Chapter 14. Visualization and Data Mining
Any result in bioinformatics, whether it is a sequence alignment, a structure prediction, or an analysis of gene expression patterns, should answer a biological question. For this reason, it is up to the investigators to interpret their results in the context of a clear question, and to make those results accessible to their colleagues. This interpretation step is the most important part of the scientific process. For your results to be useful, they must be interpretable. We'll say it again: if your results can't be interpreted, they won't help anybody, not even you.
In this chapter, we present computational tools that help you to make sense of your results. To this end, the chapter is organized so that it roughly parallels the data-analysis process. In the first part of this chapter, we introduce a number of programs that are used to visualize the sort of data arising from bioinformatics research. These programs range from general-purpose plotting and statistical packages for numerical data to programs dedicated to presenting sequence and structural information in an interpretable form. The second part of this chapter covers some tools for data mining—the process of finding, interpreting, and evaluating patterns in large sets of data—in the context of some bioinformatics applications.
The topics covered in this chapter are basically subdisciplines of the larger area of computational statistics. As you have seen in previous chapters, statistical ...