In recent years, we are witnessing an increasing number of applications that combine AI and data mining to deliver sophisticated intelligent systems. While the two disciplines have been strongly correlated, either in research or application, there have never been a time where such level of convergence exists within a single system.

For example, building data models (e.g., clustering or frequent patterns) in high speed data streams require the use of machine learning techniques in AI to fix the problem of concept drifts and time-variations. In many scientific applications, where data is distributed and large, the concept of utility in AI is used to evaluate the cost of data mining tasks (e.g., data acquisition, data mining, and model utilization) so that knowledge discovery is practically feasible in resource constrained environments. Agent-based techniques are now used to reason and coordinate knowledge discovery tasks across distributed data repositories; neutral networks are now used to optimize data mining parameters; spectral clustering is now used in case-based reasoning (CBR) for medical discovery, and incremental learning is now the means to 'idiot-proof' business intelligence systems.

Both disciplines had all along carry this potential to be used as a whole, in a closed-loop fashion, where the reasoning of AI helps to 'soften' the problems brought about by the brute force analytics of data mining. And data mining in turn, is the key to produce the relevant models and patterns that AI algorithms require. As users expect more from intelligent systems of today, there is now a need for researchers and practitioneers of both disciplines to exploit the possibilities of what this closed-loop framework can potentially offer.

The objective of this workshop is to bring together researchers and practitioneers in either or both disciplines to present and discuss their work. While the primary objective is dissemination of research results, the workshop also seeks to discuss future development of such a closed-looped framework for integrating AI and data mining as the holistic solution to intelligent system development.

We thus invite authors to submit their original and unpublished work that demonstrates current research and novel applications in this area. Some potential topics include, but not limited to, the following.

• Generic topics
  • Frameworks for integrating AI and data mining
  • Novel applications that use AI and data mining techniques
  • Metrics for evaluating intelligent systems using AI and data mining
• Data mining tasks enhanced by AI techniques
  • Sampling and feature selection
  • Utility-based data mining
  • Methods for handling concept-drifts
  • Parameters and measure optimization
  • Knowledge discovery coordination
• AI tasks enhanced by data mining techniques
  • 'Idiot-proofing' of intelligent systems
  • Case-based reasoning
  • Multi-valued logic (fuzzy logic)
  • Rough sets
  • Machine learning optimization, e.g., classification, neural networks, SVMs
  • Inductive learning through data mining models
  • Bayesian networks
  • Swarm Intelligence applied to data mining

Accurate and efficient computational tools are essential in order for biologists to make sense of the vast amounts of data being generated by high-throughput technologies such as genome sequencing and nucleotide micro-arrays. Existing intelligent systems offer powerful methods by which many biological questions can be addressed ranging from the analysis of genomic and proteomic data, to the extraction of knowledge from biomedical text and imaging, and the modelling of biological processes and molecules. The field of intelligent systems in bioinformatics is still in its infancy, however, with large amounts of knowledge still waiting to be extracted from, for example, genomic data and biomedical text, and with new technologies continually creating novel data types.

By bringing together researchers with an interest in applying intelligent systems technologies to bioinformatics problems, the Workshop on Intelligent Systems for Bioinformatics aims to bridge the gap between intelligent systems and bioinformatics.

We invite papers on mathematical, probabilistic and computational methods (in the broad realm of intelligent systems) applied in bioinformatics and computational biology, and on important biological results that are obtained from the use of these methods. Contributions can thus report on fundamental methodological research, on experimental and implementation issues involved in complex computations, and/or on the application of methods and programs that lead to discoveries of biological significance.

Acceptance of papers is subject to the significance of research and results, clarity of written presentation, and the suitability of topic for presentation at the workshop. Decisions are based on the review comments of at least two members of the program committee.Each paper is limited to 8 pages and should follow the format of Springer’s LNAI series http://www.springer.de/comp/lncs/authors.html. Papers should be submitted by email to mikael@itee.uq.edu.au (in Word, PDF or Postscript format).

• Deadline for submitting papers: 24 September 2006
• Notification of acceptances: 10 October 2006
• Deadline for submitting revised papers: 22 October 2006

The workshop proceedings will be published by the CRPIT series of the Australian Computer Society. Accepted contributors will be invited to revise their papers for a special issue of the Journal of Bioinformatics and Computational Biology. Final inclusion is subject to a re-review.

We envisage that researchers in artificial intelligence with an interest in scientific discovery and bioinformatics researchers looking for the right tools will gain from participating in this workshop. The one-day workshop will have a program of submitted contributions seen to fulfil the purpose of the workshop: to nurture collaboration between active researchers and to showcase significant and representative efforts, advancing bioinformatics and computational biology.

The workshop is held 4 December 2006, in Hobart, Australia, as a satellite to the 19th Australian Joint Conference on Artificial Intelligence (4-8 December, 2006). Workshop registration fees are set by the main conference organisers.

Dr. Mikael Bodén, School of Information Technology and Electrical Engineering, The University of Queensland, Australia (mikael@itee.uq.edu.au, http://www.itee.uq.edu.au/~mikael)

Dr. Timothy L. Bailey, Institute for Molecular Bioscience, The University of Queensland, Australia (t.bailey@imb.uq.edu.au, http://research.imb.uq.edu.au/~tbailey)

Prof. Mark A. Ragan, Institute for Molecular Bioscience, The University of Queensland, Australia (m.ragan@imb.uq.edu.au).