spacer

Bridging from Ontologies to Text Mining (BOTM)

12-14 September 2007

Dear Associates,

The EBI will host a two-day workshop organized by the EBI' s Industry Programme and the BOOTStrep consortium.  The initial part of the workshop is dedicated to contributions from academia and is followed on the second day by contributions from and for members of the Industry Programme. The scientific co-ordinator is Dietrich Rebholz-Schuhmann.

How to bring resources together?
From terminologies to ontologies …
from text mining to fact databases:

12th-14th of September 2007 (academic and industry part)
EBI, Hinxton, Cambridge, U.K.

Setup: The workshop targets members of the research community in bioinformatics, medical informatics, ontological research, computational linguistics and computer science to discuss interoperability across domains.  We will investigate on the expectations towards the different resources and their limitations from the perspective of all mentioned domains. 

In the academic part, every session will start with a presentation given by a member of the BOOTStrep project covering the topic of the session (30 min).  Thereafter the keynote speaker presents ongoing research work in the field (45 min).  The final discussion will give enough opportunity to exchange views on selected questions (60 min).
The afternoon of September 13 is dedicated to a discussion amongst members of the industry programme and members of the academic community exploring on the needs of industry regarding the resources presented in the initial parts of the workshop.  At the end of the day available software solutions will be presented to delegates.  The next day, Friday September 14th, will bring presentations from keynote speakers on ongoing research work in the field of text mining, ontology development and others.
We want to invite you to participate into the discussion on September 13th, afternoon.

Motivation: Medicine and molecular biology are nowadays data driven sciences, where electronic access to information resources and to analytical tools for electronic data is crucial for the success of ongoing research.  Increasingly different parts of the research community are collaborating to generate common benefits.  This is the case for the domains of ontological research, bioinformatics databases and text mining.  This workshop offers an opportunity to discuss research questions arising from all three domains.  Relevant input will be provided from members of the EU research project “BOOTStrep”.
BOOTStrep (Bootstrapping Of Ontologies and Terminologies STrategic REsearch Project) is funded in the EC´s 6th Framework Programme.  The project started in April 2006 and has generated several resources that will be presented and discussed as part of the workshop: a lexical resource (“BioLexicon”), an ontology on gene regulation (“GRO”), and a UIMA based software package combining a number of text mining solutions.  A fact database will be developed in the course of the 2007.

Appreciation: This workshop is unusual in the sense that it will be inspired by ongoing research work in a collaborative European project.  The goal is to explore relevant research topics on the basis of experienced researchers confronted with the results from an ambitious project. 

It is organised in co-operation between the EBI and the BOOTStrep consortium consisting of 7 partners from 5 countries, supported by the European Commission's 6th Framework.

The venue will be room M203 on the 12th September and the EBI IT Training Room on the 13th and 14th September 2007.

On-site accommodation is fully booked - we recommend that you book accommodation with the Arundel House Hotel http://www.arundelhousehotels.co.uk/ or the Travel Lodge, Cambridge Leisure Park, Clifton Way http://www.travelodge.co.uk/find_a_hotel/hotel.php?hotel_id=255

Please see registration form - we shall be providing free shuttle buses between the hotels and Hinxton.

Kind regards

Liz

Preliminary agenda:

