email 1: shirley.siu at
email 2: siuwengin at
Google scholar | LinkedIn | Twitter

Link to my previous lab’s page

Associate Research Professor
Institute of Science and Environment
University of Saint Joseph

PhD (Dr. rer. nat.) in Computational Biology, Saarland University, Germany
MSc in Computational Molecular Biology, Saarland University & Max-Planck Institute for Computer Science, Germany
MSc/BSc in Software Engineering, University of Macau, Macau

** Open PhD topics available, feel free to email me to discuss about it. 

Keywords: Computer-Aided Drug Design, Molecular Docking, Cheminformatics, Molecular Dynamics, Force Field, Machine Learning, Deep Learning, Optimization Algorithms, Therapeutic Peptides (AMP, ACP), Drug Target Prediction, GPCR, Ion Channels 


To date, drug discovery has been a major challenge due to limited knowledge of disease and difficulty in identifying the right molecular targets and drug candidates. Our research focuses on developing computational algorithms to support drug discovery by using bioinformatics methods, machine learning and optimisation algorithms. In particular, we have developed molecular docking programs to identify native binding modes of proteins, peptides, and small molecular compounds. Recently, we have also become interested in therapeutic applications of peptides (antimicrobial, anticancer, GPCR interacting, ion channel interacting) by studying the relationship between peptide molecular properties and biological activities observed in experiments. We work on modelling and simulation of proteins to study their structures and dynamics and to understand their functions. We have been involved in the development of membrane lipid force fields and more recently in the modelling of self-assembling monolayers on biochips.


Our mission is to improve computational methods to accelerate the drug discovery and development process. To this end, we have been developing bioinformatics tools that enable researchers to solve critical drug discovery problems including protein-ligand binding (PSOVina, GWOVina), drug target identification (LigTMap), biological activity (AxPEP, AcPEP) and toxicity predictions (BESTox, SSL-GCN).

Our previously developed methods can be accessed directly online via this apps portal ( Some program source codes can be downloaded from my Github page or SourceForge page. 


Therapeutic peptides are molecules with high specificity that can modulate cell signaling and transport, act as antibiotics, and target protein-protein interactions. However, while computational methods for chemical drug discovery are mature and routinely used, the corresponding methods for peptide research are far from satisfactory. The main challenge here is the larger size of peptide molecules, which have much greater conformational flexibility and computational complexity compared to chemical drugs. The project aims to develop specific computational protocols for peptide discovery and optimization, from activity prediction to sequence design. The candidate will strategically review the state of the art in silico peptide discovery-and-design methods in the research community, including methods developed in-house, and improve them for screening novel peptides, classify functions, predict activities, model protein-peptide complex structures, and rational design peptide for optimal function. Peptides whose functions are of medical importance (e.g. anti-cancer peptides) will be the focus of this study.

Candidates are required to have a background in Bioinformatics, Computational Chemistry, Computational Biology or Computer Science.

Keywords: Therapeutic Peptide; Biologics; Data Mining and Machine Learning; Molecular Docking


Determining protein-peptide interactions (PPI) is critical for understanding fundamental biological processes and for developing peptides or peptidomimetic medicines. However, the dynamic and volatile nature of PPIs makes experimental characterisation of the structures of protein-peptide complexes difficult. To date, computational prediction of binding modes between proteins and peptides with large conformational changes remains challenging. A recent comparative study of all major docking programs found that the best method could only achieve a success rate of 24% at the top-10 level and only 4% at the top-1 level, indicating that computational predictions are still unreliable.  This project aims to investigate ways to improve the accuracy of protein-peptide prediction from at least three perspectives. First, combined global docking and accelerated MD techniques will be explored to identify the binding surface and detect peptide conformations. Second, machine learning and deep learning will be used to improve success rate by classifying native and non-native binding modes. Third, the AlphaFold database, which contains 100,000 high-quality predicted structures, will be explored to support the prediction process or act as a knowledge base for learning atom-atom interaction patterns.

Candidates are required to have a background in Bioinformatics, Computational Chemistry, Computational Biology or Computer Science.

