B: short papers

Accepted Papers

Tutorial

"Bibliome-Scale Text Mining"

NEW: slides of the tutorial

Dr. Filip Ginter, University of Turku, and Dr. Sofie Van Landeghem, University of Ghent

Abstract:

In this tutorial we will present resources and techniques for large-scale text mining in the biomedical domain. We will demonstrate how to efficiently download, process and update large amounts of domain literature, using publicly available tools. We will also present the essential resources for integrating text mining data with other large bioinformatics datasets. During the tutorial, we will point out a number of practical, often undocumented, issues and typical solutions, building upon the experience gained during the development of EVEX, a literature-scale event database. The aim of the tutorial is to encourage the development of large-scale text mining resources in the biomedical domain, both user-oriented as well as serving as a foundation for further text mining research.

Short bio:

Filip Ginter holds a PhD in computer science from the University of Turku. His research focuses on event extraction in the biomedical domain, in particular the development of large-scale event resources for both BioNLP research and its applications. In addition, he is involved in several projects building methods and resources for Finnish NLP. 

Sofie Van Landeghem has a Master's degree in Computer Science and a PhD in Bioinformatics from Ghent University. Her research involves the development of automated text mining and data integration techniques to
assist knowledge discovery from the ever increasing amount of bio-molecular data. In particular, her research interests include the application of textual data to integrative systems biology studies.

Invited speaker I

"Implementing a Framework to answer complex questions related to Drug Discovery"

Therese Vachon, NIBR-IT, Novartis AG

Short bio:

Therese Vachon graduated in computer science from the Institut National des Sciences Appliquees in Lyon, France. She held positions with the Paris Stock Exchange, the University of Compiegne, and an IT consulting company before joining Novartis. She developed end-user search tools in the biomedical and chemistry field. Since 1998, she has been very active in the field of information retrieval, information extraction, text mining, development of terminologies, and integration of life sciences data using semantic capabilities. She is currently the head of Text Mining Services at NIBR-IT (Novartis Pharma AG). 

Invited speaker II

"From biomedical information integration to knowledge discovery"

Olivier Bodenreider, NLM

Abstract:

Over the past decade, knowledge resources have become increasingly available not only for humans to read and make sense of, but also electronically, which make these data amenable to automated processing. Structured knowledge have been developed and integrated in systems such as Entrez, developed by NCBI. Vast amounts of biomedical text have also been processed in order to extract entities and relations. In the clinical domain, data warehouses created from electronic health record systems have been created in virtually every institution involved in translational research. Finally, the biomedical domain is rich of many  ontologies, which provide the vocabulary for normalizing entities and relationships in these knowledge sources, as well as the domain knowledge to interpret the content of these resources. Semantic Web technologies have emerged as the infrastructure of choice for integrating biomedical information.

This talk will focus on the experimental Biomedical Knowledge Repository being developed at the National Library of Medicine. This repository leverages Semantic Web technologies to integrate the Unified Medical Language System (UMLS), 50 M relations extracted from PubMed/MEDLINE abstracts by the SemRep NLP system, as well as features from Entrez Gene. We will show how definitional knowledge from biomedical ontologies can complement assertional knowledge extracted from the literature in support of hypothesis generation and knowledge discovery.

Short bio:

Olivier Bodenreider is a Senior Scientist and Chief of the Cognitive Science Branch of the Lister Hill National Center for Biomedical Communications at the U.S. National Library of Medicine. His research focuses on terminology and ontology in the biomedical domain, both from a theoretical perspective (quality assurance, interoperability) and in their application to natural language processing, knowledge discovery and information integration. Dr. Bodenreider is a Fellow of the American College of Medical Informatics. He received a M.D. degree from the University of Strasbourg, France in 1990 and a Ph.D. in Medical Informatics from the University of Nancy, France in 1993. Before joining NLM in 1996, he was assistant professor for Biostatistics and Medical Informatics at the University of Nancy, France, Medical School.

Excursion

Dinner