LEUNG, Kwong-Sak 

Emeritus Professor,  Computer Science & Engineering

Research Professor (2018-21)

(Chair) Professor of Computer Science & Engineering (2002-2018)
in the CUHK-BGI Innovation Institution of Trans-omics (2011-2018)

Associate Director, Institute of Future Cities (2013-2021)
Director, Urban Informatics Programme, IOFC (2014-2021)
B.Sc.(Eng), Ph.D.(Lond.), Distinguished Fellow HKCS, FHKIE, SMIEEE, MIET, C.Eng. 

Dr. Leung is currently Emeritus Professor. He was Professor of Computer Science & Engineering (Chair Professor) until 2018 and was appointed as Professor in the CUHK-BGI Innovation Institution of Trans-omics in the Chinese University of Hong Kong.  He was Chairman of the Department from Aug 1999 to July 2005 and the Head of Graduate Division of Computer Science between April, 1992 and July, 1997. He worked as a senior engineer and system analyst at ERA Technology and the Headquarters computer centre of Central Electricity Generating Board respectively in England for five years before joining the Chinese University in August 1985. He has gained extensive experiences in project management and the development of large scale software for research and simulation purposes.

Dr. Leung received his B.Sc. and Ph.D. degrees from the University of London in 1977 and 1980 respectively, and is a  fellow of HKIE, a member of IET and ACM, a Life senior member of IEEE and a chartered engineer. He was nominated to be the Distinguished Fellow of Hong Kong Computer Society in 2000.  He was one of the founder members and the Chairman of ACM Hong Kong Chapter and a Council member of Hong Kong Computer Society. He contributed significantly in setting up the Engineering Faculty as a member of the Planning & Implementation Committee and all other 7 committees.  He served as a member of the Engineering Panel of the Research Grant Council of the University Grant Committee for 5 years (94-99). He was an external examiner of OUHK. Dr. Leung was member of Editorial Board for Fuzzy Sets and Systems (1999-2019) and the IT Magazine (94-98), associate editor of  International Journal of Intelligent Automation and Soft Computing (2001-2010). He has served as chairman and member of numerous international conference organizing and programme committees. He was a member of the University's Research Committee and the Convener of Engineering Panel (96-00). He has authored and co-authored over 400 publications with an average impact factor of >8.06 for the top 100 Journal papers and 4 books. His research interests are in the areas of knowledge engineering, bioinformatics, drug discovery, soft computing, genetic algorithms and programming, automatic knowledge acquisition, fuzzy logic applications, and AI architecture. 

The numbers of MPhil and PhD students graduated under his supervision are 41 and 31 respectively.

Prof. Leung is ranked among the world’s top 2% most-cited scientists (subfields: Artificial Intelligence and Bioinformatics) in the 2021 released metrics published by Stanford University for both the career-long and single-year categories. (link)

Address: Department of Computer Science and Engineering, The Chinese University of Hong Kong, Shatin, N.T. Hong Kong

Research Interests (Research Summary/Projects)

DNA Patents
Drug Patents
Intelligent Sensor Patent

Books Published Representative Journal Publications: (student name) IF: impact factor (Full publication list Google Scholar)

International Conference & Other Refereed Publications (student)

Research summary (KS Leung)

Research Group: We have a small research group containing myself, Prof KH Lee, Prof MH Wong and some 8 research students, and collaborators from Department of Biochemistry (Prof. Stephen Tsui), Department of Medicine & Therapeutic (Profs. Joseph Sung and Prof. Henry LY Chan), and Department of Clinical Oncology (Prof Tony Mok);
Prof. Hsiang-Fu KUNG, Stanley Ho Centre for Emerging Infectious Diseases
Prof. Marie Chia-Mi LIN, Department of Surgery, Prince of Wales Hospital
Prof. Pang-Chui SHAW, School of Biomedical Sciences

Research Fields: Evolutionary Computation, Data mining, and Bioinformatics

Representative Projects and Results

(1)   Finding DNA Markers of Hepatitis B Virus (HBV)

       Publications (some more in the pipeline):


(2)   Dynamic Cancer Drug Scheduling (in time sequences) for Chemotherapy

- (S. M. Tse), Y. Liang, K. S. Leung, K. H. Lee and Tony S. K. Mok, A Memetic Algorithm for Multiple Drugs Cancer Chemotherapy Schedule Optimization, IEEE Transactions on Systems, Man and Cybernetics - Part B, vol. 37, no. 1, pp.84-91, Feb. 2007.
- (Liang Y.), Leung K.S. and Tony Mok S.K.. "A Novel Evolutionary Drug Scheduling Model in Cancer Chemotherapy," IEEE Transactions on Information Technology in Biomedicine, Vol.10, No.2, pp.237-245, April, 2006.
- (Sui Man Tse), Yong Liang, K. S. Leung, K. H. Lee and Tony Mok, “Multiple Drugs Cancer Chemotherapy Scheduling by a New Memetic Optimization Algorithm”, Proceedings of the 2005 IEEE Congress on Evolutionary Computation .