Keywords: Protein-Peptide Docking; Protein Flexibility; Artificial Intelligence and Deep Learning; Alphafold

Antimicrobial peptides (AMP) are considered promising candidates for the next generation of antibiotics due to their broad spectrum of antimicrobial activity, low toxicity and high potency. The basic mechanism of AMPs is membrane destruction. However, it has been reported that AMPs can interact with and disrupt the functionality of various intracellular targets, nucleic acids and proteins. This complex mechanism involving both extracellular and intracellular targets makes it more difficult to develop resistance to AMPs. This project aims to improve our understanding of how AMP works using computational methods. Molecular dynamics simulation method (MD) is finding increasing application in computational drug discovery and has already been used to gain insight into the mechanisms of action of various antibiotics. In this project, the candidate will study AMPs that have been reported to target membranes and/or proteins, such as the heat shock proteins DnaK and GroEL. The study will involve constructing the complex structures, investigating the energetics and dynamics of the binding interactions, identifying important interactions for binding specificity, and designing peptide variants with improved functionality. 

Candidates are required to have a background in life sciences, biomedical sciences,   Bioinformatics, Computational Chemistry, Computational Biology.

Keywords: Antimicrobial Peptides; Antibiotics; Drug Discovery; Intracellular Targets

Despite two decades of discovering new drugs, there is currently no effective treatment for Alzheimer’s disease (AD). With the number of people suffering from this debilitating disease increasing at an unprecedented rate, there is an urgent need for a cure. The few drugs that are available today for AD cannot cure the disease, but only relieve the symptoms. One problem may be that these drugs are single-targeted and cannot treat the multifactorial factors involved in this complex disease, making current therapy ineffective. In this project, a network-based polypharmacological approach will be used to investigate the complex protein-protein and protein-disease network of AD. Our goal is to identify key targets from the network and then use a computational drug discovery approach to find potential leads for these targets. Existing drugs, food-derived chemicals, collection of natural and chemical compounds will be screened for their potential as AD remedies. This project involves mining of public databases for network construction, developing algorithms to extract useful information from the network, perform virtual screening and molecular study of potential lead molecules, etc.

Candidates are required to have a background in Bioinformatics, Computational Chemistry, Computational Biology or Computer Science.

Keywords: Alzheimer’s Disease; Neurodegenerative Disease; Drug-Target Network; Computer-Aided Drug Design

Mental health problems are common in older people and can include anxiety and dementia. Many older people also suffer from sleep and behavioral problems, cognitive decline, and confusion. Often patients are unable to recognize the problem themselves, resulting in the condition being discovered very late. The term “digital phenotype” refers to the use of data from personal digital devices to quantify social, physical, cognitive, emotional, and behavioral phenotypes at the individual level. It is a powerful tool to better understand patients for scientific or clinical purposes. This project will explore the use of smartphones and other wearable devices (such as smartwatches) to monitor and diagnose users’ mental health. Multimodal data will be collected from various sources (sensors, GPS, cameras, text and speech, etc.) and their relationship to the user’s psychological, emotional and behavioral conditions will be studied. In this project, statistical, machine learning, deep learning algorithms will be developed to facilitate disease detection, monitoring and clinical support of user mental health. The goal of this project is to enable accurate and early detection of mental health problems, especially in seniors, to provide better medical support and improve their quality of life.

Candidates are required to have a background in Computer Science, Information Technology, Information System, or Data Science.

Keywords: Mental Health Monitoring; Smart Device; Wearables; Physiological and Behavioral Monitoring; Digital Phenotyping; Elderly Care


Classification of ion channel interacting peptides  

Ion channels are a family of transmembrane proteins that form pores in the membrane. They regulate the influx and efflux of cations or anions in cells. Because of the important role that ion channels play in both excitable and nonexcitable tissues, they are attractive therapeutic targets for many diseases, including neurological disorders, cardiovascular and metabolic diseases, and cancers. Peptides that can bind ion channels and regulate ion flux are widely used for the pharmacological characterization of various ion channels and receptors. In this project, we investigate predictive modeling of peptides that bind ion channels using known binding sequences. The target channels are sodium, potassium and calcium ion channels. The main challenges are the limited positive data available, the highly imbalanced datasets, and the large set of protein sequence descriptors. While standard machine learning algorithms can learn the sequence patterns of binding partners with high accuracy for sequences with some similarity to the training data, it is challenging to improve the prediction accuracy for truly novel sequences.

Collaborators: Prof. Henry H.F. Kwok, Prof. Bob Zhang, Jielu Yan, University of Macau

Classification of anticancer peptides  

Cancer is one of the leading causes of death worldwide. Conventional cancer treatment relies on radiotherapy and chemotherapy, but both methods bring severe side effects to patients, as these therapies not only attack cancer cells but also damage normal cells. Anticancer peptides (ACPs) are a promising alternative as therapeutic agents that are efficient and selective against tumor cells. In this project, we explore different machine learning techniques to build predictive models for ACP classification, including feature selection, active learning, and semi-supervised learning. 

