This tutorial is aimed at researchers interested in learning about the field of bioinformatics and some of the biological background needed to undertake computational intelligence work in this area. It presumes no particular background in biology and is intended to equip newcomers with the necessary background to participate in the sessions for the Symposium on Computational Intelligence in Bioinformatics and Computational Biology.

The R statistical software is a popular and powerful tool amongst statisticians and users of statistics. The purpose of this tutorial is to familiarize attendees with the R software and to illustrate some of the ways in which it can be of use in bioinformatics analyses. The analysis and, in particular, the clustering of the gene expression microarray data will be focused upon. Both modern and more traditional clustering techniques will be used and results will be interpreted within the R software.

DNA barcoding is the technique of identifying a specimen to species using a standardized gene region. This technique is being successfully employed across the animal kingdom, and there have been advances in identifying a standard region for other kingdoms. Circa March 2010, there are in excess of 806,549 DNA barcode records for roughly 68,000 species available in the Barcode of Life Data Systems (BOLD) with the number projected to increase by an order of magnitude upon the completion of the final reference library. DNA barcode records are an aggregate of well-vetted specimen and sequence data. This wealth of standardized data presents problem opportunities for computational biologists such as error checking algorithms, feature identification from sequence and image data, multi-domain clustering and more. BOLD supports the bioinformatics community by providing web services for data acquisition.

This tutorial presents a gentle introduction to support vector machines, large margin classifiers, and kernel methods. Beginning with a simple linear classifier model, we use visualizations to complement the underlying mathematical theory, so that students will have an intuitive understanding of these powerful models. We examine the objective function, the underlying optimization problem, the optimization algorithms, and kernel conditions. Finally, we examine the application of SVMs to problems in bioinformatics and the kernels that have been defined for sequences and other objects of interest from biology.

The decision about how to represent your problem as an evolvable data structure is the key design feature in an evolutionary computation system. this tutorial will survey several examples of standard and nonstandard representations in the context of solving specific bioinformatics problems. The tutorial will also serve as an introduction to evolutionary computation and experimental design for evolutionary computation.

Phylogenetic inference, often called simply "phylogenetics", is the process of constructing a model of the hypothesized evolutionary relationships among the species or individuals in a data set. The grand goal of the endeavor is usually considered to be the reconstruction of the "tree of life", a model of how all species currently or formerly inhabiting the Earth are related. More commonly, phylogenetics is used to study the relationships among a set of closely related species. With organisms that mutate rapidly, such as HIV (human immunodeficiency virus), or when longitudinal data is available, such as via the fossil record, phylogenetics can also be used to study the relationships among individuals.

The task of inferring a putative evolutionary tree, or phylogeny, is computationally daunting for modest data sets and intractable for realistically large data sets, and thus has traditionally proceeded as a heuristic search. As with many domains, well-designed evolutionary computation techniques can be a boon to the search for phylogenies.

This tutorial will survey the field of phylogenetics, including common tree-building approaches, the software typically used by biologists and molecular biologists, and evolutionary computation contributions to the field.