Abstract
Biology has emerged as an information rich science providing many new and interesting applications for the machine learning community. Biological data is challenging to analyze because it is inherently noisy and biased. A review is given to illustrate how both effective representation of these data and proper feature selection are critical to the success of a particular computational functional genomics approach. The types of computational challenges that arise in functional genomics and current methodologies that are employed are also outlined.
Original language | English (US) |
---|---|
Pages (from-to) | 62-69 |
Number of pages | 8 |
Journal | IEEE Signal Processing Magazine |
Volume | 21 |
Issue number | 6 |
DOIs | |
State | Published - Nov 2004 |
All Science Journal Classification (ASJC) codes
- Signal Processing
- Electrical and Electronic Engineering
- Applied Mathematics