Collaborators: Prof. Lawrence Si, Carter Cheong, University of Macau



Chen, J.; Cheong, H.H. and Siu, Shirley W. I.* xDeep-AcPEP: Deep Learning Method for Anticancer Peptide Activity Prediction Based on Convolutional Neural Network and Multitask LearningJournal of Chemical Information and Modeling 2021, 61, 8, 3789–3803.

Shaikh, F.; Tai, H. K.; Desai, N. and Siu, Shirley W. I.* LigTMap: Ligand and structure-based target identification and activity prediction for small moleculesJournal of Cheminformatics 2021, 13: 44.

Wei, Ran; Wu, Qiushuang; Ai, Nana; Wang, Lei; Zhou, Mei; Shaw, Chris; Chen Tianbao; Ye Richard Dequan; Ge, Wei; Siu, Shirley W. I.; Kwok, Hang Fai. A novel bioengineered fragment peptide of Vasostatin-1 exerts smooth muscle pharmacological activities and anti-angiogenic effects via blocking VEGFR signalling pathwayComputational and Structural Biotechnology Journal 2021, 19: 2664-2675.

Zai, Yu.; Xi, Xinping; Ye, Zhuming; Ma, Chengbang; Zhou, Mei; Chen, Xiaoling; Siu, Shirley W. I.; Chen, Tianbao; Wang, Lei; Kwok, Hang Fai. Aggregation and its influence on the bioactivities of a novel antimicrobial peptide, Temporin-PF, and its analoguesInternational Journal of Molecular Sciences 2021, 22, 4509.

Bhadra, P. and Siu, Shirley W. I.* Effect of concentration, chain length, hydrophobicity, and an external electric fields on the growth of mixed alkanethiol self-assembled monolayers: A molecular dynamics studyLangmuir 2021, 37 (5): 1913–1924.


Li, Tengyue; Fong, Simon; Siu, Shirley W. I.; Yang, Xin-she; Liu, Lian-Sheng; Mohammed, Sabah. White learning methodology: A case study of cancer-related disease factors analysis in real-time PACS environment. Computer Methods and Programs in Biomedicine 2020, 197: 105724. JCR-Q1

Wong, K. M.; Tai, H. K. and Siu, Shirley W. I.* GWOVina: A grey wolf optimization approach for rigid and flexible receptor docking. Chemical Biology & Drug Design 2020, 00: 1-14.

Ma, R.; Ren, Z.; Li, B.; Siu, Shirley W. I.; Chen, G.; Kwok, H. F. Novel venom-based peptides (P13 and its derivative-M6) to maintain self-renewal of human embryonic stem cells by activating FGF and TGFß signaling pathways. Stem Cell Research & Therapy 2020, 11, 243. JCR-Q1

Yan, J.; Bhadra, P.; Li, A.; Sethiya, P.; Qin, L.; Tai, H. K.; Wong, K. H.; and Siu, Shirley W. I.* Deep-AmPEP30: Improve short antimicrobial peptides prediction with deep learning. Molecular Therapy – Nucleic Acid 2020, 20, 882-894. JCR-Q1

Chen, J. and Siu, Shirley W. I.* Machine learning approaches for quality assessment of protein structures. Biomolecules 2020, 10(4), 626. JCR-Q1

Ma, R.; Wong, S. W.; Ge, L.; Shaw, C.; Shirley W. I. Siu and Hang Fai Kwok.* In vitro & Molecular dynamic simulation study to explore physicochemical parameters for antibacterial peptide to become potent anticancer peptide. Molecular Therapy – Oncolytics 2020, 16, 7-19. JCR-Q1


Bhadra, Pratiti and Siu, Shirley W. I.* Refined empirical force field to model protein-self assembled monolayer interactions based on AMBER14 and GAFF. Langmuir 2019, 35, 29, 9622-9633. ESI-Q1

Liao, Q.; Gong, G.; Poon, T. C. W.; Ang, I. L.; Lei, K. M. K.; Siu, Shirley W. I; Wong, C. T. T.; Rádis-Baptista, G.; Lee, M. Y.. Combined transcriptomic and proteomic analysis reveals a diversity of venom-related and toxin-like peptides expressed in the mat anemone zoanthus natalensis (cnidaria, hexacorallia). Archives of Toxicology 2019, 93, 1745-1767. JCR-Q1

