• Limsoon WONG (NUS, Singapore)
  •   A Novel Principle for Childhood ALL Relapse Prediction
    Childhood acute lymphoblastic leukemia (ALL) is the most common type of cancer in children. Contemporary management of patients with childhood ALL is based on the concept of tailoring the intensity of therapy to a patient's risk of relapse. However, a significant number of patients with good prognostic characteristics relapse, while some with poor prognostic features survive. There is thus a demand to improve relapse prediction. Current treatment of childhood ALL is a process of gradually removing leukemic cells in a patient. Thus, we hypothesize that a leukemic sample consists of a mixture of leukemic cells and normal cells, where the intensity of the leukemic genetic signature measured by gene expression profile (GEP) can be used to infer the proportion of leukemic cells in the sample. In addition, as early response is known to have a great prognostic value in childhood ALL, we further expect to perform relapse prediction by the rate of the reduction of leukemic cells during treatment. To validate our hypothesis, for the first time, we generate time-series GEPs in a leukemia study. We demonstrate that the time-series GEPs are capable of mimicking the removal of leukemic cells in patients during disease treatment. We further propose to predict relapse based on the change of GEPs between different time points---the genetic status shifting (GSS) model. Our results suggest the prognostic strength of GSS is superior to that of any other prognostic factors of childhood ALL. In our study, e.g., GSS outperforms MRD by over 20% in the accuracy of relapse prediction. (* This talk is based on the dissertation of my student Dr Dong Difeng. *)
      Limsoon Wong is a provost's chair professor of computer science and a professor of pathology at the National University of Singapore. He currently works mostly on knowledge discovery technologies and their application to biomedicine. Limsoon has written about 150 research papers, a few of which are among the best cited of their respective fields. He has/had served on the editorial boards of Information Systems, Journal of Bioinformatics and Computational Biology, Bioinformatics, IEEE/ACM Transactions on Computational Biology and Bioinformatics, Drug Discovery Today, and Journal of Biomedical Semantics. He is co-founder and chairman of Molecular Connections, which is now widely considered to be one of the best SMEs in India.


  • Jung-jae KIM (NTU, Singapore)
  •   Toward Semantic Web for Biomedical Literature
    Semantic Web technologies have great potential for improving search results, especially in the biomedical domain where biologists have been intensively developing community-curated ontologies. We can apply the technologies to biomedical literature by representing the information expressed in biomedical documents with the concepts and relations of the biomedical ontologies. When successfully represented, the information stored into the ontologies will allow us to perform fine-tuned semantic searches over the literature.
    In this talk, we show three parts of a feasibility test toward the goal: 1) Manual annotation of biomedical documents with Gene Regulation Ontology (GRO), 2) a text mining system that extracts the information expressed in biomedical documents by using GRO, and 3) a proto-type semantic search engine that runs queries over the ontology-based annotations. The first part is about a new corpus annotated with GRO, called GRO corpus, which shows finer semantic granularity than other ontology-based annotations like GENIA corpus. This corpus can be used for training text mining systems, and we also introduce its applications for knowledge discovery. The second system is to identify textual semantics and represent them with GRO, and one of its advanced features is to deduce implicit information from explicitly expressed information by using inference rules that encode domain knowledge. The resultant GRO-based semantics can be retrieved by the third part of proto-type semantic search engine. One of the characteristics of the search engine is to query across multiple ontologies, merging information from the ontologies. This characteristic is based on the assumption that there is no universal ontology and the literature will be annotated with individual ontologies, thus requiring linking between the ontologies.
      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.


  • Joon Kyung SEONG (Soongsil University, Korea)
  •   Individual Subject Classification for Alzheimer's Disease
    In this talk, I propose an incremental method for AD classification using cortical thickness data. We represent the cortical thickness data of a subject in terms of their spatial frequency components, employing the manifold harmonic transform. The basis functions for this transform are obtained from the eigenfunctions of the Laplace-Beltrami operator, which are dependent only on the geometry of a cortical surface but not on the cortical thickness defined on it. This facilitates individual subject classification based on incremental learning. We utilized MR volumes provided by Alzheimer's Disease Neuroimaging Initiative (ADNI) to validate the performance of the method. Our method discriminated AD patients from Healthy Control (HC) subjects with 82% sensitivity and 93% specificity. It also discriminated Mild Cognitive Impairment (MCI) patients, who converted to AD within 18 month, from non-converted MCI subjects with 63% sensitivity and 76% specificity. In comparison with other classification methods, our method demonstrated high classification performance in the both categories, which supports the discriminative power of our method in both AD diagnosis and AD prediction.
      Joon-Kyung Seong is an assistant professor in the school of computer science and engineering at Soongsil University, Korea. His research interests include computer graphics, geometric modeling, and computational neuroimage analysis. Prof. Seong received a B.S. and a Ph.D. degrees from Seoul National University in 2000 and 2005, respectively. After his graduation, he conducted his postdoctoral research in the School of Computing at the University of Utah. In 2008, he joined the department of computer science at Korea Advanced Institute of Science and Technology (KAIST) as a research professor, while he is working in the school of computer science and engineering at Soongsil University from fall 2010.