Time Agenda
Wednesday 12-Sep-2007
09.30 - 10.00 Coffee and Registration Room M202-203
10.00 - 12.15 BioLexicon, Bio-Terminologies and related resources (ILC-CNR)
10.00 - 10.45 Keynote speaker: Olivier Bodenreider (NLM, U.S.A.)
'BioLexicon, Bio-Terminologies and related resources'
10.45 - 11.15 BootStrep speakers:
- 'The BioLexicon model and database' (Valeria Quochi and Riccardo Del Gratta, ILC-CNR, Pisa)
- 'Population of the BioLexicon' (Sophia Ananiadou, University of Manchester)
11.15 - 12.15 Discussion on for example the use of lexicon standards, integration of semantics, use cases for the BioLexicon
12.15 - 13.30 Lunch
13.30 - 15.45 Bio-Ontologies (Jena University)
13.30 - 14.15 Keynote speaker: Nigam Shah (Stanford Medical Informatics (SMI), Stanford University)
'Bio-Ontologies: current status and emerging trends'
14.15 - 14.45 BootStrep speaker: Udo Hahn (University of Jena)
'Bio-Ontologies - the BOOTSrep Perspective'
14.45 - 15.45 Discussion on for example the developed ontologies, use of and compliance to ontological standards, alignment of ontologies, others
15.45 - 16.00 Coffee break
16.00 - 18.15 Biomedical annotation of corpora, Event annotation (University of Manchester)
16.00 - 16.45 Keynote speaker: Jin Dong Kim (Tsujii Laboratory, Tokyo University)
'From text to pathway: corpus annotation for knowledge acquisition from biomedical literature'
16.45 - 17.15 BootStrep speakers:
- 'Biological Annotation of Bio-Events' (Jung-Jae Kim, EMBL-EBI)
- 'Linguistic annotation of Bio-Events' (John McNaught, University of Manchester)
17.15 - 18.15 Discussion on for example event annotation and annotation of corpora in general
18.15 Drinks and nibbles in the Hall
19.30 Dinner in the Conference Centre Restaurant
Thursday 13-Sep-2007
09.00 - 11.00 Bio-NLP (Jena University)
09.00 - 09.45 Keynote speaker: Kevin Cohen (University of Colorado)
'Testing biomedical text mining software: problems and solutions.'
09.45 - 10.15 BootStrep speaker: Udo Hahn (University of Jena)
'The NLP core system developed as part of BootStrep'
10.15 - 11.00 Discussion on for example different Bio-NLP solutions available in the public, demands to such solutions
11.00 - 11.15 Coffee break
11.15 - 13.15 Biomedical fact databases and event extraction (EBI)
11.15 - 11.45 Keynote speaker: Martin Golebiewski (EML Research GmbH, Heidelberg)
'Integration and Normalization of Biochemical Data: The SABIO-RK Database'
11.45 - 12.15 BootStrep speaker: Dietrich Rebholz-Schuhmann
'Representation of gene regulatory events from the literature in the fact database'
12.15 - 13.15 Discussion on for example generation of fact databases from the literature, purpose of fact databases, types of generalizations of facts for integration into the database, others
13.15 - 14.15 Lunch
14.15 - 16.15 Industry Programme Discussion
Discussion on needs from the industry on TM solutions and ontologies Members of the industry programme will be asked to bring forward questions that they concern.
16.15 - 16.30 Coffee break
16.30 - 18.30 Software Demonstration
Hands on demonstration of TM solutions available from the EBI (For members of the industry programme)
18.30 For Industry Programme Members and Speakers - Drinks and nibbles in the Library
19.30 For Industry Programme Members and Keynote Speakers - Dinner in the Pompeian Room
Friday 14-Sep-2007
09.00 - 10.45 Ongoing Research presentations (I)
09.00 - 9.30 Olivier Bodenreider (NLM, U.S.A.)
'Integrating biological information through Semantic Web technologies.'
09.30 - 10.00 Kevin Cohen (University of Colorado, U.S.A.)
'Bio-ontologies and concept-based text mining'
10.00 - 10.30 Nigam Shah (Stanford Medical Informatics (SMI), Stanford University)
'NCBO: The National Center for Biomedical Ontology (http://www.bioontology.org/)'
10.30 - 11.00 Coffee break
11.00 - 13.15 Ongoing Research presentations (II)
(Presentations to be selected)
11.00 - 11.30 Su Jian (Infocomm Research, Singapore)
'Advance Information Extraction Technology for Information Management'
11.30 - 12.00 John Mc Naught (NaCTeM, Manchester University, U.K.)
'Biotext Mining at the National Centre for Text Mining'
12.00 - 12.30 Questions/Discussion
12.30 - 13.30 Lunch
spacer
spacer