Shaikh, Faraz; Zhao, Yuguang ; Alvarez, Luis; Iliopoulou, Maria; Lohans, Christopher; Schofield, Christopher; Padilla-Parra, Sergi ; Siu, Shirley W. I.; Fry, Elizabeth; Ren, Jingshan; Stuart, David. Structure-based in silico screening identifies a potent Ebolavirus inhibitor from a traditional chinese medicine library. Journal of Medicinal Chemistry 2019, 62, 2928-2937. JCR-Q1


Tai, Hio Kuan; Jusoh, Siti Azma; Siu, Shirley W. I.* Chaos-embedded particle swarm optimization approach for protein-ligand docking and virtual screening. Journal of Cheminformatics 2018, 10, 62. JCR-Q1

Lin, Hang and Siu, Shirley W. I.* (2018) A hybrid cuckoo search and differential evolution approach to protein-ligand docking. International Journal of Molecular Sciences, 19 (10), 3181. ESI-Q1

Liao, Q.; Li, S.; Siu, Shirley W. I.; Morlighem, J.-É. R. L.; Wong, C. T. T.; Wang, X.; Rádis-Baptista, G.; Lee, M.-Y.. Novel neurotoxic peptides from Protopalythoa variabilis virtually interact with voltage-gated sodium channel and display anti-epilepsy and neuroprotective activies in zebrafish. Archives of Toxicology 2018, 93, 189-206. JCR-Q1

Shaikh, F.; He, J.; Bhadra, P.; Chen, X., Siu, Shirley W. I. (2018) TNF receptor type II as an emerging drug target for the treatment of cancer, autoimmune diseases, and graft-versus-host disease: Current perspectives and in silico search for small molecule binders. Frontiers in Immunology 2018 9, 1382. ESI-Q1

Liao, Q.; Gong, G.; Siu, Shirley W. I.; Wong, C. T. T.; Tse, Y. C.; Rádis-Baptista, G.; Lee, M.-Y. A novel ShK-like toxic peptide from the transcriptome of the cnidarian Palythoa caribaeorum displays neuroprotection and cardioprotection in zebrafish. Toxins 2018, 10 (6): 238. JCR-Q1

Duan, K.; Fong, S.; Siu, Shirley W. I.; Song, W.; Guan, S. S.-U. Adaptive incremental genetic algorithm for task scheduling in cloud. Symmetry 2018 10 (5), 168.

Liao, Q.; Li, S.; Siu, Shirley W. I.; Yang, B.; Huang, C.; Chan, J.; Morlighem, J.-É.; Wong, C.; Radis-Baptista, G.; Lee, M.-Y. Novel Kunitz-like peptides discovered in the zoanthid Palythoa caribaeorum through transcriptome sequencing. Journal of Proteome Research 2018, 17 (2), 891-902. JCR-Q1

Bhadra, P.; Yan, J.; Li, J.; Fong, S.; Siu, Shirley W. I.* AmPEP: Sequence-based prediction of antimicrobial peptides using distribution patterns of amino acid properties and random forest. Scientific Reports 2018, 8, 1697. JCR-Q1


Bhadra, P.; Siu, Shirley W. I.* Comparison of biomolecular force fields for alkanethiol self-assembled monolayer simulations. Journal of Physical Chemistry C 2017, 121 (47), 26340-26349 JCR-Q1

Cao, H.; Ng, M. C. K.; Jusoh, S. A.; Tai, H. K.; Siu, Shirley W. I.* TMDIM: An improved algorithm for the structure prediction of transmembrane domains of bitopic dimers. Journal of Computer Aided Molecular Design 2017, 31, 855-865.


Chan, H. K.; Mak, P. I.; Siu, Shirley W. I.* Exploring the behavior of water nanodroplet on a coplanar electrowetting-on-dielectric: A molecular dynamics approach. Micro & Nano Letters 2017, 12 (7), 486-489.

Lam, W. W. T.; Siu, Shirley W. I.* PyMOL mControl: Manipulating molecular visualization with mobile devices. Biochemistry and Molecular Biology Education 2017, 45(1), 76-83.

Shaikh, F.; Siu, Shirley W. I.* Identification of novel natural compound inhibitors for human complement component 5A receptor by homology modeling and virtual screening. Medicinal Chemistry Research 2016, 25, 1564-1573.

