Communications of the ACM
Computers 'taught' to Id Regulating Gene Sequences
The glowing areas in this zebrafish embryo show the activity of one of the brain enhancer sequences identified. The enhancer is directing the activity of a gene in the lower areas of the central nervous system and in the lens of the eye.
Credit: G. Burzynski
Johns Hopkins University (JHU) researchers have developed a tool that can teach computers how to identify commonalities in DNA sequences known to regulate gene activity, and use those commonalities to predict other regulatory regions in the genome.
"We give data to a computer and 'teach it' to distinguish between data that has no biological value versus data that has this or that biological value," says JHU professor Andrew McCallion. The computer then establishes rules, which enable it to look at new sets of data and apply what it learned.
In one study, the researchers created a training set of enhancer sequences specific to a region of the brain by compiling a list of 211 published sequences that were shown to be active in the development or function of that part of the brain. In another study, the researchers created a training set through experiments that focused on skin cells known as melanocytes. The tool was able to distinguish the features of the training sequences from the features of all other genome sequences, and produce rules that defined one set from another. Applying those rules to the whole genome, the computers were able to discover thousands of probable brain or melanocyte enhancer sequences fitting the features of the training sets.
From Johns Hopkins University
View Full Article
Abstracts Copyright © 2012 Information Inc., Bethesda, Maryland, USA
No entries found