biography: Ka-Chun Wong was born and raised in Hong Kong where he was lucky enough to be immersed in a multi-cultural environment. He received his B.Eng. in Computer Engineering from United College, The Chinese University of Hong Kong in 2008. He has also obtained his M.Phil. degree in the Department of Computer Science and Engineering at the same university in 2010. From 2011 to 2014, he has spent 3.5 years to finish his PhD degree in the Department of Computer Science at the University of Toronto. Right after his PhD study, Ka-Chun has started his research lab in the Department of Computer Science, City University of Hong Kong. His research group works have been published on Nature Communications, Advanced Science, Nucleic Acids Research, iScience (Cell Press), Briefings in Bioinformatics, Bioinformatics, IEEE/ACM Transactions, NeurIPs, AAAI, IJCAI, ICONIP, and others. He is on the editorial boards and committees of international journals and conferences. Multiple keynote and invited speeches have been delivered worldwide. He was an ACM Distinguished Speaker from 2019 to 2022. He was ranked among the Stanford's top 2% most highly cited scientists for the recent three years (versions 5,6,7).

Abstract: Matrix and Tensor factorizations are important data analytic tools in many applications, such as recommendation systems, image completion, social network data mining, wireless communications, etc. Traditionally, matrix and tensor factorizations are approached from optimization perspective. While proven to be effective, optimization-based matrix and tensor factorizations usually involve hyperparameters tuning, with one of the major hyperparameters being the matrix or tensor rank. However, when the number of hyperparameters is more than 3 or 4, tuning them becomes computationally expensive. This talk approaches the problem from the Bayesian perspective and shows how hyperparameter tuning can be eliminated while providing comparable or even better performance than corresponding optimization-based algorithms.

Biography: Yik-Chung Wu received the B.Eng. (EEE) degree in 1998 and the M.Phil. degree in 2001 from the University of Hong Kong (HKU). He received the Croucher Foundation scholarship in 2002 to study Ph.D. degree at Texas A&M University, College Station, and graduated in 2005. From August 2005 to August 2006, he was with the Thomson Corporate Research, Princeton, NJ, as a Member of Technical Staff. Since September 2006, he has been with HKU, currently as an Associate Professor. He was a visiting scholar at Princeton University, in summers of 2015 and 2017. His research interests are in general areas of machine learning and signal processing, and in particular Bayesian inference, distributed algorithms, and large-scale optimization. Dr. Wu served as an Editor for IEEE Communications Letters, and IEEE Transactions on Communications. He is currently a Senior Area Editor for IEEE Transactions on Signal Processing, an Associate Editor for IEEE Wireless Communications Letters, and an Editor for Journal of Communications and Networks. He received four best paper awards in international conferences, with the most recent one from IEEE International Conference on Communications (ICC) 2020. He was a symposium chair for many international conferences, including IEEE International Conference on Communications (ICC) 2023 and IEEE Globecom 2025. He was elected the Best Editor of the year 2023 in IEEE Wireless Communications Letters. He is an elected member of IEEE signal processing society SPCOM Technical Committee (2025-2026), and an IEEE Distinguished Lecturer (Vehicular Technology Society 2025 class).