(3)  Motif Discovery and Gene Network Learning
- T.M. Chan, K.S. Leung, K.H. Lee, M.H. Wong 1, C.K. Lau , Stephen K.W. Tsui, Subtypes of Associated Protein-DNA (Transcription Factor-Transcription Factor Binding Site) Patterns, Nucleic Acids Research, August 2012; doi: 10.1093/nar/gks749
-PY Wong, TM Chan, MH Wong, KS Leung,"Predicting Approximate Protein-DNA Binding Cores Using Association Rule Mining" ICDE 2012 (International Conference on Data Engineering) (accepted)
- (Chan, T.M.), Leung, K.S., and Lee, K.H.,"Memetic Algorithms for de novo Motif Discovery" IEEE Transactions on Evolutionary Computation, 2011.(accepted)
- T.M. Chan, K.C. Wong, K.H. Lee, M.H. Wong, C.K. Lau, Stephen K.W. Tsui, K.S. Leung, Discovering approximate-associated sequence patterns for protein-DNA interactions. Bioinformatics, 2011, 27(4), pp. 471-478.
- Leung, KS, (Wong, KC), (Chan, TM), Wong, MH, Lee, KH, Lau, CK, and Tsui, Stephen, "Discovering Protein-DNA Binding Sequence Patterns Using Association Rule Mining," Nucleic Acids Research. , pp.1-14, 6.2010, doi: 10.1093/nar/gkq500.
- (Chan T.M.), (G. Li), K.S. Leung and K.H.Lee,  Discovering multiple realistic TFBS motifs based on a generalized model, BMC Bioinformatics, 2009, 10:321
- (Chan, T.M.), Leung, K.S., and Lee, K.H., “TFBS Identification Based on Genetic Algorithm with Combined Representations and Adaptive Post-processing,” Bioinformatics, Vol.24, No.3, pp341-349, Oxford Journals, Feb 2008 
- (G. Li), (T.M. Chan), K.S. Leung and K.H.Lee, A Cluster Refinement Algorithm for Motif Discovery, IEEE/ACM Transaction on Computational Biology and Bioinformatics (accepted)
- (Chan, T.M)., Leung, K.-S., and Lee, K.-H., "TFBS identification by position- and consensus-led genetic algorithm with local filtering," Proceedings of the 9th annual conference on Genetic and evolutionary computation, London, England, 7-11 July 2007, (GECCO 07),  pp. 377–384.
- (LY Lo), ML Wong, KH Lee, KS Leung "High-order dynamic Bayesian Network learning with hidden common causes for causal gene regulatory network". BMC Boinformatics 16 (1), 1
- (LY Lo), ML Wong, KH Lee, KS Leung. "Time Delayed Causal Gene Regulatory Network Inference with Hidden Common Causes". PloS ONE, 2015, 10 (9), e0138596
- (Peter LY Lo), KS Leung and KH Lee, "Inferring Time-Delayed Causal Gene Network using Time-series Expression Data ", IEEE/ACM Transaction on Computational Biology and Bioinformatics, 2015.Vol. 12, Issue 1,142-154

(4) Computer-aided drug discovery and protein-ligand docking

    ***Drug Patents***

- HJ Li, KS Leung, MH Wong and PJ Ballester. "USR-VS: a web server for large-scale prospective virtual screening using ultrafast shape recognition techniques". Nucleic Acids Research, 2016. DOI: 10.1093/nar/gkw320
- HJ Li, KS Leung, MH Wong and PJ Ballester. "Correcting the impact of docking pose generation error on binding affinity prediction". BMC Bioinformatics, 2016. Manuscript accepted
- XN Shi, HJ Li, H Yao, X Liu, LLi, KS Leung, HF Kung, D Lu, MH Wong, and Marie CM Lin. In silico Identification and in vitro and in vivo Validation of Anti-Psychotic Drug Fluspirilene as a Potential CDK2 Inhibitor and a Candidate Anti-Cancer Drug. PLoS ONE, 10(7):e0132072, 2015. DOI: 10.1371/journal.pone.0132072
- HJ Li, KS Leung, MH Wong and PJ. Ballester. Low-Quality Structural and Interaction Data Improves Binding Affinity Prediction via Random Forest. Molecules, 20(6):10947-10962, 2015. DOI: 10.3390/molecules20061094
- (HJ Li), KS Leung1, MH Wong1 and PJ  Ballester. “Improving AutoDock Vina Using Random Forest: The Growing Accuracy of Binding Affinity Prediction by the Effective Exploitation of Larger Data Sets.” Molecular Informatics, Article first published online: 12 FEB 2015, DOI: 10.1002/minf.201400132
- XN Shi, (HJ L)i, H Yao, X Liu, L Li, KS Leung, HF Kung, MH Wong, and Marie CM Lin. "Adapalene Inhibited the Activity of Cyclin-Dependent Kinase 2 in Colorectal Carcinoma". Molecular Medicine Reports. (accepted)
- (HJ Li), KS Leung, MH Wong and PJ Ballester,"Substituting Random Forest for Multiple Linear Regression Improves Binding Affinity Prediction of Scoring Functions: Cyscore as a Case Study", BMC Bioinformatics, 2014, 15(1):291  DOI: 10.1186/1471-2105-15-291   Highly Accessed
- (HJ Li), KS Leung, T Nakane and MH Wong. "iview: an interactive WebGL visualizer for protein-ligand complex". BMC Bioinformatics, 15(1):56, 2014. DOI: 10.1186/1471-2105-15-56
(HJ Li), KS Leung, P. Ballester, MH Wong. "istar: A Web Platform for Large-Scale Protein-Ligand Docking", PLoS ONE 9(1): e85678, 2014. DOI:10.1371/journal.pone.0085678
- (Hongjian Li), Kwong-Sak Leung, and Man-Hon Wong. idock: A Multithreaded Virtual Screening Tool for Flexible Ligand Docking. 2012 IEEE Symposium on Computational Intelligence in Bioinformatics and Computational Biology (CIBCB), pp.77-84, San Diego, United States, 9-12 May 2012. DOI: 10.1109/CIBCB.2012.6217214
- (Ching-Man Tse), (Hongjian Li), Kwong-Sak Leung, Kin-Hong Lee, and Man-Hon Wong. Interactive Drug Design in Virtual Reality. 15th International Conference on Information Visualisation (IV), pp.226-231, London, United Kingdom, 13-15 July 2011. DOI: 10.1109/IV.2011.72