  • Sun KIM (SNU, Korea)
  •   Cancer Research Using Genome-wide Genetic and Epigenetic Data
    Recent advances in sequencing technologies, known as the next or 3rd generation sequencing technologies, opened up unprecedented opportunities for scientists to measure accurate genetic and epigenomic information at the highest resolution on the genome scale. Thus the genome-wide genetic and epigenetic data has been widely used for research in biology and medical sciences. In this talk, based on my research experience in human cancer for last seven years, I will talk about how this genome-wide genetic and epigenetic data can be used to perform the integrated data analysis of epigenetic events, such DNA methylation, histone modifications, and microRNAs, with genome-wide gene expression data, cancer-related transcription factors (TFs) and their binding sites (TFBS), and CpG islands in the promoter regions. The genome-wide data provides scientists valuable global information. However, the integrated analysis of genetic and epigenetic elements at the genome scale is a very complicated task, thus we need to use additional information to interpret or navigate the genome-wide data. I am going to talk about what kind of additional information can be useful for the integrated analysis tasks and hope to discuss how text mining techniques can help scientists to utilize the genome-wide data.
      Sun Kim is Associate Professor in the School of Computer Science and Engineering, Director of Bioinformatics Institute, and an affiliated faculty for the Interdisciplinary Program in Bioinformatics at Seoul National University. Before joining SNU, he was Chair of Faculty Division C; Director of Center for Bioinformatics Research, an Associate Professor in School of Informatics and Computing; and an Adjunct Associate Professor of Cellular and Integrative Physiology, Medical Sciences Program at Indiana University (IU) Bloomington. Prior to joining IU in 2001, he worked at DuPont Central Research from 1998 to 2001, and at the University of Illinois at Urbana-Champaign from 1997 to 1998. Sun Kim received B.S and M.S and Ph.D in Computer Science from Seoul National University, KAIST and the University of Iowa, respectively.
    Sun Kim is a recipient of Outstanding Junior Faculty Award at Indiana University 2004, US NSF CAREER Award DBI-0237901 from 2003 to 2008, and Achievement Award at DuPont Central Research in 2000. He is actively contributing to the bioinformatics community, serving on the editorial board for journals including co-editor-in-chief for International Journal of Data Mining and Bioinformatics, serving as a board of directors member for ACM SIG Bioinformatics, as vice chair for education for the IEEE Computer Society Technical Committee on Bioinformatics. He has been co-organizing many scientific meetings including ACM BCB 2011 as a program co-chair, IEEE International Conference on Bioinformatics and Biomedicine (BIBM) 2008 as a program co-chair and 2009 as a conference co-chair.


  • Mi-Ryoung SONG (GIST, Korea)
  •   The Role of reelin in Neuronal Migration and Cortical Development Disorder
    Neuronal migration disorder is a genetic disease that displays a broad range of anatomical and developmental deformity due to problems in diverse aspects of neuronal development including neurogenesis, migration and circuit formation. Particularly, the migration of newborn neurons from their birth place to ultimate cortical layers is critical for proper layer formation of the cortex during neural development. The cortical layers are established in an inside-out fashion, i.e., the early-born neurons stay at the deep layers and later-born neurons migrate past older neurons to occupy the superficial layer. Reelin is the one of major secreted molecules that dictates neurons to migrate and stop at the correct layer. The reeler mice lacking Reelin exhibited malformed cortical layers as well as abnormal reeling gait behavior. The human patients with defective reelin function also exhibited similar phenotype. In this study, we show that the reeler mice display diverse migration defects in multiple places of central nervous system with behavioral problems, that may correlate with other molecules in the reelin signal pathway. Together, Reelin-dependent neuronal migration form a basis for brain functions and behavior.
      Mi-Ryoung Song is currently an assistant professor of the School of Life Science at the Gwangju Institute of Science and Technology (GIST) in South Korea. She is an associate editor of Archives of Pharmacal Research and a member of Society for Neuroscience. She received her BS and MS in 1995 and 1997, respectively, from Seoul National University, South Korea and her PhD in Neuroscience in 2003 from Johns Hopkins University, USA. She worked as a post-doctoral researcher for the Salk Institue of Biological Studies, USA from 2004 to 2007. She is a recipient of Paralyzed Veterans of America Fellowship Award.


  •   Clinical Text Processing for Decision Support
    Facilitating sharing and analyzing data for patients' care was seen as an achievable goal as early as in the 1960s. Yet processing clinical text still presents significant challenges. This talk will discuss some of the challenges and goals of clinical NLP. The talk will then focus on applications of clinical NLP for clinical decision support, using the NIH Clinical Center evidence-based practice module as an example. The talk will present the development, implementation and evaluation of the system designed to automatically extract patient information from an EMR, create sophisticated queries, search nursing and medical databases, and deliver evidence-based resources at the point of care.
      Dr. Dina Demner-Fushman is a Staff Scientist for the Communications Engineering Branch at the National Library of Medicine. She conducts research in clinical decision support, clinical question answering, use of natural language processing in information retrieval, human computer interaction aspects of information retrieval, and information retrieval in biomedical domain. Her interest in biomedical language processing stems from years of clinical practice (M.D. obtained from Kazan State Medical Institute in 1980) and clinical research (Doctorate (Ph.D.) in Medical Science earned from Moscow Medical and Stomatological Institute in 1989.) She earned her MS and PhD in Computer Science from the University of Maryland, College Park in 2003 and 2006, respectively. She earned her B.S degree in Computer Science from Hunter College, CUNY in 2000.