• Jae Sook Cheong (ETRI, Korea)
  •   Tag Graph: a graph-based tagging system for files
    Remembering things depends heavily on associations for humans. Retrieval of memory on some object or fact is not only triggered by many sensory data. Even we consider only using words for information retrieval from human memory, there are many routes to reach the information that we are looking for. Currently we search for a file in a computer or on web by entering specific words or a specific order of words. When we do not know the exact words in the file name or in the contents of the file, or the exact path to the file, we cannot find fast the file that we were looking for. Tagging method is proposed to overcome this. In order to use this method effectively, however, users must enter all the tag words directly for each file, and different tag words are often used for one meaning. In addition, if the word that is occurred to the user as a related word for the desired file is not in the corresponding tag list, users have to explicitly think about other related words that might be in the tag list, or words associated to the original word. In this talk, we present a system called tag graph: a graph-based tagging system for easy access to files. Tag words are organized in a graph with edges representing association relationships. With proposed method, it is relatively easier to tag files. Moreover, a user can search for a digital item by exploring the tag graph with many different words, even when he or she does not know the exact words used in the file name or in the contents of the file.
      Jae-Sook Cheong received the B.A. degree in computer science and engineering from Pohang University of Science and Technology, Pohang, Korea, in 1996, the M.Phil. degree in computer science and engineering from Hong Kong University of Science and Technology, Hong Kong, China, in 2000, and the Ph.D. degree in information and computing sciences from Utrecht University, Utrecht, The Netherlands, in 2006. From 2006 until now, she has been working in Electronics and Telecommunications Research Institute, Daejeon, Korea, in as a Senior Researcher. Her research interests include computational geometry, manipulations, and modeling interactions between human and mobile digital contents.


  • Kwoh Chee Keong (NTU, Singapore)
  •   Drug-Target Interaction Prediction by Learning From Local Information and Neighbors
    NLP and in silico methods provide efficient ways to predict possible interactions between drugs and targets. Supervised learning approach, Bipartite Local Model (BLM), has recently been shown to be effective in prediction of drug-target interactions. However, for drug-candidate compounds or target-candidate proteins that currently have no known interactions available, its pure “local” model is not able to be learned and hence BLM may fail to make correct prediction when involving such kind of new candidates.

    A simple procedure called Neighbor-based Interaction-profile Inferring (NII) when integrated it into the existing BLM method to handle the new candidate problem can inferred interaction profile to be treated as label information and is used for model learning of new candidates. This functionality is particularly important in practice to find targets for new drug-candidate compounds and identify targeting drugs for new target-candidate proteins.

    We tested the approach in the experiment for the prediction of interactions between drugs and four categories of target proteins. Especially for Nuclear Receptors, BLM-NII achieves the most significant improvement as this dataset contains many drugs/targets with no interactions in the cross validation. This demonstrates the effectiveness of the NII strategy.
      Dr. Kwoh Chee Keong is in the School of Computer Engineering. He is the Programme Director, MSc (Bioinformatics) and Deputy Director, Biomedical Engineering Research Centre, NTU. He studied Electrical Engineering and Master in Industrial System Engineering from NUS; and Ph.D. from the Imperial College. His research interests include Data Mining and Soft Computing and Graph-Based inference; applications areas include Bioinformatics and Biomedical Engineering. His is in the Editorial Board Members of The International Journal of Data Mining and Bioinformatics; TheScientificWorldJOURNAL; Network Modeling and Analysis in Health Informatics and Bioinformatics (NetMAHIB); Theoretical Biology Insights; and Bioinformation. He was Guest Editor for many journals such as JMMB; International Journal on Biomedical and Pharmaceutical Engineering and others. He has been often invited as a organizing member or referee and reviewer for a number of premier conferences and journals, including GIW, IEEE BIBM, RECOMB, PRIB, BIBM, ICDM, and iCBBE and others.


  • Jung-jae Kim (NTU, Singapore)
  •   Biomedical Ontology Alignment For Equivalence and Subsumption Correspondences
    Ontology alignment refers to the task of finding correspondences between entities in different ontologies. It facilitates inter-operability between applications using different ontologies as the correspondences allow them to understand one another's data. We present our novel methods for the discovery of both equivalence and subsumption correspondences between the concepts of different ontologies and use them for knowledge representation and integration in the biomedical domain. For equivalence correspondence discovery, we introduce a novel technique called BOAT. In BOAT, we improve accuracy by combining a word-based comparison with a structural comparison. Given a pair of concepts, we collect difference words and determine if each of them distinguishes the concepts by using the ontology structures. Concept pairs with no such distinguishing difference words are then considered equivalent. BOAT is also one of the fastest matchers as it reduces the time taken for matching large ontologies using a candidate selection technique that selects only concept pairs with high similarities for comparison. Equivalence correspondences are alone insufficient to fully support inter-operability. Subsumption correspondences complement them by explicitly stating the generalization of a concept in one ontology over other concepts in another ontology. Instance-based techniques can be used to determine whether a subsumption correspondence exists between a pair of concepts based on the common instances they share. However, this technique cannot be applied to ontologies which are not instantiated. We propose a technique for subsumption and equivalence correspondence discovery, which resolves this issue by instantiating ontologies with their annotations on text corpora.
      Jung-jae Kim is currently an Assistant Professor of the School of Computer Engineering at Nanyang Technological University (NTU) in Singapore. He is a member of Bioinformatics Research Centre and of Centre for Computational Intelligence at NTU. He is an editor of Journal of Biomedical Semantics and a member of the Association for Computational Linguistics. He received his BSc, MS, and PhD in 1998, 2000, and 2006, respectively, from KAIST, South Korea. He has worked as a post-doctoral researcher for the Text Mining group of European Bioinformatics Institute (EBI) from 2006 to 2009.


  • Sung Wing Kin (NUS, Singapore)
  •   Structural variation identification and its applications in decoding cancer genome
    Next generation sequencing (NGS) enables us to resequence the individual genome efficiently and cost-effectively. Many works have applied this technology to extract SNPs in genome-wide scale. Another type of mutation is structural variation (SV), that is the mutation of a region of length > 50bp. This presentation will describe a novel method to identify SVs utilizing NGS. We will also present the application of our pipeline to identify SVs in chronic myelogenous leukemia (CML) and Hepatocellular carcinoma (HCC).
      Sung Wing Kin is an associate professor in the Department of Computer Science, School of Computing, NUS. Also, he is a senior group leader in Genome Institute of Singapore. He has over 15 years experience in Algorithm and Bioinformatics research. He also teaches courses on bioinformatics for both undergraduate and postgraduate. Recently, he was conferred the 2003 FIT paper award (Japan), the 2006 National Science Award (Singapore), and the 2008 Young Researcher Award (NUS) for his research contribution in algorithm and bioinformatics.


  • Hyunju Lee (GIST, South Korea)
  •   Integrative approaches for DNA copy number aberrations in cancer
    This talk presents integrative approaches for the analysis of DNA copy number aberrations (CNAs) and gene expressions in cancer. CNAs are one of important molecular signatures in cancer initiation, development, and progression.However, these aberrations span through a wide range of chromosomes, so it is hard to distinguish cancer related genes from other genes that are not closely related to cancer but located in the broadly aberrant regions. To address this issue, we developed the wavelet based method to distinguish cancer-driving genes from passenger genes. We also developed the biclustering method for revealing the structural changes in DNA and functional changes in RNA to discover cancer related pathway.