(5)  Genetic Parallel Programming

                -  (S. M. Cheang), K. H. Lee and K.S. Leung “Applying Genetic Parallel Programming to Synthesize Combinational Logic Circuits,” IEEE Transactions on Evolutionary Computation, Vol.11, No.4, pp.503-520, August 2007.
-  (C
heang S.M.), Leung K.S. and Lee K.H. “Genetic Parallel Programming: Design and Implementation,” Evolutionary Computation (MIT-Press) Vol. 14 Issue 2, pp. 129-156, 2006 (impact factor: 3.2)


(6)   Learning Bayesian Network by a new Hybrid Evolutionary Algorithm

       -M.L. Wong and K.S. Leung, "An Efficient Data Mining Method for Learning Bayesian Network Using an Evolutionary Algorithm-Based Hybrid
IEEE Transactions on Evolutionary Computation, Vol.8, No.4, pp.378-404, August 2004. (impact factor 3.688).
       -M.L. Wong, ( S. Y. Lee) and K.S. Leung "Data Mining of Bayesian Networks Using Cooperative Co-evolution"  Decision Support Systems. 38,
            pp. 451-472.


(7)   Non-linear Integral for Data Mining

            Addresses the issue of dependency of input attributes successfully in data mining. It has the unique advantage of recovering the explicit dependencies among attributes as well as giving high prediction rates in classification.

          - (Xu K.B.), Wang Z.Y., Heng P.A.. and Leung K.S. “Classification by Nonlinear Integral Projections” Special Issue on
          Knowledge Discovery and Data Mining, IEEE Transactions on Fuzzy Systems
, (Special issue on Fuzzy Systems in Knowledge
             Discovery & Data Mining), Vol.11, No.2, pp187-201,  April 2003.

      - (Rong Yang), Z.Y. Wang, P.A. Heng, and K.S. Leung, “Fuzzified Choquet integral with fuzzy-valued integrand and its
         application on temperature prediction,” IEEE Trans. SMCB, Vol.38, no.2, pp367-380, April 2008.
      - K.S. Leung, M.L. Wong, W. Lam, Z.Y. Wang and (K.B. Xu ) "Learning Nonlinear Multiregression Networks Based on
         Evolutionary Computation", IEEE Transactions on Systems, Man and Cybernetics Part B, Vol.32, No.5, pp.630-644,
         October 2002.


(8)   New type of Bayesian Networks

           We have invented a new Bayesian network that addresses the functional relationship problem of the attributes.


-(W.H. Shum), K.S. Leung, and M.L. Wong, "Learning Functional Dependency Networks based on Genetic Programming" ICDM'05, the proceedings The Fifth IEEE International Conference on Data Mining, New Orleans, Louisiana, U.S.A., November 27-30, 2005, the IEEE Computer Society Press. (full paper, acceptance rate: 10.95%)

**Intelligent Sensor Patent**
(9) Project Management Experience
i.   Senior Engineer, ERA Technology, England: Project leader for several international R&D projects (80-84)
ii. System Analyst, Central Electricity Generating Board, England: Responsible for planning, design and coding
of the software of electrical system and generators for nuclear power station real time simulator projects.(84-85)
iii. Managed and developed 8 major computer hardware and software systems) e.g.:

Our group will move our attention to creating new algorithms for high impact real-life genomic problems such as gene networks acquisition, large scale data mining on Transcription Factors and Transcription Factor Binding Sites, multiple gene sequence alignment, marker extraction, and functional region identification problems. We have been working on new data structures, indexing and EAs with dynamic time warping (DTW) to solve these problems. Prof MH Wong who is an expert in database and DTW has been contributing in this new drive. We are working on real life Genomic problems on Hepatitis-B, HIV and Diabetes. Drug/Ligand discovery is also vigorously being pursued.

 Bioinformatic Research Roadmap: