Workshop Objectives

Life sciences has become a major area of data mining research with genomics and proteomics being the prime motivators for the need to develop and apply machine learning and data mining techniques to analyse large amounts of data that is produced all over the world. Data Mining in Functional Genomics and Proteomics is a multi-disciplinary research area that involves a close collaboration between researchers from a number of diverse areas, such as computer science, mathematics, and statistics, to biology, medicine, genomics and proteomics. This collaboration of disciplines has evolved because of the: (i) advances that have occurred in data production and acquisition facilities, such as the introduction of high throughput genomics and proteomics microarrays, (ii) enormous amounts of data that is generated from each experiment or investigation that cannot be analyzed using ordinary data mining tools and techniques, and (iii) strong interest from many groups (research institutes, hospitals, academia, pharmaceuticals, etc.) who want to benefit from this wealth of data. Many efforts are being undertaken by researchers working in this field.

This workshop encourages the researchers to present ongoing research and development that represents either (or both):

• Integrated data mining: Approaches that cover from experimental data to preprocessing, data analysis, presenting/visualizing results and, finally, interpretation of the results. The contributions following this format should use recent or completely new datasets and interesting application scenarios.
• Exploratory machine learning and data mining techniques, proposing challenging approaches: They could be new methodologies or adapted techniques from other fields.

The aim of this workshop is to bring together researchers working on different topics related to data mining and machine learning in Life Sciences. In particular we are interested to focus on current issues and trends and also emphasize on what should be the future directions for generic and applied research in this field.

The intended audience are reseachers and practitioners who are working in the above fields and under one or more of the following topics.

Topics

• Data pre-processing, data understanding
• Data management methods
• Data mining architectures, data bases
• Machine learning, NN, GA, SVM
• Statistics
• Soft computing techniques
• Gene expression analysis
• Gene networks and pathways
• Comparative genomics
• Post-processing, knowledge/model integration
• Integration of various forms of genomics and proteomics data
• Genomics knowledge structure and dissemination
• Association rules, and knowledge discovery from time series data
• Data Visualization, Association Graphs
• Biological Modeling and Artificial Life

Organizing committee

• Prof. J.M. Peña (UPM – Spain), Co-Chair [jmpena@fi.upm.es]
• Dr. A. Fazel Famili (NRC – Canada), Co-Chair [fazel.famili@nrc-cnrc.gc.ca]
• Prof. Ana Teresa Freitas (INESC-ID/IST, Portugal) [atf@vinci.inesc-id.pt]
• Prof. Jaakko Hollmén (Helsinki Uni. of Technology, Finland) [Jaakko.Hollmen@tkk.fi]
• Prof. Alexander Schliep (Comp. Science, Rutgers Univ. USA) [schliep@cs.rutgers.edu]
• Prof. Henrik Bostrom (Stockholm University, Sweden) [henrik.bostrom@dsv.su.se]
• Prof. Min-Ling Zhang (South East University, Nanjing, China) [zhangml@seu.edu.cn]
• Prof. Evgenii Vityaev (Russian Academy of Science, Russia) [vityaev@math.nsc.ru]

Submission

Interested participants are requested to submit their papers in PDF or Postscript. Authors should submit their papers using Springer LNCS format. For templates please refer to: http://www.springer.de/comp/lncs/authors.html. Papers should not exceed 10 pages.

A selected group of papers may be chosen for an extended version and a second review targeting a special issue of a related JCR-cited journal (to be announced).

Author should send their papers as a PDF file to the following addresses: Fazel Famili <Fazel.Famili@nrc-cnrc.gc.ca> and Jose M Peña <jmpena@fi.upm.es>

Workshop Proceedings

The Workshop Proceedings are available and can be downloaded from this link.

Key Dates

This workshop will be held in Athens, Greece on September 5th, immediately prior to the start of the ECML/PKDD conference. All workshop participants are expected to register for the main conference. Attendance to the workshop will be limited to 35-40 people. The participants will be selected by the organizing committee after reviewing submitted papers or statement of their current research. Those wishing to attend the workshop without submitting a paper should send a statement of their current research to the workshop chair or one of the workshop co-chairs.

The workshop will accept a maximum of 10 accepted papers. Each session will end with a 10-15 minutes summary and discussion. Workshop proceedings will be printed prior to the workshop and will be distributed among the participants.

Schedule