Week 3 - Reading (Part 1)

Week 3 - Reading (Part 1) - P e r s p e c t i v e s 14...

Info iconThis preview shows pages 1–2. Sign up to view the full content.

View Full Document Right Arrow Icon

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
This is the end of the preview. Sign up to access the rest of the document.

Unformatted text preview: P e r s p e c t i v e s 14 1094-7167/01/$10.00 © 2001 IEEE IEEE INTELLIGENT SYSTEMS how living systems perform difficult tasks routinely (rang- ing from molecular phenomena such as protein-folding to organism-level phenomena such as cognition). The definition of intelligent systems in biology can lead to hours of debate. Some—the lumpers—say that all high- performance systems that do something difficult with (or to) biological data should be considered intelligent systems. Others—the splitters—insist that the term “intelligent sys- tem” should be reserved for systems using the methods typically associated with modern AI. For this article, I will be a lumper. However, some systems are clearly more intel- ligent than others. An emphasis on molecular biology Biology is the study of living systems and how they work. Using intelligent systems to understand biology can be applied across many scales, from the atomic details of biological molecules to the interactions of species in an ecosystem. The areas that have received the most attention, however, are those where the data glut is most evident, and methods are needed immediately to manage this informa- tion. DNA sequencing technologies were the first to pro- duce large amounts of data, and they provided the founding impetus for bioinformatics. Figure 1 in the Guest Editor’s Introduction on page 9 shows the number of DNA bases in Genbank, the major DNA database, over the last 20 years. The human genome contains approximately 3 billion DNA bases, and a rough draft of this sequence is now available. 1,2 More recently, biologists have developed other high- throughput experimental methods that produce large amounts of data. These include methods for measuring the expression of all genes within a population of cells simul- taneously and quantitatively (using DNA microarrays), rapidly assessing the ability of biological molecules to interact with one another (using yeast-two hybrid), quickly identifying the compounds present in a mixture of biological molecules (using mass spectroscopy), and determining the detailed 3D structure of biological mole- cules (using x-ray crystallography and nuclear magnetic resonance [NMR] spectroscopy). If you collect a lot of data, the intelligent systems will come. Certain key features of biological data make intelligent systems critical for their analysis. • Biological data is normally collected with a relatively low signal-to-noise ratio. This creates a need for robust analysis methods. • Biology’s theoretical basis is still in its infancy, so few “first principle” approaches have any chance of work- ing yet. This creates a need for statistical and proba- bilistic models....
View Full Document

This note was uploaded on 04/02/2008 for the course ENGR 213 taught by Professor Clague during the Spring '08 term at Cal Poly.

Page1 / 5

Week 3 - Reading (Part 1) - P e r s p e c t i v e s 14...

This preview shows document pages 1 - 2. Sign up to view the full document.

View Full Document Right Arrow Icon
Ask a homework question - tutors are online