CFP

MACHINE LEARNING JOURNAL Special Issue Methods in Functional Genomics

http://www.genomethods.org/mlj/

Guest editors: Paola Sebastiani (University of Massachusetts, Amherst) Marco Ramoni (Harvard Medical School) Isaac Kohane (Harvard Medical School)

In June 2000, leaders of the Human Genome Project, Craig Venter of Celera Genomics, and U.S. President Clinton announced the completion of a ``working draft" DNA sequence of the human genome: the genetic blueprint for a human being. The legacy of that a announcement is the challenge to annotate this map, by understanding the functions of genes and their interplay with proteins and the environment to create complex, dynamic living systems. This understanding is the goal of functional genomics.

Recent technological advances enable biomedical investigators to observe the genome of entire organisms in action by simultaneously measuring the level of activation of thousands of genes under the same experimental conditions. This technology, known as microarrays, provides today unprecedented discovery opportunities and it is reshaping biomedical sciences. Parallel to these technological advances has been the development of machine learning methods able to integrate and understand the data generated by this new kind of experiments. However, most of this research has been conducted outside the traditional machine learning research community. The aim of this special issue is to bridge this divide by inviting researches to communicate their methodological advances in automated learning from functional genomics to the core machine learning community. The special issue seeks contributions of significant methodological content and high potential impact on the functional genomics research community.

Topics of particular interest include, but are not limited to:

• Hybridization detection, signal amplification and noise control in microarray experiments.

• Differential analysis and classification of gene expression data.

• Clustering and other unsupervised approaches to class discovery in functional genomics.

• Temporal profiling and analysis of dynamic genomic systems.

• Dependency discovery and reverse engineering of genetic networks.

• Validation methods to assess reliability and reproducibility of experiments.

The production of the Special Issue is expected to proceed according to the following schedule:

May 15, 2002 Submission of a preliminary abstract. June 15, 2002 Full manuscripts submission. Sept 1, 2002 Notification of acceptance. December 1, 2002 Final revisions due. Spring 2003 Special Issue publication.

Submission instructions:

1. Authors who intend to contribute to the special issue should send a tentative title and abstract to Paola Sebastiani at the address below before May 15, 2002.