Communications of the ACM
A Computer Model to nderstand the Genetic Basis of Disease
A new computer model can predict the effects mutations in the human genome can have on gene splicing.
Credit: enot-polskun/iStockphoto
University of Toronto researchers have developed Splicing-based Analysis of variants (SPANR), a computer model that can predict the effects mutations in the human genome would have on splicing.
SPANR applies machine learning to solve the problem of understanding how the genome signals for splicing, which traditionally has been a challenge because it involves very complex interactions between DNA splicing motifs that are not simple to model.
SPANR was trained on healthy genomes and data concerning how these genes are normally spliced. An algorithm then uses these statistics to build a model, from which it can predict how likely a specific mutation is to alter splicing in new scenarios.
"Because it captures something about the biological mechanism of splicing, it can be used to predict mutations as well--so the effects of mutations, even though the model has never seen mutations during training," says Toronto researcher Hui Yuan Xiong.
In addition, Xiong notes SPANR accurately predicted 94 percent of its genes that already are linked to well-studied diseases. It also has uncovered many new mutations that could cause various diseases, including 39 new mutations that could be related to autism.
From The Varsity (Canada)
View Full Article
Abstracts Copyright © 2015 Information Inc., Bethesda, Maryland, USA
No entries found