Ngai, J. C. F.; Mak, P. I.; Siu, Shirley W. I.* ProtPOS: A python package for the prediction of protein preferred orientation on a surface. Bioinformatics 2016, 32, 2537-2538. JCR-Q1


Ng, M. C. K.; Fong, Simon; Siu, Shirley W. I.* PSOVina: The hybrid particle swarm optimization algorithm for protein-ligand docking. Journal of Bioinformatics and Computational Biology 2015, 13 (3), 1541007. Most Read and Most Cited Paper in JBCB

Wang, R.; Zhou, H.; Siu, Shirley W. I.; Gan, Y.; Wang, Y.; Ouyang, D.* Comparison of three molecular simulation approaches for cyclodextrin-ibuprofen complexation. Journal of Nanomaterials 2015, Article ID 193049. ESI-Q1

Fong, S.*; Liang, J.; Siu, Shirley W. I.; Chan, J. H. Efficient variation-based feature selection for medical data classification. Journal of Medical Imaging and Health Informatics 2015, 5, 1093-1098.

Fong, S.*; Siu, Shirley W. I.; Zhou, S.; Chan, J. H.; Mohammed, S.; Fiaidhi, J. Real-time analysis of vital signs using incremental data stream mining techniques with a case study of ARDS under icu treatment. Journal of Medical Imaging and Health Informatics 2015, 5, 1108-1115.


Siu, Shirley W. I.; Pluhackova, K.; Böckmann, R. A.* Optimization of the OPLS-AA force field for long hydrocarbons. Journal of Chemical Theory and Computation 2012, 8, 1459-1470. JCR-Q1

Borisovska, M.; Schwarz, Y. N.; Narzi, D.; Siu, Shirley W. I.; Kesavan, J.; Mohrmann, R.; Böckmann, R. A.; Bruns, D.* Membrane-proximal tryptophanes of synaptobrevin II stabilize priming of secretory vesicles. Journal of Neuroscience 2012, 32, 15983-15997. JCR-Q1


Wang, L.; Siu, Shirley W. I.; Gu, W.; Helms, V.* Downhill binding energy surface of the barnase-barstar complex. Biopolymers 2010, 93, 977–985.

Jusoh, S. A.; Welsch, C.; Siu, Shirley W. I.; Böckmann, R. A.; Helms, V.* Contribution of charged and polar residues for the formation of the E1-E2 heterodimer from Hepatitis C Virus. Journal of Molecular Modeling 2010, 16, 1625-1637.


Siu, Shirley W. I.; Böckmann, R. A.* Low free energy barrier for ion permeation through double-helical gramicidin. Journal of Physical Chemistry B 2009, 113, 3195-3202. ESI-Q1

Vacha, R.; Siu, Shirley W. I.; Petrov, M.; Böckmann, R. A., Barucha-Kraszewska, J.; Jurkiewicz, P.; Hof, M.; Berkowitz, M. L.; Jungwirth, P.* Effects of alkali cations and halide anions on the DOPC lipid membrane. Journal of Physical Chemistry A 2009, 113, 7235-7243. ESI-Q1


Narzi, D.; Siu, Shirley W. I.; Stirnimann, C. U.; Grimshaw, J. P.A.; Glockshuber, R.; Capitani, G.; Böckmann, R. A.* Evidence for proton shuffling in a thioredoxin-like protein during catalysis. Journal of Molecular Biology 2008, 382, 978-986. JCR-Q1

Siu, Shirley W. I.; Vacha, R.; Jungwirth, P.; Böckmann. R. A.* Biomolecular simulations of membranes: Physical properties from different force fields. Journal of Chemical Physics 2008, 128, 125103. Selected for April issue of Virtual Journal of Biological Physics Research. ESI-Q1


Siu, Shirley W. I. and Böckmann, R. A.* Electric field effects on membranes: gramicidin A as a test ground. Journal of Structural Biology 2007 157, 545-556. JCR-Q1


Antes, I.+*; Siu, Shirley W. I.+; Lengauer, T. DynaPred: A structure and sequence based method for the prediction of MHC class I binding peptide sequences and conformations. Bioinformatics 2006, 22 (14), e16-e24. JCR-Q1 +equal contributions



Chen, J.; Cheong, H. H and Siu, Shirley W. I.* BESTox: A convolutional neural network regression model based on binary-encoded SMILES for acute oral toxicity prediction of chemical compounds. In: Martín-Vide C., Vega-Rodríguez M., Wheeler T. (eds) Algorithms for Computational Biology. AlCoB 2020. Lecture Notes in Computer Science, vol 12099. Springer, Cham

Ao, M. C. and Siu, Shirley W. I.* Evaluating variants of firefly algorithm for ligand pose prediction in protein-ligand docking program. In Proceedings of the 12th International Conference on Bioinformatics and Biomedical Technology (ICBBT2020), accepted.

