Bioinformatics by Jonathan M. Keith

Author:Jonathan M. Keith
Language: eng
Format: epub
Publisher: Springer New York, New York, NY

The first term of L c (x) does not depend on the class and is therefore neglected in DLDA. DLDA places patients into the class for which the absolute value of the second term is minimized.

3.3 Univariate Gene Selection

Diagonal linear discriminant analysis can be directly applied to microarray data. Nevertheless, gene selection considerably improves its performance. In gene selection, we impose additional regularization by limiting the number of genes in the signature. A simple way to select informative genes is to rank them according to a univariate criterion measuring the difference in mean expression values between the two classes. We suggest a regularized version of the t- statistic also used for detecting differential gene expression. For gene i, it is defined as

Download

Copyright Disclaimer:
This site does not store any files on its server. We only index and link to content provided by other sites. Please contact the content providers to delete copyright contents if any and email us, we'll remove relevant links or contents immediately.