Gao, L. and Siu, Shirley W. I.* Study of data imbalanced problem in protein-peptide binding prediction. In Proceedings of the 12th International Conference on Bioinformatics and Biomedical Technology (ICBBT2020), accepted.


Tai, H. K.; Lin, H.; Siu, Shirley W. I.* Improving the efficiency of psovina for protein-ligand docking by two-stage local search. In the Proceeding of the 2016 IEEE Congress on Evolutionary Computation (CEC2016), Vancouver, Canada, July 24-29, 2016.


Ngai, J. C. F.; Mak, P. I.; Siu, Shirley W. I.* Predicting favorable protein docking poses on a solid surface by particle swarm optimization. In the Proceedings of the 2015 IEEE Congress on Evolutionary Computation (CEC2015), 2745-2752, Sendai, Japan, May 25-28, 2015.


Siu, Shirley W. I.; Wong, T. K. F.; Fong, S. Comparison of cutoff strategies for geometrical features in machine learning-based scoring functions. Proceedings of the 9th International Conference on Advanced Data Mining and Applications (ADMA2013), Hangzhou, China, December 14-16, 2013, LNAI 8347, 336-347, Springer, 2013.


Wang, R.; Siu, Shirley W. I.; Böckmann, R. A. Fine-grained protein mutation extraction from biological literature. Proceedings of International Conference on Electronic Computer Technology (ICECT-2009), Macau, 2009.

Leung, A.; Fong, S.; Siu, Shirley W. I. Smart card-based irregular access patterns detection system. IEEE International Conference on e-Technology, e-Commerce and e-Service (EEE 2004), Taipei, Taiwan, 28-31 March 2004, pp.546-553.

Fong, S.; Siu, Shirley W. I. An integrative framework of predictive mining methods for medical prognosis. IASTED the 2nd International Conference on Biomedical Engineering (BioMED 2004), Innsbruck, Austria, 16-18 February 2004.

Fong, S.; Siu, Shirley W. I.; Sun, A. Market watcher agent for e-commerce. IASTED the International Conference on Artificial Intelligence and Applications (AIA 2004), Innsbruck, Austria, 16-18 February 2004.

Leung, A.; Fong, S.; Siu, Shirley W. I. Smart card-based identification and access control model with real-time suspicious action detection mechanism. IASTED The International Conference on Artificial Intelligence and Applications (AIA 2004), Innsbruck, Austria, 16-18 February 2004.

Siu, Shirley W. I.; Fong, S.; Guo, Z. S.; Si Tou, K. F. Context-aware for service discovery in ad hoc environment. IASTED Intl. Conf. on Wireless and Optical Communication (WOC-2003), Banff, Canada, 14-16 July, 2003.

Siu, Shirley W. I.; H. M. Au. Solution for electronic ticket in mobile media. Proceedings of Macau IT Week 2002 Seminar Series, Macau, Oct 4-6 2002.

Siu, Shirley W. I.; Guo, Z. S.; Fong, S.; Zhuang, Y. Extending e-ticketing service with mobile transactions. Proceedings of the 1st International Conference on Information Technology and Applications (ICITA-2002), Bathurst, Australia, Nov. 25-29, 2002.

Fong, S.; Siu, Shirley W. I.; Sun, A., WebSpy: Retrieving web contents for e-business intelligence. Proceedings of the 1st International Conference on Information Technology and Applications (ICITA-2002), Bathurst, Australia, Nov. 25-29, 2002.

Guo, Z. S.; Siu, Shirley W. I.; Wong, C. T. Full-scale online event ticketing system – the design and implementation. Proceeding of the 13th Chinese Process Control Conference, Macau and ZhuHai, China, Jul 29-Aug 2, 2002.

Siu, Shirley W. I.; Guo, Z. S. Application of electronic ticket to online trading with smart card technology. Proceedings of the 6th INFORMS Conference on Information Systems and Technology (CIST-2001), Miami Beach, Florida, U.S., Nov.3-4 2001, pp.222-239.